ISPRS International Journal of Geo-Information

21 pages, 5145 KB

Open AccessArticle

Airborne LiDAR Point Cloud Building Reconstruction Based on Planar Optimal Combination and Feature Line Constraints

by Zhao Hai, Cailin Li, Baoyun Guo, Xianlong Wei, Zhuo Yang and Jinhui Zheng

ISPRS Int. J. Geo-Inf. 2026, 15(2), 92; https://doi.org/10.3390/ijgi15020092 - 20 Feb 2026

Viewed by 548

This paper proposes a building reconstruction framework for airborne LiDAR data to address the challenge of automated modeling under conditions of uneven point cloud density and missing vertical walls, generating high-precision and structurally compact 3D building models. The method first combines adaptive resolution [...] Read more.

This paper proposes a building reconstruction framework for airborne LiDAR data to address the challenge of automated modeling under conditions of uneven point cloud density and missing vertical walls, generating high-precision and structurally compact 3D building models. The method first combines adaptive resolution hypervoxels with a global graph cut optimization strategy to extract precise roof plane primitives from sparse point clouds of buildings. Subsequently, it infers building facades and internal vertical walls based on point cloud projection contours and height change detection, thereby completing the wall structures commonly missing in airborne LiDAR data. Finally, a feature line constraint term is introduced into the hypothesis-and-selection-based reconstruction framework to guide the structural optimization of candidate planes, ensuring the reconstructed model closely matches the actual building geometry. The proposed method was evaluated on multiple public airborne LiDAR datasets, demonstrating its effectiveness through qualitative and quantitative comparisons with various state-of-the-art approaches. Full article

(This article belongs to the Special Issue Spatial Data Science and Knowledge Discovery)

► Show Figures

Figure 1

26 pages, 6887 KB

Open AccessArticle

Decoding Urban Riverscape Perception: An Interpretable Machine Learning Approach Integrating Computer Vision and High-Fidelity 3D Models

by Yuzhen Tang, Shensheng Chen, Wenhui Xu, Jinxuan Ren and Junjie Luo

ISPRS Int. J. Geo-Inf. 2026, 15(2), 91; https://doi.org/10.3390/ijgi15020091 - 20 Feb 2026

Viewed by 516

Abstract

Visual perception serves as a crucial interface connecting human psychology with the built environment. However, current studies on urban riverscapes often rely on static 2D imagery, failing to capture the spatial depth and immersive experience essential for ecological validity. Furthermore, the “black box” [...] Read more.

Visual perception serves as a crucial interface connecting human psychology with the built environment. However, current studies on urban riverscapes often rely on static 2D imagery, failing to capture the spatial depth and immersive experience essential for ecological validity. Furthermore, the “black box” nature of traditional machine learning models hinders the understanding of how specific environmental features drive public perception. To address these gaps, this study proposes an innovative framework integrating high-fidelity 3D models, computer vision (CV), and interpretable artificial intelligence (XAI). Using the River Thames (London) and the River Seine (Paris) as diverse case studies, we constructed high-precision 3D digital twins to quantify 3D spatial metrics (e.g., Viewshed Area, H/W Ratio) and applied the SegFormer model to extract 2D visual elements (e.g., Green View Index) from water-based panoramic imagery. Subjective perception data were collected via immersive Virtual Reality (VR) experiments. Random Forest models combined with SHAP were employed to decode the non-linear driving mechanisms of perception. The results reveal three universal principles: (1) Sense of Affluence and Vibrancy are primarily driven by high building density and vertical enclosure, challenging the traditional preference for openness in waterfronts; (2) Scenic Beauty is determined by a synergy of high Green View Index and quality artificial interfaces, suggesting a preference for nature-culture integration; (3) Sense of Boredom is significantly positively correlated with Viewshed Area, indicating that empty prospects without visual foci lead to monotony. This study demonstrates the efficacy of integrating Digital Twins and XAI in revealing robust perception mechanisms across different urban contexts, providing a scientific, evidence-based tool for precision urban planning and riverside regeneration. Full article

► Show Figures

Figure 1

23 pages, 21368 KB

Open AccessArticle

Vegetation Greenness Changes in Northeast China Dominated by Climate Change and Ecological Restoration

by Cui Jin, Xiuling Wang, Zeyu Zhang, Linze Li, Haoran Wang, Gaoyu Li and Hongyan Cai

ISPRS Int. J. Geo-Inf. 2026, 15(2), 90; https://doi.org/10.3390/ijgi15020090 - 20 Feb 2026

Viewed by 525

Abstract

Vegetation in Northeast China has undergone complex changes under the dual pressures of climate change and human activities. Quantifying long-term vegetation dynamics and identifying their key drivers are critical for regional sustainability, ecological engineering construction, and environmental conservation. Ecological restoration plays a pivotal [...] Read more.

Vegetation in Northeast China has undergone complex changes under the dual pressures of climate change and human activities. Quantifying long-term vegetation dynamics and identifying their key drivers are critical for regional sustainability, ecological engineering construction, and environmental conservation. Ecological restoration plays a pivotal role in vegetation protection and recovery in this region; however, it has often been overlooked as a core driver in previous studies. This study analyzed the spatiotemporal dynamics of vegetation in Northeast China based on the long-term satellite-based leaf area index (LAI) datasets from 2000 to 2020, investigated the factors driving the spatiotemporal variation in LAI, and quantified the respective contributions of climate change and human activities to its change. The results showed that: (1) The LAI in Northeast China increased at a rate of 0.0292 yr⁻¹ since 2000, with 80.8% of the region showing vegetation improvement, predominantly within ecological restoration zones; however, urbanization induced severe local vegetation degradation. The Natural Forest Conservation Program (NFCP) exhibited the highest LAI growth rate (0.0315 yr⁻¹), followed by the Shelterbelt Program for Liaohe River (SPLR) and the Three-North Shelterbelt Program (TNSP) (0.0313 yr⁻¹ and 0.0294 yr⁻¹, respectively). (2) Land use type, soil type, and evapotranspiration were the primary single drivers of LAI spatial heterogeneity, and the interaction between land use and soil types has the most significant impact on it. (3) Climate change and human activities jointly accounted for 78.4% of the LAI variations across the study area, with the relative contribution of human activities (C_HA = 68.9%) being significantly higher than that of climate change (C_CC = 31.1%). In the vegetation browning regions of the three ecological restoration zones, the contribution of human activities exceeded 60%. In contrast, the dominant drivers of vegetation greening varied substantially among the zones: greening in the TNSP and SPLR was primarily regulated by climate change (C_CC > 50%), whereas in the NFCP it was mainly driven by human activities. This study highlights the key role of human activities (especially ecological restoration programs) in the improvement of vegetation cover in Northeast China, which can help to assess the benefits of ecological restoration in Northeast China, provide references for ecological and environmental management policy formulation, and promote the construction of regional ecological civilization. Full article

► Show Figures

Figure 1

29 pages, 9521 KB

Open AccessArticle

Evolutionary Characteristics and Dynamic Mechanism of the Global Transportation Carbon Emission Spatial Correlation Network

by Yi Liang, Han Liu, Zhaoge Wu, Xiaoduo Wang and Zhaoxu Yuan

ISPRS Int. J. Geo-Inf. 2026, 15(2), 89; https://doi.org/10.3390/ijgi15020089 - 19 Feb 2026

Cited by 1 | Viewed by 429

Abstract

This study constructs a global transportation carbon emission spatial correlation network via a modified gravity model and explores its evolutionary characteristics and dynamic mechanisms by integrating three-dimensional evolutionary analysis (node, overall, structural) and temporal exponential random graph model (TERGM). The main findings are [...] Read more.

This study constructs a global transportation carbon emission spatial correlation network via a modified gravity model and explores its evolutionary characteristics and dynamic mechanisms by integrating three-dimensional evolutionary analysis (node, overall, structural) and temporal exponential random graph model (TERGM). The main findings are as follows: (1) Global transportation carbon emission spatial correlation intensity keeps rising, with improved connectivity and integration, forming three regionally agglomerated correlation poles centered on the United States (America), China (Asia) and major European countries (Europe). (2) Network centrality distributes asymmetrically: Switzerland, Norway and the United States remain core nodes, while China, Japan and other Asian economies with strong direct correlation radiation are not in the core tier. (3) Third, evolutionary dynamics stem from the synergistic interaction of multidimensional attributes. ① Economic level positively drives bidirectional connection emission and attraction; economic scale and openness curb emission but boost attraction, while tertiary industry structure inhibits both. ② Only economic level and government efficiency exert significant positive effects on absdiff, fostering network heterophilic attraction. ③ Spatial and institutional proximity in edgecov effectively facilitate connection formation. ④ Endogenous network variables present a collaborative mechanism of reciprocity and transmission, constrained by network density. ⑤ Temporal effects show early connection structure forms path dependence, resulting in low dynamic variability and overall network stability. Full article

(This article belongs to the Special Issue Spatial Data Science and Knowledge Discovery)

► Show Figures

Figure 1

26 pages, 3984 KB

Open AccessArticle

Exploring Spatial Patterns of Short-Term Rental Accommodations in Lisbon with Geographic Information System (GIS)

by Jorge Ferreira and Gonçalo Antunes

ISPRS Int. J. Geo-Inf. 2026, 15(2), 88; https://doi.org/10.3390/ijgi15020088 - 18 Feb 2026

Viewed by 936

Abstract

There has been substantial debate regarding the consequences of overtourism in cities. Scholars have also examined variables that are directly and indirectly related to tourism, including demography, urban rehabilitation and requalification, gentrification, speculation in the real estate market, the influence of digital booking [...] Read more.

There has been substantial debate regarding the consequences of overtourism in cities. Scholars have also examined variables that are directly and indirectly related to tourism, including demography, urban rehabilitation and requalification, gentrification, speculation in the real estate market, the influence of digital booking platforms, and the expansion of short-term rental (STR) accommodation. This research seeks to develop a clearer spatial understanding of this last one. By analyzing their distribution, density (maximum occupancy), and clustering and by employing Geographic Information Systems (GIS), this article will propose methodologies to better visualize spatial patterns, providing different perspectives of the city of Lisbon and its most tourism-intensive parishes. The article finds that STRs in Lisbon have expanded rapidly, concentrating overwhelmingly in six historic parishes where STR supply and maximum occupancy now exceed resident populations and housing availability. GIS analysis reveals intense clustering in central neighborhoods—especially Alfama—indicating significant tourism pressure and signs of overtourism. These spatial patterns correlate with depopulation and rising housing costs. The study concludes that STR are now a decisive factor in urban imbalance and that detailed spatial analysis is essential for regulating tourism, defining carrying-capacity thresholds, and developing more sustainable, socially just urban planning policies. Full article

(This article belongs to the Special Issue Spatial Data Science and Knowledge Discovery)

► Show Figures

Figure 1

24 pages, 7660 KB

Open AccessArticle

Reasoning over Heterogeneous Geospatial Schemas: Aligning Authoritative Taxonomies and Collaborative Folksonomies Through Large Language Models

by Fabíola Andrade Souza and Silvana Philippi Camboim

ISPRS Int. J. Geo-Inf. 2026, 15(2), 87; https://doi.org/10.3390/ijgi15020087 - 18 Feb 2026

Viewed by 567

Abstract

Semantic interoperability remains a critical challenge in Spatial Data Infrastructures (SDIs), particularly when aligning authoritative taxonomies with collaborative folksonomies. Traditional alignment tools often fail to bridge the semantic and structural asymmetry between these schemas. This paper evaluates the capability of Large Language Models [...] Read more.

Semantic interoperability remains a critical challenge in Spatial Data Infrastructures (SDIs), particularly when aligning authoritative taxonomies with collaborative folksonomies. Traditional alignment tools often fail to bridge the semantic and structural asymmetry between these schemas. This paper evaluates the capability of Large Language Models (LLMs), specifically distinguishing between traditional architectures and emerging Large Reasoning Models (LRMs), to perform semantic alignment between the Brazilian national topographic data model standard (EDGV) and OpenStreetMap (OSM). Using a formal ontology as a prompting scaffold, we tested seven model versions (including ChatGPT 5, DeepSeek R1, and Gemini 2.5) on their ability to bridge the gap between rigid hierarchical classes and the dynamic, ‘long-tail’ vocabulary of the folksonomy. Results reveal a distinct trade-off: while traditional LLMs exhibited ‘lexical rigidity’ and popularity bias—failing to map low-frequency tags—Reasoning Models demonstrated significantly improved capacity for semantic expansion, correctly identifying complex many-to-one (n:1) relationships across linguistic barriers. However, this reasoning depth often came at the cost of ‘hallucination by over-specification’ and syntactic instability in generating OWL code. We conclude that a neuro-symbolic approach, positioning LRMs as ‘Semantic Catalysts’ within a Human-in-the-Loop (HITL) workflow, provides a viable pathway for interoperability, balancing generative power with the need for logical rigor and spatial validation. Full article

(This article belongs to the Special Issue LLM4GIS: Large Language Models for GIS)

► Show Figures

Figure 1

19 pages, 2618 KB

Open AccessArticle

Quantifying the Spatial Burden of Informal Ride Provision for Older Adults Using Activity Space Analysis and GIS

by Rebecca L. Mauldin, Stephen P. Mattingly, Soeun Jang, Swasati Handique, Mahshid Haque and Rupal Parekh

ISPRS Int. J. Geo-Inf. 2026, 15(2), 86; https://doi.org/10.3390/ijgi15020086 - 17 Feb 2026

Viewed by 410

Abstract

Older adults’ well-being is strongly shaped by their capacity to navigate and access places beyond their immediate surroundings. Lack of adequate transportation can limit their access to health care, services, and social opportunities. For older adults in the United States who do not [...] Read more.

Older adults’ well-being is strongly shaped by their capacity to navigate and access places beyond their immediate surroundings. Lack of adequate transportation can limit their access to health care, services, and social opportunities. For older adults in the United States who do not or no longer drive, getting private automobile rides from others is their primary mode of transportation, but this reliance can burden their ride providers. Measuring and assessing the geospatial burden of providing rides is important for research and policies that aim to address both negative effects for ride providers and older adults’ unmet travel needs. In this manuscript, we propose an approach that collects data to assess ride providers’ geospatial activity spaces for their own routine activities and for providing rides. By comparing the two activity spaces, we propose a method to operationalize geospatial ride-providing burden, using three potential burden indicators. Using data from an exploratory study (N = 12 ride providers), we apply these burden indicators and correlate them to other indicators of burden (i.e., days/month giving rides, monetary costs, missed work, increased stress). We conclude that the share of the activity space for providing rides falling beyond the area of the ride provider’s routine personal travel (what we call Burden Indicator B) may be a useful indicator of geospatial burden of providing rides. Full article

(This article belongs to the Special Issue Spatial Data Science and Knowledge Discovery)

► Show Figures

Figure 1

22 pages, 5177 KB

Open AccessArticle

VGGT-Geo: Probabilistic Geometric Fusion of Visual Geometry Grounded Transformer Priors for Robust Dense Indoor SLAM

by Kai Qin, Jing Li, Sisi Zlatanova, Haitao Wu, Hao Wu, Yin Gao, Dingjie Zhou, Yuchen Li, Sizhe Shen, Xiangjun Qu, Zhenxin Zhang, Banghui Yang and Shicheng Xu

ISPRS Int. J. Geo-Inf. 2026, 15(2), 85; https://doi.org/10.3390/ijgi15020085 - 16 Feb 2026

Viewed by 1228

Abstract

With the rapid evolution of Digital Twins and Embodied AI, achieving fast, dense, and high-precision 3D perception in unknown environments has become paramount. However, existing Visual SLAM paradigms face a critical dilemma: geometry-based methods often fail in texture-less areas due to feature scarcity, [...] Read more.

With the rapid evolution of Digital Twins and Embodied AI, achieving fast, dense, and high-precision 3D perception in unknown environments has become paramount. However, existing Visual SLAM paradigms face a critical dilemma: geometry-based methods often fail in texture-less areas due to feature scarcity, while learning-based approaches frequently suffer from scale drift and unphysical deformations. To bridge this gap, we propose VGGT-Geo, a novel SLAM system that synergizes generative priors from Large Foundation Models with multi-modal geometric optimization. Distinguishing itself from simple cascaded architectures, we construct a Probabilistic Geometric Fusion framework, consisting of (1) Generative Warm-start, leveraging the holistic scene understanding capabilities of the VGGT, (2) Confidence-Aware Optimization to extract dense features via DINOv3 and predict their confidence map, and (3) a Multi-Modal Constraint Closure that fuses point-line features and metric depth priors to constrain rotational Degrees of Freedom in Manhattan Worlds. We conducted systematic evaluations on TUM, Replica, Tanks and Temples, and a challenging self-collected dataset featuring extreme lighting and texture-less walls. Experimental results demonstrate that VGGT-Geo exhibits superior robustness and accuracy in unseen environments. On our most challenging dataset, it achieves an Absolute Trajectory Error of 4–5 cm and a Relative Rotation Error of 0.79°, outperforming current state-of-the-art methods by approximately 50% in trajectory accuracy. This study validates that synergizing the intuition of Large Foundation Models with geometric rigor is a viable path toward next-generation robust SLAM. Full article

(This article belongs to the Special Issue Urban Digital Twins Empowered by AI and Dataspaces)

► Show Figures

Figure 1

20 pages, 3481 KB

Open AccessArticle

Construction of a Driving Route Inference Model Integrating Road Network Topology and Traffic Dynamics

by Yuxia Bian, Jinbao Liu, Xiaolong Su and Yuanjie Tang

ISPRS Int. J. Geo-Inf. 2026, 15(2), 84; https://doi.org/10.3390/ijgi15020084 - 16 Feb 2026

Viewed by 337

Abstract

The deployment volume of urban surveillance cameras has reached hundreds of thousands or even millions with the advancement of intelligent transportation systems (ITSs), indicating an enormous scale. However, the number of small-field-of-view surveillance cameras in large-scale traffic areas is insufficient to achieve full [...] Read more.

The deployment volume of urban surveillance cameras has reached hundreds of thousands or even millions with the advancement of intelligent transportation systems (ITSs), indicating an enormous scale. However, the number of small-field-of-view surveillance cameras in large-scale traffic areas is insufficient to achieve full coverage of urban traffic zones. In the fields of ITSs, this study proposes a traffic information-based driving route inference method to clarify target vehicles’ paths in zones with monitoring blind spots and enhance the collaborative capability between surveillance cameras and traffic networks. First, this study maps traffic roads containing monitoring blind spots and their topologies into Bayesian network (BN) structures. The influencing factors of the target vehicle path can be analyzed, extracted, and quantified by the known data in a traffic network. A weight analysis method is utilized to estimate the weight coefficients of the influencing factors on the basis of the traditional BN model, thereby realizing the driving routes based on traffic networks. This study conducted experiments in Xinbei District, Changzhou City, and Jiangsu Province, China. Experimental results verify that the proposed method can accurately infer and reconstruct driving routes with monitoring blind zones. This method can provide theoretical support for analyzing driving directions at complex traffic intersections and enabling driving route inference in traffic network areas with monitoring blind spots. Full article

(This article belongs to the Topic Geospatial AI: Systems, Model, Methods, and Applications)

► Show Figures

Figure 1

34 pages, 17669 KB

Open AccessArticle

Integrating Health Status Transitions and Service Demands: A Spatial Framework for Elderly Care Service Resource Allocation

by Zhe Wang and Ying Zhou

ISPRS Int. J. Geo-Inf. 2026, 15(2), 83; https://doi.org/10.3390/ijgi15020083 - 15 Feb 2026

Viewed by 496

Abstract

With the deepening of population ageing, the spatial planning of an elderly care service system faces unprecedented challenges. Building an elderly care service network that aligns with the pace of population ageing has become increasingly important and urgent. Based on annual longitudinal data [...] Read more.

With the deepening of population ageing, the spatial planning of an elderly care service system faces unprecedented challenges. Building an elderly care service network that aligns with the pace of population ageing has become increasingly important and urgent. Based on annual longitudinal data on older adults’ health status and care service utilization from Japan’s Long-Term Care Insurance (LTCI) system, this study quantifies the relationship between changes in health status and elderly care service demand using a discrete time homogeneous Markov model and Poisson regression analysis. Subsequently, Geographic Information System (GIS) techniques are applied to conduct spatial analysis of the urban built environment to identify living service centres for older adults. Indicators including distance, supply–demand balance, and service capacity are then integrated through multi-objective clustering optimization to construct a multi-level elderly care service network system, achieving a quantitative linkage between elderly health status and spatial demand-oriented planning. Finally, the proposed integrated framework, which combines health status transitions, service demand estimation, and spatial allocation, is applied to Qinhuai district in Nanjing, China, generating practical policy recommendations that promote the integration of healthy ageing and precision service delivery. Full article

(This article belongs to the Special Issue HealthScape: Intersections of Health, Environment, and GIS&T (2nd Edition))

► Show Figures

Figure 1

28 pages, 786 KB

Open AccessArticle

How Well Do Current Geoportals Support Geodata Discovery? An Empirical Study

by Susanna Ankama, Auriol Degbelo, Erich Naoseb, Christin Henzen and Lars Bernard

ISPRS Int. J. Geo-Inf. 2026, 15(2), 82; https://doi.org/10.3390/ijgi15020082 - 14 Feb 2026

Viewed by 428

Abstract

Implementing effective geospatial data discovery mechanisms in geoportals is crucial for facilitating easy access to geospatial data and services. Despite existing efforts to formulate geoportal design requirements, understanding end-user issues beyond a single geoportal in the context of geodata discovery is still lacking. [...] Read more.

Implementing effective geospatial data discovery mechanisms in geoportals is crucial for facilitating easy access to geospatial data and services. Despite existing efforts to formulate geoportal design requirements, understanding end-user issues beyond a single geoportal in the context of geodata discovery is still lacking. To address this gap, this study reports on a usability study conducted in Germany and Namibia, with the aim of examining issues faced by users during geodata search and discovery. The study employed a mixed-method approach combining Retrospective Think-Aloud (RTA) interviews and structured questionnaires. The results reveal key usability issues, including inefficient search mechanisms, inefficient presentation of search results, lack of user guidance, inefficient map interactions, and inefficient metadata descriptions. Additionally, the study revealed a difference in user perceptions regarding user experience aspects between the two user groups. The findings are of interest to the designers of geoportals in the context of open data reuse and spatial data infrastructure. Full article

► Show Figures

Figure 1

18 pages, 10625 KB

Open AccessArticle

An Integrated Approach to Evaluating the Spatial Allocation Efficiency of Urban Public Health Surveillance

by Shuzhen Xiao and Bisong Hu

ISPRS Int. J. Geo-Inf. 2026, 15(2), 81; https://doi.org/10.3390/ijgi15020081 - 14 Feb 2026

Viewed by 414

Abstract

Contingency epidemic outbreaks, such as the novel coronavirus (COVID-19) pandemic in 2020, have underscored the vital function of public health emergency response systems within national strategic frameworks. Public health surveillance and early warnings are imperative for safeguarding peoples’ lives, maintaining social stability, and [...] Read more.

Contingency epidemic outbreaks, such as the novel coronavirus (COVID-19) pandemic in 2020, have underscored the vital function of public health emergency response systems within national strategic frameworks. Public health surveillance and early warnings are imperative for safeguarding peoples’ lives, maintaining social stability, and promoting economic development. Existing studies are inadequate for accurately evaluating the efficiency of an urban public health surveillance system from a comprehensive perspective. In this work, an integrated framework was proposed for the evaluation of the spatial allocation efficiency of urban public health surveillance. This integrated approach incorporates three key aspects, spatial coverage, overlap, and accessibility, enabling a measurable evaluation of the overall spatial allocation efficiency. We utilized the proposed method to investigate the placement efficiency of the nucleic acid testing sites during the epidemic in Nanchang, China. The findings showed that using the integrated evaluation method based on coverage, overlap, and accessibility provides a more accurate reflection of the efficiency of existing site placements. It offers a flexible measurement system for evaluating urban surveillance site allocation strategies. This study introduces a novel perspective for the efficiency assessment of public health surveillance site placements, contributes to the development of public health emergency response systems, and provides a technical foundation for future contingency planning in public health surveillance. Full article

(This article belongs to the Special Issue HealthScape: Intersections of Health, Environment, and GIS&T (2nd Edition))

► Show Figures

Figure 1

26 pages, 2554 KB

Open AccessArticle

Semi-Automated Reporting from Environmental Monitoring Data Using a Large Language Model-Based Chatbot

by Angelica Lo Duca, Rosa Lo Duca, Arianna Marinelli, Donatella Occhiuto and Alessandra Scariot

ISPRS Int. J. Geo-Inf. 2026, 15(2), 80; https://doi.org/10.3390/ijgi15020080 - 14 Feb 2026

Viewed by 541

Abstract

Producing high-quality analytical reports for the environmental domain is typically time-consuming and requires significant human expertise. This paper describes MeteoChat, a semi-automatic framework for efficiently generating specialized environmental reports from heterogeneous environmental data. MeteoChat utilizes a Large Language Model (LLM) fine-tuned and integrated [...] Read more.

Producing high-quality analytical reports for the environmental domain is typically time-consuming and requires significant human expertise. This paper describes MeteoChat, a semi-automatic framework for efficiently generating specialized environmental reports from heterogeneous environmental data. MeteoChat utilizes a Large Language Model (LLM) fine-tuned and integrated with Retrieval-Augmented Generation (RAG). The system’s core is its plug-and-play philosophy, which separates analytical reasoning from the data source and the report’s intended audience. The fine-tuning phase uses data-agnostic, parameterized question–context–answer triples defined by an environmental expert to teach the LLM domain-specific analytical logic and audience-appropriate communication styles. Subsequently, the RAG phase integrates the model with actual datasets, which are processed via an Extract–Transform–Load (ETL) workflow to generate statistical summaries. This architectural separation ensures that the same reporting engine can operate on different sources, such as meteorological time series, satellite imagery, or geographical data, without additional training. Users interact with the system via a web-based conversational interface, where responses are tailored for either technical experts (using explicit calculations and tables) or the general public (using simplified, narrative language). MeteoChat has been tested with real data extracted from the micrometeorological network of ARPA Lazio. Full article

(This article belongs to the Special Issue LLM4GIS: Large Language Models for GIS)

► Show Figures

Figure 1

24 pages, 8056 KB

Open AccessArticle

What Dominates the Variation in Habitat Quality from a “Future” Perspective Based on Interpretable Machine Learning: Evidence from the Mid-Section of the Tianshan Mountains (MSTM), China

by Keqi Li, Qingwu Yan, Fei Li, Andong Guo, Minghao Yi, Xiaosong Ma, Zihao Wu and Guie Li

ISPRS Int. J. Geo-Inf. 2026, 15(2), 79; https://doi.org/10.3390/ijgi15020079 - 14 Feb 2026

Viewed by 404

Abstract

Exploring future habitat quality changes in the Mid-Section of the Tianshan Mountains (MSTM) is crucial for regional biodiversity conservation. This study utilizes climate projection data from CMIP6 and integrates the SD-PLUS-InVEST analytical framework to simulate future LULC and habitat quality under three distinct [...] Read more.

Exploring future habitat quality changes in the Mid-Section of the Tianshan Mountains (MSTM) is crucial for regional biodiversity conservation. This study utilizes climate projection data from CMIP6 and integrates the SD-PLUS-InVEST analytical framework to simulate future LULC and habitat quality under three distinct future scenarios. Additionally, the XGBoost-SHAP model is applied to identify and interpret the key regulatory factors within the modeling framework that influence habitat quality spatial heterogeneity. The results show the following: (1) the projections under the three 2035 scenarios generally follow the development trend of 2020, with continued spread of dry land and construction land, but general reduction in the ecological land, reflecting an intensifying conflict between land development and ecological preservation. (2) Habitat quality varies significantly across scenarios, generally exhibiting a “U-shaped” distribution pattern characterized by larger areas of high and low quality and smaller areas of moderate quality. Within the SSP5–8.5 scenario, habitat quality is relatively poor, accompanied by pronounced spatial heterogeneity and imbalance. (3) NDVI is identified as the dominant factor influencing habitat quality spatial heterogeneity, followed by GDP, TEM, and DEM. Although the influence of these factors varies slightly across scenarios, their relative importance remains generally consistent, reflecting the structural stability and response coherence of the ecosystem. Full article

(This article belongs to the Special Issue Spatial Data Science and Knowledge Discovery)

► Show Figures

Figure 1

28 pages, 8127 KB

Open AccessArticle

CARAG: Context-Aware Retrieval-Augmented Generation for Railway Operation and Maintenance Question Answering over Spatial Knowledge Graph

by Wenkui Zheng, Mengzheng Yang, Yanfei Ren, Haoyu Wang, Chun Zeng and Yong Zhang

ISPRS Int. J. Geo-Inf. 2026, 15(2), 78; https://doi.org/10.3390/ijgi15020078 - 14 Feb 2026

Viewed by 662

Abstract

General-purpose large language models excel at open-domain question answering, but in railway operation and maintenance (O&M) scenarios they still suffer from hallucinated knowledge and poor domain adaptation. In practice, railway O&M knowledge mainly arises from two heterogeneous sources: spatio-temporal data such as train [...] Read more.

General-purpose large language models excel at open-domain question answering, but in railway operation and maintenance (O&M) scenarios they still suffer from hallucinated knowledge and poor domain adaptation. In practice, railway O&M knowledge mainly arises from two heterogeneous sources: spatio-temporal data such as train trajectories, which are organized along the spatial layout of railway lines, and domain documents such as operating rules, which exhibit varying degrees of structural regularity. Traditional retrieval-augmented generation (RAG) systems usually flatten these multi-source data into a single unstructured text space and perform global retrieval in one embedding space, which easily introduces noisy context and makes it difficult to precisely target knowledge for specific lines, sections, or equipment states. To overcome these limitations, we propose CARAG, a context-aware RAG framework tailored to railway O&M data. CARAG treats domain documents and spatial data as a unified knowledge substrate and builds a spatial knowledge graph with concept and instance levels. On top of this knowledge graph, a GraphReAct-based multi-turn interaction mechanism guides the LLM to reason and act over the concept knowledge graph, dynamically navigating to spatially and semantically relevant candidate regions, within which vector retrieval and instance-level graph retrieval are performed. Experiments show that CARAG significantly outperforms baseline RAG methods on RAGAS metrics, confirming the effectiveness of structure-guided multi-step reasoning for question answering over multi-source heterogeneous railway O&M data. Full article

(This article belongs to the Special Issue LLM4GIS: Large Language Models for GIS)

► Show Figures

Figure 1

30 pages, 61260 KB

Open AccessArticle

Predicting Cropland Non-Agriculturalization Susceptibility Using Multi-Source Data and Graph Attention Networks: A Case Study of Wuhan, China

by Shiqi Wan, Lina Huang and Zhangying Xia

ISPRS Int. J. Geo-Inf. 2026, 15(2), 77; https://doi.org/10.3390/ijgi15020077 - 14 Feb 2026

Viewed by 368

Abstract

Cropland non-agriculturalization (CNA) threatens food security, ecosystem services, and sustainable development amid accelerating global urbanization. However, existing monitoring methods are often retrospective and lack adequate spatial and temporal resolution for proactive management. This study proposes GS-GAT, a graph-based deep learning framework for predicting [...] Read more.

Cropland non-agriculturalization (CNA) threatens food security, ecosystem services, and sustainable development amid accelerating global urbanization. However, existing monitoring methods are often retrospective and lack adequate spatial and temporal resolution for proactive management. This study proposes GS-GAT, a graph-based deep learning framework for predicting CNA susceptibility at the meso-spatial scale. A spatial graph was constructed for the non-central districts of Wuhan, China, and multisource features were extracted across four dimensions: imagery, land cover, topography, and socioeconomics. A comprehensive intensity index is developed to compute susceptibility levels at the street-block level based on multi-year land use data from 2018 to 2022. To address class imbalance, GraphSMOTE is employed to enhance minority node representation. The key model of GS-GAT is trained across four temporal snapshots using attention-based feature aggregation and joint optimization of classification and structural reconstruction losses. Experimental results show that GS-GAT demonstrated an average AUC of 85.6% and an F1 score of 82.6%, which increased to 93% and 91%, respectively, under relaxed evaluation criteria, whereby baseline models such as SVM and XGBoost were outperformed. Ablation studies confirm the contributions of feature fusion and GraphSMOTE to model robustness and minority class detection. The proposed framework offers a scalable and interpretable approach for early identification of cropland conversion risks, supporting more targeted land-use management and cropland protection strategies. Full article

► Show Figures

Graphical abstract

21 pages, 3195 KB

Open AccessArticle

Location Prediction of Urban Fire Station Based on GMM Clustering and Machine Learning

by Xiaomin Lu, Lijuan Wang, Haowen Yan, Haoran Song, Yan Wang, Zhiyi Zhang and Na He

ISPRS Int. J. Geo-Inf. 2026, 15(2), 76; https://doi.org/10.3390/ijgi15020076 - 12 Feb 2026

Viewed by 432

Abstract

Most machine learning (ML)-based facility location studies utilize uniform grid partitioning, often overlooking spatial heterogeneity. This limitation can compromise the validity and practical applicability of the resulting site selections. In response to this issue, this paper uses fire stations as the research subject [...] Read more.

Most machine learning (ML)-based facility location studies utilize uniform grid partitioning, often overlooking spatial heterogeneity. This limitation can compromise the validity and practical applicability of the resulting site selections. In response to this issue, this paper uses fire stations as the research subject and proposes a location prediction method that considers the heterogeneous characteristics within cities. Firstly, the Gaussian Mixture Model (GMM) is adopted based on the Point of Interest (POI) data to determine the clustering centres of the study area. Secondly, a Voronoi diagram is constructed to divide the study area reasonably. Then, a comprehensive feature matrix is constructed by integrating multi-source spatial data and five machine learning models: Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost) and Logistic Regression (LR). These are then used for training and evaluation. Finally, the GBDT model with the best performance in terms of both the F1 score and the AUC value was selected to predict the location of fire stations in Chengguan District, Lanzhou City. The results demonstrate the GBDT model’s effectiveness in identifying the rationale behind existing fire station locations and predicting potential new locations. It predicts 12 suitable locations for new fire stations, and the suitability of these predicted locations is validated by comparing them with the existing fire station locations, 8 of which are in the same block as existing fire stations in Chengguan District. Adding micro fire stations at four new predicted locations would improve response efficiency. The results of the feature importance analysis show that road accessibility is the primary factor affecting fire station location selection. This study’s proposed method effectively enhances the reasonableness of fire station site selection and provides a basis for planning fire stations in new urban areas in the future. Full article

► Show Figures

Figure 1

25 pages, 2447 KB

Open AccessReview

Assistive Navigation Technologies for Inclusive Mobility: Identifying Key Environmental Factors Influencing Wheelchair Navigation Through a Scoping Review

by Ali Ahmadi, Maryam Naghdizadegan Jahromi, Mir Abolfazl Mostafavi, Ernesto Morales and Nouri Sabo

ISPRS Int. J. Geo-Inf. 2026, 15(2), 75; https://doi.org/10.3390/ijgi15020075 - 12 Feb 2026

Cited by 1 | Viewed by 803

Abstract

Despite advancements in navigation apps for wheelchair users, there is no consensus on which environmental factors to prioritize for personalized accessible routes. This scoping review synthesizes factors influencing wheelchair mobility in urban settings, evaluates measurement methods, and assesses their integration into routing algorithms. [...] Read more.

Despite advancements in navigation apps for wheelchair users, there is no consensus on which environmental factors to prioritize for personalized accessible routes. This scoping review synthesizes factors influencing wheelchair mobility in urban settings, evaluates measurement methods, and assesses their integration into routing algorithms. Following Arksey and O’Malley’s framework and PRISMA-ScR guidelines, we analyzed six databases for English-language articles from 2005 to 2023, supplemented by an updated search covering 2023 to 2026. Two reviewers screened 6966 records and examined 79 full-text articles, with 24 meeting the inclusion criteria for data extraction. Environmental factors were categorized into static and dynamic factors affecting mobility. Key components included sidewalks (96%), ramps (63%), curb cuts (54%), stairs (50%), crosswalks (50%), and streets (38%). Common factors examined were length, slope, width, and surface properties. Data collection methods varied: 42% relied on measurements, 8% used user assessments and sensors, while 50% combined both approaches. Recent studies (2023–2026) demonstrate increasing adoption of AI and machine learning techniques, including crowdsourced smartphone data and generative AI for feature detection. This review identifies essential factors for wheelchair navigation and highlights significant gaps in dynamic factor assessment and real-time data integration. Full article

► Show Figures

Figure 1

21 pages, 15335 KB

Open AccessArticle

Mining the Tourism Destination Image and Analyzing Influence Mechanisms

by Shan Huang, Xu Lu, Jingqun Lu and Jinghua Zhang

ISPRS Int. J. Geo-Inf. 2026, 15(2), 74; https://doi.org/10.3390/ijgi15020074 - 12 Feb 2026

Viewed by 445

Abstract

Background: Research on spatial imagery as perceived by humans is an important frontier for deepening the theoretical understanding of Tourism Destination Image and promoting sustainable urban development. Significance: This study, from the perspective of tourists, explores the correlation mechanism between the cognitive image [...] Read more.

Background: Research on spatial imagery as perceived by humans is an important frontier for deepening the theoretical understanding of Tourism Destination Image and promoting sustainable urban development. Significance: This study, from the perspective of tourists, explores the correlation mechanism between the cognitive image and affective image of urban space. This is of great significance for enhancing the overall spatial quality of cities, promoting the integration of the man–land relationship, and driving the sustainable development of tourism. Method: In this study, we took Harbin as the case site, collected 89,375 reviews and 23,561 review images of 488 scenic spots on the Mafengwo and Ctrip platforms, and constructed a multimodal dataset. We classified the image scenes with the help of the Places365-CNN model. We then extracted text emotional features by utilizing the SnowNLP deep learning algorithm. We constructed a map of the spatial influence mechanism acting on cognitive image and emotion through MGWR. Results: The experimental results showed that in the level of Pleasure, the five indicators NHS, HPA, RPA, PDS and WRV had significant spatial correlations with urban sentiment. In the level of Arousal, the three indicators PD, MaSD and WRV showed significant spatial characteristics. Conclusions: This study reveals the influence mechanism of urban spatial perception elements on tourists’ emotions. It not only deepens the understanding of the Tourism Destination Image theory, but also provides a practical path based on the optimization of perception scenarios for the improvement of urban space, which has important implications for regional sustainable development. Full article

(This article belongs to the Special Issue Knowledge-Guided Map Representation and Understanding)

► Show Figures

Figure 1

27 pages, 1125 KB

Open AccessArticle

Spatial Autocorrelation Latent in Geographic Theory: A Call to Action

by Daniel A. Griffith

ISPRS Int. J. Geo-Inf. 2026, 15(2), 73; https://doi.org/10.3390/ijgi15020073 - 10 Feb 2026

Viewed by 632

Abstract

This paper exposes the latent but potent role of seemingly hidden spatial autocorrelation (SA) in all geographic theories, highlighting that it is everywhere, matters, and is a fundamental property of geotagged phenomena. This narrative examines and extends the literature about the inescapable nature [...] Read more.

This paper exposes the latent but potent role of seemingly hidden spatial autocorrelation (SA) in all geographic theories, highlighting that it is everywhere, matters, and is a fundamental property of geotagged phenomena. This narrative examines and extends the literature about the inescapable nature of the SA paradigm and the near-universal mixing of positive and negative SA. This study summary transcends the widespread but often implicit treatment of SA within geographic theories that their assumptions help achieve when they embed spatial processes, shape geospatial expectations, and define independent areal units so that these theory-delineating constraints largely absorb SA, reducing residual spatial dependence/correlation and improving conjectural validity, masking its presence for decades if not centuries. This paper explores selected prominent human geography theories (spatial optimization, agricultural location, gravity-model-based spatial interaction, central place systems), cultural and humanistic geography, geohumanities abstractions, physical geography theories (plate tectonics, climatology, uniformitarianism, soil formation), cartographic theories (geometric projections, semiotic/communication, cognitive/perceptual, geographic information systems anchored spatial analysis), and basic geospatial data gathering methodologies (qualitative and quantitative spatial sampling). It demonstrates that across the discipline of geography, exposing masquerading SA deepens theoretical coherence and strengthens methodological integrity, encouraging integrated spatial reasoning that bridges interpretive and analytical traditions. This article concludes by providing exemplifications of bringing scholastically unrealized SA in geographic theories out of obscurity, together with certain salient benefits from doing so, affirming the magnitude of fulfilling its major objective: SA is poised for discovery in all geospatial theories, from those for human and humanistic geography, through physical geography, to those for cartography as well as methodologies concerning all georeferenced data collection missions. Full article

(This article belongs to the Special Issue Cartography and Geovisual Analytics)

► Show Figures

Figure 1

23 pages, 6955 KB

Open AccessArticle

Scale and Aggregation Effects of MAUP on Built-Up Area Concentration: Evidence from the Łódź Metropolitan Area

by Marta Nalej

ISPRS Int. J. Geo-Inf. 2026, 15(2), 72; https://doi.org/10.3390/ijgi15020072 - 10 Feb 2026

Viewed by 514

Abstract

Spatial analyses of built-up areas based on aggregated land cover data are inherently affected by the Modifiable Areal Unit Problem (MAUP). This study quantifies the influence of the data scale and the areal unit configuration on Lorenz-based measures of the concentration of the [...] Read more.

Spatial analyses of built-up areas based on aggregated land cover data are inherently affected by the Modifiable Areal Unit Problem (MAUP). This study quantifies the influence of the data scale and the areal unit configuration on Lorenz-based measures of the concentration of the built area. Using Łódź Metropolitan Area (Poland) as a case study, harmonized land cover datasets at scales of 1:10,000 and 1:100,000 were analysed with regular square and hexagonal grids of varying sizes, as well as irregular cadastral units. Concentration was measured using a Lorenz curve-based coefficient and sensitivity to zonation was assessed using the coefficient of variation. The results show that the data scale is the primary determinant of the concentration values, with coarser-scale data consistently producing higher and more variable coefficients. Increasing the size of the areal unit leads to a systematic decrease in the concentration measured, while differences in unit geometry and location exert a comparatively minor influence. Irregular cadastral units improve spatial interpretability, but do not reduce susceptibility to MAUP. The findings confirm the strong scale dependency of concentration measures and highlight the necessity of multiscale approaches in quantitative analyses of built-up areas. Full article

(This article belongs to the Special Issue Spatial Data Science and Knowledge Discovery)

► Show Figures

Figure 1

16 pages, 6120 KB

Open AccessArticle

An Application of the Grid-Based Two-Step Floating Catchment Area Method to Assess the Spatial Accessibility of Green Spaces in Seoul, South Korea

by Jin Shin and Jinwoo Park

ISPRS Int. J. Geo-Inf. 2026, 15(2), 71; https://doi.org/10.3390/ijgi15020071 - 10 Feb 2026

Viewed by 720

Abstract

The conventional Two-Step Floating Catchment Area (2SFCA) method treats large-scale facilities as single centroids, leading to systematic under- and overestimation of spatial accessibility measures. To address this limitation, this study proposes a Grid-based G2SFCA methodology that disaggregates supply facilities into grid cells to [...] Read more.

The conventional Two-Step Floating Catchment Area (2SFCA) method treats large-scale facilities as single centroids, leading to systematic under- and overestimation of spatial accessibility measures. To address this limitation, this study proposes a Grid-based G2SFCA methodology that disaggregates supply facilities into grid cells to better capture their shape and assigns them as multiple access points. Using green spaces in Seoul, South Korea, as a case study, we compared the measures from the proposed method with the conventional centroid-based approach using descriptive statistics and spatial inequality indices. The results indicate that the grid-based method significantly stabilized the distribution, nearly halving the standard deviation and reducing the Gini coefficient. In addition, our proposed method corrected the centroid-induced overestimation of accessibility and provided a more precise identification of underserved areas. By resolving the supply-side centroid problem, our study provides a more robust and realistic foundation for assessing spatial equity in urban planning and resource allocation. Full article

► Show Figures

Figure 1

23 pages, 4718 KB

Open AccessArticle

Spatiotemporal Particle Swarm Optimization for Future Cost Allocation in Large-Scale Transportation Infrastructure Maintenance

by Pengcheng Zhang, Wen Yi, Yongze Song, Peng Wu, Albert P. C. Chan and Yali Gao

ISPRS Int. J. Geo-Inf. 2026, 15(2), 70; https://doi.org/10.3390/ijgi15020070 - 9 Feb 2026

Viewed by 403

Abstract

Transportation infrastructure is vital for sustaining communities and fostering economic development. Urbanization and climate change have led to the rapid deterioration of road transport systems, posing significant challenges for future sustainability. Current transportation infrastructure maintenance planning often prioritizes immediate needs and short-term deterioration [...] Read more.

Transportation infrastructure is vital for sustaining communities and fostering economic development. Urbanization and climate change have led to the rapid deterioration of road transport systems, posing significant challenges for future sustainability. Current transportation infrastructure maintenance planning often prioritizes immediate needs and short-term deterioration indicators, which can overlook long-term changes and future funding constraints. Long-term road maintenance planning is challenged by the large number of decision variables and the complex temporal and spatial dependencies that govern pavement deterioration. Most existing optimization models overlook spatial relationships among road segments, resulting in low computational efficiency, especially for large-scale networks. To address this gap, this study proposes a Spatiotemporal Particle Swarm Optimization for Cost Allocation (SPOCA) model that integrates spatial clustering and heuristic optimization for large-scale decision-making. An age-filtered spatial clustering process first groups roads with similar ages and proximity to preserve spatial structure and reduce problem dimensionality, while a spatial relationship term embedded in the optimization captures correlations among neighboring clusters to improve coordinated decision-making. A case study of Western Australia demonstrates that the SPOCA model reduces computational time by 38% compared with the non-spatial model, while maintaining comparable accuracy and significantly improving network-level pavement quality. The SPOCA model provides a scalable and practical tool to support policymakers in developing efficient and sustainable infrastructure maintenance strategies. Full article

(This article belongs to the Special Issue Spatial Information for Improved Living Spaces)

► Show Figures

Figure 1

24 pages, 6103 KB

Open AccessArticle

Enhancing Alarm Localization in Multi-Window Map Interfaces with Spatialized Auditory Cues: An Eye-Tracking Study

by Jing Zhang, Xiaoyu Zhu, Wenzhe Tang, Weijia Ge, Yong Zhang and Jing Li

ISPRS Int. J. Geo-Inf. 2026, 15(2), 69; https://doi.org/10.3390/ijgi15020069 - 6 Feb 2026

Viewed by 457

Abstract

Modern geo-information platforms commonly adopt multi-window map interfaces that integrate heterogeneous data, such as dynamic maps and live camera feeds. These interfaces impose high cognitive load and slow spatial event detection. Operators must rapidly locate the source of visual alarms, a task often [...] Read more.

Modern geo-information platforms commonly adopt multi-window map interfaces that integrate heterogeneous data, such as dynamic maps and live camera feeds. These interfaces impose high cognitive load and slow spatial event detection. Operators must rapidly locate the source of visual alarms, a task often leading to delays under high visual workload. To address this challenge, this study investigated whether spatialized auditory cues can improve alarm localization in such complex monitoring interfaces. A controlled experiment with 24 participants used a within-subjects design to test factors of auditory spatial cueing (none, binaural, monaural), display dynamics (dynamic, static), and interface complexity (4, 8, 12 panes). Behavioral and eye-tracking data measured detection accuracy, efficiency, and gaze patterns. Results showed that dynamic displays and high interface complexity impaired performance, indicating increased cognitive load. In contrast, monaural lateralized auditory alarms substantially improved detection efficiency and mitigated visual overload. Interaction analyses revealed that binaural cues reduced the performance costs of dynamic displays, whereas monaural cues compensated for high-density layouts. These findings demonstrate that spatialized auditory alarms effectively support spatiotemporal situational awareness and improve operator performance in high-load geo-surveillance systems. The study offers empirical and practical implications for designing cognitively ergonomic, multimodal interfaces that move beyond purely visual alarm designs. Full article

► Show Figures

Figure 1

22 pages, 1889 KB

Open AccessArticle

HD Maps for Autonomous Vehicles: Implications for Cartographic Theory and Practice

by Dariusz Gotlib, Georg Gartner and Krzysztof Miksa

ISPRS Int. J. Geo-Inf. 2026, 15(2), 68; https://doi.org/10.3390/ijgi15020068 - 4 Feb 2026

Viewed by 1290

Abstract

High-Definition (HD) Maps have become a cornerstone of autonomous vehicle (AV) technology, enabling precise localization, perception, and decision-making. Despite their increasing prominence in the automotive and geospatial industries, HD Maps remain underexplored in the field of cartography. There are many studies and publications [...] Read more.

High-Definition (HD) Maps have become a cornerstone of autonomous vehicle (AV) technology, enabling precise localization, perception, and decision-making. Despite their increasing prominence in the automotive and geospatial industries, HD Maps remain underexplored in the field of cartography. There are many studies and publications on HD Maps, but only a few of them directly address their links with cartography. Therefore, the research presented in this article focuses on this issue, filling an existing research gap. This paper examines the origins, technical characteristics, and conceptual frameworks of HD Maps, drawing on both the established literature and conceptual reflections. The results highlight that an extension of traditional cartographic definitions needs to be considered in order to encompass the concept of HD Maps as dynamic, machine-oriented infrastructures. By placing HD Maps as an important element in the development of cartography, the authors note both the prospect of a broader application of cartographic theory and the potential contribution of cartographers to the further development of HD Maps, as well as a potential paradigm shift toward the era of “maps for machines”. Full article

► Show Figures

Figure 1

30 pages, 7158 KB

Open AccessArticle

Extracting Duckweed/Algal Bloom-Type Black–Odorous Waters from Remote Sensing Images Based on SwinTf-Unet Model

by Jingtao Sun, Chenyang Li and Lijun Zhang

ISPRS Int. J. Geo-Inf. 2026, 15(2), 67; https://doi.org/10.3390/ijgi15020067 - 3 Feb 2026

Viewed by 529

Abstract

Duckweed/algal bloom-type black–odorous waters (DAWs) exhibit composite optical properties of vegetation and pollution, posing intractable remote sensing identification challenges in complex environments. Current methods suffer from three critical limitations: a misclassification rate exceeding 25% due to spectral confusion with artificial green covers, an [...] Read more.

Duckweed/algal bloom-type black–odorous waters (DAWs) exhibit composite optical properties of vegetation and pollution, posing intractable remote sensing identification challenges in complex environments. Current methods suffer from three critical limitations: a misclassification rate exceeding 25% due to spectral confusion with artificial green covers, an 18.7% false-negative rate for small patches (stemming from the imbalance between CNNs and Transformers), and insufficient feature dimensionality to characterize the dual properties of DAWs. To address these gaps, this study proposes a novel method that integrates the ASGICTVS feature set with a customized SwinTf-Unet model. The ASGICTVS feature set combines vegetation-sensitive metrics, optical water quality indicators, and visual features. The SwinTf-Unet model utilizes an optimized 4 × 4 window, an embedded feature fusion module, and an adaptive shifted window stride to balance global context capture and local detail reconstruction. Experiments on 21,104 GF-2 satellite samples demonstrate that the method achieves 87.50% precision, 88.41% recall, an 85.32% F1-score, and an 83.46% Intersection over Union (IoU), outperforming DeepLabV3+ by 14.56 percentage points in the IoU. With an inference time of 0.87 s per 512 × 512-pixel image and a stable performance across cross-regional datasets (IoU: 82.1–85.3%), it exhibits strong efficiency and generalization. This study resolves DAW spectral confusion, enables high-precision segmentation, and establishes a standardized feature threshold system, providing reliable technical support for large-scale automated DAW monitoring and regional water environment management. Full article

(This article belongs to the Topic Advances in Earth Observation Technologies to Support Water-Related Sustainable Development Goals (SDGs))

► Show Figures

Figure 1

25 pages, 15438 KB

Open AccessArticle

Day–Night All-Sky Scene Classification with an Attention-Enhanced EfficientNet

by Wuttichai Boonpook, Peerapong Torteeka, Kritanai Torsri, Daroonwan Kamthonkiat, Yumin Tan, Asamaporn Sitthi, Patcharin Kamsing, Chomchanok Arunplod, Utane Sawangwit, Thanachot Ngamcharoensuktavorn and Kijnaphat Suksod

ISPRS Int. J. Geo-Inf. 2026, 15(2), 66; https://doi.org/10.3390/ijgi15020066 - 3 Feb 2026

Viewed by 1187

Abstract

All-sky cameras provide continuous hemispherical observations essential for atmospheric monitoring and observatory operations; however, automated classification of sky conditions in tropical environments remains challenging due to strong illumination variability, atmospheric scattering, and overlapping thin-cloud structures. This study proposes EfficientNet-Attention-SPP Multi-scale Network (EASMNet), a [...] Read more.

All-sky cameras provide continuous hemispherical observations essential for atmospheric monitoring and observatory operations; however, automated classification of sky conditions in tropical environments remains challenging due to strong illumination variability, atmospheric scattering, and overlapping thin-cloud structures. This study proposes EfficientNet-Attention-SPP Multi-scale Network (EASMNet), a physics-aware deep learning framework for robust all-sky scene classification using hemispherical imagery acquired at the Thai National Observatory. The proposed architecture integrates Squeeze-and-Excitation (SE) blocks for radiometric channel stabilization, the Convolutional Block Attention Module (CBAM) for spatial–semantic refinement, and Spatial Pyramid Pooling (SPP) for hemispherical multi-scale context aggregation within a fully fine-tuned EfficientNetB7 backbone, forming a domain-aware atmospheric representation framework. A large-scale dataset comprising 122,660 RGB images across 13 day–night sky-scene categories was curated, capturing diverse tropical atmospheric conditions including humidity, haze, illumination transitions, and sensor noise. Extensive experimental evaluations demonstrate that the EASMNet achieves 93% overall accuracy, outperforming representative convolutional (VGG16, ResNet50, DenseNet121) and transformer-based architectures (Swin Transformer, Vision Transformer). Ablation analyses confirm the complementary contributions of hierarchical attention and multi-scale aggregation, while class-wise evaluation yields F1-scores exceeding 0.95 for visually distinctive categories such as Day Humid, Night Clear Sky, and Night Noise. Residual errors are primarily confined to physically transitional and low-contrast atmospheric regimes. These results validate the EASMNet as a reliable, interpretable, and computationally feasible framework for real-time observatory dome automation, astronomical scheduling, and continuous atmospheric monitoring, and provide a scalable foundation for autonomous sky-observation systems deployable across diverse climatic regions. Full article

(This article belongs to the Topic Advances in Sensor Data Fusion and AI for Environmental Monitoring)

► Show Figures

Figure 1

18 pages, 4409 KB

Open AccessArticle

CAE-RBNN: An Uncertainty-Aware Model of Island NDVI Prediction

by Zheng Xiang, Cunjin Xue, Ziyue Ma, Qingrui Liu and Zhi Li

ISPRS Int. J. Geo-Inf. 2026, 15(2), 65; https://doi.org/10.3390/ijgi15020065 - 3 Feb 2026

Viewed by 395

Abstract

The unique geographical isolation and climate sensitivity of island ecosystems make them valuable for ecological research. The Normalized Difference Vegetation Index (NDVI) is an important indicator when monitoring and evaluating these systems, and its prediction has become a key research focus. However, island [...] Read more.

The unique geographical isolation and climate sensitivity of island ecosystems make them valuable for ecological research. The Normalized Difference Vegetation Index (NDVI) is an important indicator when monitoring and evaluating these systems, and its prediction has become a key research focus. However, island NDVI prediction remains uncertain due to a limited understanding of vegetation growth and insufficient high-quality data. Deterministic models fail to capture or quantify such uncertainty, often leading to overfitting. To address this issue, this study proposes an uncertainty prediction model for the island NDVI within a coding–prediction–decoding framework, referred to as a Convolutional Autoencoder–Regularized Bayesian Neural Network (CAE-RBNN). The model integrates a convolutional autoencoder with feature regularization to extract latent NDVI features, aiming to reconcile spatial scale disparities with environmental data, while a Bayesian Neural Network (BNN) quantifies uncertainty arising from limited samples and an incomplete understanding of the process. Finally, Monte Carlo sampling and SHAP analysis evaluate model performance, quantify predictive uncertainty, and enhance interpretability. Experiments on six islands in the Xisha archipelago demonstrate that CAE-RBNN outperforms the Convolutional Neural Network–Recurrent Neural Network (CNN-RNN), the Convolutional Recurrent Neural Network (ConvRNN), Convolutional Long Short-Term Memory (ConvLSTM), and Random Forest (RF). Among them, CAE-RBNN reduces the MAE and MSE of the single-time-step prediction task by 8.40% and 10.69%, respectively, compared with the suboptimal model and decreases them by 16.31% and 22.57%, respectively, in the continuous prediction task. More importantly, it effectively quantifies the uncertainty of different driving forces, thereby improving the reliability of island NDVI predictions influenced by the environment. Full article

(This article belongs to the Topic Advances in Multi-Scale Geographic Environmental Monitoring: Ecosystem Differences and Multi-Scale Comparisons)

► Show Figures

Figure 1

18 pages, 8076 KB

Open AccessArticle

Relationships Between Spatial Metrics and Forest Landscape Beauty Across Viewing Distance Zones: Implications for Forest Management in Ino Town, Japan

by Xinrui Zheng and Norimasa Takayama

ISPRS Int. J. Geo-Inf. 2026, 15(2), 64; https://doi.org/10.3390/ijgi15020064 - 2 Feb 2026

Viewed by 806

Abstract

To develop targeted forest management strategies, management staff must understand the statistical relationships between forest aesthetic values and landscape metrics across specified distance ranges. However, as the existing studies based on distance-zone theory have failed to isolate the impacts of landscape features in [...] Read more.

To develop targeted forest management strategies, management staff must understand the statistical relationships between forest aesthetic values and landscape metrics across specified distance ranges. However, as the existing studies based on distance-zone theory have failed to isolate the impacts of landscape features in different zones, their practical applicability to forest management is limited. The present study aims to clarify the different effects of landscape elements on the modeling of forest scenic beauty. To this end, the relevant features are divided into near (0–400 m), middle (400 m–2.5 km), and far (2.5–5 km) zones. A regression analysis stratified by viewing zones confirmed the dominant role of the near zone and revealed different influences of individual landscape elements across the viewing zones. The landscape patterns identified through a cluster analysis, together with pattern-specific regression models, further clarified different explanatory powers of the landscape elements under different conditions, highlighting the elements that should be prioritized to enhance aesthetic value. These findings refine the existing theories and clarify how landscape elements influence aesthetic value across different viewing zones, highlighting the importance of distance-specific landscape element management. Full article

(This article belongs to the Special Issue Spatial Data Science and Knowledge Discovery)

► Show Figures

Figure 1

29 pages, 8564 KB

Open AccessArticle

Spatial Equity of Children’s Extracurricular Activity Facilities Under Government–Market Dual Provision Systems: Evidence from Tianjin

by Jiehui Geng, Peng Zeng, Jinxuan Li, Xiaotong Ren and Liangwa Cai

ISPRS Int. J. Geo-Inf. 2026, 15(2), 63; https://doi.org/10.3390/ijgi15020063 - 1 Feb 2026

Cited by 1 | Viewed by 720

Abstract

Ensuring equitable and inclusive access to children’s extracurricular activity facilities represents a profound manifestation of educational equity and is crucial for promoting children’s holistic development and societal sustainability. However, the underlying spatial mechanisms shaping their equity remain insufficiently explored. Using Tianjin’s central urban [...] Read more.

Ensuring equitable and inclusive access to children’s extracurricular activity facilities represents a profound manifestation of educational equity and is crucial for promoting children’s holistic development and societal sustainability. However, the underlying spatial mechanisms shaping their equity remain insufficiently explored. Using Tianjin’s central urban area as a case study, this study examines the spatial accessibility and equity of such facilities under dual government–market provision systems. The multi-mode Huff two-step floating catchment area model (MM-Huff-2SFCA) was employed to assess accessibility across walking, e-bike, public transport, and private car modes, integrating facility quality, household preference, and time-based distance decay. Equity was further evaluated using Lorenz curves and Gini coefficients across multiple spatial scales, while geographically weighted regression (GWR) identified spatial heterogeneity in factors such as child population density, transport infrastructure, household economic status, and basic education coverage. Results indicate that macro-level spatial balance masks substantial micro-scale inequities, particularly among transport-disadvantaged groups. Government and market systems exhibit contrasting spatial logics, forming a compensation–complementarity pattern across urban space. These findings underscore the need for refined and differentiated governance in extracurricular activity facilities planning, integrating spatial planning, transport accessibility, and social equity to advance child-friendly urban development and equitable public service provision. Full article

(This article belongs to the Special Issue Spatial Information for Improved Living Spaces)

► Show Figures

Figure 1

Journal Menu

Journal Browser

ISPRS Int. J. Geo-Inf., Volume 15, Issue 2 (February 2026) – 41 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI