Search Results (255)

The big data revolution transformed how we think of data analytics in many ways. Critical amongst them are the somewhat interconnected ideas of volunteered geographic information, crowdsourcing, and the big data property of variety. The robust literature concerning conceptual neighborhood graphs in two of these cases considers objects whose datatypes are held stable between the relations under consideration. This, however, is a limiting factor in these three application spaces due to the unknown form that data will take. This paper considers two avenues for the conceptual neighborhood graph to take as directions to address current complications facing reasoning tasks within a practically dirty world motivated by various sources of data: discretization conceptual neighborhood graphs (changing between corresponding vector and raster spaces) and cartographic generalization conceptual neighborhood graphs (changing the form of the objects in question). This paper provides insights as to what considerations should be considered when embarking upon this idea and demonstrates these concepts applied to prior conceptual neighborhood graphs. Full article

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. Full article

Waterfront brownfield urban public parks (WBUPPs) are complex regeneration projects that require comprehensive assessment of environmental remediation, climate resilience, urban connectivity, and social well-being. This study proposes a structured GIS-based spatial analysis protocol that operationalizes key attributes of brownfields, waterfronts, public parks, and sustainability, with the aim of examining how digital tools can support WBUPP planning processes. Using free and open source resources and datasets (QGIS and OpenStreetMap), the approach produces eight core thematic maps that spatially organize 39 of 50 criteria identified from the literature and classified under economic, environmental, and social sustainability dimensions. This mapping protocol streamlines navigation for planners through complex datasets and offers researchers a foundation for thematic spatial analyses aligned with these literature-based criteria. The protocol is illustrated with Brooklyn Bridge Park in New York City—an 85-acre waterfront redevelopment that demonstrates heritage conservation, ecological restoration, and financial viability. The results highlight identifiable spatial patterns such as dual zones (urban buffer and recreation), winding pathways, and clustered amenities. At the same time, the analysis underscores the importance of data validation, as inconsistencies in volunteered geographic information require cross-referencing with multiple sources and field verification. The analysis shows that WBUPPs require tailored approaches that integrate land–water mobility, heritage adaptation, nature-based solutions, and equitable service distribution. This criteria-driven protocol offers adaptable guidance for future waterfront brownfield regeneration, while emphasizing that digitalization enhances the process, but it cannot replace hybrid analytical methods that combine quantitative spatial analysis with qualitative evaluations. Full article

Urban mobility is a central challenge for sustainable and inclusive cities, as climate change, congestion, and spatial inequality increasingly reveal mobility patterns as expressions of deeper social and spatial structures. Inclusive urban mobility examines whether transport systems equitably support the everyday movements and accessibility needs of historically marginalized and underserved populations. The integration of artificial intelligence with geographic information science, combined with multimodal geospatial data fusion, provides powerful tools to diagnose and address these disparities by integrating heterogeneous data sources such as satellite imagery, GPS trajectories, transit records, volunteered geographic information, and social sensing data into scalable, high-resolution urban mobility analytics. This paper presents a systematic survey of recent GeoAI studies that fuse multiple geospatial data modalities for key urban mobility tasks, including accessibility mapping, demand forecasting, and origin–destination flow prediction, with particular emphasis on inclusive and equity-oriented applications. The review examines 18 multimodal GeoAI studies identified through a PRISMA-ScR screening process from 57 candidate publications between 2019 and 2025. The survey synthesizes methodological trends across data-, feature-, and decision-level fusion strategies, highlights the growing use of deep learning architectures, and examines emerging techniques such as knowledge graphs, federated learning, and explainable AI that support equity-relevant insights across diverse urban contexts. Building on this synthesis, the review identifies persistent gaps in population coverage, multimodal integration, equity optimization, explainability, validation, and governance, which currently constrain the inclusiveness and robustness of GeoAI applications in urban mobility research. To address these challenges, the paper proposes a structured research roadmap linking these gaps to concrete methodological and governance directions including equity-aware loss functions, adaptive multimodal fusion pipelines, participatory and human-in-the-loop workflows, and urban data trusts to better align multimodal GeoAI with the goals of inclusive, just, and sustainable urban mobility systems. Full article

Volunteered Geographic Information (VGI) is geographic data obtained from voluntary contributions of individual contributors on social media and non-social media platforms, where contributors exhibit diverse interests and behavior patterns. While studies have found that the COVID-19 pandemic has influenced VGI contributor behavior on social media platforms (Facebook, X, and Instagram, etc.), less is known about contribution behaviors on non-social media VGI platforms such as OpenStreetMap (OSM). This study investigates how individual OSM contributors’ data contribution behaviors changed after the COVID-19 outbreak, using New York City as a case study. Metrics quantifying temporal, spatial, thematic, participation, and social interaction aspects of contribution behavior were developed to characterize individual-level contribution behaviors in both the pre- and post-COVID periods (2016–2019 and 2020–2023, respectively). Contributors were clustered into three groups based on pre-COVID behavioral patterns (as reflected by the metrics) using the K-Means algorithm. The resulting model was then applied to identify changes in contributors’ cluster memberships in the post-COVID period. Results reveal differences in contribution behaviors between the two time periods. Compared to pre-COVID contributors, post-COVID contributors, on average, showed stronger contribution engagement, including longer lifespans, larger spatial extent of edits, higher contribution volumes, a greater emphasis on modification over creation, and stronger co-editing network interactions. Healthcare amenity-related edits remained a small fraction of total contributions across both periods and all clusters. Contributors participating in data contribution in both time periods generally increased data contribution engagement after the COVID outbreak, characterized by longer lifespans, broader spatial coverage, more balanced creation and modification, and stronger network centrality. These findings highlight changes in individual contribution behavior under COVID-19 and exhibits the value of examining VGI contribution at the individual level. Full article

Background/Objectives: The Democratic Republic of the Congo (DRC) has a history of low coverage (<50%) with all first-year-of-life vaccines for children aged 12–23 months, resulting in frequent outbreaks of vaccine-preventable diseases. In response, the DRC’s Expanded Program on Immunization (EPI) is applying innovations to improve vaccination coverage, including using geospatial data to inform vaccination planning (geo-referenced microplans). This report describes a proof of concept to geo-locate, by locality of residence, never-vaccinated children (NVC) or incompletely vaccinated children (IVC); use those data to prepare geo-referenced microplans for rounds of Periodic Intensification of Routine Immunization (PIRIs); and implement the PIRIs. Methods: In 2022, in Kindu and Kibombo Health Zones (HZs), Maniema Province, DRC, children aged 0–23 months were enumerated with inquiries about their vaccination status and reasons for non-vaccination by locality of residence. The enumeration was coupled with the collection of the localities’ geographic coordinates, facilitating the spatial illustration of estimated proportions of NVC by locality. Coordinates for HZ and health area (HA) landmarks and borders were also collected. We created maps that informed geo-referenced PIRI microplans, placing an emphasis on deploying vaccination teams to localities with high proportions of NVC, especially those in remote and riverine locations. To account for inclusion of children aged up to 59 months in the PIRIs, enumeration data were extrapolated to estimate the numbers of NVC and IVC in this wider age range. Volunteers mobilized communities for the PIRIs, HA staff vaccinated age-eligible children, and vaccination teams were geographically tracked. Results: In Kindu, 29,837 children aged 0–23 months were enumerated in 430 localities; among them, 38% were NVC and 6% IVC. In Kibombo, 9582 children aged 0–23 months were enumerated in 168 localities; among them, 50% were NVC and 16% IVC. In both HZs, reasons for never vaccination were primarily associated with knowledge- or belief-related factors, while reasons for incomplete vaccination were associated with access-related factors. Between HAs and localities, there was heterogeneity in the proportions of NVC and IVC and in the reasons for non-vaccination. The numbers of NVC and IVC aged 0–59 months were estimated at 28,220 and 4613 in Kindu and 12,038 and 3785 in Kibombo. Approximately 2000 health staff and community volunteers were engaged for implementation of each of the three PIRIs. The number of children vaccinated during the three PIRIs ranged from 15,500 to 26,500 and from 10,500 to 15,500 in Kindu and Kibombo, respectively. Data suggest that vaccinated children originated from >90% of localities identified during the cartography. Tracking data showed that vaccination teams visited localities with high proportions of NVC, including those that were remote and riverine. Conclusions: Geo-referenced microplanning with engagement of health staff and communities succeeded in vaccinating at least 40,000 children who were not routinely benefiting from health services in two HZs in the DRC; similar innovative strategies could be considered elsewhere. Applying new technologies to existing microplanning strategies can enhance their success. Full article

This paper publishes 735,000 historical passenger entries from the German North Sea port of Bremen, created between 1830 and 1939, and now structured, enriched, and processed into a research-ready database. It provides an overview of the original archival documents and their datafication, beginning with a historical account of why the passenger lists were created and which information they recorded. Building on extensive prior work—largely carried out by a team of volunteer transcribers with expertise in family history and genealogy—the lists were transcribed manually and first made available online in 2003. To enhance their analytical value, we computationally post-processed these data through (1) data cleaning, especially addressing spelling variants and transcription errors; (2) data normalisation, including conversion into standardised formats; and (3) data augmentation by adding identifiers, geographic information, and multiple classifications. Finally, we discuss limitations of the resulting dataset as well as its analytical potential. Full article

This study investigates flooding and erosion impacts and human responses in Aoraki Mount Cook and Westland Tai Poutini national parks in Aotearoa New Zealand. These fast-eroding landscapes provide important test cases and insights for considering the public access dimensions of climate change. Our objectives were to explore and characterise the often-overlooked role of public access as a ubiquitous concern for protected areas and other area-based conservation approaches that facilitate connections between people and nature alongside their protective functions. We employed a mixed-methods approach including volunteered geographic information (VGI) from a park user survey (n = 273) and detailed case studies of change on two iconic mountaineering routes based on geospatial analyses of digital elevation models spanning 1986–2022. VGI data identified 36 adversely affected locations while 21% of respondents also identified beneficial aspects of recent landscape changes. Geophysical changes could be perceived differently by different stakeholders, illustrating the potential for competing demands on management responses. Impacts of rainfall-triggered erosion events were explored in case studies of damaged access infrastructure (e.g., roads, tracks, bridges). Adaptive responses resulted from formal or informal (park user-led) actions including re-routing, rebuilding, or abandonment of pre-existing infrastructure. Three widely transferable dimensions of public access management are identified: providing access that supports the core functions of protected areas; evaluating the impacts of both physical changes and human responses to them; and managing tensions between stakeholder preferences. Improved attention to the role of access is essential for effective climate change adaptation in parks and reserves. Full article

This study introduces SquareSwish, a smooth, self-gated activation $f\left(x\right)=x\sigma {\left(x\right)}^2$, and benchmarks it against ten established activations (ReLU, LeakyReLU, ELU, SELU, GELU, Snake, LearnSnake, Swish, Mish, Hard-Swish) across six CNN architectures (EfficientNet-B1/B4, EfficientNet-V2-M/S, ResNet-50, and Xception) under a uniform transfer-learning protocol. Two geographically grounded datasets are used in this study. FuelRiskMap-TR comprises 7686 satellite images of urban fuel stations in Türkiye, which is semantically enriched with the OpenStreetMap context and YOLOv8-Small rooftop segmentation (mAP@0.50 = 0.724) to support AI-enabled, ICT-integrated risk screening. In a similar fashion, FuelRiskMap-UK is collected, comprising 2374 images. Risk scores are normalized and thresholded to form balanced High/Low-Risk labels for supervised training. Across identical training settings, SquareSwish achieves a top-1 validation accuracy of 0.909 on EfficientNet-B1 for FuelRiskMap-TR and reaches 0.920 when combined with SELU in a simple softmax-probability ensemble, outperforming the other activations under the same protocol. By squaring the sigmoid gate, SquareSwish more strongly attenuates mildly negative activations while preserving smooth, non-vanishing gradients, tightening decision boundaries in noisy, semantically enriched Earth-observation settings. Beyond classification, the resulting city-scale risk layers provide actionable geospatial outputs that can support inspection prioritization and integration with municipal GIS, offering a reproducible and low-cost safety-planning approach built on openly available imagery and volunteered geographic information. Full article

Urban revitalization processes are increasingly requiring inclusive and data-driven approaches that address spatial inequalities and support the achievement of the Sustainable Development Goals (SDGs). The article presents a methodology for utilizing social geoparticipation tools in the revitalization process of the Warsaw University of Technology campus. The study demonstrates how campus-scale geoparticipation can incorporate SDGs and spatial justice principles in micro-urban contexts, with a methodology that is transferable to city-scale projects and provides practical guidance for inclusive and sustainable urban governance. This enables the transformation of volunteered geographic information (VGI) data and spatial databases into practical spatial knowledge that supports sustainable urban development. Empirical analysis of 710 responses and nearly 1000 mapped locations revealed that 83% of respondents identified insufficient greenery as the primary spatial problem. At the same time, accessibility (β = 0.618) and green infrastructure quality (β = 0.553) were the strongest predictors of the need for change. The collected feedback from the academic community was processed using exploratory data analysis and spatial statistics into a spatial knowledge base. ESRI’s ArcGIS Experience Builder (Developer Edition version 1.16) was employed in the app’s development. A custom function was developed to meet the requirements of the geo-questionnaire fully. The application was ultimately deployed within the CENAGIS domain of the IT infrastructure at Warsaw University of Technology. Authors employed the structural equation modeling (SEM) method and provided statistical analysis of community expectations. The findings provide actionable evidence for urban planners, campus managers, and decision-makers seeking to implement data-driven, participatory revitalization strategies, demonstrating how social geoparticipation can directly inform sustainable design and policy-making at both campus and city levels. Full article

Urban models support sustainable, resilient, and equitable planning, but their validity hinges on underlying spatial data. This study examines the epistemological and technical consequences of relying on two dominant yet divergent platforms—OpenStreetMap (OSM) and Google Maps—for extracting proximity-based amenities within the 15-min city framework. Across four European contexts—Versilia, Gothenburg, Nice, and Vienna—we compare (i) data completeness and spatial coverage; (ii) semantic categories; and (iii) the effects of data heterogeneity on accessibility modelling. Findings show that OSM, while semantically consistent and openly accessible, systematically underrepresents peripheral amenities, introducing bias towards urban cores in accessibility metrics. Conversely, Google Maps provides broader coverage but is constrained by dependencies on extraction methods, opaque data structures, and ambiguous classification schemes, which hinder reproducibility, reduce interpretability, and limit its analytical robustness. These divergences yield distinct accessibility landscapes and competing readings of functionality and spatial equity. We argue that data source choice and protocol design are epistemological decisions and advocate transparent, hybrid strategies with cross-platform semantic harmonisation to strengthen robustness, equity, and policy relevance. Full article

Emergency medical services confront significant challenges in delivering timely patient assessments within geographically isolated or disaster-impacted regions. While drones (unmanned aircraft systems, UAS) show transformative potential in healthcare, standardized protocols for drone-assisted patient evaluations remain underdeveloped. This study introduces the ABCD-IN-BARS protocol, a 9-step telemedicine checklist integrating patient-assisted maneuvers and drone technology to systematize remote emergency assessments. A wait-list randomized controlled trial with 68 first-aid-trained volunteers evaluated the protocol’s feasibility. Participants underwent web-based modules and in-person simulations and were randomized into immediate training or waitlist control groups. The ABCD-IN-BARS protocol was developed via a content validity approach, incorporating expert-rated items from the telemedicine literature. Outcomes included time-to-assessment, provider confidence (Modified Cooper–Harper Scale), measured at baseline, post-training, and 3-month follow-up. Ethical approval and informed consent were obtained. Most of the participants can complete the assessment with a cue card within 4 min. A mixed-design repeated measures ANOVA assessed the effects of Time (baseline, post-test, 3-month follow-up within subject) on assessment durations. Assessment times improved significantly over three time points (p = 0.008), improving with standardized protocols, while patterns were similar across groups (p = 0.101), reflecting skill retention at 3 months and not affected by injury or not. Protocol adherence in simulated injury identification increased from 63.3% pre-training to 100% post-training. Provider confidence remained high (MCH scores: 2.4–2.7/10), and Technology Acceptance Model (TAM) ratings emphasized strong Perceived Usefulness (PU2: M = 4.48) despite moderate ease-of-use challenges (EU2: M = 4.03). Qualitative feedback highlighted workflow benefits but noted challenges in drone maneuvering. The ABCD-IN-BARS protocol effectively standardizes drone-assisted emergency assessments, demonstrating retained proficiency and high usability. While sensory limitations persist, its modular design and alignment with ABCDE principles offer a scalable solution for prehospital care in underserved regions. Further multicenter validation is needed to generalize findings. Full article

Geospatial Artificial Intelligence (GeoAI) offers a scalable solution for automating the generation and updating of volunteered geographic information (VGI) maps—addressing the limitations of manual contributions to crowd-source mapping platforms such as OpenStreetMap (OSM). This study evaluates the accuracy of GeoAI-generated buildings specifically, using two Generative Adversarial Network (GAN) models. These are OSM-GAN—trained on OSM vector data and Google Earth imagery—and OSi-GAN—trained on authoritative “ground truth” Ordnance Survey Ireland (OSi) vector data and aerial orthophotos. Altogether, we assess map feature completeness, shape accuracy, and positional accuracy and conduct qualitative visual evaluations using live OSM database features and OSi map data as a benchmark. The results show that OSi-GAN achieves higher completeness (88.2%), while OSM-GAN provides more consistent shape fidelity (mean HD: 3.29 m; σ = 2.46 m) and positional accuracy (mean centroid distance: 1.02 m) compared to both OSi-GAN and the current OSM map. The OSM dataset exhibits moderate average deviation (mean HD 5.33 m) but high variability, revealing inconsistencies in crowd-source mapping. These empirical results demonstrate the potential of GeoAI to augment manual VGI mapping workflows to support timely downstream applications in urban planning, disaster response, and many other location-based services (LBSs). The findings also emphasize the need for robust Quality Assurance (QA) frameworks to address “AI slop” and ensure the reliability and consistency of GeoAI-generated data. Full article

The Sustainable Development Goals (SDGs) have become the global framework for evaluating the effectiveness of humanitarian projects. Humanitarian mapping is considered a popular voluntary geographic information technique that provides data for disaster response. Although humanitarian mapping has contributed significantly to the SDGs, there is a lack of in-depth studies on the state of this relationship. This paper aims to assess the potential relationship between the SDGs and humanitarian mapping by (1) analyzing SDG indicators to determine their potential contribution to humanitarian mapping, and (2) identifying the actual contribution of humanitarian mapping projects to the SDGs. To achieve this, the study uses a structured methodology that combines SDG indicator analysis with project-level data filtering and text mining. Three major humanitarian mapping platforms—HOT-TM, MapSwipe, and Ushahidi—are examined in order to capture their potential and actual contributions to the SDG framework. Ultimately, the study highlights the strong alignment between humanitarian mapping activities and the need to monitor the SDGs, particularly in water, urban infrastructure, and land use, emphasizing the potential of volunteer-driven geospatial data to address critical data gaps. Full article

Turkey, a country with a unique blend of traditional and modern lifestyles, has made significant progress in promoting gender equality and is recognized as a pioneer in advancing women’s rights in the region. However, despite these advances, gender inequalities persist in various respects. This study aims to examine gender perception in a Turkish sample. Employing a cross-sectional and descriptive research design, the study was conducted with 1053 literate participants aged 18 and above who volunteered. Data were collected using a Demographic Information Form and the gender perception scale. The findings suggest that gender perception in Turkey is shifting toward a more egalitarian perspective, reflecting a departure from traditional norms. Several key factors were identified as contributors to this transformation, including education level, employment status, urbanization, socio-economic background, and geographical region of residence. These variables play a critical role in shaping gender perceptions and fostering societal change. By analyzing and contextualizing the results, this study offers valuable insights into the ongoing evolution of gender norms in Turkey. It underscores the importance of continued efforts to promote gender equality and serves as a foundation for future research on the sociocultural dynamics influencing gender perceptions. Full article