ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060253

Authors: Budi Siswanto Ketut Wikantika Albertus Deliar Tri Muji Susantoro

Paddy field sustainability is essential for food security in paddy-dependent countries but is shaped by complex and spatially heterogeneous interactions among environmental, social, and economic factors. Conventional land-use models often assume spatial stationarity, limiting their ability to capture localized dynamics. This study proposes a spatially explicit analytical framework by integrating Geographically Weighted Logistic Regression (GWLR) with multi-layer probabilistic surface analysis to model and classify paddy field sustainability. The framework is applied in Indramayu and Majalengka Regencies, Indonesia, using 400 stratified samples (53% paddy, 47% non-paddy) and 10,000 prediction points. Results show that GWLR outperforms global models, explaining 25.5% of deviance compared to 7.4% for logistic regression. More importantly, it reveals spatially non-stationary relationships: environmental variables exhibit relatively continuous effects, while social and economic variables show strong local heterogeneity. By transforming local coefficients into integrated probability surfaces, this study introduces a novel typology distinguishing stable paddy fields, vulnerable areas, and spatially differentiated sustainability conditions. This approach moves beyond aggregate accuracy metrics and highlights the importance of spatial context in land-use analysis. The proposed framework offers a transferable method to support place-based agricultural protection strategies in complex geographical systems.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060252

Authors: Lorenzo Gabrielli Patrizia Sulis Sara Thabit Marco Minghini

Open, non-governmental building datasets have become increasingly important for urban analysis, exposure modelling, and policy support. Despite their growing use, little is known about the consistency, completeness, and comparability of the semantic information they provide at a continental scale. This study presents the first systematic comparison of the semantic attributes of six major pan-European open building datasets—OpenStreetMap, EUBUCCO, Microsoft Global ML Building Footprints, Overture Maps, GHS-OBAT, and the Digital Building Stock Model (DBSM)—using the 27 EU Member States as a common reference area. Five key semantic attributes (height, typology, building age, number of floors, and building material) were harmonised and analysed in terms of completeness and value distributions across countries and degrees of urbanisation. The workflow combines API-based data ingestion, distributed geospatial processing, and high-performance computing to handle around 1.250 billion building footprints. Results reveal pronounced heterogeneity in semantic content across datasets. Remote-sensing-derived products (GHS-OBAT and DBSM) exhibit the highest levels of attribute completeness for height, typology, and building age, but rely on aggregated or coarse semantic representations. In contrast, community-driven and conflated datasets (OpenStreetMap and Overture Maps) provide richer and more detailed semantic schemas, albeit with low and spatially uneven completeness. Completeness patterns vary substantially across countries and urbanisation classes, and high completeness values often mask limited semantic informativeness due to the prevalence of unknown or aggregated attribute values. Overall, the findings demonstrate that no single dataset is universally optimal regarding consistency and completeness of building footprints’ semantic attributes. Nonetheless, the paper provides practical guidance for selecting suitable data sources depending on spatial scale, attribute requirements, and analytical objectives.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060251

Authors: Chunlan Guo Biao Liu Furong Wang Yong Xu Yu Zhou Emily Ying Yang Chan Bo Huang

City Information Modelling (CIM) and Urban Digital Twins (UDT) are pivotal for advancing smart urban planning and city management, yet empirical evidence on their real-world implementation is scarce. Following a sequential mixed-methods design, this study addresses this gap through a global investigation analyzing 33 projects across diverse geographic contexts. Findings reveal that these technologies are predominantly applied in 3D visualization (60.6%) and urban planning (48.5%), with significant underutilization in climate adaptation (9.1%) and AI-driven robotics (3.0%). A pronounced physical–social data divide exists, with infrastructure data prioritized over human-centric inputs. Technology stacks converge on GIS, IoT, and BIM. However, an interoperability paradox persists, as internal integration outpaces cross-organizational connectivity. Governance is predominantly public-sector-led, but multi-actor ecosystems are also involved. The study concludes with actionable recommendations to rebalance implementation portfolios, integrate socio-economic data, and advance both technical and institutional interoperability, thereby harnessing CIM and UDT for transformative urban planning and city management.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060249

Authors: Weiwu Wang Zhaoyang Teng Zihao Guo Jie He

Low-altitude logistics is increasingly considered a promising solution for urban last-mile delivery, yet how urban morphology is associated with the simulated cost of drone logistics networks across cities remains unclear. This study examines model-based relationships between urban spatial form and the cost performance of drone logistics networks under unified simulation assumptions. A multi-tier facility location model is developed and applied to 101 Chinese cities, with simulated annealing used to obtain cost-minimizing configurations of drone take-off and landing facilities. An XGBoost model with SHAP analysis is employed to interpret nonlinear associations and interaction patterns between urban morphology indicators and simulated network cost, while K-means clustering is used to identify representative morphology–cost patterns. The results show that built-up area and landscape shape index are the most influential predictors in the adopted modeling setting, both exhibiting threshold-like sensitivity ranges. Simulated network costs increase more rapidly when built-up area exceeds approximately 1000 km2 and when landscape shape index falls within 5–15, with a notable interaction between them. Three morphology–cost types are further identified, reflecting systematic differences in simulated network organization. These findings provide simulation-derived evidence for morphology-sensitive planning of low-altitude logistics infrastructure, while actual deployment decisions still require calibration with local demand, operational, regulatory, and airspace conditions.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060250

Authors: Eirini Nektaria Konstantinou Andriani Skopeliti Byron Nakos

Modern web and tourist maps use pictorial symbols to help users quickly and easily identify Points of Interest (POIs). Pictorial symbols are sometimes misinterpreted due to poor design choices. As a result, it is important to evaluate pictorial symbols with map users. This paper uses an online questionnaire to examine how different graphic parameters—such as frame outline, frame background, frame shape, color hue, and pictogram category (semantic, visual, or arbitrary)—are perceived by map users. The evaluation of pictograms includes three aspects: understanding, to capture the map reader’s opinion; preference, to investigate the map maker’s choice; and appropriateness, to document the evaluation of an existing map. Seven popular Points of Interest (POIs) were selected for the evaluation of pictorial symbols: Hotel, Restaurant, Parking, Museum, Airport, Hospital, and Church. Based on the questionnaire results and the statistical analysis of 520 responses, several conclusions were drawn. Users prefer symbols with a frame outline and a frame background. They also prefer symbols with a white background, which increases contrast and improves legibility. In contrast, users do not have a strong preference for a specific frame shape. In general, users can recognize symbol groups based on frame shape, but the effect is stronger when the color hue appears in the frame background or outline. The statistical analysis demonstrates that perceived appropriateness constitutes an objective measure related to comprehension. Furthermore, appropriateness is independent of the pictogram classification as semantic, visual, or arbitrary. Instead, it is determined by the graphic ability of the pictogram to represent a specific POI. This conclusion reaffirms the importance of designing successful semantic and visual pictograms or adopting those already familiar to map users, as familiarity has also been identified as an important factor by this research. Overall, this paper, based on user evaluations, provides practical insights to improve pictorial symbols on a tourist map.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060248

Authors: Xiangjun Cheng Hongmei Zhang Chao Li Sining Xu

Recent advances in land system research depend heavily on efficient access to large-scale, multi-source remote sensing spatiotemporal databases. Although Text-to-SQL provides natural language interfaces, the scale and spatial complexity of remote sensing schemas generate significant noise for large language models, increasing inference costs and latency. This study presents graph-enhanced retrieval for accurate schema pruning (GRASP), a graph-based framework for schema pruning in remote sensing information systems. GRASP frames schema pruning as a semantic retrieval task and constructs a heterogeneous graph that represents both question semantics and database structure. By integrating a relation-aware transformer, a relational graph attention network, and pre-trained BERT representations, GRASP enhances schema understanding and supports joint table-column prediction through entity-level cross-attention. A dual-task objective combining contrastive learning with dynamic-threshold prediction mitigates class imbalance, while database value sampling and demonstration retrieval optimize inference performance. Experiments show that GRASP substantially improves schema pruning in spatiotemporal query scenarios: a 7B open-source LLM with GRASP surpasses an unaugmented 32B model on Spider; meanwhile, the framework also yields promising results on SpatialSQL, achieving a favorable balance among accuracy, cost, and deployment flexibility. GRASP provides a practical pathway for interdisciplinary researchers to query remote sensing databases in natural language, aiding spatiotemporal analysis.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060247

Authors: Taeyun Jeong Dawoon Jeong Meejeong Kim

South Korea has been advancing the National Digital Twin Land initiative; however, many existing urban digital twin projects have relied on non-standard, visualization-oriented datasets, thereby encountering persistent difficulties in securing interoperability and reusability. In particular, the lack of a standardized methodology capable of systematically fusing fragmented public administrative data with 3D geospatial information remains a major barrier to the practical use of digital twins in administrative operations. To address this gap, this study proposes a standardized urban digital twin data construction methodology that complies with the international standard while effectively accommodating Korea’s building-related public datasets. Specifically, the OGC CityGML Building module is adopted as the reference model, and an extension is implemented to design a data model that extends and integrates heterogeneous sources—such as building height records, building register attributes, and road-name address data—within a unified standard schema. Furthermore, using Busanjin-gu, Busan Metropolitan City, as a case area, we develop high-precision LoD 1~4 building objects from aerial surveying outputs and empirically validate an end-to-end workflow by loading and visualizing the resulting dataset on a national public platform. By constructing operational digital twin data that tightly couples physical geometry with administrative semantics and verifying its feasibility in an actual platform environment, this study establishes a practical, standards-based foundation for deploying and operating geospatial digital twins in smart city and related urban governance applications.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060246

Authors: Zoe Misiri Alkistis Antonopoulou Nikolaos Depountis Panagiotis Ioannidis Andreas Kazantzidis

This study presents a geospatial framework for assessing landslide risk along one of the most landslide-prone road networks in Greece, located in the Region of Epirus. Utilizing a field-verified inventory of 295 active landslides, the research evaluates five key predisposing factors (lithology, slope, elevation, land use, and cumulative annual precipitation) using the bivariate Frequency Ratio (FR) statistical model. Among six tested configurations, the baseline model integrating all factors demonstrated the highest reliability, quantitatively validated through Prediction Rate Curves yielding an Area Under the Curve (AUC) of 0.788 with the use of an independent dataset of 126 landslides. As a spatial outcome of this statistically validated configuration, nearly 80% of the study area was classified within Moderate to Very High susceptibility zones. The resulting Landslide Susceptibility Index (LSI) was converted into an event-based Landslide Hazard Index (LHI) and integrated with a weighted Road Vulnerability Map based on functional importance and traffic volume. The final Landslide Risk Map highlights critical risk clusters along major transportation corridors traversing weak geological formations, steep slopes, and high-precipitation areas. This quantitative approach provides a focused decision-support tool for regional authorities to prioritize geotechnical monitoring and allocate resources for road infrastructure improvement and safety.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060245

Authors: Ricardo Gacitua Javier Pereira Hernán Astudillo Carla Taramasco Pedro Contreras

Background: Multi-criteria decision analysis (MCDA) has become a dominant approach for glacier hazard susceptibility mapping, widely used to support risk management and climate adaptation planning. However, despite its widespread adoption, the role of MCDA outputs remains conceptually ambiguous: hazard classifications are often interpreted as predictive representations of risk, even though they are derived from preference-dependent decision models. This raises a critical but underexamined question regarding the reliability of MCDA-based glacier hazard assessments. This issue becomes particularly relevant in the current transition toward data-driven and artificial intelligence (AI)-based approaches for hazard modelling, where similar challenges of interpretability, validation, and reliability arise. Methods: To address this issue, we conducted a systematic literature review following the PRISMA 2020 protocol, analysing peer-reviewed studies published between 2015 and 2025. After screening 571 records, 60 studies were included. Data were extracted using a structured framework and synthesised through quantitative descriptive analysis and qualitative assessment of modelling practices, including method selection, criteria weighting, uncertainty treatment, validation, and geographical distribution. This study conducts a structured methodological audit—not a catalogue—of multi-criteria decision analysis (MCDA) applications in glacier hazard susceptibility mapping. Results: The analysis reveals a consistent methodological pattern. The Analytic Hierarchy Process (AHP) dominates current practice (36/60 studies, 60%), typically implemented through GIS-based weighted overlay with expert-derived weights. Critically, 80% of studies (48/60) derive criteria weights exclusively from expert judgement, with no data-driven calibration or sensitivity testing of subjective inputs. This epistemic reliance on unstructured or semi-structured expert elicitation, presented without robustness analysis, forms a central concern of this review. Moreover, empirical validation is limited: only 21/60 studies (35.0%) report quantitative performance metrics. Uncertainty and robustness analyses are rarely conducted, and most studies rely on single-model configurations without comparative evaluation. Despite these limitations, the resulting hazard maps are frequently presented as objective spatial predictions. The evidence base is also geographically concentrated, with 48/60 studies (80.0%) located in High Mountain Asia. Conclusions: The findings indicate a systematic mismatch between how MCDA-based hazard maps are constructed and how they are interpreted. In most cases, MCDA functions as a decision-structuring framework rather than a validated predictive model, yet its outputs are commonly treated as predictive evidence. This gap has important implications for the use of such models in risk management and climate adaptation, particularly in the emerging context of AI-driven hazard modelling, where issues of model validation, interpretability, and reliability become even more critical. Advancing the field requires explicit validation against observed events, systematic robustness and sensitivity analysis, transparent uncertainty modelling, and comparative evaluation of alternative or hybrid decision frameworks.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060244

Authors: Paul J. Markakis Jordan M. Malof Leslie Collins Kyle Bradbury

Point data, such as population, disease incidence, and greenhouse gas emissions, are commonly aggregated to a uniform grid of raster data for storage and representation. In many remote sensing applications, polygons are instead used to describe regions of interest (e.g., countries and cities) which form the spatial basis for analysis. The values associated with these polygons are estimated by aggregating the underlying gridded raster data within the boundary of the polygon. The conventional approach to this aggregation relies on determining if the grid cell centroid lies within the polygon, which has accuracy limitations with potentially severe consequences. In this work, we quantify the consequence of sub-optimally aggregating gridded raster data to polygons, demonstrating that the use of the centroid alone is rarely the most accurate. Across real-world population, greenhouse gas emissions, and snowfall datasets, we further demonstrate that these aggregation-method differences emerge systematically across commonly used geographic boundaries, particularly for coarse-resolution raster datasets aggregated to county- and city-scale polygons. We compare centroid aggregation with proportional aggregation and bilinear interpolation using 2× and 10× upsampling. The centroid method is consistently sub-optimal, generally underperforming alternative aggregation methods when the polygon area is larger than the grid cell area. Worse, the centroid method may exhibit up to 100× the error of the other aggregation methods when polygon area is no larger than grid cell area. Our findings suggest that centroid aggregation is often sub-optimal relative to alternative approaches, particularly in low-PGR settings.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060243

Authors: Xinyu Chen Yin Ma Kai Wu Xing Pang Guoqing Li Ruikai Ma Linhan Yang Chuang Peng Jiayu Zhi Jiabin Yuan

Automated linkage between geoscientific literature and datasets is essential for improving data reuse, reproducibility, and knowledge discovery, yet existing methods often struggle with implicit dataset references, heterogeneous spatial–temporal expressions, and inconsistent naming conventions. To address this problem, we propose a literature–data linkage framework that integrates candidate retrieval, large language model (LLM)-based structured extraction, normalization, and knowledge graph construction. The framework first identifies candidate fragments through BM25-based retrieval, regex filtering, and whitelist-assisted scoring, and then applies schema-constrained prompting to extract dataset names and key attributes, including temporal coverage, spatial scope, resolution, provider, and role. The extracted results are subsequently normalized to canonical forms and ingested into a Neo4j-based knowledge graph linking articles, datasets, institutions, and regions. Experiments on a cross-journal benchmark show that the proposed framework achieves 93.79% precision, 90.66% recall, and 92.20% F1-score. Comparative experiments across multiple LLM backbones further indicate that the framework remains effective across both proprietary and open-source models, while ablation results confirm that candidate retrieval and normalization are the two most influential components for balanced extraction performance. The resulting knowledge graph provides a structured representation of literature–data linkages and supports exploration of dataset reuse patterns, provenance relations, and cross-document connections. These results demonstrate that carefully constrained LLM extraction, combined with retrieval and normalization, provides a robust and interpretable pathway for transforming unstructured geoscientific literature into structured and reusable knowledge.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060242

Authors: Fang Liu Tianrui Li Jiangtao Li

The widespread use of mobile Internet- and location-based services has generated large-scale check-in data in location-based social networks, creating opportunities for intelligent urban-mobility analysis and personalized mobility services. Making the next point-of-interest (POI) recommendation is an important task in this setting because it supports context-aware destination suggestion, travel assistance, and smart mobility services. However, existing methods still face challenges in jointly modeling higher-order mobility patterns, uneven time intervals, geographic reachability, and fine-grained intra-day temporal regularities. To address these issues, this paper proposes ASTHN, an Adaptive Spatio-Temporal Hypergraph Network for next POI recommendation. ASTHN constructs three fine-grained spatio-temporal context hypergraphs from minimum time interval, spatial proximity, and hourly preference, and uses hypergraph neural networks to learn view-specific POI representations. A context-adaptive fusion module then aligns and integrates multi-source spatio-temporal signals, while an ST-GRU with spatio-temporal gates captures dynamic trajectory evolution. Temperature scaling is further applied at the output layer to alleviate overly concentrated score distributions. Experiments on Foursquare-NYC and Foursquare-TKY show that ASTHN consistently outperforms representative baselines. With results reported as mean ± std over three random seeds, ASTHN improves over the strongest baseline by 3.79%, 14.62%, 2.28%, and 1.24% on NYC in Recall@5, Recall@10, NDCG@5, and NDCG@10, respectively. On TKY, the corresponding improvements are 5.83%, 37.20%, 13.86%, and 20.49%. Ablation, parameter, complexity, and application-oriented case analyses further demonstrate the effectiveness, stability, and practical usability of ASTHN for next POI recommendation in urban-mobility scenarios.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060241

Authors: Eva Savina Malinverni Marsia Sanità

Hybrid classification approaches, combining pixel-based and object-based classification models, are being increasingly adopted to overcome the inherent limitations of Very-High-Resolution (VHR) image analysis. This paper proposes a hybrid classification framework that integrates probabilistic pixel-based classification, object-based aggregation, and rule-based refinement to produce GIS-ready Land Use/Land Cover (LULC) maps specifically designed for urban and regional planning. WorldView-2 imagery is first processed using an AdaBoost classifier to derive pixel-level class memberships; these results are subsequently aggregated at the object level (OBIA classification), following segmentation. Beyond thematic labeling, a Stability Map is introduced to quantify intra-object classification reliability, enabling the spatial identification of unstable or heterogeneous objects. The novelty lies not only in the integration of pixel and object paradigms but also in the operational utility of the Stability Map. When combined with rule-based reasoning, it provides a decision-oriented GIS product. The results demonstrate superior classification accuracy and enhanced interpretability compared to standard pixel-based or object-based approaches, highlighting the framework’s relevance for geospatial data analysis and planning-oriented applications.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060240

Authors: Zexuan Liu Jiaji Gao Jun Yang

Against the background of industrial transformation and urban regeneration in old industrial bases, understanding the spatial pattern and driving mechanisms of industrial heritage is essential for its conservation and sustainable use. This study investigates 277 industrial heritage sites in Liaoning Province (including nationally designated sites, potential heritage within cultural relic protection units at all levels, and sites recognized by the China Association for Science and Technology) using kernel density estimation, standard deviation ellipse, and the GeoDetector model. The results reveal a significantly clustered distribution characterized by “dense in central–southern Liaoning, sparse in the periphery,” forming three major agglomerations: the Shenyang core, the Anshan–Benxi–Liaoyang heavy industry triangle, and the Dalian coastal industrial belt. Temporally, the distribution shows distinct phases closely linked to industrial development history and major socio-political events. Land use, GDP, and climatic factors dominate the spatial differentiation, with GDP and annual average temperature exhibiting the strongest combined explanatory power (41.67%). Based on these dominant factors and the identified core agglomeration areas, differentiated protection and utilization strategies should be formulated for core versus peripheral areas, different industrial types, and various historical periods. This provides direct empirical evidence for industrial heritage management and cultural revitalization in old industrial regions.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060239

Authors: Qianlong Rao Jiakai Li Meng Zhang Xinqi Liang Xunyu Liu Miao Lu Yingqiang Song

Understanding land-use change and landscape-pattern responses in large river basins is important for spatial optimization and ecological-security maintenance. Previous studies have often examined land-use dynamics or landscape-pattern change separately, leaving limited evidence on their coupled structural relationships and on how future land-use configurations may diverge under alternative policy scenarios. To address this gap, this study examines the Yangtze-Yellow River basins using multi-temporal land-use data from 2000 to 2020. By combining land-use transition analysis, dynamic-degree analysis, centroid-migration analysis, landscape metrics and the Patch-generating Land Use Simulation (PLUS) model, we construct an analytical framework that links historical land-use restructuring, landscape-pattern response and multi-scenario simulation. The results show that land-use change from 2000 to 2020 was dominated by bidirectional conversion among cropland, forest and grassland, together with continued built-up land expansion. Forest and built-up land increased by 12,886 km2 and 19,085 km2, respectively, whereas cropland and unused land decreased by 35,468 km2 and 18,145 km2, indicating clear structural adjustment and regional differentiation. Landscape metrics further indicate that land-use restructuring was accompanied by increasing fragmentation and heterogeneity: the number of patches (NP) increased from 170,699 to 178,701, Shannon’s diversity index (SHDI) rose from 1.4025 to 1.4272, and contagion (CONTAG) declined from 32.2854 to 31.0796. The 2030 simulations reveal distinct scenario trade-offs. Under the natural development scenario, cropland decreases by 9653 km2 and built-up land expands by 9778 km2, suggesting continued pressure from construction-space expansion. Under the cropland-protection scenario, cropland increases by 4063 km2, but grassland decreases by 5868 km2, indicating that cropland retention may partly transfer pressure to ecological land. Under the sustainable development scenario, cropland loss is reduced to 5244 km2, forest increases by 5547 km2, grassland shifts to a slight increase of 422 km2, and built-up expansion slows to 7731 km2, suggesting a more balanced pathway for coordinating built-up land control, ecological continuity and land-use structure optimization. Overall, these findings offer a quantitative reference for coordinating territorial spatial planning, land-resource allocation and ecological-security maintenance in the Yangtze-Yellow River basins.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060238

Authors: Jiawei Li Yuli Han Chong Chen Tingdi Chen Xianghui Xue Liangyu Pu Zhaowang Su Hengjia Liu Shuhua Zhang Jing Yang Dongsong Sun

Large language models (LLMs) offer new possibilities for natural-language interaction with geospatial analysis systems, but their use in remote sensing instrument data analysis remains limited by weak execution control, poor reproducibility, and limited integration with domain-specific computation. The paper presents an agent for Incoherent Doppler wind LiDAR (ICDL) data analysis, named ICDL-Agent, a tool-augmented LLM framework for remote sensing instrument workflows. The system maps conversational user requests to executable analysis pipelines for wind retrieval, uncertainty estimation, visualization, and higher-level diagnostics through structured planning over a registry of domain-specific tools. To improve execution reliability, the system combines schema-constrained workflow generation, shared-state reuse of intermediate scientific products, and validation with bounded repair. In addition to supporting routine LiDAR processing, the framework can generate new tools when required and adapt to related analytical tasks through domain-aware guidance and procedural documentation. We evaluate the system on multiple atmospheric wind-observation datasets in China and show that it faithfully reproduces the refined Doppler wind-retrieval pipeline, achieving representative R2/MAE values of 0.52/3.73 m/s against ERA5 and 0.80/2.31 m/s against radiosonde observations, while supporting downstream analyses such as profile comparison, climatological interpretation, and gravity-wave diagnostics. More broadly, this study demonstrates how constrained LLM orchestration can support LiDAR researchers, remote-sensing instrument teams, and geospatial analysts seeking transparent, reproducible, and automated scientific data-processing workflows.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060237

Authors: Jianjun Shi Jiayi Sun Wenxin Shan Yongsheng Jia Yingkang Yao Hongsheng Wang

The assessment of tunnel blasting effects traditionally relies on manual inspection and contact measurements, which are subjective, inefficient, and lack comprehensive quantification. To address this, this study proposes a novel closed-loop framework that integrates multi-view 3D reconstruction with intelligent recognition for quantitative blasting evaluation and parameter optimization. Rather than claiming novelty in these basic computer vision algorithms, the novelty of this work lies in their tunnel blasting oriented integration: reconstructed geometry is converted into blasting relevant indicators and then linked to parameter adjustment decisions within a closed-loop workflow. The framework begins with a standardized image acquisition workflow designed for challenging tunnel environments (e.g., dust, uneven light), followed by image enhancement using histogram equalization and bilateral filtering. A key improvement is an enhanced SIFT feature matching strategy, which incorporates a BBF optimized K-D tree and RANSAC to achieve robust correspondence establishment on texture-repetitive rock surfaces. This enables the generation of high-precision 3D models of the tunnel face via Structure from Motion (SfM) and Poisson surface reconstruction. From these models, quantitative indices are automatically extracted: rock mass structural planes are clustered via the ISODATA algorithm, structural traces are delineated using a minimum cost path method, and face flatness is evaluated through curvature analysis. These indices form the basis for intelligent blasting assessment. Crucially, the assessment results are directly fed back to optimize blasting parameters (e.g., adding cut holes, adjusting auxiliary hole spacing). Field application in the Huangtai Tunnel demonstrated that this closed-loop framework significantly improved face flatness (achieving over 50% improvement in the high-curvature area ratio) and contour control. Further verification in the Donghongshan Tunnel showed that the proportion of the sharp feature region decreased from 20.3% to 7.9% after optimization. The proposed framework transitions blasting management from empirical judgment to a data driven, intelligent optimization process, offering a scalable solution for enhancing quality and efficiency in tunnel construction.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060236

Authors: Ying Chen Jixian Zhang Juan Ge Zhanji Peng

Geographical knowledge graphs (GeoKGs) have long experienced several fundamental challenges in representing complex spatial relationships, such as limited dimensionality, insufficient quantification of relationship strength, and weak reasoning capabilities. To address these issues, this study presents the multidimensional spatial relation knowledge graph (MDSR-KG) framework. The novelty of this framework lies in advancing the shift toward spatial relation node-based representation, thereby elevating the spatial relations from edge structures to independent, computable, and inferable structured nodes. This approach was complemented by a parametric method aimed at quantifying the relation strength between nodes, thereby facilitating an advancement from discrete relations to continuous and interpretable association weighting. In experiments conducted in this study using the Berlin OpenStreetMap data, we noted that for complex spatial queries, the MDSR-KG framework significantly outperformed the baseline models in accuracy and completeness. The framework also exhibited advanced reasoning capabilities, such as ranking and recommendation, which are lacking in traditional methods. Thus, the framework lays a theoretical foundation for advancing from geographic feature recognition to spatial relationship comprehension.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060235

Authors: Zhen Lei Ting L. Lei

Integer Linear Programming (ILP) is a powerful way to formulate sophisticated optimization models for making geospatial decisions in GIS. One of the general modeling constructs in ILP is the multi-level closest assignment (MLCA) constraint in the reliable facility location models with facility failure considerations. Compared with simpler constructs (such as the single-level closest assignment constraint), it involves assigning customers to backup facilities when the closer facility is unavailable. Part of the art of ILP modeling is to find suitable linear constructs to express such complex logic. The desired linear constructs may or may not exist. Even if a model construct is given, whether it can faithfully enforce the intended meaning is unknown. The correctness of the modeling construct is often shown based on informal reasoning or is not verified at all. Consequently, unverified ILP models may be (occasionally) infeasible or give wrong solutions. With the advancement of computerized theorem proving, it is becoming possible to mechanically prove the correctness of modeling constructs in ILP. In this article, we demonstrate that sophisticated model constructs such as MLCA can be proven using induction. This overcomes the inabilities of prior works to handle multiple levels of recursive definitions. Consequently, we are able to provide a first proof (formal or informal) that the specific MLCA form is mathematically correct. Given the generality of the induction method, we expect that it can be applied to prove the correctness of other types of models.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060234

Authors: Jinyu Zhang Deqin Fan James Haworth Xuesheng Zhao Hanxiao Zhai Dongxue Han

Point-of-interest (POI) data are widely used to spatialize and predict socioeconomic variables, yet their consistency across regions and over time, as well as their cross-regional generalizability, remain insufficiently understood. This study examines these issues using county-level units in China for 2010 and 2020 from three perspectives: relationship structure, cross-regional generalization, and model improvement. First, a power-law model is applied to characterize the nonlinear relationship between POI density and population density and to assess its spatiotemporal heterogeneity. Second, generalizability is evaluated by comparing model parameters and predictive performance under random and spatially stratified sampling. Third, multi-source geospatial data, including nighttime lights, road networks, and land use, are integrated to compare linear, spatial, machine learning, and ensemble models. Results reveal a consistent sublinear relationship with strong spatial heterogeneity. Under spatially independent validation, predictive accuracy declines and becomes more variable, indicating limited cross-regional generalization. Integrating multi-source data with ensemble learning improves stability and reduces uncertainty. POI remains the dominant predictor, though its relative importance becomes more concentrated in 2020. Overall, the study highlights the limitations of POI-based population estimation and proposes strategies to enhance robustness and generalizability.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060233

Authors: Fragkiskos Gryllakis Nikos Pelekis Christos Doulkeridis Yannis Theodoridis

This work presents a trajectory indexing pipeline for accelerating Social Spatio-Temporal Keyword Pattern (S2KP) queries over Multiple-Aspect Trajectory (MAT) data. An S2KP query forms a sequence of spatial, temporal, textual, and social-rating constraints over trajectory episodes. The constraints are formulated in the form of regular expressions, thus offering high expressiveness and flexibility in query formulation. In this paper, we enhance spatial pruning by enhancing a well-established MAT index, the Episode-Based Multiple-Aspect Trajectory (EMT) Dual Index. The EMT Dual Index is augmented with curve-based keys (Hilbert, Z-order, and Gray-coded Z-order mappings), so that spatially related entities are projected into one-dimensional key ranges, enabling additional subtree pruning through interval overlap while preserving exact final matching semantics. The intervals are induced by the numbering of cells generated by a curve. Our experimental study on two representative MAT datasets (one synthetic and one real) demonstrates the effectiveness of our proposal.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060232

Authors: Liping Yan Peiran Wu Shaofeng Wang Haojie Jia Jingkai Huang

Ride-hailing dispatch systems face significant challenges under fluctuating demand and dynamic traffic conditions, where efficient coordination is essential for both platform performance and driver income among large-scale ride-hailing vehicles. This paper constructs a grid-based ride-hailing vehicle dispatch decision model (GRV-DDM), which provides a structured and quantifiable representation of vehicles and orders, effectively capturing spatio-temporal heterogeneity in dynamic traffic environments. Based on this model, a Bi-Level Optimization Multi-Directional Dispatch Decision Algorithm (BO-MDDA) is proposed. At the macro level, evolutionary game theory is employed to adaptively guide collective vehicle strategies toward supply–demand equilibrium, while at the micro level, deep reinforcement learning optimizes individual drivers’ real-time dispatch decisions to maximize long-term profits. A bidirectional feedback mechanism is further designed to integrate macro-level collective intelligence with micro-level individual decision-making. Experimental results across diverse traffic scenarios demonstrate that the proposed approach outperforms classical dispatch algorithms in terms of efficiency and robustness.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060231

Authors: Lieven Raes Joep Crompvoets

The expansion of accessible, fine-grained city data has significantly increased opportunities for evidence-based and informed policy-making. Despite this evolution, extracting actionable insights from heterogeneous data sources and effectively communicating findings remain persistent challenges. Most existing visualisation approaches and research prioritise technical implementation by focusing on how to visualise, often neglecting the importance of policy-driven visualisation questions and data contexts. This led to flawed analyses, particularly in complex domains such as smart cities and urban policy-making using digital twins. This article presents a novel, practical, step-by-step policy visualisation methodology grounded in empirical smart city research, shifting the emphasis toward policy-element-based questions informed by data-informed evidence. The methodology was successfully applied, tested, and adapted, resulting in an implementable, structured, and integrative approach that aligns with policymakers’ established policy design, implementation, and evaluation cycles. Through this approach, 20 user-driven smart city policy visualisations were operationalised and implemented in strategic policy decision-making contexts across smart city domains, including mobility, spatial planning, and environment. The results demonstrate how dashboards, algorithmic simulations, and digital twins visualisations can be systematically deployed to support evidence-informed decision-making.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060230

Authors: Junyi Shi Lijun Yu Ze Liu Hui Wang Yueping Nie

Linear heritage corridors are increasingly exposed to spatially heterogeneous pressures from climate change and human activities, yet integrated geospatial frameworks for corridor-scale risk identification remain limited. Taking the Beijing–Hangzhou Grand Canal as a representative linear World Heritage corridor, this study developed a GIS-based spatiotemporal assessment framework to quantify natural risk, anthropogenic pressure, and their coupled patterns during 1995–2024. Approximately 350 canal segments were constructed as comparable assessment units and linked with 49 heritage sites and 18 World Heritage canal sections through a multi-scale spatial framework integrating canal sections, buffer zones, and heritage sites. Natural risk was characterized using extreme temperature, precipitation, and drought indices, while anthropogenic pressure was represented by nighttime lights, population density, impervious surface, and road density. The results reveal a clear north–south gradient in integrated natural risk, with higher values concentrated in the southern canal sections. Among the three natural-risk modules, temperature, precipitation, and drought contributed weights of 0.594, 0.242, and 0.164, respectively, indicating the dominant role of heat-related processes. The first two principal components of anthropogenic pressure explained 80.8% of the total variance. Four dominant coupling types were identified, among which the dual high-pressure type was concentrated mainly in the southern canal and marked the most critical areas of compound risk. This study provides a geospatial approach for hotspot detection and spatial decision support for the conservation of large linear heritage systems.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060229

Authors: Liping Yan Haojie Jia Shaofeng Wang Peiran Wu Wenzhi Zhao

Multi-Agent Reinforcement Learning (MARL) provides an effective approach for urban multi-intersection traffic signal control. However, existing methods have faced two fundamental challenges, policy homogenization and inefficient credit assignment. The former led to convergent agent policies that failed to adapt to heterogeneous traffic patterns, while the latter prevented agents from accurately evaluating their individual contributions to system performance. To address these issues, this paper proposes a Multi-Agent Hierarchical Contrastive Learning Traffic Signal Control (MAHCL-TSC) model. The model incorporates an unsupervised contrastive learning module that enhances the discriminative power of state representations, thereby alleviating policy homogenization. Additionally, it designs a hierarchical graph convolutional credit allocation network that leverages road network topology and functional characteristics to enable structure-aware collaborative value estimation, significantly improving the precision of credit assignment. Based on these components, a Contrastive QTRAN with Hierarchical Graph Convolution (CQTRAN-HGC) algorithm is proposed, which jointly optimizes contrastive learning loss and QTRAN constraint loss. Experiments conducted in the Simulation of Urban Mobility (SUMO) simulation environment on 4 × 4 and 6 × 6 synthetic grid networks demonstrate that the proposed model improves traffic signal control performance under the tested structured simulation settings and shows potential scalability as the network size increases.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15060228

Authors: Dulce Mata Paula Gil Ángela Bellido Olvido Tello

Spain’s extensive marine jurisdiction—comprising a continental shelf of approximately 100,000 km2 and an Exclusive Economic Zone approaching one million km2—requires robust geospatial frameworks to support ecosystem assessment and marine policy implementation. This study presents GIS-based methodologies developed by the Spanish Oceanographic Institute (IEO-CSIC) within national initiatives such as LIFE IP INTEMARES project and the implementation of Marine Strategy Framework Directive (European Directive 2008/56/EC). The geospatial workflows developed for these initiatives integrates heterogeneous spatial datasets—such as multibeam bathymetry, acoustic backscatter, Remote Operated Vehicle (ROV) and towed-camera transects, sediment samples, oceanographic profiles, and species-habitat occurrence records—into a unified spatial analysis environment. Applied methods include digital terrain modeling, derivation of geomorphometric indices (e.g., slope, rugosity, curvature), image classification, and spatial statistics to quantify habitat extent, condition, and anthropogenic pressures. An integrated spatial analysis framework combining environmental and anthropogenic data is used to support zoning and management decisions within Marine Protected Areas (MPAs). Additionally, the deployment of WebGIS platforms facilitates data dissemination, iterative review, and stakeholder engagement, thereby enhancing transparency and accessibility. The resulting high-resolution maps, harmonized datasets, and computed spatial indicators—aligned with Marine Strategy Framework Directive (MSFD) descriptors such as habitat distribution (D1C4–C5) and seafloor integrity (D6C2–C3)—demonstrate how GIScience methods provide reproducible, decision-ready information to support the monitoring and management of Spain’s diverse marine ecosystems.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050227

Authors: Péter Czomba Klára Czimre Károly Teperics Gyöngyi Bujdosó Ernő Molnár Gábor Négyesi Bálint Bence Juhász

Enhancing spatial orientation and map-reading skills is a cornerstone of geography education, yet the comparative efficacy of physical versus virtual reality learning environments (VRLEs) remains a subject of ongoing debate. This study evaluates the development of navigational competencies through a counterbalanced crossover experimental design involving 20 geography and geography teacher major students. Participants performed standardized spatial tasks, including bearing calculation and distance estimation, in both the volcanic landscape of the Tapolca Basin, Hungary, and its smartphone-based 360-degree virtual reality (VR) counterpart. To assess longitudinal retention and cross-modal transfer, a three-month interval was maintained between the two learning phases, supported by a robust pre-test/post-test framework. Results indicate that while both environments are susceptible to spatial distortions driven by the visual dominance of physiographic landmarks, VR-based training effectively scaffolds the cognitive frameworks required for real-world navigation. The findings confirm that spatial mental models acquired in a virtual setting possess significant cognitive resilience, as navigational accuracy was maintained over the three-month interval. In conclusion, this research justifies a hybrid pedagogical approach, where immersive digital simulations serve as a preparatory tool for physical fieldwork. The synergy of both modalities is essential for cultivating the resilient spatial intelligence required for professional geographic practice.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050226

Authors: Wenjuan Lu Dongping Ming Xi Mao Jizhou Wang Pengda Wu

In the contemporary field of geographic information, place name services serve as a core application support in geographic information science, widely applied in public services, cultural tourism, emergency management, and other scenarios. Place name service composition is a critical link in the integration of spatiotemporal knowledge and intelligent services for place names, determining the ability to rapidly solve complex place name problems. Traditional case-based reasoning methods are primarily rule-driven, making it difficult to deeply integrate semantic and graph structural features, and they also lack precision in measuring the similarity of multi-type place name service cases. To address this, this paper integrates knowledge graphs and case-based reasoning to propose a place name service composition method that balances semantic and graph structural similarity, aiming to enhance the response efficiency and recognition accuracy of complex natural language queries. The method consists of two steps: the first is constructing a knowledge graph case base. Semantic feature extraction is performed on the standard geographic question-answering standard dataset GeoQuery corpus to build a place name service knowledge graph case base that integrates semantic associations and spatial attributes. The second step is constructing a similarity model. The method combines four similarity measures—DeBERTa, TF-IDF, SimHash, and maximum common subgraph—and employs the Analytic Hierarchy Process for weighting to develop a novel similarity evaluation model for case-based reasoning. Experiments demonstrate that this method achieves a 21% improvement in F1-score compared to traditional rule-based methods. Furthermore, the developed prototype system for the intelligent recommendation of place name service composition achieves a recommendation accuracy of 92.64%. This research holds significant practical implications and application value for advancing the geographic information field toward intelligent and precision-based development.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050225

Authors: Ziye Liu Jianyu Li Shumin Wang Jingyue Huang Mingxing Hu

Free-floating bike-sharing (FFBS) systems play a valuable role in alleviating traffic congestion and reducing carbon emissions, making them vital to sustainable urban transportation. Although extensive research has investigated the relationship between the built environment and cycling behavior, the adverse effects of air pollution and its interaction with the built environment remain insufficiently understood. In this study, multisource data from Shenzhen are used, and an XGBoost–SHAP model is employed to comprehensively investigate the nonlinear associations among the FFBS trip volume, built environment, and air pollution while considering the spatial heterogeneity in interaction effects. The results indicate that population density, road density, building density, and PM2.5 are the most influential factors. In addition, significant temporal heterogeneity is observed between weekdays and weekends. The effects of the built environment variables and their interactions are more pronounced on weekdays than on weekends. More importantly, an interaction analysis reveals that the positive influence of compact urban development on cycling is conditional: in high-density areas with elevated pollution exposure, the health risks associated with air pollution can offset or even outweigh the mobility benefits of compactness. Overall, this study identifies the complex, spatially heterogeneous mechanisms through which the built environment and air quality jointly shape FFBS usage. These findings provide important evidence for integrating environmental health considerations into compact city planning and offer practical insights for promoting cycling and sustainable urban mobility in high-density cities.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050224

Authors: Yanbin Hu Wenhui Zhou Yi Li Hongzhi Miao

Road disasters such as subsidence and bridge failures pose severe threats to traffic safety. Existing warning distance calculation methods typically assume homogeneous traffic flow and overlook the spatial heterogeneity of vehicle responses across different vehicle types, limiting their applicability for geospatial early warning systems. This paper proposes a dynamic warning distance model that integrates mixed-traffic flow composition—comprising human-driven vehicles (HDVs), Level 2 advanced driver-assistance system vehicles (ADASVs), and automated vehicles (AVs) of Level 3 and above—within a geospatial risk propagation framework. The model introduces vehicle-type weighting coefficients to quantify response differences, incorporates interaction delays calibrated through SUMO microsimulations, and accounts for cascading reaction delays caused by abrupt HDV braking. The methodology is illustrated using a counterfactual reconstruction of the 2024 Meizhou–Dapu Expressway collapse in China (52 fatalities). Based on reconstructed traffic conditions (80% HDVs, 15% ADASVs, 5% AVs; average speed 27.5 m/s; flow 1800 veh/h), the calculated dynamic warning distance is 153 m, which is 12% shorter than the speed-matched conventional stopping sight distance of 174 m (computed under consistent wet-pavement assumptions). Sensitivity analyses reveal that warning distance decreases substantially with increasing AV penetration (to 42 m in AV-dominated scenarios, a potential reduction of up to 74% compared with the HDV-dominated baseline, provided that residual HDVs are supported by V2X-based alerting) and varies monotonically with traffic flow, demonstrating the model’s adaptive capability. The proposed framework provides a theoretical foundation for adaptive geospatial disaster warning strategies and offers practical guidance for infrastructure development in the era of mixed-traffic automation.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050223

Authors: Emad Felemban Muhammad Hammad Faizan Ur Rehman

Crowd simulation is essential for applications in evacuation planning, transportation systems, urban analytics, virtual reality, and intelligent mobility. Despite substantial progress, research in this field remains fragmented across diverse modeling paradigms, behavioral abstractions, simulation settings, implementation tools, and evaluation practices. To provide a unified overview, this study conducts a Systematic Mapping Study (SMS) of 54 peer-reviewed primary studies published between 2021 and 2025. Guided by a structured set of 15 research questions, the SMS examines dominant modeling paradigms, associated modeling techniques, spatial representations, behavioral layers, learning methods, and agent capabilities. The study further analyses simulation characteristics—including behavior types, granularity levels, temporal modes, environment types, and application domains—alongside implementation aspects such as programming tools and simulation platforms. Additionally, the mapping covers evaluation practices by identifying reported performance metrics and methodological approaches. Based on the extracted evidence, we propose a comprehensive taxonomy. The results highlight prevailing trends, gaps, and fragmentation in crowd simulation research, including uneven reporting of metrics, limited integration of learning-based methods, and inconsistencies in behavioral modeling. The study also synthesizes key technical challenges and corresponding solutions proposed in recent literature, offering a structured foundation for future research.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050222

Authors: Lin Yang Hui Li Peng Yu Weihong Wu

The reconstruction of ancient geographical scenarios is significant for understanding environmental changes and civilizational evolution. However, human activities, as the main subjects in these scenes, cannot be directly reconstructed due to the lack of written records. Archaeological sites, formed through long-term human activities and natural processes, preserve material traces of ancient human behaviors within specific spatiotemporal contexts and provide critical evidence for inferring behaviors lacking written records. However, behavioral processes within site scenarios are difficult to observe and express directly. To address this challenge, we proposed a behavioral inference mapping method based on archaeological remains, integrating geography, archaeology, and behavioral science to support the inference and structured expression of ancient human behaviors. We first analyzed the relationships between behaviors and remain elements, and developed principles for inferring ancient human behaviors from remains. Secondly, combined with spatial analysis of geographic entities, we proposed multiscale geometric representations, methods for extracting and analyzing the geographical features of remains. We constructed a rule-driven mapping method of geographical features of archaeological remains and ancient human behaviors. Finally, the Taixi Site in Hebei Province and the Lingjiatan Site in Anhui Province were used as examples to verify the applicability and effectiveness of this method. This approach bridges remains and ancient human behaviors, demonstrates strong adaptability for behavioral-process inference, and provides new perspectives for settlement landscape reconstruction.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050220

Authors: Ziqiang Li Jianchao Xi Sui Ye Zumilaiti Aihemaitijiang

Tourism safety in high altitude destinations is strongly affected by the combined effects of environmental constraints, tourism exposure, and safety support capacity. The Qinghai–Tibet Plateau (QTP), characterized by high altitude, complex terrain, sparse settlements, and limited emergency accessibility in remote areas, provides a representative case for tourism risk assessment in extreme plateau environments. To predict and interpret the spatial pattern of tourism risk on the QTP, this study constructs an assessment framework based on “Hazard–formative factors + Risk exposure + Safety security” and integrates XGBoost with SHAP interpretable machine learning. Eleven indicators representing environmental conditions, tourism exposure, and safety support capacity were used to model tourism risk at a 1 km × 1 km spatial resolution. The optimized XGBoost model achieved an AUC of 0.877, indicating good predictive performance. The results show that tourism risk on the QTP presents a spatial pattern of “high in the northwest and low in the southeast”. High risk and relatively high risk areas account for approximately 74.98% of the study area and are mainly distributed in remote hinterlands and northwestern plateau regions, whereas low risk areas are concentrated around southeastern river valleys, towns, mature scenic areas, and major transport corridors. SHAP analysis indicates that Distance to towns is the most important factor influencing predicted tourism risk, followed by Reception facility kernel density, Relief degree of land surface, and Scenic spot kernel density. Nonlinear and interaction analyses further suggest that remoteness, tourism facilities, terrain relief, and scenic area concentration jointly shape the predicted risk pattern. The findings provide spatial evidence for differentiated tourism risk management, including regular tourism development in relatively safe urban and scenic nodes, controlled management of medium risk tourism corridors, and stricter access management in remote high risk areas.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050221

Authors: Qing Han Zicheng Wang Chao Yin Zhiwei Hou Tianci Yao

Large-scale classification of architectural styles in Chinese traditional settlements is important for heritage conservation and geospatial documentation, but scalable deployment remains constrained by the high cost of expert annotation because villages are widely distributed, the imagery is captured from heterogeneous viewpoints, and each architectural tradition exhibits substantial intra-class variation. To address this bottleneck, we propose CTSMatch, a label-efficient semi-supervised framework that combines an ImageNet-pretrained EfficientNetV2 backbone with SoftMatch-based adaptive pseudo-label weighting so that ambiguous but informative unlabeled samples can still contribute to training, thereby reducing reliance on costly expert annotation. We also construct SemiCTS, an extension of the original CTS dataset that adds 4360 unlabeled images. Using only 545 labeled samples, CTSMatch achieves 96.93% accuracy on SemiCTS, outperforming the strongest fully supervised baseline (Dense-TL-Aug) by 2.73 percentage points and two standard semi-supervised baselines (FixMatch and FreeMatch) by 3.06 percentage points. Beyond classification, we further analyze the feature space to examine stylistic lineage through intra-style heterogeneity, inter-style transitions, and outlier detection. The results reveal two broad regional groupings, a northern cluster (Jing, Jin, Su) and a southern cluster (Chuan, Min, Wan), connected by gradual transitions rather than rigid boundaries. Approximately 15% of the samples are identified as atypical cases, including 8.7% comprising regional variants and 6.3% comprising hybrid forms. These findings show that CTSMatch provides a practical label-efficient framework for architectural heritage classification while supporting the interpretable analysis of stylistic diversification and convergence in Chinese traditional settlements.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050219

Authors: František Mužík Lukáš Běloch

In recent years, augmented reality has become a popular method of spatial data visualization, both via the most popular and basic plane-based method and more advanced automatic positioning of visualizations based on predefined real-world locations. The aim of this study is to provide new insights into geolocated 3D visualizations in AR using a visual positioning system (VPS). VPS technology enables the creation of visualizations that can be displayed with high accuracy directly on a specific area of interest. This approach is especially well-suited to cultural heritage preservation, as it can be used to visualize destroyed buildings or archaeological sites. The result of the study is a mobile application created using the Unity game engine, which allows users to access AR visualizations as well as additional context in the form of pop-up texts or photographs. Thanks to the display of AR visualization directly at the chosen location, the user can better understand the context of the whole scene. This is because it is a more immersive experience than simply viewing a 3D model on a computer or mobile phone screen.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050218

Authors: Qiuxiao Chen Yu Liu Long Zhou Yanguang Chen Heng Chye Kiang Xiuxiu Chen Guoqiang Shen

This research presents a comprehensive spatial–temporal analysis of urban form and growth in Charlotte and Mecklenburg County, North Carolina, USA, from 1900 to 2017 at the land parcel level. Employing a data fusion framework, we integrate diverse datasets—including historical cadastral records, census data, remote sensing imagery, and infrastructure maps—to examine urban morphology through Euclidean and fractal geometries. Urban growth was reconstructed and visualized by decade and cumulatively, revealing dynamic patterns of expansion, densification, and fragmentation. Using scatterplot matrices and the Hausdorff box-counting algorithm, we quantified urban form across major land use types and temporal intervals. The fusion of socio-physical variables with mathematical functions enabled multi-scale modeling of urban transitions, aligning spatial, temporal, and thematic dimensions. Key findings include: (1) multidirectional spatial expansion resulting in a sprawling urban footprint at different rates over 117 years; (2) exponential growth between 1950 and 2000 with slower rates before and after manifesting a classic S-curve urban development by Northam; (3) a pivotal moment in 1993 when urbanized and rural lands reached parity, reflecting balanced urbanization in terms of population and land area for cities and rural areas for Mecklenburg; and (4) consistent quantitative relationships—linear, polynomial, exponential, logarithmic, and proportional—between urban form and growth metrics. This study’s novelty lies in its integrated spatial–temporal framework not only for combining both Euclidean and fractal geometric analyses with fused multi-source data to uncover the evolving structure of urban landscapes, but also for offering valuable insights into efficient land uses to assess equitable land and population dynamics, all aiming to achieve a good understanding of and sound policies for Charlotte, Mecklenburg and beyond.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050217

Authors: Lasith Niroshan James D. Carswell

Geospatial Artificial Intelligence (GeoAI) enables the automated generation of built environment map features, such as building outlines/footprints, on a global scale. However, the integration of these AI-generated datasets into Volunteered Geographic Information (VGI) platforms like OpenStreetMap (OSM) risks incorporating ‘AI slop’, consisting of geometrically inconsistent/unreliable data, into the online map. While the OSM “Code of Conduct for Automated Edits” provides a policy framework for data ingestion, it lacks a machine-enforceable mechanism for real-time quality gating. This paper proposes a GeoAI-Gatekeeper to perform this task—an automated process that applies empirical Acceptable Quality Thresholds (AQT) to address the GeoAI data governance problem. Because the Gatekeeper utilizes an intrinsic, no-reference evaluation of geometric fidelity, it can assess incoming AI-generated data streams in real-time without requiring ground-truth benchmarks. Importantly, it focuses exclusively on the geometric validation of building footprints, acknowledging for now that semantic enrichment, such as tagging, remains a human-centric task. The presented GeoAI-Gatekeeper is a working prototype developed for a specific urban area, systematically triaging incoming AI-generated data into three tiers; Auto-Accept, Manual Review, and Reject. It provides a Web-GIS interface for Human-in-the-Loop (HITL) functionality to ensure the OSM community remains the final arbiter of acceptable data quality. Testing the Gatekeeper in Dublin (Ireland) demonstrates that our solution can auto-ingest 93.6% of features with a 14x reduction in human review effort while still adhering to OSM’s cartographic integrity standards. By implementing qualitative community guidelines into machine-enforceable thresholds, our approach introduces a viable methodology for next-generation hybrid VGI systems. Importantly, it ensures that the transition towards automated data ingestion reinforces, rather than undermines, the reliability of global crowd-source mapping datasets.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050216

Authors: Hai Lan Frances Currin-Brinkman

Translating fine-resolution air pollution surfaces into health equity assessments requires aggregating exposure to administrative units, yet the equity implications of this choice are rarely tested. This study links annual 300 m nitrogen dioxide (NO2) surfaces from the New York City Community Air Survey (2009–2023) with childhood asthma emergency department (ED) visit rates across 42 neighborhoods, comparing area-weighted, population-weighted, and residential-weighted aggregation throughout. Strong spatial convergence was observed in both NO2 and ED burden (Pearson correlations between 2009 baseline levels and Theil–Sen slopes of −0.96 and −0.95). Panel first-difference estimation yielded a significant within-neighborhood association between NO2 decline and ED rate decline (coefficient 0.022, p-value below 0.05). The most deprived fifth of neighborhoods received 47% of the total avoided ED burden, four times the share of the least deprived fifth. However, NO2 reductions were nearly equal across poverty quintiles. The pro-poor distribution of health benefits was driven by baseline health inequality, not by differential pollution reduction. The three aggregation methods produced near-identical results for all metrics because within-neighborhood exposure variability was uncorrelated with poverty (r = −0.14). In cities where baseline disease burden is concentrated in disadvantaged communities, broad-based air quality improvement may contribute to pro-poor health gains without targeted intervention.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050215

Authors: Tong Zhang Yunfei Shi Wenjie Jiang Chunguang Lyu Shuangshuang Shi

Large-scale WebGIS visualization of 3D building models is often constrained by large requested payloads, client-side memory pressure, and runtime state-parsing overhead. This study proposes a five-dimensional orthogonal decoupling framework and a 16-bit state-word-driven scheduling method for 3D building models. The Boundary-based Spatial Proxy–Geometric Detail–Component Complexity–Texture Appearance–Semantic Information (B-D-C-T-S) framework organizes model representations into five separately addressable and schedulable dimensions, covering spatial proxies, geometry, components, textures, and semantics. A compact 16-bit structured state word is used to represent runtime states and reduce dependence on repeated text-based state parsing, supporting fixed-offset bitwise decoding, exclusive-OR (XOR)-based differencing, constraint checking, and incremental updating. A centroid-assigned Home Tile strategy is further introduced to reduce redundant semantic payloads for cross-tile objects. The method was evaluated using a single-building BIM model and an urban-scale photogrammetric mesh dataset. Under the tested initial-view setting, staged decoupled loading reduced the first-screen requested payload by 93.1% compared with monolithic loading. State-word-based C-field extraction achieved an approximately 144-fold speedup over JSON deserialization and C-field lookup. The Home Tile strategy reduced the total semantic payload by 44.1% in the semantic-redundancy test. In the 1.12 GB first-screen memory test, state-word-driven D1 tile scheduling loaded only 22.7 MB of physical payload, with stable resident memory of approximately 88.1 MB. These results indicate that the proposed method supports object-level state representation, selective resource activation and scheduling, Home Tile semantic routing, incremental updating, and first-screen memory control within tiled Web3D pipelines.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050214

Authors: Yong Wang Donghua Li Wenyu Zhou Linrong Fu Lin Lu Chenyang Zhang

As a novel urban leisure activity, Citywalk is reshaping the spatial organization of urban tourism resources and spatial experience patterns. This phenomenon provides a crucial entry point for understanding new tourist–destination relationships from the perspective of spatial behavior. This paper takes Harbin, an Internet-Famous City (IFC), as a case study and integrates multi-source data, including pedestrian trajectories, social media texts, and urban infrastructure. A cross-modal analytical framework for Citywalk networks is constructed to examine the structural evolution of Citywalk networks and the relationship between digital-space and physical-space in the context of IFCs. The results indicate that: (1) During its rise as an IFC, Harbin’s Citywalk network transformed from a single-core agglomeration structure to a multi-nodal radial structure, exhibiting a pattern of core reinforcement and outward expansion. (2) Online visibility was associated with the emergence of new nodes and network expansion, but a structural misalignment was observed between digital-space association and physical-space linkage. (3) Emotional differentiation among newly visible nodes further reflected the uneven development of the Citywalk network, while concentrated digital attention was accompanied by persistent structural imbalance. This study highlights the digital–physical misalignment in urban tourism networks, suggests the important role of social media in shaping tourists’ route imagination and emotional evaluation, and provides references for the spatial optimization and sustainable management of urban tourism resources in the new development stage.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050213

Authors: Ruibo Wang Weiming Cheng Xinlong Feng Wei Li

Monitoring cropland dynamics in arid regions is critical for balancing food security with water scarcity constraints. However, distinguishing fragmented agricultural oases from spectrally similar desert vegetation remains a persistent challenge due to spectral confusion and landscape heterogeneity. To address these challenges, this study developed the STGP-OCE feature cube on the Google Earth Engine platform (GEE) by integrating the Oasis Cooling Effect (OCE) into the commonly used STGP (Spectral, Textural, Geomorphic, and Phenological) feature space, coupled with the XGBoost ensemble model. Through ablation experiments and feature importance analysis, we quantified the feature construction mechanism for arid regions. Oasis Cooling Intensity emerged as the most influential variable (Gain score: 0.315), demonstrating that the thermal signature of continuous anthropogenic irrigation serves as a robust thermodynamic proxy to resolve the spectral ambiguity between crops and drought-tolerant desert vegetation. By hierarchically coupling this thermal indicator with textural features to suppress fragmentation noise, topographic constraints to filter non-arable terrain, and phenological trajectories, the STGP-OCE feature cube achieved an Overall Accuracy of 95.12% and a Precision of 94.95%, significantly outperforming models built on lower-dimensional cubes as well as existing global land cover products. We generated a 10 m annual cropland dataset for Xinjiang, China, revealing a substantial 32.9% expansion (19,360 km2) from 2015 to 2024, mainly occurring in vulnerable oasis–desert transition zones and coinciding with reported reclamation activities. These highlight the continuous agricultural encroachment into desert margins, while the proposed STGP-OCE cube provides a reliable methodology for high-precision cropland monitoring in arid regions.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050212

Authors: Guiming Zhang

“Laws” of geography such as Tobler’s First Law (spatial autocorrelation) and Zhu’s Third Law (environmental similarity) offer fundamental principles for spatial prediction and mapping, yet their implications for digital soil mapping (DSM) are often opaque because the underlying principles and mechanisms of DSM models are rarely inspectable in typical DSM workflows. This study presents an interactive geovisualization portal that demystifies Tobler’s Law, Zhu’s Law, and a combined formulation in spatial prediction processes, using soil organic matter (SOM) concentration prediction in Xuancheng, China, as a case study. The portal integrates multiple DSM frameworks that operationalize two geographic laws—inverse distance weighting (IDW), individual predictive soil mapping (iPSM), an iPSM-IDW hybrid, ordinary kriging (OK), and regression kriging (RK)—and couples them with user-configurable parameters such as neighborhood size, distance-decay factor, and variogram model. The portal provides coordinated, interactive views that link SOM predictions to dynamic map and diagnostic statistical charts for explaining location-level predictions, visualizing the manifestation of geographic laws in constructing local predictions, examining weight allocation patterns, and assessing overall prediction accuracy. Additionally, a built-in sensitivity analysis enables users to investigate and understand the effects of varying the geographic law, modeling framework, and modeling parameters on prediction results. This geovisualization portal advances interpretable DSM by rendering its underlying geographic principles, model mechanics, and parameter influences visually inspectable.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050211

Authors: Haijun Sun Di Wang

The rapid accumulation of Waste Electrical and Electronic Equipment (WEEE) presents severe environmental and resource challenges in high-density metropolises. Traditional reverse logistics (RL) network designs often overlook urban morphological constraints and treat recovery rates as static parameters. To address these gaps, this study proposes a GIS-integrated low-carbon WEEE RL framework. A Spatial Multi-Criteria Decision Analysis (MCDA) workflow first deduces optimal facility layouts avoiding ecological exclusion zones. Subsequently, a Fuzzy Mixed-Integer Linear Programming (FMILP) model endogenizes the dynamic recovery rate and enforces discrete vehicle dispatching, solved via an advanced Geospatially Constrained Multiple-Priority Genetic Algorithm (MPGA). Validated in Jinan, China, the framework consistently outperforms contemporary benchmarks. Crucially, it reveals that traditional continuous models underestimate urban carbon footprints by 34.6%. By adopting the optimal spatial compromise, policymakers can achieve a 19.9% carbon reduction at a marginal 12.7% profit sacrifice, effectively harmonizing decarbonization with commercial viability.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050210

Authors: Qicheng Huang Ruiju Zhang Jian Wang

We propose NPMV-SLAM, an RGB-Depth neural implicit dense SLAM system based on multi-resolution voxels and feature point clouds. The method demonstrates exceptional performance in tracking accuracy and reconstruction quality, aiming to address the shortcomings of traditional visual SLAM in texture detail modeling and geometric consistency, as well as the limitations of existing neural implicit methods in real-time performance and scene scalability. (1) We innovatively propose a position-enhanced encoding mechanism that fuses multi-resolution hash voxel grids with feature point clouds. This design fully leverages the high sensitivity of point clouds to high-frequency geometric details and the global structural continuity provided by voxels, achieving complementary advantages during network training and inference, thereby comprehensively enhancing the system’s reconstruction generalization capability. (2) Furthermore, we design an adaptive sampling strategy guided by point cloud density priors. This strategy fundamentally alleviates the core issue of insufficient scene scalability through data-driven online point cloud reconstruction. By filtering out invalid, non-surface sampling points, it concentrates computational resources on object surface regions, significantly reducing computational redundancy in empty areas, and achieves efficient point cloud spatial indexing with the aid of a vector database similarity search algorithm. While maintaining operational efficiency, our method significantly improves both detailed reconstruction capability and global reconstruction completeness. Experiments conducted on multiple indoor scenes from the Replica and TUM datasets show that our approach achieves notable improvements in tracking accuracy, rendering quality, and mapping accuracy, successfully balancing precision and efficiency.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050209

Authors: Mingzhi Zhang Hongyong Yuan Dongri Song Chun Bao Rui Li Zhikun Hu

Gully type debris flows are sudden, highly destructive geological hazards requiring accurate, real-time monitoring for effective early warning. However, single-modal visual monitoring is sensitive to complex environments, while existing multi-modal fusion approaches rely on static strategies, limiting adaptability and modal complementarity. Blurred boundary segmentation, class imbalance, and real-time deployment challenges also remain unaddressed. To overcome these issues, this study proposes a cross-modal dynamic feature fusion framework integrating visible and infrared imagery, consisting of a shared backbone for multi-scale feature extraction, a dynamic feature aggregation module for adaptive heterogeneous fusion, a lightweight context-aware semantic segmentation network, and a composite loss function to enhance boundary delineation and mitigate class imbalance. Validated on a self-constructed dual-modal debris flow dataset and public benchmarks, the method achieves an mIoU of 75.6%, outperforming state-of-the-art methods by 3.1%. It meets real-time monitoring requirements and exhibits strong generalization, providing a practical solution for debris flow monitoring with great potential for disaster early warning deployment.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050208

Authors: Zixuan Teng Zezhong Zheng Xiangyang Sun Hao Xue

Road networks are fundamental components of transportation infrastructure and play a crucial role in various geospatial applications. Although deep learning-based semantic segmentation models have achieved promising results in extracting roads from high-resolution remote sensing imagery, the resulting networks often suffer from topological fragmentation due to occlusions and shadows. To address this issue, we propose a topology-aware road extraction method that integrates deep learning-based segmentation with a graph-based connectivity refinement strategy. Specifically, a Pyramid Scene Parsing Network (PSPNet) is first employed to generate initial road probability maps. Subsequently, a connectivity-oriented post-processing pipeline is introduced, which incorporates a multi-source cost function strategy and a direction-aware Dijkstra search algorithm. By utilizing endpoint tangent vectors as inertial weights, the algorithm effectively reconstructs fragmented segments while ensuring geometric smoothness and topological consistency. Furthermore, a dynamic road width restoration strategy is applied to transform refined skeletons into physically consistent road entities. Experiments conducted on two publicly available datasets, CHN6-CUG and DeepGlobe, demonstrate the effectiveness of the proposed method. Quantitative results show that the refinement process significantly enhances road connectivity with a minimal trade-off in pixel-level accuracy. Specifically, the Conn metric increases by 0.1989 on the CHN6-CUG dataset and 0.3055 on the DeepGlobe dataset, while MIoU remains high with only marginal decreases of 1.07% and 0.45%, respectively. These findings indicate that the method effectively restores structural continuity, helping with reliable road network generation and subsequent integration into Geographic Information System (GIS)-based applications such as urban planning and autonomous navigation.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050207

Authors: Kyle Gillespie Dev Raj Paudyal

The development of a 3D digital cadastre is a key objective of Australia’s Cadastre 2034 strategy for modernising land information infrastructure. Jurisdictions across Australia are progressively transitioning from conventional 2D cadastral systems towards 3D cadastral models to better represent complex land and property rights, particularly in dense urban environments. In New South Wales (NSW), LandXML is currently the standard for digital cadastral lodgement. However, its limitations in supporting 3D spatial data representation have prompted investigation of alternative standards such as LandInfra and its InfraGML encoding. The aim of this study is to investigate how LandInfra handles existing cadastral information in New South Wales, Australia. In particular, this study is a technical and structural comparison of LandXML and InfraGML, examining data modelling workflows and geometric encoding. A hybrid research methodology integrating Design Science Research (DSR) and Case Study Research (CSR) was applied. Two representative cadastral plans—a standard deposited plan and a strata plan—were digitised using LISCAD 2025 v25.9.23.1 and AutoCAD Civil 3D 2026 V1 and subsequently modelled in both LandXML and InfraGML formats. Validation was conducted using KITModelViewer and schema validators, with comparative analysis of development cycle, modelling structure, usability, and workflow. This study demonstrates that InfraGML offers semantic richness and structural flexibility compared to LandXML within the scope of the examined case studies, although its practical adoption is constrained by limited commercial software support and may present adoption challenges for practitioners. The findings of this research suggest that LandInfra offers considerable potential for advancing the future development of 3D cadastre in Australia. In this context, InfraGML is positioned as a promising data standard for ongoing investigation and future research, rather than an immediate substitute for LandXML. Within the scope of this study, a fully operational 3D cadastral implementation is neither developed nor validated within existing legal or institutional frameworks, and complex 3D scenarios are not addressed. Future research should explore integration with CAD platforms, legislative implications of 3D survey features, complex volumetric cases, and formal 3D topological validation, and alternative modelling approaches, such as using Nested Parcels method and InfraJSON encoding.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050206

Authors: Merve Pınar Öztürk Ömer Kaya

Coastal provinces where tourism and transport activities concentrate generate spatially heterogeneous air pollution burdens and health-relevant exposure conditions. However, integrated spatial evidence linking tourism-transport pressure with seasonal multi-pollutant burden remains limited. This study develops a GIS-based analytical framework for four major Turkish coastal provinces—Antalya, Muğla, Aydın, and İzmir—to examine the spatial relationship between tourism-transport pressure and seasonal air pollution dynamics. The framework combines a multi-criteria Tourism-Transport Suitability Index (SUI) derived from 11 spatial criteria using AHP and Fuzzy SIWEC; reference-normalized RMS-based multi-pollutant composite surfaces for PM10, SO2, NO2, NOx, NO, O3, and CO; a seasonal difference layer; and province-level Spearman correlation analysis based on random point sampling. The results show that tourism–transport pressure concentrates along coastal belts and major accessibility corridors, while pollutant-specific seasonal behaviors vary across provinces. Zonal statistics and correlation analyses indicate that the SUI–pollution relationship is generally weak and context-dependent. Rather than supporting a single deterministic tourism–pollution mechanism, the findings show that this relationship is spatially selective and seasonally mediated, with the seasonal-difference metric providing a clearer signal than absolute seasonal levels in some provinces, particularly in Aydın and İzmir. Overall, the framework offers a transferable GIS-based approach for evaluating tourism-transport pressure and seasonal multi-pollutant burden at the provincial scale.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050205

Authors: Ruochen Mei Zhi Zhang Qiuxia Xu

Currently, two kinds of local spatial deviation indicators, namely local spatial heteroscedastic statistics and local spatial variance, with their associated tests have been proposed for estimating and inferring the characteristics of a spatial process at the second-order moment level, which is of wide potential application in spatial data analysis. Nonetheless, the performance of the indicators with their associated tests remains to be systematically investigated. Due to their mixed application orientations and the difficulty in theoretically comparing their performance, we design proper simulation experiments to assess their performance in estimating the variance function of a spatial process and detecting the local spatial heteroscedasticity and the boundaries of spatial homogeneous clusters. Some worthwhile findings are obtained and their performance from different application orientations is clarified. Based on the findings, two real-life spatial datasets are analyzed to demonstrate the applications of the indicators with their associated tests.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050203

Authors: Qin Li Zhenze Yang Xingping Wu Wenlong Li Yijun Liu Lixin Jia

The 2024 World Heritage inscription of the Beijing Central Axis shifts the focus of historic district governance to quality-oriented urban regeneration. However, evaluating the precise alignment between infrastructural topology and cultural meaning remains a methodological challenge. To move beyond macro-level assumptions, this study constructs a novel “spatial–semantic coupling” diagnostic framework. Integrating multi-source street-view data, Space Syntax, and the zero-shot semantic extraction capabilities of the CLIP model, we performed high-resolution visual semantic identification across 550 fine-grained sampling points in the 6.6 km2 South Central Axis Core Area. Rather than merely observing a general “decoupling,” our diagnostic tool successfully mapped the complex spectrum of spatial alignments. While it accurately diagnosed areas with “idle spatial potential”—where high Global Integration (Mean = 0.924) fails to translate into Visual Attraction (r = −0.03) or Historical Perception (r = 0.01)—it also precisely identified “Synergistic” heritage cores and “hidden gems” within capillary hutongs. Furthermore, the framework diagnosed a severe “green island” effect (Mean = 0.26) and a structural contradiction between Spaciousness and Historical Perception (r = −0.33). By utilizing Bivariate LISA to geographically pinpoint these varying coupling characteristics (e.g., severe “High–Low” spatial frictions at gateway transportation hubs), this study establishes a highly scalable, data-driven analytical paradigm for targeted micro-renewal, ensuring the precise alignment of physical centrality and cultural perception in complex historic districts globally.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050204

Authors: Martha Gkika Orfeas Karountzos Konstantinos Kepaptsoglou

Population growth and changing urban activity increase pressure on public transport to be efficient and equitable. This study examines how specific socioeconomic conditions around Athens Metro stations influence ridership patterns, with particular emphasis on employment structure, education levels, and household characteristics such as parking availability. Using 2021 census data and monthly station ridership for 2021, 10 min walking isochrone catchments are delineated for each station, and socioeconomic indicators are spatially aggregated to these zones. We screen variables through correlation analysis and estimate month-specific Ordinary Least Squares (OLS) models to capture seasonal effects. The best-performing month is then analyzed to examine spatial non-stationarity, while Principal Component Analysis (PCA) reduces multicollinearity and highlights the most influential latent socioeconomic dimensions. The results indicate strong spatial disparities: central interchange stations show consistently high demand, whereas peripheral stations exhibit lower and more variable ridership. Localized relationships link ridership to employment structure, educational profiles, and indicators of car availability, such as household parking, suggesting uneven accessibility and mobility opportunities across the metropolitan area. The proposed GIS-spatial econometric workflow supports targeted, equity-oriented interventions and transit-oriented development and is transferable to other cities with comparable open ridership and census datasets.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050202

Authors: Dong Li Mengmeng Liu Houzeng Han Jian Wang Lei Wang

Outdoor jogging is a significant component of daily physical activities that benefit public health and urban living environments. However, it is still challenging to untangle the intricate associations between environmental variables and jogging paces, due to nonlinear interactions, spatial heterogeneity, and inadequacy in model interpretability. To this end, an interpretable spatial machine learning framework based on the integration of the Geographically Weighted Random Forest (GW-RF) model and SHapley Additive exPlanations (SHAP) is proposed. Drawing on multi-source urban datasets and Beijing’s large-scale jogging trajectory data, this model allows for global and local interpretation of environmental effects on the built, natural, and visual dimensions. The findings are as follows: (1) Built environment variables demonstrate the greatest explanatory power, with street network configuration (GAC, GAI) and population density identified as the dominant predictors of jogging intensity; (2) All environmental variables exhibit nonlinear threshold effects, with SHAP analysis revealing sign-switching points and optimal ranges—moderate NDVI and sky openness promote jogging while extreme values suppress it; (3) Natural and visual variables operate within distinct comfort thresholds, where moderate annual mean temperature, green view index, and sky openness are consistently associated with higher jogging intensity; and (4) The GW-RF model achieves superior predictive performance (R2 = 0.7939, RMSE = 8.54, MAE = 5.72) over five benchmark models, confirming the necessity of spatial weighting in nonlinear ensemble learning. By revealing nonlinear response patterns and effective environmental ranges, the study presents quantitative evidence for the understanding urban physical activities and providing methodological guidance for fostering healthier and more activity-supportive urban environments.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050201

Authors: Xiaoqing Ju Daichao Li Yunqiang Zhu Li Yu Qiang Wang Yichen Yang Renwen Xia Peng Ye Shu Wang

Media texts convey emotions and stances that can shape the evolution of public opinion, which calls for comparable quantitative sentiment analysis. However, most existing approaches assign a single sentiment score to an entire article, making it difficult to distinguish functional differences across sentences and to clarify who expresses the sentiment and what the evaluation targets, thereby limiting interpretability and cross-source comparability. To address this issue, we propose a fine-grained sentiment quantification method for media texts that jointly considers sentence types and opinion holder–target structure. The method obtains sentence-level sentiment scores and simultaneously extracts sentence types, opinion holders, and opinion targets, enabling article-level structured quantification and comparison under a unified evaluation setting. In our implementation, a large language model (LLM) is primarily used for semantic parsing and structured extraction. Experiments demonstrate that the proposed method delivers stable performance on the sentiment score regression task (R2 = 0.899, MAE = 0.088, MSE = 0.027; relative to the strongest fine-tuned pretrained language model baseline in our comparison, RoBERTa with R2 = 0.871, this corresponds to a 2.8-percentage-point gain in R2 and an 8.3% reduction in MAE), and effectively supports opinion holder–target identification (holder weighted average F1 = 0.812; target loose F1 = 0.691 in a supplementary evaluation). Building on these outputs, the method can further reveal the spatial distribution of sentiment bias in global media coverage, highlighting relative sentiment patterns in cross-national narratives.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050200

Authors: Ramón Fernando López-Osorio Lidia Yadira Pérez-Aguilar Evangelina Avila-Aceves Yedid Guadalupe Zambrano-Medina María Alejandra Quintero-Morales Edgar Rubén Montiel Andrade

Aridity is a key climatic factor influencing ecosystem dynamics and land degradation in arid and semi-arid regions. This study analyzes the spatial relationship between aridity and land cover degradation in northwestern Mexico during 2005–2020 using a Geographically Weighted Regression (GWR) model, complemented by spatial autocorrelation techniques including Moran’s I and Local Indicators of Spatial Association (LISA). Aridity was derived from climatic data, and land cover transitions were used as proxies for degradation. The results indicate that the study area is predominantly characterized by arid and semi-arid conditions, where degradation-related transitions are strongly concentrated. In particular, transitions from shrubland to grassland (59.53%) and from shrubland to bare soil (93.60%) occur primarily under arid conditions, highlighting the high vulnerability of these ecosystems to water deficit. The GWR model explains approximately 49.5% of the spatial variability in degradation. However, residual analysis shows strong spatial autocorrelation (Moran’s I = 0.72, p < 0.001), indicating spatially structured patterns not fully captured by the model. These findings demonstrate that, although aridity is a key driver, additional factors influence degradation patterns.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050199

Authors: Jiangbing Sun Yan Zhang Longxing Tian Jiali Li Miao Tian Jie Chen Liufeng Tao Qinjun Qiu

The scientific data of the Earth surface system is characterized by multi-source heterogeneity and dynamic correlation, so constructing an efficient data association network and enabling intelligent knowledge services is a hot topic. Nevertheless, confronted with the existing challenges of onerous data acquisition, inadequate precision of data recommendation, excessive time and labor consumption, as well as insufficient semantic reasoning in intelligent question-and-answer (Q&A) systems, we propose an intelligent framework that integrates dynamic optimization and retrieval-augmented generation (RAG) technology to address the problems of strong subjectivity in the setting of edge weight thresholds in association networks and insufficient semantic inference in intelligent Q&A. First, a multidimensional association network is constructed based on metadata features, redundant edge pruning is achieved through dynamic threshold analysis, and key nodes are identified by combining complex network centrality theory to optimize network structure and storage efficiency. Secondly, the RAG-based intelligent Q&A model is designed to transform the association triples into a paragraph-based knowledge base, generate a domain Q&A dataset using a large language model GPT-4o, and fine-tune the word embedding model to improve the semantic representation accuracy. Experiments show that the number of network edges is reduced by about 70% after optimization, and the node importance analysis accurately identifies key data nodes; the fine-tuned model improves each index by 6% on average in the retrieval task, and the Q&A system significantly outperforms the traditional method in terms of indexes such as relevance and completeness. This study provides innovative solutions for the intelligent service of scientific data in Earth surface systems and promotes the deep integration of association networks and generative AI.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050198

Authors: Caitlin Haedrich Anna Petrasova Ondrej Mitas Chris Jones Ross K. Meentemeyer Helena Mitasova

Since the early 2000s, there has been rising research interest in using tangible user interfaces (TUIs) in geospatial education, terrain modeling and analysis, landscape design and planning, and collaborative decision making. Many of these systems explicitly model geospatial data and allow users to interact with complex computational workflows by direct manipulation of a shared tangible interface. However, prior research has largely examined these systems within disciplinary silos and with a wide variety of terminology, limiting synthesis and cross-domain applicability. To address this gap, we define a unifying term, geocomputational tangible user interfaces (G-TUIs), and establish a set of criteria for identifying such systems. We then conduct a systematic literature review to examine the types of technologies (interfaces, sensors, software) used and how these systems are applied across different fields. We find G-TUIs are most commonly applied in educational and urban or landscape design contexts, yet empirical evidence evaluating their effectiveness remains limited. We highlight the potential for these systems in participatory approaches to social–environmental challenges and provide four case studies from our own work that demonstrate how geocomputational TUIs can be impactful and purposeful in education, participatory science, and stakeholder collaboration. We conclude by highlighting current research directions, challenges, and future research opportunities.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050197

Authors: Claire Ponciano Falk Würriehausen Markus Schaffert Hartmut Müller Jean-Jacques Ponciano

Star-based schemes, such as the 5-star Linked Open Data model and its geospatial extensions, are widely used to characterize openness and interoperability. However, in practice, higher star ratings are often assigned on the basis of technical properties such as RDF exposure or schema publication without requiring the satisfaction of foundational metadata quality conditions. This weakens the monotonic interpretation of star levels and can produce ambiguous signals for data users. To address this issue, we propose the LETTER framework, a multi-dimensional evaluation model in which seven independent binary dimensions describe metadata readiness for reuse: Provenance (P), Access (A), Structure (S), Connections (C), License (L), Identifiers (I), and Quality (Q). The framework is aligned with FAIR principles and mapped to ISO 19115 and ISO 19157 concepts. We evaluate it through an exploratory comparative case study of four purposively selected datasets from the German Spatial Data Infrastructure (GDI-DE): Municipal Points of Interest (Trier), Thuringia Digital Elevation Model (DEM), Administrative Units (VG250), and INSPIRE Digital Land Model (DLM). The results show that datasets receiving comparatively high star ratings may still lack machine-actionable provenance, quality evidence, stable identifiers, or robust access conditions. In particular, the analysis highlights a recurring ‘PDF Trap’, where relevant trust information exists only in narrative documentation and therefore remains inaccessible to automated reuse workflows. We conclude that LETTER provides clearer diagnostic power than scalar star ratings by exposing which metadata functions are actually satisfied and which remain missing.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050196

Authors: Christina D. Perella Jelena Vukomanovic Caleb R. Hickman Adam J. Terando Mitchell J. Eaton Marie Schaefer

A common challenge when modeling social–ecological systems (SESs) is defining the spatial extent of the system. Boundaries that do not adequately capture both social and ecological processes and their interactions can lead to mischaracterization of the system, while expanding boundaries too widely can impact model complexity and required resources. Socially, boundaries can invoke and influence identity, culture, power, and sense of place. Boundary decisions benefit from flexible, iterative approaches and the expertise of local communities. Here, we use a structured database search supplemented with citation searching to identify and review the literature that addresses choosing or defining spatial boundaries in SESs mapping or modeling and, when applicable, how participatory methods were used in the research process. In a review of the resulting 79 studies, we discovered that pre-existing social or ecological boundaries were used most frequently (36 and 18 publications, respectively). Twenty-one publications combined social and ecological boundaries or data to create custom boundaries, and four studies used an alternative approach to conventional boundaries. Informed by the literature review, we present a general framework for defining boundaries at the outset of SES research. We then connect the framework to a specific case study based on a collaborative project with Tribal, university, and federal scientists to develop a social–ecological climate adaptation plan. We present guiding questions alongside candidate boundaries for our study system and explore the tradeoffs of these boundary options, which can function as a useful template for other social–ecological research collaborations.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050195

Authors: Xi Gong Yujian Lu Rebecca A. Girardet Hannah M. C. Schreier Zhenlong Li Theresa H. Cruz Yan Lin

Sentiment expressions related to child maltreatment (CM) in public discourse are influenced by demographic, economic, and cultural factors and individual characteristics. Using 188,429 geotagged CM-related tweets during 2018–2022, we explored public sentiment expression about CM across the contiguous U.S. We applied multiscale geographically weighted regression (MGWR) to examine how contextual factors relate to the percentage of CM-related tweets with negative sentiment at the county level, revealing the spatial heterogeneity and varying geographic scales of these associations. Counties with higher male-to-female ratios and lower education levels tended to express negative sentiment in CM-related tweets, with consistent patterns observed nationwide. Five factors exhibited spatially varying associations by U.S. region, with higher levels of negative sentiment in the following contexts: a lower percentage of residents living in group quarters or a higher percentage of same-sex couples (Eastern and Central); fewer households lacking broadband access (Central); a higher percentage of single-parent households (New England and Southern Mississippi River); and areas where professionals are mandated to report CM (Great Lakes and Southern Appalachian Mountains). This study provides critical insights for policymakers to adjust policies, educators to design focused interventions, and the public to raise CM awareness. The methodology also provides a valuable framework for investigating public discourse on other social issues.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050194

Authors: Roger Cesarié Ntankouo Njila Mir Abolfazl Mostafavi Jean Brodeur Sonia Rivest

Sensor data are increasingly used in monitoring spatiotemporal phenomena for diverse applications such as flood management, urban traffic, air quality control, forest fire management, etc. Real-time modelling and representation of such evolving phenomena is fundamental for efficient and near-real-time decision-making processes. In addition to simple and local alerts about occurring changes over time at a given location, as is the case in Sensor Event Service (SES), the decision-making process may require more global spatial information, such as knowing if the monitored phenomenon is expanding or contracting around a given spot or if it is moving from one spot to another, especially for non-punctual spatial features. For such cases, spatiotemporal information should be computed over the whole set of distributed data from which the geometry of monitored phenomena can be assessed. This paper proposes an event-driven fuzzy rule-based decentralized spatial reasoning approach to compute spatiotemporal changes occurring in vague shape phenomena from distributed sensor data streams. Inferring local and partial spatial changes from individual nodes over the sensor network is prior to the computation of developing changes that the monitored phenomenon undergoes over the whole area covered by the sensor network. In this approach, we suggest a Fuzzy-Extended Spatiotemporal Change Pattern (FESTCP) to compute spatiotemporal changes about fuzzy regions. To evaluate our method, simulated case studies of ambient air pollution in Quebec City are carried out. The results reveal that the proposed method could provide satisfactory information about spatiotemporal changes in real-world phenomena monitored by a sensor network for a real-time decision-making process.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050193

Authors: Catherine Trudelle Christophe Claramunt Eliott Libner Rodolphe Gonzales

This paper introduces a comparative analysis of urban housing conflicts across eight major Canadian cities, Toronto, Vancouver, Québec, Ottawa, Calgary, Edmonton, St. John’s, and Halifax, over a 20-year period. Using Large Language Models (LLMs), we implement a structured workflow to extract, classify, and organize more than one thousand conflict instances from diverse textual sources, including municipal reports, media archives, and non-governmental organization publications. The methodological contribution lies in demonstrating how an LLM-assisted pipeline, combining schema-based extraction, prompt perturbation, and a two-phase calibration procedure, can generate structured, multi-city conflict datasets while addressing challenges such as output homogenization and sensitivity to prompt design. The findings highlight both shared national tendencies and city-specific configurations with post-2020 conflicts intensifying. Overall, the study proposes a transparent workflow for applying LLMs to conflict-related text analysis and offers an exploratory overview of the spatial, temporal, and semantic regularities of housing conflicts in Canadian cities.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050192

Authors: Sajib Sarker Md. Rakibul Hasan Kauser Anik Kumar Saha Abul Azad Xin Wang

Rapid urbanization in South Asian coastal cities is systematically dismantling natural cooling infrastructure, driving unprecedented urban heat island (UHI) intensification with severe consequences for human health, energy systems, and urban livability. Despite growing research attention, comprehensive frameworks that simultaneously capture temporal UHI dynamics, machine learning-based thermal projections, and community-grounded validation remain scarce, particularly for secondary coastal cities in tropical developing regions. This study addresses these gaps by investigating UHI dynamics in Chattogram City Corporation (CCC), Bangladesh, through three integrated methodological pillars: (1) multi-temporal remote sensing analysis using Landsat 5 and 8 imagery spanning 2005–2025; (2) comparative evaluation of five machine learning algorithms (LightGBM, Random Forest, XGBoost, SVM, and MLP) for land use/land cover (LULC) classification and land surface temperature (LST) regression, with iterative scenario projections for 2029, 2033, and 2037; and (3) a structured public perception survey of 384 residents validated through participatory mapping and focus group discussions. Landsat analysis revealed dramatic LULC transformations: built-up areas expanded 88% (12,649 to 23,719 acres), while waterbodies declined 53.1% and vegetation decreased 21.9%. Mean LST increased by 9.09 °C (from 30.94 °C to 40.03 °C), with mean UHI intensity rising from 19.59 to 33.88 standardized units over two decades. LightGBM achieved optimal LULC classification (F1-weighted: 0.765) while Random Forest best predicted LST (RMSE: 1.51, R2: 0.809). Projections indicate continued thermal escalation, with mean LST reaching 43.64 °C and UHI intensity exceeding 37.41 standardized units by 2037. Persistent thermal hotspots were identified in the southwestern coastal corridor, western industrial belt, and central business district. Community survey data corroborated satellite-derived patterns, with 73.44% of respondents observing environmental degradation, yet only 22% aware of formal heat mitigation policies, and 87% supporting vegetation-based cooling interventions. This integrated framework advances urban thermal monitoring in tropical coastal cities and provides spatially targeted, community-endorsed evidence for climate-responsive urban planning.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050191

Authors: Katrin Reichert Anna-Lena Heppenheimer Julian Keil Frank Dickmann Dennis Edler

The subjective perception of safety in public space is a crucial indicator of urban participation, shaping how people experience and navigate their surroundings. Urban fear spaces highlight how physical, social, and emotional factors unequally structure access to and use of public environments, linking spatial perception to social justice. This paper addresses the question: What opportunities and limitations does a mixed-methods approach—combining immersive Virtual Reality (VR), electrodermal activity (EDA) measurement, and semi-structured interviews—offer for examining subjective perceptions of urban fear? It offers a methodological reflection on an exploratory study of potential fear spaces on the campus of Ruhr University Bochum, hypothesizing that mixed-methods integration reveals non-conscious arousal patterns inaccessible via verbal data alone. We discuss methodological potentials and limitations in integrating physiological data within qualitative frameworks. The study design comprised VR simulation, physiological signal acquisition, and qualitative interpretation and triangulation. Findings show that combining immersive VR with EDA detects non-conscious physiological arousal patterns that would remain inaccessible through verbal data alone, while simultaneously revealing substantial interpretative challenges that necessitate qualitative contextualization. Integrating interviews proved vital for linking physiological patterns to subjective meaning. The reflection concludes with implications for applying such multimodal approaches in participatory urban planning and spatial research.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050190

Authors: Runya Fu Enxu Wang

Boosting urban vitality (UV) in residential living spaces has become a core component of advancing the people-centered urbanization strategy. However, previous research has mainly focused on exploring UV at the scales of streets, blocks, and grids, with few nonlinear explorations conducted across different temporal dimensions at the scale of residents’ daily life. Therefore, this article adopts the XGBoost-SHAP model to explore the nonlinear and interaction effects of a built environment (BE) on UV across multi-scale community life circles (CLC), distinguishing between daytime and nighttime on weekdays and weekends. The results indicate that UV on weekends is higher than on weekdays, except for 5 min CLC (5MCLC). UV is highest in 10 min CLC (10MCLC) and lowest in 5MCLC. The mean building height (MBH) and Normalized Difference Vegetation Index (NDVI) have always been the most important indicators affecting UV. Unlike previous studies, the green view index (GVI) and sky view factor (SVF) are negatively associated with UV. The nonlinear relationship between BE and UV on weekdays exhibits greater regularity. The effects of other BE indicators on UV exhibits spatiotemporal heterogeneity, with the relative influence changes in commercial accessibility (CA), distance to metro (DSM) and distance to bus (DSB) being the most significant. The nonlinear and threshold effects of BE on UV show significant changes, except for GVI, SVF, and NDVI, at different times and scales. The threshold for cultural and leisure accessibility (CLA) is higher on weekdays than on weekends, whereas that for DSM is higher on weekends than on weekdays. The interaction effects between the building density (BD) and MBH, park and square accessibility (PSA), and DSM is significant at different scales. This study will provide a scientific basis for optimizing BE and differentiated planning of CLC, which further contributes to enhancing UV and promoting urban sustainable development.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050189

Authors: Yun Qiu Fangjie Cao Qianxin Wang

The urban heat island effect, a typical rapid urbanization issue, arises from natural surfaces covered by impermeable layers via urban sprawl. To clarify its unclear response to urban expansion under human–land synergy, this paper proposes a multidimensional urban expansion model and a random forest–intelligence integrated method for high-precision large-region population mapping. Taking the Pearl River Delta urban agglomeration as a sample, its urban expansion is divided into five modes to explore thermal environment impacts. The results show: (1) The proposed random forest–intelligence method achieves 84% overall accuracy in 30 m resolution population mapping. (2) The Pearl River Delta urban agglomeration is dominated by vertical expansion, but all cities have population-shrinking regions, especially around Guangzhou and Shenzhen. (3) From 2010 to 2020, Pearl River Delta urban agglomeration impervious surface expansion and population growth were mismatched: impervious surface extended to fringes, while population grew in core areas. (4) The expansion of impervious surface does not always exacerbate the urban heat island effect; when the per-capita land area is less than 1.8 m2, it can actually mitigate the effect. (5) Guangzhou–Foshan–Zhaoqing and Shenzhen–Dongguan–Huizhou integration reduces heat island intensity. Core cities driving surrounding areas via clustered, interconnected development alleviates this effect.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050188

Authors: Yunlin Tu Wenzhong Shi Yangjie Sun

Indoor space segmentation is essential for indoor navigation, 3D reconstruction, and Building Information Modeling (BIM). However, reliable segmentation from unstructured 3D point clouds remains challenging due to structural voids caused by occlusion and noise, as well as the difficulty of distinguishing permanent structural elements from dense non-structural clutter. To address these issues, this paper proposes a semantic-grid structural completion method for indoor space segmentation from 3D point clouds. The method first integrates RandLA-Net-based semantic segmentation with geometric similarity correction to improve structural consistency. Subsequently, a semantic-grid structural completion algorithm detects and fills structural voids under height constraints; this process employs dual-grid structural marking with a 2D semantic occupancy grid and a 3D voxel grid to identify missing observations and generates synthetic points with inherited semantic labels to restore structural integrity within the scene. A density-aware height difference filtering method is then applied to remove non-structural clutter and clearly separate structural elements from the rest of the scene. Finally, indoor spaces are delineated through connectivity-based segmentation and inverse distance-weighted label propagation. Experiments on public datasets, including S3DIS, UZH and Structured3D, demonstrate that the proposed method consistently outperforms existing approaches, achieving a mean F1 Score of 0.99, an Intersection over Union (IoU) of 0.98, and a Segmentation Error Rate (SER) of 0 in most scenarios, particularly in occlusion-affected and structurally complex indoor environments.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050187

Authors: Ruifan Huang Haitao Wang Xuying Ma

Urban morphology, encompassing both horizontal landscape patterns and three-dimensional architectural structures, plays a pivotal role in modulating urban heat distribution. However, conventional models often fail to capture the intricate spatial nonstationarity and nonlinear coupling of these drivers at the block scale. Recognizing that land surface temperature (LST) exhibits distinct diurnal and nocturnal thermal cycles, this study explicitly incorporates spatial heterogeneity analysis to systematically evaluate the relative and local contributions, marginal effects, and interaction mechanisms of multidimensional urban morphology on diurnal LST variations. To achieve this objective, geographically weighted extreme gradient boosting and SHapley Additive exPlanations were employed to decipher these complex driving mechanisms from a morphological perspective. The results indicate the following: (1) Built environment variables predominate the spatial heterogeneity of LST in Xi’an, China, with their governing mechanisms shifting diurnally—characterized by a midday NDVI-induced evapotranspiration cooling effect and an atmospheric back-radiation warming effect associated with PM2.5 during the night and early morning. (2) The driving mechanisms exhibit pronounced spatial nonstationarity; while the northeastern and northern sectors are primarily influenced by the synergistic interaction between surface albedo and PM2.5, the central-western and southern regions are governed by population density and 3D architectural morphology. (3) Significant nonlinear interaction thresholds and non-monotonic response mechanisms were identified across the variables. By resolving localized thermal responses through the lens of spatial heterogeneity, this research provides a robust scientific framework for precision urban planning and the mitigation of the urban heat island effect.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050186

Authors: Il-Jung Seo

High-resolution GPS trajectories pose a geospatial processing challenge: transforming temporally ordered observations into structured spatial representations that retain intra-trip state transitions at metropolitan scale. This study develops and validates a scalable geospatial transformation workflow for detecting and structuring recurrent mid-trip stops from large-scale trajectory data. Using approximately 97 million GPS observations from Seoul’s public bike-sharing system, stopping episodes are identified through speed-based segmentation and density-based spatial clustering (DBSCAN). Recurrent stopping hotspots are attributed with spatial context via a land-use overlay and proximity analysis to pedestrian crossings. Sequential transitions between recurrent hotspots are represented as directed and weighted hotspot-to-hotspot networks, whose structural properties are evaluated using connectivity, clustering, path length, and modularity metrics under degree-preserving randomization. The workflow emphasizes explicit parameterization and modular processing, aligning with reproducible GIS-based spatial analytical frameworks. By converting fine-grained trajectory observations into validated mesoscopic connectivity representations, the framework provides a transferable geospatial processing pipeline for extracting structured connectivity information from high-resolution trajectory datasets.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050185

Authors: Xunyu Yin Wenxiang Shu Shengdong Nie Hengkai Li Hongtao Liu

Lepidolite deposits are rare-metal deposits in which lepidolite is the principal industrial mineral. Owing to thin overburden and widespread open-pit mining, their exploitation supports raw material supply for the new energy industry but also continuously disturbs mining ecosystems, thereby threatening regional ecological security. Under the combined effects of fragile natural conditions and human-induced mining disturbance, traditional fixed-weight evaluation methods have difficulty identifying stage-wise changes and localized high-risk characteristics of ecological security in lithium mining areas. Taking the lithium mining area of Huaqiao Township, Yichun, as a case study, this study constructed an ecological-security evaluation system based on the Driver–Pressure–State–Impact–Response–Management (DPSIRM) framework and introduced variable weight (VW) theory to develop a penalty-dominated state variable weight model. This model enabled the dynamic adjustment of indicator weights across years and evaluation units, while the geographic detector was used to identify the main driving factors. Results showed that (1) from 2010 to 2024, ecological security exhibited a stage-wise pattern of initial improvement followed by degradation, and low-security areas first contracted and then expanded outward; (2) vegetation coverage was a key driving factor, while interactions between any two factors were stronger than the effect of a single factor, indicating that cumulative multi-stressor effects strongly shaped spatial differentiation; and (3) compared with the constant weight (CW) method, the VW method produced finer stratification within the severely degraded tail at the Shixiawo mining site across the four assessment years, demonstrating applicability at a representative mining site in this Huaqiao case study. These findings provide a scientific basis for ecological assessment, restoration, and coordinated resource management in lithium mining areas.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050184

Authors: Zixuan Liu Yangge Tian Qingwen Xiong Duanning Chen

The digital preservation and dissemination of historical and cultural heritage is a pivotal area at the intersection of digital humanities and geographic information science. To address the challenges of multi-source heterogeneity, limited dimensionality, and inadequate public engagement, this study designed and implemented an interactive visualization platform using modern Web technologies. Taking the Leshan Confucian Temple (religious heritage) and the former site of Wuhan University (educational heritage) as case studies, the platform integrates four types of heterogeneous data (geospatial coordinates, architectural attributes, visitor behavioral records, and multimedia imagery) into a unified spatiotemporal information model. Core technical implementations are built upon a lightweight front-end stack including the Gaode Map JavaScript API for geographic visualization, ECharts for dynamic statistical charting, and the Tailwind CSS framework for a fully responsive front-end interface. Key interactive features encompass linked map markers with contextual information windows, user-driven chart filtering, and paginated loading of cultural relic cards. Evaluation results demonstrate that the platform achieves cross-device response delay ≤3 s, supports spatially grounded, dynamic, and presentation of cultural heritage information, and attains a System Usability Scale (SUS) score of 82.5. This work offers a lightweight, scalable technical solution for advancing digital recording and public communication of historical and cultural heritage, while contributing to the theoretical discourse on spatial narrative and multi-source data integration in digital humanities.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050183

Authors: Seongbeom Park Jong Ho Won Jaekyung Lee

COVID-19 was a prolonged public-health shock that disrupted mobility, access to services, and household spending. Although the official U.S. poverty rate declined to 11.1%, the Supplemental Poverty Measure rose to 12.9%, suggesting that material hardship persisted unevenly across places. This study asks whether pre-existing livelihood vulnerability and local epidemic burden translated into geographically concentrated consumption losses during 2020–2022. Because sustained consumption loss can erode households’ health-related spending, tracking where spending declines concentrate helps connect local social and environmental conditions to how communities withstand a health crisis. We analyze consumer expenditure, unlike prior research relying on aggregate retail sales, to capture fine-grained economic strains as a proxy for shock-absorption capacity. A Livelihood Vulnerability Index (LVI) was calculated for each U.S. county using 16 socio-economic variables, and counties were classified as high- or low-risk. A multilevel model then examined how socio-economic and COVID-19 factors at county and census tract levels shaped consumption changes. Higher-risk communities experienced greater consumption reductions. At the census tract level, the non-White ratio, vacancy rate, built year, per capita income, education level, and housing value were significant. At the county level, COVID-19 cases and deaths, crowding, public transportation use, and vehicle availability mattered most. These findings support place-targeted strategies that combine public-health response with socio-environmental interventions to reduce disparities rooted in pre-existing vulnerability.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050182

Authors: Muhammad Azeem Sadiq Philip Kibet Langat Arjun Neupane

Enterprise spatial data supply chains (SDSCs) increasingly support high-stakes decision-making; yet, the provenance in operational geospatial systems is often fragmented across metadata records, workflow logs, and application-specific formats. This limits traceability, reproducibility, auditability, and fitness-for-purpose assessment, particularly when organisations need to explain how spatial products were created, with which parameters, spatial references, and dependencies. This study proposes the Enterprise Spatial Data Provenance Knowledge Infrastructure (ESDPKI), a standards-aligned framework that treats provenance as enterprise knowledge infrastructure rather than passive metadata. Using a design science research approach, the study synthesised the literature-derived requirements, standards-based interoperability constraints, and representative spatial data supply chain workflows to develop four artefacts: a six-layer reference architecture, the GeoPROV minimal semantic profile, a validation-gated ingestion and governance mechanism, and a reproducible evaluation blueprint with service-level objectives. Together, these artefacts support provenance capture, semantic normalisation, validation, queryable lineage, catalogue linkage, and policy-aware disclosure across enterprise environments. The resulting design makes geospatial operations, parameters, geometry, and coordinate reference system context machine-actionable, enabling lineage tracing, impact analysis, discovery-time fitness-for-purpose assessment, and stronger governance at scale. ESDPKI therefore provides a coherent architectural pathway for operationalising trustworthy, explainable, and scalable spatial provenance in enterprise settings.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15050181

Authors: Hyeryeon Jo Miyeon Ahn Youngeun Kang

Grid-level population projection is essential for spatial planning under demographic decline, particularly for ensuring that population allocation accounts for grid extinction risk. This study develops a two-stage machine learning framework to predict residential grid transitions across South Korea’s 1 km grid system and assess how spatial policies shape depopulation outcomes through 2050. Stage 1 employs Random Forest classification to predict grid state transitions (macro-averaged F1 score = 0.694), while Stage 2 applies LightGBM regression for population prediction (coefficient of determination = 0.950). The extinction probability map from Stage 1 is incorporated into scenario simulations to adjust population allocation based on predicted residential viability. Feature importance analysis reveals that baseline population, household count, and demographic composition are key determinants of grid-level residential transitions. Five spatial development scenarios simulated through 2050 reveal substantial policy sensitivity. Cumulative extinction rates range from 3.1% under extreme dispersion to 24.5% under extreme concentration, representing a 25 percentage point divergence attributable to spatial allocation policy. Provincial heterogeneity is pronounced, with rural provinces facing extinction rates up to 39.9% while metropolitan areas remain largely unaffected. Comparing scenario outcomes enables pre-identification of policy-sensitive grids (19.5%) where allocation choices determine residential survival. These grids are predominantly located in areas with high forest cover and greater spatial isolation compared to stable grids, but differ in demographic profiles. Aging-Vulnerable grids (14.0%) exhibit high aging ratios with limited economic base, while Moderate-Vulnerability grids (5.5%) show younger demographics with relatively higher economic activity. These differential characteristics provide a spatially explicit basis for differentiated policy responses. Beyond depopulation planning, the spatial outputs of this framework can inform related planning domains such as land use transition planning, carbon management, and infrastructure prioritization under demographic decline.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040180

Authors: Jing Zhang Liyu Hu Yunqi Zhu Yu Zhang Xuanyi Kuang Jingjing Li Wa Gao

Multi-window map interfaces are widely used in geospatial monitoring systems and map-based analytical environments, where users must rapidly locate task-relevant information across multiple spatial displays. Designing visual cues and display conditions that effectively support visual search in such environments remains an important challenge for map interface design. This study examines how luminance contrast and highlighting influence visual search performance in multi-window map interfaces. A within-subject eye-tracking experiment was conducted using five highlighting conditions (No Highlighting as the control condition, Outer Border Highlighting, Text Highlighting, Title-Bar Highlighting, and Background Highlighting) and three luminance-contrast levels (low, medium, and high). Behavioral performance (accuracy and reaction time) and eye-movement measures (total viewing duration, fixation count, saccade count, and time to first fixation) were analyzed to evaluate how perceptual visibility and visual cue structures affect spatial information search. Results show that higher luminance contrast improved accuracy and reduced reaction time, although differences between medium and high contrast were small, suggesting that performance stabilized once a sufficient visibility threshold was reached. All highlighting conditions facilitated search relative to the control condition, with background and title-bar highlighting producing the most efficient gaze behavior and earlier target acquisition. A significant interaction between luminance contrast and highlighting was also observed, indicating that structured highlighting mitigates the performance costs associated with low contrast. Eye-movement evidence further indicates that region-based cues guide attention at the level of spatial interface regions rather than simply increasing local salience. These findings provide empirical guidance for improving spatial information retrieval efficiency in multi-window geospatial interfaces.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040179

Authors: Chenfeng Xu Yihan Li Zibo Zhu Zhengyang Zou Xing Geng Yike Hu

Against the backdrop of rising psychological stress and declining physical fitness in cities, how streetscape characteristics and Myers–Briggs Type Indicator (MBTI) personality traits jointly influence cycling willingness across different contexts remains underexplored. Using Shenzhen, China, as a case study, we integrated objective bicycle-sharing travel records from 2021 and subjective pairwise ratings of 1000 street-view images from 960 participants. Cycling willingness was extrapolated through the TrueSkill algorithm and a ResNet50-based model, while street view elements were extracted via DeepLabV3+ and summarized into five indicators. Multivariate regression and multifactor ANOVA were used to test main and moderating effects across six cycling contexts. Results show that (1) Objective cycling indicators and subjective willingness exhibit a pattern of lower values in the center and higher values in the periphery. (2) The Spatial Green Index, Sky Openness Index, Path Freedom Index, and Facility Accessibility Index are the main influencing factors, while the Interface Enclosure Index has the weakest and most context-dependent effect. (3) Intuition/Feeling traits are more salient in leisure and exploration, Judging/Thinking in fitness and transport, and Extraversion/Feeling in social and companion contexts. These findings provide evidence for optimizing urban street cycling spaces in a multi-context and personality-informed manner.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040178

Authors: Ekinhan Eriskin

Road traffic safety is central to socially resilient and sustainable cities, yet many middle-income countries lack harmonized subnational data on exposure, infrastructure, and enforcement. This study examines whether routinely available demographic composition can serve as a practical structural baseline for provincial traffic accident rates and as a diagnostic layer for richer safety models. Using official province–year data from Türkiye (2008–2019 and 2022–2024; n = 1215), demographic shares by sex, education, and age were treated as compositional inputs and transformed using isometric log-ratio (ILR) methods, with GDP per person included as a scalar covariate. A Tabular Residual Network (ResNet) was trained on the historical panel and evaluated on a post-period calibration/evaluation window (2022–2024), which was used for checkpoint selection and seed screening rather than as an independent held-out test set. Among the evaluated specifications, the ResNet seed-ensemble achieved the strongest performance on the 2022–2024 calibration/evaluation period (R2 = 0.5717), outperforming the best single-seed model (R2 = 0.5539), a province-specific last-value-carried-forward temporal heuristic based on 2019 values (R2 = 0.4779), tree-based tabular benchmarks (Random Forest: R2 = 0.1328; XGBoost: R2 = 0.0706), and pooled statistical reference models (linear: R2 = 0.1375; negative binomial: R2 = 0.0686; Poisson: R2 = −0.0634). Year-wise diagnostics indicated gradual temporal drift, suggesting that periodic recalibration or the inclusion of additional policy-relevant covariates is needed to preserve calibration. Overall, ILR-based compositional geodemography provides a scalable and interpretable baseline for traffic safety monitoring and prioritization in data-constrained settings.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040177

Authors: Di Yang Qiujie Lin Haoran Li Jinliu Chen Hong Ni Pengcheng Li Ying Hu Haoqi Wang

The journal retracts the article titled “Unraveling Spatial Nonstationary and Nonlinear Dynamics in Life Satisfaction: Integrating Geospatial Analysis of Community Built Environment and Resident Perception via MGWR, GBDT, and XGBoost” [...]

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040176

Authors: Yuhong Bai Shuyan Yang Changfeng Li Wangshu Mu

Rapid urbanization in megacities has exacerbated the spatial mismatch between employment and housing, necessitating effective spatial optimization strategies. However, classical optimization models often rely on the idealized assumption of “proximity maximization,” failing to account for the complex, nonlinear regularities of actual human mobility. To address this disconnect between theoretical modeling and real-world behavior, this study establishes a job–housing balance optimization framework integrated with empirical commuting patterns. Using Shenzhen as a case study, we analyze citywide commuting big data since 2024 to characterize the power law relationship between commuting population size and distance. We propose a novel optimization model that partitions residential areas into “commuting rings” on the basis of observed distance-decay functions rather than simple Euclidean proximity. We applied the proposed method to current and future planning scenarios and successfully generated spatial regulation schemes that decentralize employment functions to peripheral areas while strategically densifying residential zones. By respecting the “heavy-tailed” nature of commuting distributions, this approach offers urban planners a more robust tool for reducing aggregate commuting burdens without violating the behavioral realities of the workforce.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040175

Authors: Hosang Han Jangwon Suh

Accurate prediction of mineral concentrations from sparse exploration data is important for resource estimation. This study evaluates hybrid prediction models combining machine learning (ML) and geostatistics to predict aluminum (Al) concentrations. Twelve hybrid configurations were generated by combining six ML backbones—Random Forest, XGBoost, AdaBoost, ResNet, U-Net, and Spatial Transformer Network—with Ordinary Kriging (OK) and Universal Kriging (UK). Model performance was evaluated using 10-fold spatial cross-validation (CV) to reduce spatial leakage, and hyperparameters were tuned by grid-search CV within the training folds. For the hybrid models, residual kriging was fitted using cross-fitted out-of-fold residuals to reduce optimistic bias and prevent information leakage. The results showed no consistent performance separation between OK and UK variants. More importantly, the effect of integration was backbone dependent rather than uniformly beneficial. RF-based predictions showed the strongest overall out-of-sample performance, whereas hybrid gains for other backbones were generally modest. After multiple-comparison correction, most differences between standalone and hybrid models were not statistically significant. These findings indicate that increasing model complexity through hybridization does not guarantee improved accuracy and highlight the importance of spatially explicit, bias-aware evaluation when selecting prediction strategies for mineral resource exploration.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040174

Authors: Aikaterini Stamou Eleni Karachaliou Ioannis Tavantzis Efstratios Stylianidis

Urban heat dynamics are strongly influenced by the interaction between built structures, surface materials, and vegetation cover. This study investigates the relationship between land surface temperature (LST) and key urban morphological and structural parameters in a municipality of Thessaloniki, Greece. LST was retrieved from Landsat imagery using the NDVI-based emissivity method within Google Earth Engine (GEE). To characterize the urban form of the study area, a WorldView-2 summer image was classified to extract indices of surface roughness, built-up density, greenness density, building orientation and roof material type. Statistical analyses, including regression models and one-way ANOVA, were applied to assess the influence of these parameters on LST variability. Results reveal significant correlations between LST and both structural and vegetative factors, highlighting the cooling role of urban greenness and the amplifying effect of dense built-up areas and specific roof materials. The findings provide valuable insights into the spatial drivers of urban heat at a high-resolution scale, and offer practical guidance for planning strategies designed to lessen heat intensity in compact urban environments.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040173

Authors: Oluwadamilola Salau Steven M. Quiring

Urban pluvial flooding presents growing challenges for disaster risk management, yet most susceptibility studies rely on watershed-based frameworks that inadequately capture the localized dynamics of urban systems. This study proposes a city-scale flood susceptibility modeling framework for Cincinnati, Ohio. Cincinnati was chosen because it is a city with a documented history of severe urban flooding, including a once-in-a-century storm in 2016. Multi-source historical flood data were compiled from NOAA storm event records and crowdsourced reports to enhance spatial coverage. Four machine learning algorithms (Random Forest, Support Vector Machine, XGBoost, and Logistic Regression) were implemented to identify the most effective approach for urban pluvial flood prediction. Random Forest (RF) and Support Vector Machine (SVM) achieved the highest accuracy (0.84) and demonstrated strong discriminatory power. RF was selected as the optimal model because it had a higher AUC (90%) and the lowest RMSE (0.35). To assess generalizability, the RF model was validated on updated land use data and flood records from a 2020 storm event. It demonstrated robust performance (accuracy = 0.89, RMSE = 0.36, precision = 0.75, recall = 1, and AUC = 0.95), despite urban development changes. This study’s novelty lies in combining multi-source flood records with a grid-based machine learning framework and rigorously validating model robustness under evolving urban conditions. The results advance urban pluvial flood susceptibility modeling and offer actionable guidance for evidence-based flood risk management worldwide.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040172

Authors: Miljenko Lapaine Temenoujka Bandrova Kerkovits Krisztián

This paper revisits the Lambert conformal conic (LCC) projection and rederives its equations using a new notation, V, defined as the reciprocal of the commonly used U, which simplifies the expressions. Based on the resulting distortion formulas, conditions determining whether the projection has two, one, or no standard parallels are obtained. An optimal LCC configuration is defined by requiring equal local linear scale factors at the bounding parallels and symmetric maximum and minimum distortions about unity. Applied to the territory of Bulgaria (φS ≈ 41°14′, φN ≈ 44°13′), this criterion yields optimized standard parallels at φ1 ≈ 41°40′ and φ2 ≈ 43°47′. The corresponding local linear scale factors range from ca. 0.999832 to 1.000168, i.e., symmetric distortions of approximately ±1.7 × 10−4. Compared with existing implementations such as BGS2000 and BGS2005, the proposed configuration slightly reduces the distortion range and provides a more balanced distribution of scale over the country.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040171

Authors: Guanglei Zheng Yuchai Wan Xun Zhang Xiansheng Liu

Reliable air-quality monitoring is essential for urban exposure assessment and environmental policy, yet many downstream applications are hindered by sparse regulatory stations and noisy real-world measurements. While diffusion models have shown promise for probabilistic spatiotemporal imputation, common conditioning strategies can be brittle: purely input-based conditioning may drift from sparse constraints, whereas hard clamping can introduce a clean–noisy mismatch and propagate corrupted readings during reverse sampling. In this work, we propose STGPD (SpatioTemporal Graph Posterior Diffusion), a probabilistic framework that formulates city-scale pollutant reconstruction as posterior sampling on a graph-structured spatiotemporal field. STGPD enforces noise-aware soft consistency by re-noising visible observations to the current diffusion level and fusing a noise-matched measurement term with the model prior via variance-weighted fusion under an explicit observation-noise model. To improve spatial extrapolation in heterogeneous urban environments, we further construct a dual-view graph that combines geographic proximity with functional similarity derived from static descriptors. Experiments on real-world monitoring data in Augsburg, Germany, for PM10 and NO2 show that STGPD provides a robust probabilistic reconstruction framework under extreme sparsity, station outages, and synthetic sensor-noise injection in this sparse-monitoring case study. Compared with strong deterministic and diffusion-based baselines, STGPD achieves improved reconstruction accuracy (MAE/RMSE) and better-calibrated uncertainty estimates (CRPS) under the current evaluation protocols.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040170

Authors: Yueying Chen Wenbin Wei Jie Xiao Siqi Zheng

The development of digital technology offers unprecedented opportunities in the documentation, conservation, and interpretation of cultural heritage. Due to its high precision, efficiency, and visualization, this technology provides innovative ways for people to interact with heritage sites. However, its dramatic development introduces several problems, including systematic deficiencies in high-precision data acquisition, difficulties in effectively integrating multi-source heterogeneous data, and an inability to reconstruct context during the digital restoration of heritage. Thus, this research proposes a framework of digital re-contextualization, reintegrating the lost physical space, visual information, and mental experience into a coherent whole through triangulation comparison, interpretive restoration, and experiential virtual reconstruction. Taking the Dingjiazha M5 Muraled Tomb as a case study, this article details how this framework was applied to systematically consolidate the archaeological literature and material-sourced spatial data to construct a reliable and verifiable digital replica of the in situ heritage site. This framework shifts the focus from mere data documentation to knowledge production and experiential reconstruction, ensuring the scientific integrity of the restoration and allowing more members of the public to access the heritage site. It also demonstrates how lost historical spaces can be reborn in the digital realm in a way that is both responsible and rich with interpretive depth.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040169

Authors: Alireza Mohammadi Arshad Ahmed Elahe Pishgar Munazza Fatima Robert Bergquist

Water pipe smoking, or hookah smoking, is a growing public health concern ingrained in urban leisure cultures. Even though hookah smoking is common, the localized spatial drivers of this activity are still poorly understood. In order to close this gap, this study examined the locations of 273 hookah cafés in the Tabriz metropolis in Iran, modeling the distribution of these cafés against eight urban predictors: population density, road networks, and six distinct land use categories, such as commercial, administrative, educational, industrial, religious, and recreational land use. We combined Kernel Density Estimation (KDE) with Local Bivariate Relationships (LBR) using a high-resolution spatial approach. The findings indicate a non-random and spatially clustered pattern, using entropy-based measures of local relationship complexity. With the highest mean entropy value (0.84) and percentage of significant relationships (87.7%), educational land use density was found to be the best predictor. Additionally, there was a robust and consistent correlation with commercial land use density. Relationships with administrative and recreational land uses, on the other hand, showed lower entropy and were weaker and more dispersed. According to this study’s findings, the distribution of hookah cafés is spatially correlated to youth concentration and commercial activity patterns. Entropy analysis reveals substantial neighborhood-level variation in predictor influence, highlighting the value of local spatial analysis for identifying place-specific exposure.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040168

Authors: Cristina Allende-Prieto Pablo Rodríguez-Gonzálvez David Álvarez-Fuertes Raquel Perdiguer-Lopez

This study applies InSAR time series analysis derived from Sentinel-1 satellite data (ascending and descending orbits) processed with ISCE2 and StaMPS (v.4.1) software to evaluate deformation dynamics in three landfill types near Gijón, Spain. Initially, the data were validated against the European Ground Motion Service (EGMS) dataset using a set of Persistent Scatterers (PS) in an urban control area through two analytical approaches (EGMS protocol and PSDefoPAT(2023)). The results showed high consistency, with 82–85% of points classified as highly reliable. Subsequently, this control group was compared with PS from each landfill type (active sanitary, operational inert, and closed inert). Significant deformation differences were found in each landfill type: the active sanitary landfill exhibited distinct anomalies depending on orbit, with strong residual variance instability detected (p < 0.003) in both. Operational inert landfills showed significant anomalies (p < 0.001) in both orbits with variable stability, while closed inert landfills displayed strong stability (p > 0.7) and variable anomalies. These results confirm the efficacy of InSAR approaches for detecting active landfill zones to aid in locating illegal or unauthorized dumping sites and to direct in situ inspection planning.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040167

Authors: Qingyan Wang Yixin Wang Junping Zhang Yujing Wang Shouqiang Kang

Point cloud semantic segmentation is a core component in indoor scene understanding and autonomous driving. Under weak point-level supervision, only a small subset of points is annotated, making effective use of unlabeled points critical yet non-trivial. Many existing approaches rely on prediction confidence to filter pseudo labels or enforce consistency, which can bias training toward easy points and amplify early mistakes. Consequently, confidently wrong predictions may be reinforced, while uncertain points around class boundaries or in geometrically complex regions are less utilized, limiting further gains. An evidential uncertainty decomposition framework is introduced for weakly supervised point cloud semantic segmentation. Network outputs are interpreted as evidential distributions, and uncertainty is decomposed to separate lack-of-knowledge uncertainty from boundary-related ambiguity, providing a more informative reliability signal for unlabeled points. Based on this signal, different constraints are applied to different subsets: reliable points are trained with pseudo labels together with prototype-based regularization to encourage intra-class compactness; boundary-ambiguous points are guided by evidential consistency to improve boundary learning; and points with high epistemic uncertainty are excluded from pseudo-label-based supervision to mitigate error reinforcement. In addition, an uncertainty calibration term on sparsely labeled points helps stabilize training. Experiments on S3DIS, ScanNet-V2, and SemanticKITTI yield 67.7%, 59.7%, and 53.3% mIoU, respectively, with only 0.1% labeled points, comparing favorably with prior weakly supervised point cloud segmentation methods.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040166

Authors: Xin Wang Gang Liu Jing He Xiangbing Zhou Zhiyong Luo

With the rapid development of Intelligent Transportation Systems (ITSs), traffic prediction, a crucial component of ITSs, has garnered growing scholarly attention. The appli-cation of deep learning into traffic prediction has emerged as a prominent research direction, especially amid the rapid advancement of pretrained large language models (LLMs), which offer substantial benefits in time-series analysis through cross-modal knowledge transfer. In response to this advancement, this study introduces an innovative model for traffic flow prediction, designated as WGLLM. To capture spatiotemporal characteristics inherent in traffic flow data, this model incorporates a sequence embedding layer constructed on the stationary wavelet transform (SWT) and long short-term memory (LSTM), in conjunction with a spatial embedding layer founded on graph convolutional networks (GCNs). Additionally, a fully connected layer is utilized to integrate embeddings into the LLMs for comprehensive global dependency analysis. To verify the effectiveness of the proposed approach, experiments were carried out on two real traffic flow datasets. The experimental results demonstrate that WGLLM achieves superior predictive performance compared to multiple mainstream baseline models, accompanied by a significant enhancement in prediction accuracy.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040164

Authors: Shuo Zhang Pengcheng Liu Hongran Ma Mingwu Guo

(1) Background: Curve data compression plays a critical role in efficient storage, transmission, and multi-scale visualization of vector spatial data, especially for complex geographic boundaries. Achieving high compression efficiency while preserving geometric fidelity remains a challenging task. (2) Methods: This study proposes a vector curve compression framework based on a convolutional autoencoder. Curve data are segmented and resampled to unify network input, after which coordinate-difference sequences are encoded into low-dimensional latent vectors through convolutional layers and reconstructed via a symmetric decoder. (3) Results: Experiments conducted on a global island boundary dataset demonstrate that the proposed method achieves effective data reduction with stable reconstruction accuracy. Specifically, compared with the classical Douglas–Peucker (DP) algorithm, Fourier series (FS) methods, and fully connected autoencoders (FCAs), the 1D CAE exhibits superior and more robust reconstruction performance, especially under high compression ratios. It achieves the lowest positional deviation (PD = 42.41) and the highest spatial fidelity (IoU = 0.9991, with a relative area error of only 0.0067%), while maintaining high computational efficiency (57.32 s). Sensitivity analyses reveal that a convolution kernel size of 1 × 7 and a segment length of 25 km yield the optimal trade-off between representational capacity and model stability. (4) Conclusions: The proposed method enables efficient vector curve compression and reliable coastline reconstruction, and is particularly suitable for small- and medium-scale cartographic applications up to a map scale of 1:250 K.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040165

Authors: Sehan Kim Choong-Hyeon Oh

Urban neighborhood parks are essential infrastructure for sustainable cities, supporting physical and mental health, social cohesion, and climate adaptation. Equity-oriented park planning, however, requires accurate identification of residents who can access parks within network-constrained travel time thresholds. Many accessibility studies estimate served populations using coarse administrative zones and areal-weighting assumptions, which can bias results in heterogeneous, vertically developed districts. This study develops a building-based population allocation framework (implemented via a building centroid overlay) that integrates Statistics Korea’s census output areas (2023 Q4 release) with the Ministry of Land, Infrastructure and Transport (MOLIT)’s GIS Integrated Building Information database (2023 Q4 release) and applies it to Yongsan-gu (Yongsan District), Seoul. Park entrances were verified and digitized using street-view imagery available on multiple web map platforms, and walkable service areas (5 and 10 min) were delineated via network analysis. Potential service coverage and unserved population were then estimated under three spatial configurations—administrative dong (neighborhood-level administrative unit in Seoul; hereafter administrative unit), census output area, and building-based allocation—and compared. Under the 10 min scenario, the unserved share reached 24.6% at the administrative unit level but decreased to 5.9% and 4.3% when using census output areas and building-based allocation, respectively. The building-based approach additionally revealed micro-scale clusters of unserved residents near localized pedestrian constraints and boundary-crossing areas that are obscured by zone-based methods. These findings demonstrate the sensitivity of access-based potential service coverage diagnostics to spatial unit choice and population disaggregation and suggest that building-based population allocation can improve the targeting of park pro-vision policies and promote spatial equity in dense, vertically developed cities.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040162

Authors: Wen Cao Yinbao Zhang Runsheng Li Liqiu Ren He Chen

In the era of information explosion, the effective configuration of labels on maps is crucial for the rapid comprehension of information. The point-feature label placement problem, particularly in large-scale and high-density scenarios with spatial mutual-exclusion constraints, is a classic NP-hard discrete optimization challenge. Existing metaheuristic algorithms (e.g., Simulated Annealing and Genetic Algorithm) often struggle to achieve high-quality global layouts due to their propensity to become trapped in local optima, inefficient random point-selection processes, and inadequate modeling of the spatial mutual-exclusion and blocking constraints between labels. To address these limitations, this paper proposes a Progressive Reinforcement Learning (PRL) algorithm specifically tailored for the point-feature label placement problem. The algorithm models the label placement process as a sequential decision-making problem within the Reinforcement Learning framework, optimized through agent–environment interaction. Its core design comprises the following: (1) a staircase-like policy learning mechanism that shifts from “broad exploration in the early stage to precise exploitation in the later stage” to balance global search and local optimization; (2) a data mining-based Intelligent Action Screening (IAS) mechanism, which dynamically identifies and prioritizes “high-value action points” critical for improving layout quality by constructing the “Contribution Decline Degree” and “Contribution Support Degree” metrics. Experiments on large-scale real-world POI datasets (10,000, 20,000, and 32,312 points) demonstrate that the proposed algorithm significantly outperforms 13 state-of-the-art comparative algorithms, including Simulated Annealing, Genetic Algorithm, Differential Evolution, POPMUSIC, and DBSCAN, in terms of both placement quality and the number of successfully placed labels. It exhibits remarkable adaptability and competitiveness in handling high-density and complex scenarios.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040163

Authors: Yong Tang Jianhua Gong Yi Li Jieping Zhou Jun Sun

Worldwide visual geo-localization aims to predict the geographic coordinates of an image capture location from visual content alone, posing unique challenges due to the vast scale of the Earth’s surface and pervasive visual ambiguity across distant regions. Existing approaches face distinct limitations as follows: retrieval-based methods demand massive geo-tagged databases and scale poorly; alignment-based models lack interpretability and are vulnerable to visually similar scenes; and large vision-language models (LVLMs) offer semantic reasoning but suffer from hallucination. A natural solution is retrieval-augmented generation (RAG), yet we observe that directly injecting retrieved candidates as context causes severe context poisoning. To address this, we propose HybridGeo, a dual-stream late-fusion framework that decouples retrieval from reasoning. A retrieval stream applies continuous alignment with spatial–semantic clustering to produce stable regional anchors; a reasoning stream performs context-free Chain-of-Thought inference to yield an independent coordinate estimate. The two streams are fused only at the decision stage via a spatial–consistency module that triggers weighted averaging under agreement or confidence-based arbitration under conflict. Experiments on Im2GPS3k show that HybridGeo achieves 73.89% Country@750km accuracy, outperforming the retrieval baseline by 7.27% and 8.23%, and surpassing both VLM-only and RAG baselines. These results demonstrate that late fusion effectively avoids context poisoning while enabling complementary benefits from both streams.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040161

Authors: Xian Guo Wenjing Ding Yichuan Wang Jie Jiang

Street-view imagery supports fine-grained urban monitoring, but most street-scene change detection methods are pixel-centric or object-centric and cannot explicitly capture the evolution of inter-entity spatial relations needed for interpretable tasks (e.g., compliance inspection and post-disaster assessment). To address this, we propose SSPRCD, a scene graph-based framework that extracts entity-relation triplets with pixel locations, builds spatial knowledge graphs, and achieves stable node alignment via intra-/inter-temporal consistency. Graph differencing then identifies added, removed, and unchanged entities/relations, while nGED and graph2vec jointly quantify structural discrepancies between temporal scenes. Experiments on the TSUNAMI dataset, with comparisons across two object detectors and seven scene graph generation backbones, show that SSPRCD achieves a macro-F1 of 0.65 for the object-level task, F1 of 0.72 for binary change detection, and F1 of 0.89 for relation-level detection, consistently outperforming baseline methods. Overall, SSPRCD delivers relation-aware and topology-informed change explanations that improve the interpretability of street-block level change analysis for geospatial in-formation updating and urban applications.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040160

Authors: Qianyin Jiang Jianshang Liao Qiuyu Lin Junkang Zhang

Remote sensing object detection is fundamental to Earth observation, yet remains challenging when relying on a single sensing modality. While optical imagery provides rich spatial and textural details, it is highly sensitive to illumination and adverse weather; conversely, Synthetic Aperture Radar (SAR) offers robust all-weather acquisition but suffers from speckle noise and limited semantic interpretability. To address these limitations, we leverage the potential of foundation models for optical–SAR object detection via a novel gated–guided fusion approach. By integrating transferable and generalizable representations from foundation models into the detection pipeline, we enhance semantic expressiveness and cross-environment robustness. Specifically, a gated–guided fusion mechanism is designed to selectively merge cross-modal features with foundational priors, enabling the network to prioritize informative cues while suppressing unreliable signals in complex scenes. Furthermore, we propose a dual-stream architecture incorporating attention mechanisms and State Space Models (SSMs) to simultaneously capture local and long-range dependencies. Extensive experiments on the large-scale M4-SAR dataset demonstrate that our method achieves state-of-the-art performance, significantly improving detection accuracy and robustness under challenging sensing conditions.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040159

Authors: Xing Tu Yu Xia

Exploring public awareness, participation, and emotional inclination toward intangible cultural heritage (ICH) clarifies public attitudes and demands toward traditional culture, providing a crucial basis for targeted ICH protection and inheritance. Based on ICH text big data collected from China’s mainstream social media platform Weibo, this study improves the TF-IDF algorithm, integrates LDA topic analysis for semantic feature mining, and trains a new sentiment analysis model to explore public emotional attitudes and their formation mechanisms. The study is geographically limited to China and covers the entire year of 2023. The results show that: (1) Public ICH perception is multi-dimensional, with close attention to crafts like paper-cutting and traditional Chinese medicine; action-oriented terms reflect dynamic inheritance demands. Public discussions focus on three dimensions: ICH inheritance and development (39%), introduction and promotion (45%), and public experience and participation (16%), with the latter accounting for a low proportion. (2) Public sentiment toward ICH is predominantly positive, with all regions scoring above 0.730 (full score = 1), and Zhejiang (0.751) and Jiangsu (0.750) ranking significantly higher. (3) Spatial econometric analysis reveals marked regional differences in ICH sentiment distribution, mainly affected by three key factors—the number of ICH projects, the number of inheritors, and regional GDP—with regression coefficients of 0.699, 0.632, and 0.458 (p < 0.01). This finding provides a basis for formulating targeted ICH protection strategies.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040158

Authors: Qianhan Wang Yuechen Li

With accelerating global urbanization and increasingly diverse demands for public spaces, promoting urban low-carbon transitions and enhancing residents’ quality of life have become central missions of modern urban development. As one of the city’s primary arteries, streets—through their green landscapes, slow-moving transportation systems, and public facilities—play an indispensable role in reducing carbon emissions, promoting healthy living, and improving residents’ well-being. In this study, the Yubei District of Chongqing was selected as the research area, and an automated evaluation framework was proposed for street visual quality, based on multi-source street view data and ensemble learning. PSP-Net semantic segmentation model was employed to extract eight key visual indicators from street view images, including green view index, Visual Entropy (Entropy), sky view factor (SVF), drivable space, sidewalk, safety facilities, buildings, and enclosure. Based on these features, a Stacking-based ensemble learning model was constructed, integrating multiple base models such as Random Forest, XGBoost, and LightGBM, with Linear Regression as the meta-learner, to predict street visual quality. The results demonstrate that the ensemble model significantly outperforms any single model, achieving a correlation coefficient (r) of 0.77 and effectively capturing the complex perceptual features of street environments. This study provides a reliable, intelligent, and quantitative method for large-scale evaluation of urban street visual quality, while supplying data support and decision-making references for street renewal and spatial optimization.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040157

Authors: Iván Ramos-Diez Sara Barilari Jonas Ljunggren Sofie Hellsten Noelia Ferreras-Alonso

The urgency to mitigate greenhouse gas emissions and address the accelerating impacts of climate change has placed renewable energy as a core part of global climate strategies. However, the expansion of renewable infrastructures with a focus on solar systems often generates competition with other land uses, raising concerns about land availability, environmental integrity, and social acceptance. Renewable energy solutions deployment must be aligned with sustainable land-use planning, particularly in diverse and multifunctional landscapes. This study presents a GIS-based Multi-Criteria Decision-Making (MCDM) methodology to identify the most suitable areas for implementing a set of six land-use-based adaptation and mitigation solutions (LAMSs) focused on solar energy. Using Python-based processing algorithms and high-resolution spatial datasets, the methodology integrates technical, environmental, and socioeconomic criteria to generate suitability maps for three different case studies across Europe: Almería (Spain), Valle d’Aosta (Italy), and the Azores (Portugal). Results reveal significant geographical disparities in suitability due to the different land constraints. Almería and the Azores demonstrate high potential for photovoltaic and agrovoltaic farms, while Valle d’Aosta’s mountainous terrain is more limited for these measures. Floating solar and solar land management measures show limited applicability across all sites. The analysis highlights the value of place-based approaches in energy planning and the utility of GIS-MCDM tools to support evidence-based decision-making, enabling context-sensitive deployment of renewable energy infrastructure.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040156

Authors: Xuefei Gu Jieun Seo

Under rapid urbanization, street crime poses growing challenges to urban safety. Existing studies often treat gray and green spaces as independent variables, limiting the understanding of nonlinear crime patterns and spatiotemporal heterogeneity. Using day–night street crime data from Shanghai between 2010 and 2020, this study applies an interpretable machine learning framework combining CatBoost and SHAP to examine how the coupling of gray–green spatial structures influences street crime. Gray–green spatial morphology is quantified using both MSPA- and Fragstats-based indicators, which are integrated into composite coupling indices. The results indicate that gray–green structural coupling exhibits significant nonlinear and threshold-dependent effects on street crime. Compared with conventional Fragstats metrics, MSPA-based structural indicators demonstrate stronger explanatory power. Theft-specific analysis further indicates that gray-space core–edge structures exhibit higher crime risk at night, with this effect becoming more pronounced in the later period. Across both study periods and day–night contexts, green branch areas (G_BRANCH) consistently show stable inhibitory effects, with the strongest suppression occurring when G_BRANCH values range between 0 and 1.6 and interact with gray core–edge structures (B_CORE and B_EDGE). These findings provide quantitative evidence that gray–green spatial structures function through coupled, nonlinear interactions and offer targeted spatial planning implications for crime prevention in high-density cities.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040155

Authors: Renata Ďuračiová Tomáš Ič Tomasz Oberski

While parameters such as slope and aspect are routinely considered in solar radiation modelling, the role of terrain or surface roughness remains underexplored, with no universally accepted method for its calculation. This study compares several approaches to quantifying terrain or surface roughness in several geographical information system (GIS) environments (ArcGIS, QGIS, WhiteboxTools, and SAGA GIS) and introduces local fractal dimension, computed using a custom Python script, as an additional metric. The aim is to evaluate the influence of surface roughness on potential solar radiation modelling and to examine its relationship with other terrain parameters. The analysis is based on case studies from both a rugged alpine environment in the Tatra Mountains (Tichá and Kôprová dolina (valleys), Kriváň peak; 944–2467 m a.s.l.) and an urban environment (the city of Poprad, near the High Tatras, Slovakia). The results demonstrate that surface roughness can significantly affect potential solar radiation modelling in areas with high surface variability. The findings are applicable not only to solar radiation studies, but also to other fields of spatial modelling, where incorporating surface roughness can improve the accuracy and robustness of spatial analyses and predictions.

ISPRS International Journal of Geo-Information doi: 10.3390/ijgi15040154

Authors: Terence Love

Variety Dynamics (VD) is a new methodology to identify reasons for failures in spatial data infrastructure (SDI) governance and standardisation as well as potential opportunities for improvement. SDI governance and standardisation situations are often shaped by multiple feedback loops and do not conform to the assumptions needed for causal analysis. This combination is an intrinsic basis for faulty decision and policy making. Variety Dynamics presents geographic information science with a new ability to address the above issues and reveal otherwise hidden structural factors. It shows that most SDI initiatives for change are ineffective because they do not influence variety distributions. Standards are published, coordinating bodies established, and technical platforms deployed without significant changes in equitable outcomes. Variety Dynamics also reveals opportunities for successful SDI policy initiatives leveraging data sovereignty changes that force infrastructure migration and temporarily invert transaction cost structures. After data sovereignty is established, however, any SDI governance and standardisation problems will be likely locked in through path dependencies and accumulated switching costs.