ISPRS International Journal of Geo-Information

25 pages, 8743 KB

Open AccessArticle

Irregular Area Cartograms for Local-Level Presentation of Selected SDGs Indicators Based on Earth Observation Data

by Anna Markowska and Dariusz Dukaczewski

ISPRS Int. J. Geo-Inf. 2025, 14(12), 500; https://doi.org/10.3390/ijgi14120500 - 18 Dec 2025

Viewed by 365

The objective of this study is to explore the applicability of irregular area cartograms for the visualization of sustainable development indicator components, utilizing earth observation (EO) data. The analysis focuses on selected Sustainable Development Goals (SDG 11 ‘Make cities and human settlements inclusive, [...] Read more.

The objective of this study is to explore the applicability of irregular area cartograms for the visualization of sustainable development indicator components, utilizing earth observation (EO) data. The analysis focuses on selected Sustainable Development Goals (SDG 11 ‘Make cities and human settlements inclusive, safe, resilient and sustainable’ and SDG 13 ‘Take urgent action to combat climate change and its impacts’) and specific targets and indicators related to green urban areas and air quality (targets: 13.2, 11.6, and 11.7; indicators: 11.6.2., 11.7.1., 13.2.2.). A comprehensive review of the relevant literature indicates that irregular area cartograms are employed only sporadically in the context of SDG monitoring, particularly at lower levels of territorial division (i.e., communes and counties). To address this gap, a series of thematic maps, including choropleth maps and irregular area cartograms, was developed. These visualizations are based on EO-derived datasets and supplemented with statistical information obtained from the Local Data Bank of the Statistics Poland. The analysis demonstrates that irregular area cartograms provide an effective means of visualizing spatial disparities in variables such as urban green space availability and air pollution at the commune and county levels. These visualizations enhance the interpretability of complex indicator structures and support more nuanced assessments of progress toward selected Sustainable Development Goals, especially in spatially detailed analytical frameworks. Preliminary usability testing among potential users revealed that irregular area cartograms are perceived as an interesting visualization technique that enhances data interpretation. Full article

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

► Show Figures

Figure 1

28 pages, 5922 KB

Open AccessArticle

Effects of a VR Mountaineering Education System on Learning, Motivation, and Cognitive Load in Compass and Map Skills

by Cheng-Pin Yu and Wernhuar Tarng

ISPRS Int. J. Geo-Inf. 2025, 14(12), 499; https://doi.org/10.3390/ijgi14120499 - 18 Dec 2025

Viewed by 331

Abstract

This study aimed to design a virtual reality (VR)–based mountaineering education system and examined its effects on junior high school students’ learning outcomes, motivation, and cognitive load in compass operation and map reading. The system integrated 3D terrain models and interactive mechanisms across [...] Read more.

This study aimed to design a virtual reality (VR)–based mountaineering education system and examined its effects on junior high school students’ learning outcomes, motivation, and cognitive load in compass operation and map reading. The system integrated 3D terrain models and interactive mechanisms across four instructional modules: Direction Recognition, Map Symbols, Magnetic Declination Adjustment, and Resection Positioning. By incorporating immersive 3D environments and hands-on virtual exercises, the system simulates authentic mountaineering scenarios, enabling students to develop essential field orientation and navigation skills. An experimental design was implemented, with participants assigned to either an experimental group learning with the VR system or a control group receiving slide-based instruction. Data were collected using pre-tests, post-tests, and questionnaires, and analyzed using SPSS for descriptive statistics, paired-sample t-tests, independent-sample t-tests, and one-way ANCOVA at a significance level of α = 0.05. The findings indicated that the experimental group achieved significantly higher post-test learning performance than the control group (F = 6.37, p = 0.014). Moreover, significant or highly significant improvements were observed across the four dimensions of learning motivation—attention, relevance, confidence, and satisfaction. The experimental group also exhibited a significantly lower extraneous cognitive load (p = 0.024). Therefore, the VR mountaineering education system provides an immersive, safe, and effective approach to teaching mountaineering and outdoor survival skills. Full article

► Show Figures

Figure 1

23 pages, 30210 KB

Open AccessArticle

Local Altimetric Correction of Global DEMs in Data-Scarce Floodplains: A Practical GNSS-Based Approach

by Jose Miguel Fragozo Arevalo, Jorge Escobar-Vargas and Jairo R. Escobar Villanueva

ISPRS Int. J. Geo-Inf. 2025, 14(12), 498; https://doi.org/10.3390/ijgi14120498 - 18 Dec 2025

Viewed by 453

Abstract

A reliable Digital Elevation Model (DEM) is a key input for land use planning and risk management, particularly in floodplains where low-resolution models often fail to represent subtle topographic variations. In many regions worldwide, high-precision elevation data are unavailable, necessitating the development of [...] Read more.

A reliable Digital Elevation Model (DEM) is a key input for land use planning and risk management, particularly in floodplains where low-resolution models often fail to represent subtle topographic variations. In many regions worldwide, high-precision elevation data are unavailable, necessitating the development of methods to enhance existing global digital elevation models (DEM). This study proposes a practical and replicable methodology to improve the vertical accuracy of global DEMs in flat terrains with limited data availability. The approach is based on correcting the altimetric differences between the DEM and GNSS-RTK-surveyed topographic points, incorporating land cover classification to refine adjustments. The methodology was tested in the Ranchería River delta in Riohacha, La Guajira, Colombia, using four global DEMs: FABDEM, SRTM, ASTER, and ALOS. Results showed a significant reduction in root mean square error (RMSE), with improvements of up to 76.691% for ASTER, 55.882% for FABDEM, 55.932% for SRTM, and 36.842% for ALOS. The proposed method requires minimal computational resources and no advanced programming. Due to minimal data requirements, it makes it a scalable and replicable solution for similar floodplain environments. These enhancements in local altimetric accuracy could help to improve the reliability of hydrodynamic modeling, with direct implications for flood risk management and decision-making in vulnerable flatland areas. Full article

► Show Figures

Graphical abstract

22 pages, 5552 KB

Open AccessArticle

MSA-UNet: Multiscale Feature Aggregation with Attentive Skip Connections for Precise Building Extraction

by Guobiao Yao, Yan Chen, Wenxiao Sun, Zeyu Zhang, Yifei Tang and Jingxue Bi

ISPRS Int. J. Geo-Inf. 2025, 14(12), 497; https://doi.org/10.3390/ijgi14120497 - 17 Dec 2025

Viewed by 313

Abstract

An accurate and reliable extraction of building structures from high-resolution (HR) remote sensing images is an important research topic in 3D cartography and smart city construction. However, despite the strong overall performance of recent deep learning models, limitations remain in handling significant variations [...] Read more.

An accurate and reliable extraction of building structures from high-resolution (HR) remote sensing images is an important research topic in 3D cartography and smart city construction. However, despite the strong overall performance of recent deep learning models, limitations remain in handling significant variations in building scales and complex architectural forms, which may lead to inaccurate boundaries or difficulties in extracting small or irregular structures. Therefore, the present study proposes MSA-UNet, a reliable semantic segmentation framework that leverages multiscale feature aggregation and attentive skip connections for an accurate extraction of building footprints. This framework is constructed based on the U-Net architecture, incorporating VGG16 as a replacement for the original encoder structure, which enhances its ability to capture low-discriminative features. To further improve the representation of image buildings with different scales and shapes, a serial coarse-to-fine feature aggregation mechanism was used. Additionally, a novel skip connection was built between the encoder and decoder layers to enable adaptive weights. Furthermore, a dual-attention mechanism, implemented through the convolutional block attention module, was integrated to enhance the focus of the network on building regions. Extensive experiments conducted on the WHU and Inria building datasets validated the effectiveness of MSA-UNet. On the WHU dataset, the model demonstrated a state-of-the-art performance with a mean Intersection over Union (mIoU) of 94.26%, accuracy of 98.32%, F1-score of 96.57%, and mean Pixel accuracy (mPA) of 96.85%, corresponding to gains of 1.41% in mIoU over the baseline U-Net. On the more challenging Inria dataset, MSA-UNet achieved an mIoU of 85.92%, indicating a consistent improvement of up to 1.9% over the baseline U-Net. These results confirmed that MSA-UNet markedly improved the accuracy and boundary integrity of building extraction from HR data, outperforming existing classic models in terms of segmentation quality and robustness. Full article

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

► Show Figures

Figure 1

26 pages, 1085 KB

Open AccessArticle

Can Urban Information Infrastructure Development Improve Resident Health? Evidence from China Health and Retirement Longitudinal Survey

by Huiling Zhao, Chenyang Yu and Zhanchuang Han

ISPRS Int. J. Geo-Inf. 2025, 14(12), 496; https://doi.org/10.3390/ijgi14120496 - 16 Dec 2025

Viewed by 482

Abstract

Taking the “Broadband China” policy (BCP) as a quasi-natural experiment, this paper utilizes nationwide tracking data from the China Health and Retirement Longitudinal Survey (CHARLS) for 2011, 2013, 2015, and 2018 and employs a Difference-in-Differences (DID) model to evaluate whether and how urban [...] Read more.

Taking the “Broadband China” policy (BCP) as a quasi-natural experiment, this paper utilizes nationwide tracking data from the China Health and Retirement Longitudinal Survey (CHARLS) for 2011, 2013, 2015, and 2018 and employs a Difference-in-Differences (DID) model to evaluate whether and how urban information infrastructure development affects resident health. We identify a clear and significant improvement in health outcomes attributable to BCP. After the implementation of BCP, physical health and mental health increase by 2.5% and 1.7%, respectively. Furthermore, mechanism analysis confirms that BCP enhances resident health primarily by improving information and communication technology (ICT) levels and by promoting local economic development. The positive health effect of BCP is more pronounced in regions with a better medical environment, suggesting the presence of complementary public-service capacity. At the individual level, heterogeneity tests reveal that BCP exerts a stronger positive influence on the physical health of male and rural respondents, while the benefits for older respondents are relatively smaller. At the city level, the health-promoting effect of BCP is stronger in economically less developed regions, and cities with higher administrative status exhibit more substantial health improvements. 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, 4317 KB

Open AccessArticle

A Semantic Collaborative Filtering-Based Recommendation System to Enhance Geospatial Data Discovery in Geoportals

by Amirhossein Vahdat, Thierry Badard and Jacynthe Pouliot

ISPRS Int. J. Geo-Inf. 2025, 14(12), 495; https://doi.org/10.3390/ijgi14120495 - 13 Dec 2025

Viewed by 754

Abstract

Traditional geoportals depend primarily on keyword-based search, which often fails to retrieve relevant datasets when metadata are heterogeneous, incomplete, or inconsistent with user terminology. This limitation reduces the efficiency of data discovery and selection, particularly in domains where metadata quality varies widely. This [...] Read more.

Traditional geoportals depend primarily on keyword-based search, which often fails to retrieve relevant datasets when metadata are heterogeneous, incomplete, or inconsistent with user terminology. This limitation reduces the efficiency of data discovery and selection, particularly in domains where metadata quality varies widely. This study aims to address this challenge by developing a semantic collaborative filtering recommendation system designed to enhance dataset discovery in geoportals through the analysis of implicit user interactions. The system captures users’ search queries, viewed datasets, downloads, and applied filters to infer feedback and organize it into a user–item matrix. Because interaction data are typically sparse, semantic user clustering is applied to mitigate this limitation by grouping users with semantically related interests through hierarchical relationships represented in the Simple Knowledge Organization System (SKOS). However, as users often need complementary datasets to complete specific tasks, association rule mining is employed to identify co-occurrence patterns in search histories and enhance task-related result diversity. The final recommendation scores are then computed by factorizing the user–item matrix with Alternating Least Squares (ALS), using cosine similarity on the latent user vectors to identify nearest neighbors, and applying a standard user-based neighborhood prediction model to rank unseen datasets. The system is implemented within an existing ontology-based geoportal as a standalone, configurable component, requiring only access to user interaction logs and dataset identifiers. Evaluation using precision, recall, and Precision@5 demonstrates that increasing user interactions improves recommendation performance by strengthening behavioral evidence used for ranking. The findings indicate that integrating semantic relationships and behavioral patterns can strengthen dataset discovery in geoportals and complement conventional metadata-based search mechanisms. Full article

(This article belongs to the Special Issue Intelligent Interoperability in the Geospatial Web)

► Show Figures

Figure 1

22 pages, 35558 KB

Open AccessArticle

Mapping Pastoral Mobility: A Geospatial Inventory of Temporary Dwellings Within the Southern Carpathians

by Emil Marinescu, Sidonia Marinescu and Liliana Popescu

ISPRS Int. J. Geo-Inf. 2025, 14(12), 494; https://doi.org/10.3390/ijgi14120494 - 11 Dec 2025

Viewed by 533

Abstract

Temporary pastoral settlements are a keystone of high-mountain ecologies, yet they are not included in any official datasets. Therefore, to fill this gap, this research aims to create the first systematic spatial inventory of high-altitude rural temporary dwellings (sheepfolds and shelters) and land [...] Read more.

Temporary pastoral settlements are a keystone of high-mountain ecologies, yet they are not included in any official datasets. Therefore, to fill this gap, this research aims to create the first systematic spatial inventory of high-altitude rural temporary dwellings (sheepfolds and shelters) and land use in the central part of the Southern Carpathians, one of the major traditional areas for sheep breeding in Romania. The data sources include 1:5000 orthophotos, 1:25,000-scale topographic maps, the Corine Land Cover model, field investigation campaigns, and forestry maps. Each one provided complementary information, which was integrated through cross-comparison and ground truth validation for settlement status and the consistent classification of land-use categories. The methodological steps followed are as follows: digitizing shelters, sheepfolds, and agricultural surfaces; overlaying elements of interest for the study; using Data Management, Spatial Analyst, Conversion Tools, and Field Calculation; and interpreting graphical and cartographical materials. Through overlay analysis, we examined how temporary settlements correlate with land-use categories; the ArcGIS Saptial Analyst tools enabled the identification of altitudinal patterns and spatial clusters. We identified 753 sheepfolds and 5411 shelters in this part of the Carpathians, situated at high altitudes, closely connected to the transhumance and pendulation phenomenon. The analysis of land use for the altitude-temporary settlements within the Parâng-Cindrel Mountains highlighted the fact that the traditional agriculture is still carried on by the locals, but biodiversity is at stake where fields are abandoned. Implications regarding the ecological and environmental impact of grazing in the area, conflict mitigation, and livestock protection as well as the cultural dimension are discussed. The study provides the first spatially explicit inventory of these shelters and sheepfolds, providing a cornerstone for interdisciplinary policy-making, conservation, and local development priorities. Full article

► Show Figures

Figure 1

29 pages, 10236 KB

Open AccessArticle

A Graph Data Model for CityGML Utility Network ADE: A Case Study on Water Utilities

by Ensiyeh Javaherian Pour, Behnam Atazadeh, Abbas Rajabifard, Soheil Sabri and David Norris

ISPRS Int. J. Geo-Inf. 2025, 14(12), 493; https://doi.org/10.3390/ijgi14120493 - 11 Dec 2025

Viewed by 571

Abstract

Modelling connectivity in utility networks is essential for operational management, maintenance planning, and resilience analysis. The CityGML Utility Network Application Domain Extension (UNADE) provides a detailed conceptual framework for representing utility networks; however, most existing implementations rely on relational databases, where connectivity must [...] Read more.

Modelling connectivity in utility networks is essential for operational management, maintenance planning, and resilience analysis. The CityGML Utility Network Application Domain Extension (UNADE) provides a detailed conceptual framework for representing utility networks; however, most existing implementations rely on relational databases, where connectivity must be reconstructed through joins rather than represented as explicit relationships. This creates challenges when managing densely connected network structures. This study introduces the UNADE–Labelled Property Graph (UNADE-LPG) model, a graph-based representation that maps the classes, relationships, and constraints defined in the UNADE Unified Modelling Language (UML) schema into nodes, edges, and properties. A conversion pipeline is developed to generate UNADE-LPG instances directly from CityGML UNADE datasets encoded in GML, enabling the population of graph databases while maintaining semantic alignment with the original schema. The approach is demonstrated through two case studies: a schematic network and a real-world water system from Frankston, Melbourne. Validation procedures, covering structural checks, topological continuity, classification behaviour, and descriptive graph statistics, confirm that the resulting graph preserves the semantic structure of the UNADE schema and accurately represents the physical connectivity of the network. An analytical path-finding query is also implemented to illustrate how the UNADE-LPG structure supports practical network-analysis tasks, such as identifying connected pipeline sequences. Overall, the findings show that the UNADE-LPG model provides a clear, standards-aligned, and operationally practical foundation for representing utility networks within graph environments, supporting future integration into digital-twin and network-analytics applications. Full article

► Show Figures

Figure 1

28 pages, 53273 KB

Open AccessArticle

Automatic Detection of Podotactile Pavements in Urban Environments Through a Deep Learning-Based Approach on MLS/HMLS Point Clouds

by Elisavet Tsiranidou, Daniele Treccani, Andrea Adami, Antonio Fernández and Lucía Díaz-Vilariño

ISPRS Int. J. Geo-Inf. 2025, 14(12), 492; https://doi.org/10.3390/ijgi14120492 - 11 Dec 2025

Viewed by 585

Abstract

Pedestrian accessibility is a critical dimension of sustainable and inclusive transportation systems, yet many cities lack reliable data on infrastructure features that support visually impaired users. Among these, podotactile paving plays a vital role in guiding movement and ensuring safety at intersections and [...] Read more.

Pedestrian accessibility is a critical dimension of sustainable and inclusive transportation systems, yet many cities lack reliable data on infrastructure features that support visually impaired users. Among these, podotactile paving plays a vital role in guiding movement and ensuring safety at intersections and transit nodes. However, tactile paving networks remain largely absent from digital transport inventories and automated mapping pipelines, limiting the ability of cities to systematically assess accessibility conditions. This paper presents a scalable approach for identifying and mapping podotactile areas from mobile and handheld laser scanning data, broadening the scope of data-driven urban modelling to include infrastructure elements critical for visually impaired pedestrians. The framework is evaluated across multiple sensing modalities and geographic contexts, demonstrating robust generalization to diverse transport environments. Across four dataset configurations from Madrid and Mantova, the proposed DeepLabV3+ model achieved podotactile F1-scores ranging from 0.83 to 0.91, with corresponding IoUs between 0.71 and 0.83. The combined Madrid–Mantova dataset reached an F1-score of 0.86 and an IoU of 0.75, highlighting strong cross-city generalization. By addressing a long-standing gap in transportation accessibility research, this study demonstrates that podotactile paving can be systematically extracted and integrated into transport datasets. The proposed approach supports scalable accessibility auditing, enhances digital transport models, and provides planners with actionable data to advance inclusive and equitable mobility. Full article

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

► Show Figures

Figure 1

15 pages, 741 KB

Open AccessArticle

Spatializing Trust: A GeoAI-Based Model for Mapping Digital Trust Ecosystems in Mediterranean Smart Regions

by Simona Epasto

ISPRS Int. J. Geo-Inf. 2025, 14(12), 491; https://doi.org/10.3390/ijgi14120491 - 10 Dec 2025

Viewed by 444

Abstract

As digital transformation intensifies, the governance of spatial data infrastructures is becoming increasingly dependent on the capacity to generate and sustain trust—technological, institutional and civic. This challenge is particularly acute in the Mediterranean region, where disparities in how geospatial data are produced, accessed, [...] Read more.

As digital transformation intensifies, the governance of spatial data infrastructures is becoming increasingly dependent on the capacity to generate and sustain trust—technological, institutional and civic. This challenge is particularly acute in the Mediterranean region, where disparities in how geospatial data are produced, accessed, and validated are created by uneven digital development and fragmented governance structures. In response to this, this paper introduces an integrated framework combining geospatial artificial intelligence (GeoAI) and blockchain technologies to support transparent, verifiable and spatially explicit models of digital trust. Based on case studies from the Horizon 2020 TRUST project, the framework defines trust through territorial indicators across three dimensions: digital infrastructure, institutional transparency, and civic engagement. The system uses interpretable AI models, such as Random Forests, K-means clustering and convolutional neural networks, to classify regions into trust typologies based on multi-source geospatial data. These outputs are then transformed into semantically structured spatial products and anchored to the Ethereum blockchain via smart contracts and decentralized storage (IPFS), thereby ensuring data integrity, auditability and version control. Experimental results from pilot regions in Italy, Greece, Spain and Israel demonstrate the effectiveness of the framework in detecting spatial patterns of trust and producing interoperable, reusable datasets. The findings highlight significant spatial asymmetries in digital trust across the Mediterranean region, suggesting that trust is a measurable territorial condition, not merely a normative ideal. By combining GeoAI with decentralized verification mechanisms, the proposed approach helps to develop accountable, explainable and inclusive spatial data infrastructures, which are essential for democratic digital governance in complex regional environments. Full article

► Show Figures

Figure 1

21 pages, 3290 KB

Open AccessArticle

Education Deserts and Local Outcomes: Spatial Dimensions of Educational Inequalities in Romania

by Angelo-Andi Petre, Liliana Dumitrache, Alina Mareci and Alexandra Cioclu

ISPRS Int. J. Geo-Inf. 2025, 14(12), 490; https://doi.org/10.3390/ijgi14120490 - 10 Dec 2025

Viewed by 609

Abstract

Spatial accessibility to education represents a key component of spatial justice, yet significant disparities persist between urban and rural areas in Romania. The present paper introduces the concept of education deserts as settlements where the population lacks proper access to education within a [...] Read more.

Spatial accessibility to education represents a key component of spatial justice, yet significant disparities persist between urban and rural areas in Romania. The present paper introduces the concept of education deserts as settlements where the population lacks proper access to education within a reasonable commuting distance and travel time, with a focus on high schools. Open-source demographic and institutional data and GIS-based spatial analysis were used in identifying education deserts across Romania. These were later evaluated based on a 20 min travel time or a 25 km distance threshold computed using OpenStreetMap API data. To assess the multidimensional nature of education deserts, a Composite Demand Index (CDI) and an Access Hardship Index (AHI) have been developed. Both were integrated into a final Education Desert Index (EDI) that captures unmet demand and spatial constraints. Results indicate that 34.3% of Romanian settlements (1092 LAU2s) and 15.2% of the high school-aged population reside in education deserts, found predominantly in the country’s North-East, South, and Centre regions. These areas coincide with rural, peripheral zones characterised by infrastructural deficits and low educational attainment. Findings reveal spatial inequities in upper secondary education provision between urban and rural communities. The present study offers a replicable methodological framework for evaluating educational accessibility and supports evidence-based policymaking aimed at reducing spatial disparities in education. Full article

► Show Figures

Figure 1

17 pages, 6761 KB

Open AccessArticle

Risk of Hypoxia in Short-Term Residents in Qinghai–Xizang Plateau Based on the Disaster System Theory Model

by Zemin Zhi, Qiang Zhou, Qiong Chen, Fenggui Liu, Yonggui Ma, Ziqian Zhang and Weidong Ma

ISPRS Int. J. Geo-Inf. 2025, 14(12), 489; https://doi.org/10.3390/ijgi14120489 - 10 Dec 2025

Viewed by 497

Abstract

Recognized as the world’s “Third Pole”, the Qinghai–Xizang Plateau poses significant challenges to human health due to its harsh environment. With improved transportation and a tourism boom industry bringing over 90 million low-altitude residents to the plateau annually, hypoxia has become a critical [...] Read more.

Recognized as the world’s “Third Pole”, the Qinghai–Xizang Plateau poses significant challenges to human health due to its harsh environment. With improved transportation and a tourism boom industry bringing over 90 million low-altitude residents to the plateau annually, hypoxia has become a critical concern. This study analyzes oxygen content data (2017–2022) together with environmental variables including elevation, temperature, precipitation, and vegetation cover, using the GeoDetector method to identify key drivers of near-surface oxygen distribution. Within the framework of disaster system theory, we evaluated the risk of hypoxia among short-term residents. Results show that the near-surface oxygen distribution across the plateau is primarily regulated by climatic and topographic factors. Interactions among environmental variables markedly enhance the explanatory power for spatial variation in oxygen content, with the coupled effects of humidity, atmospheric pressure, elevation, and temperature being especially pronounced. A high hypoxia hazard prevails across the plateau, particularly in the high-altitude western, northern, and central regions. The spatial distribution of hypoxia risk is strongly shaped by human activities, with high-risk zones clustering in densely populated towns, transportation corridors, and regions of intensive tourism. This results in a distinctive coexistence of “high hazard–low exposure” and “low hazard–high exposure” patterns. These findings provide scientific insights for tourism planning, health protection, and risk management in plateau regions. Full article

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

► Show Figures

Figure 1

32 pages, 39257 KB

Open AccessArticle

A Novel Region Similarity Measurement Method Based on Ring Vectors

by Zhi Cai, Hongyu Pan, Shuaibing Lu, Limin Guo and Xing Su

ISPRS Int. J. Geo-Inf. 2025, 14(12), 488; https://doi.org/10.3390/ijgi14120488 - 9 Dec 2025

Viewed by 350

Abstract

Spatial distribution similarity analysis has extensive application value in multiple domains including geographic information science, urban planning, and engineering site selection. However, traditional regional similarity analysis methods face three key challenges: high sensitivity to directional changes, limitations in feature interpretability, and insufficient adaptability [...] Read more.

Spatial distribution similarity analysis has extensive application value in multiple domains including geographic information science, urban planning, and engineering site selection. However, traditional regional similarity analysis methods face three key challenges: high sensitivity to directional changes, limitations in feature interpretability, and insufficient adaptability to multi-type data. Addressing these issues, this paper proposes a rotation-invariant spatial distribution similarity analysis method based on ring vectors. This method comprises three stages. First, the traversal starting point of the ring vector is dynamically selected based on the maximum value point of the regional feature matrix. Next, concentric ring features are extracted according to this starting point to achieve multi-scale characterization. Finally, the bidirectional weighted comprehensive distance of ring vectors between regions is calculated to measure the similarity between regions. Three experimental sets verified the method’s effectiveness in terrain matching, engineering site selection, and urban functional area identification. These results confirm its rotational invariance, feature interpretability, and adaptability to multi-type data. This research provides a new technical approach for spatial distribution similarity analysis, with significant theoretical and practical implications for geographic information science, urban planning, and engineering site selection. Full article

► Show Figures

Figure 1

27 pages, 8908 KB

Open AccessArticle

Reducing Extreme Commuting by Built Environmental Factors: Insights from Spatial Heterogeneity and Nonlinear Effect

by Fengxiao Li, Xiaobing Liu, Xuedong Yan, Zile Liu, Xuefei Zhao and Lu Ma

ISPRS Int. J. Geo-Inf. 2025, 14(12), 487; https://doi.org/10.3390/ijgi14120487 - 9 Dec 2025

Viewed by 494

Abstract

Nowadays, the number of people enduring extreme commuting is increasing, exacerbating traffic problems and harming individual well-being. To quantify the extreme commuting, we propose an extreme commuting severity (ECS) index that combines the number of extreme commuting trips with their specific distances, where [...] Read more.

Nowadays, the number of people enduring extreme commuting is increasing, exacerbating traffic problems and harming individual well-being. To quantify the extreme commuting, we propose an extreme commuting severity (ECS) index that combines the number of extreme commuting trips with their specific distances, where a one-way trip with a commuting distance of at least 25 km is regarded as an extreme commuting trip. In Beijing, the ECS index shows substantial spatial variability, with maximum values exceeding 30,000 for origins and 50,000 for destinations, underscoring the severe commuting burden in specific areas. By integrating the geographically weighted random forest (GWRF) with Shapley additive explanations (SHAP), we model both nonlinear effects and spatial heterogeneity in how the built environment shapes extreme commuting. Compared with benchmark models, the proposed GWRF model achieves the highest predictive performance, yielding the largest R² and the lowest absolute and relative indicators across both generation and attraction scenarios. Notably, the GWRF improves explanatory power over the global model by a substantial margin, highlighting the importance of incorporating spatial heterogeneity. SHAP-based global importance results show that residential density (17.58%) is the most influential factor for ECS, whereas in the attraction scenario, company density exhibits the strongest contribution (20.7%), reflecting the strong pull of major employment clusters. Local importance maps further reveal pronounced spatial differences in effect direction and magnitude. For instance, although housing prices have modest global importance, they display clear spatial heterogeneity: they exert the strongest influence on extreme commuting generation within the Fourth Ring Road and around the North Fifth Ring, whereas in the attraction scenario, their effects concentrate in the southern part of the core area. These findings provide new empirical insights into the mechanisms underlying extreme commuting and highlight the need for spatially differentiated planning strategies. Full article

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

► Show Figures

Figure 1

30 pages, 8433 KB

Open AccessArticle

Creating Choropleth Maps by Artificial Intelligence—Case Study on ChatGPT-4

by Parinda Pannoon and Rostislav Netek

ISPRS Int. J. Geo-Inf. 2025, 14(12), 486; https://doi.org/10.3390/ijgi14120486 - 9 Dec 2025

Viewed by 806

Abstract

This study explores the potential of ChatGPT-4, an AI-powered large language model, to generate thematic maps and compare its outputs to the traditional method in which maps are produced manually by humans using GIS software. Prompt engineering is a crucial methodology of large [...] Read more.

This study explores the potential of ChatGPT-4, an AI-powered large language model, to generate thematic maps and compare its outputs to the traditional method in which maps are produced manually by humans using GIS software. Prompt engineering is a crucial methodology of large language models that can enhance output quality. The main objective of this study is to assess the capability of AI-generated maps and to compare the quality with a traditional method. The study evaluates two prompt patterns: basic (zero-shot prompts) and advanced (Cognitive Verifier and Question Refinement). The performance of AI-generated maps is assessed based on attempts, errors, incorrect results, and map completeness. The final stage involved evaluating AI-generated maps against cartographic rules to assess their suitability. ChatGPT-4 performs well in generating suitable choropleth maps but faced challenges in understanding the prompts and potential errors in the generated code. Advanced prompts reduced errors and improved the quality of outputs, particularly for complex map elements. This paper enhances the understanding of AI’s role in cartography and further research in automated cartography. The study assesses cartographic aspects, offering insights into the strengths and limitations of AI in cartography, illustrating how large language models can process geospatial data and adhere to cartographic principles. The study also paves the way for future innovations in automated geovisualization. Full article

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

► Show Figures

Figure 1

18 pages, 398 KB

Open AccessArticle

Building Climate Solutions Through Trustful, Ethical, and Localized Co-Development

by Christy Caudill, Cheila Avalon-Cullen, Carol Archer, Rose-Anne Smith, Nathaniel K. Newlands, Anne-Teresa Birthwright, Peter L. Pulsifer and Markus Enenkel

ISPRS Int. J. Geo-Inf. 2025, 14(12), 485; https://doi.org/10.3390/ijgi14120485 - 8 Dec 2025

Viewed by 440

Abstract

The Small Island Developing States (SIDSs) in the Latin American and Caribbean region remain among the most vulnerable to climate change, as increasingly frequent and severe disasters threaten infrastructure, human life, and progress toward the Sustainable Development Goals. Addressing these risks requires urgent [...] Read more.

The Small Island Developing States (SIDSs) in the Latin American and Caribbean region remain among the most vulnerable to climate change, as increasingly frequent and severe disasters threaten infrastructure, human life, and progress toward the Sustainable Development Goals. Addressing these risks requires urgent regional and localized approaches grounded in coordinated climate risk assessment, anticipatory action, and Earth observation science-informed modeling with key support from a strong global community of practice. However, barriers remain to achieving local adaptation measures, including global action measures that conclude before local uptake of climate resilience practices are realized, reinforcing cycles of project impermanence. In this paper, we detail a Jamaica-focused case study that articulates such barriers impeding science and data-informed disaster risk reduction strategies, policies, and durable project implementation. The case study was a longitudinal co-development initiative led by a team of Jamaican and international interdisciplinary, cross-sector experts on climate-related disasters in SIDS. Using principles of co-design, discourse analysis, and systems thinking, the study underscores the need for a place-based framework that centers relevant sectors of society and often-marginalized voices as foundational to bottom-up climate resilience. The resulting Relationship and Place-Based Framework offers a model for localized climate science and technology development and ethical international collaboration for climate action that emphasizes local ownership and self-determination, as bottom-to-top feedback loops are key for managing multi-hazard dynamics and residual risks. Full article

► Show Figures

Figure 1

32 pages, 6985 KB

Open AccessArticle

Iterative Score Propagation Algorithm (ISPA): A GNN-Inspired Framework for Multi-Criteria Route Design with Engineering Applications

by Hüseyin Pehlivan

ISPRS Int. J. Geo-Inf. 2025, 14(12), 484; https://doi.org/10.3390/ijgi14120484 - 8 Dec 2025

Viewed by 368

Abstract

Traditional route optimization frameworks often suffer from “spatial blindness,” addressing the problem through abstract matrices devoid of geographical context. To address this fundamental methodological gap, this study proposes the Iterative Score Propagation Algorithm (ISPA), a transparent, GNN-inspired framework that reframes optimization as a [...] Read more.

Traditional route optimization frameworks often suffer from “spatial blindness,” addressing the problem through abstract matrices devoid of geographical context. To address this fundamental methodological gap, this study proposes the Iterative Score Propagation Algorithm (ISPA), a transparent, GNN-inspired framework that reframes optimization as a holistic corridor problem. ISPA’s robustness and superiority were tested against established Multi-Criteria Decision-Making (MCDM) methods (WLC, TOPSIS, VIKOR) across three diverse engineering scenarios (Rural Highway, Pipeline, Trekking Trail) and two distinct weighting philosophies (Entropy and AHP). The holistic analysis reveals that ISPA achieves the highest final score (0.815) across all six test conditions, demonstrating both the highest overall mean performance (0.629) and the greatest stability (1.000). Furthermore, its flexible cost function successfully modeled unconventional objectives, such as a “climbing reward,” enabling a paradigm shift from cost minimization to experience maximization. ISPA’s superior performance stems from its structural advantage in contextualizing spatial data. This work introduces a new, spatially-aware approach that transforms route planning from a static calculation into a dynamic design and scenario analysis tool for planners and engineers. Full article

► Show Figures

Figure 1

29 pages, 12133 KB

Open AccessArticle

GIS-Based Analysis of Retail Spatial Distribution and Driving Mechanisms in a Resource-Based Transition City: Evidence from POI Data in Taiyuan, China

by Xinrui Luo, Rosniza Aznie Che Rose and Azahan Awang

ISPRS Int. J. Geo-Inf. 2025, 14(12), 483; https://doi.org/10.3390/ijgi14120483 - 7 Dec 2025

Cited by 1 | Viewed by 692

Abstract

Rapid urbanization in China has reshaped retail spatial structures, creating challenges of accessibility and service equity. This study employs a Geographic Information Systems (GIS)-based analytical framework to examine the spatial distribution and driving mechanisms of retail outlets in Taiyuan, a resource-based transition city [...] Read more.

Rapid urbanization in China has reshaped retail spatial structures, creating challenges of accessibility and service equity. This study employs a Geographic Information Systems (GIS)-based analytical framework to examine the spatial distribution and driving mechanisms of retail outlets in Taiyuan, a resource-based transition city in central China. Using 2023 Point of Interest (POI) data and a 2 km × 2 km grid system, kernel density estimation (KDE), Average Nearest Neighbor (ANN) Analysis, Location Quotient (LQ), and spatial autocorrelation were applied to identify clustering patterns and functional specialization. The GeoDetector (Word version, downloaded 2025) model further quantified the explanatory power of twelve natural, social, economic, and transportation variables. Results reveal a polycentric retail structure, with high-density clusters in Yingze and Xiaodian districts and under-supply in Jiancaoping and Jinyuan. Population density, nighttime light (NTL) intensity, and school distribution emerged as the strongest drivers, while topography constrained expansion. By integrating GIS-based spatial statistics with GeoDetector, the study demonstrates a transferable framework for analyzing urban retail spatial patterns. The findings extend retail geography to transition cities and provide practical guidance for optimizing retail allocation, enhancing service equity, and supporting spatial decision-making for sustainable urban development. Full article

(This article belongs to the Topic Spatial Decision Support Systems for Urban Sustainability)

► Show Figures

Figure 1

17 pages, 14035 KB

Open AccessArticle

Quantifying Percent Traffic Congestion (pTC) and Mobility Bottleneck Dynamics at Atlanta’s Spaghetti Junction

by Jeong Chang Seong, Jiwon Yang, Jina Jang, Seung Hee Choi, Brian Vann and Chul Sue Hwang

ISPRS Int. J. Geo-Inf. 2025, 14(12), 482; https://doi.org/10.3390/ijgi14120482 - 6 Dec 2025

Viewed by 639

Abstract

Highway interchanges are vulnerable components of transport networks, often prone to congestion and crashes. Traditional monitoring methods like loop detectors or travel time queries often fail to capture the granular spatiotemporal distribution of bottlenecks in detail. To address this gap, this study introduces [...] Read more.

Highway interchanges are vulnerable components of transport networks, often prone to congestion and crashes. Traditional monitoring methods like loop detectors or travel time queries often fail to capture the granular spatiotemporal distribution of bottlenecks in detail. To address this gap, this study introduces a new approach to quantify congestion and analyze bottleneck dynamics at Atlanta’s Tom Moreland Interchange, one of the nation’s most congested sites. A percent Traffic Congestion (pTC) metric was developed from the Google Maps Traffic Layer for twelve directional routes and validated against observed travel times obtained independently through the Google Maps Routes API. Traffic imagery collected every ten minutes for four months and 746 crash records were analyzed. Findings reveal distinct spatial patterns and temporal dynamics of congestion, with northbound I-85 and eastbound I-285 most affected during afternoon peaks. A quadratic model provided the best fit between pTC and travel times (R² = 0.85), confirming pTC as a reliable congestion indicator. An LSTM model using pTC time series also accurately predicted mobility trends at the I-285 west to I-85 north bottleneck. Additionally, Seasonal-Trend decomposition using LOESS (STL) identified congestion anomalies, and their association was analyzed with crashes. The proposed methodology offers transportation agencies a cost-effective framework for monitoring, measuring, and understanding congestion in complex interchanges. Full article

► Show Figures

Figure 1

19 pages, 8434 KB

Open AccessArticle

Predicting Persistent Forest Fire Refugia Using Machine Learning Models with Topographic, Microclimate, and Surface Wind Variables

by Sven Christ, Tineke Kraaij, Coert J. Geldenhuys and Helen M. de Klerk

ISPRS Int. J. Geo-Inf. 2025, 14(12), 480; https://doi.org/10.3390/ijgi14120480 - 5 Dec 2025

Viewed by 537

Abstract

Persistent forest fire refugia are areas within fire-prone landscapes that remain fire-free over long periods of time and are crucial for ecosystem resilience. Modelling to develop maps of these refugia is key to informing fire and land use management. We predict persistent forest [...] Read more.

Persistent forest fire refugia are areas within fire-prone landscapes that remain fire-free over long periods of time and are crucial for ecosystem resilience. Modelling to develop maps of these refugia is key to informing fire and land use management. We predict persistent forest fire refugia using variables linked to the fire triangle (aspect, slope, elevation, topographic wetness, convergence and roughness, solar irradiation, temperature, surface wind direction, and speed) in machine learning algorithms (Random Forest, XGBoost; two ensemble models) and K-Nearest Neighbour. All models were run with and without ADASYN over-sampling and grid search hyperparameterisation. Six iterations were run per algorithm to assess the impact of omitting variables. Aspect is twice as influential as any other variable across all models. Solar radiation and surface wind direction are also highlighted, although the order of importance differs between algorithms. The predominant importance of aspect relates to solar radiation received by sun-facing slopes and resultant heat and moisture balances and, in this study area, the predominant fire wind direction. Ensemble models consistently produced the most accurate results. The findings highlight the importance of topographic and microclimatic variables in persistent forest fire refugia prediction, with ensemble machine learning providing reliable forecasting frameworks. Full article

► Show Figures

Figure 1

26 pages, 6470 KB

Open AccessArticle

Impact of Synthetic Data on Deep Learning Models for Earth Observation: Photovoltaic Panel Detection Case Study

by Enes Hisam, Jesus Gimeno, David Miraut, Manolo Pérez-Aixendri, Marcos Fernández, Rossana Gini, Raúl Rodríguez, Gabriele Meoni and Dursun Zafer Seker

ISPRS Int. J. Geo-Inf. 2025, 14(12), 481; https://doi.org/10.3390/ijgi14120481 - 4 Dec 2025

Viewed by 922

Abstract

This study explores the impact of synthetic data, both physically based and generatively created, on deep learning analytics for earth observation (EO), focusing on the detection of photovoltaic panels. A YOLOv8 object detection model was trained using a publicly available, multi-resolution very high [...] Read more.

This study explores the impact of synthetic data, both physically based and generatively created, on deep learning analytics for earth observation (EO), focusing on the detection of photovoltaic panels. A YOLOv8 object detection model was trained using a publicly available, multi-resolution very high resolution (VHR) EO dataset (0.8 m, 0.3 m, and 0.1 m), comprising 3716 images from various locations in Jiangsu Province, China. Three benchmarks were established using only real EO data. Subsequent experiments evaluated how the inclusion of synthetic data, in varying types and quantities, influenced the model’s ability to detect photovoltaic panels in VHR imagery. Physically based synthetic images were generated using the Unity engine, which allowed the generation of a wide range of realistic scenes by varying scene parameters automatically. This approach produced not only realistic RGB images but also semantic segmentation maps and pixel-accurate masks identifying photovoltaic panel locations. Generative synthetic data were created using diffusion-based models (DALL·E 3 and Stable Diffusion XL), guided by prompts to simulate satellite-like imagery containing solar panels. All synthetic images were manually reviewed, and corresponding annotations were ensured to be consistent with the real dataset. Integrating synthetic with real data generally improved model performance, with the best results achieved when both data types were combined. Performance gains were dependent on data distribution and volume, with the most significant improvements observed when synthetic data were used to meet the YOLOv8-recommended minimum of 1500 images per class. In this setting, combining real data with both physically based and generative synthetic data yielded improvements of 1.7% in precision, 3.9% in recall, 2.3% in mAP@50, and 3.3% in mAP@95 compared to training with real data alone. The study also emphasizes the importance of carefully managing the inclusion of synthetic data in training and validation phases to avoid overfitting to synthetic features, with the goal of enhancing generalization to real-world data. Additionally, a pre-training experiment using only synthetic data, followed by fine-tuning with real images, demonstrated improved early-stage training performance, particularly during the first five epochs, highlighting potential benefits in computationally constrained environments. Full article

(This article belongs to the Topic Artificial Intelligence Models, Tools and Applications)

► Show Figures

Figure 1

34 pages, 6591 KB

Open AccessArticle

Comparative Framework for Multi-Modal Accessibility Assessment Within the 15-Minute City Concept: Application to Parks and Playgrounds in an Indian Urban Neighborhood

by Swati Bahale, Amarpreet Singh Arora and Thorsten Schuetze

ISPRS Int. J. Geo-Inf. 2025, 14(12), 479; https://doi.org/10.3390/ijgi14120479 - 2 Dec 2025

Viewed by 538

Abstract

Urban neighborhoods in India face an uneven distribution and limited accessibility to parks and playgrounds, particularly in dense mixed-use areas where rapid urbanization constrains green infrastructure planning. To address these challenges, the Sustainable Transportation Assessment Index (SusTAIN) framework was developed to evaluate sustainable [...] Read more.

Urban neighborhoods in India face an uneven distribution and limited accessibility to parks and playgrounds, particularly in dense mixed-use areas where rapid urbanization constrains green infrastructure planning. To address these challenges, the Sustainable Transportation Assessment Index (SusTAIN) framework was developed to evaluate sustainable transportation in Indian urban neighborhoods, with ‘Accessibility’ identified as a crucial subtheme. Recent advancements in Geographic Information Systems (GISs) and urban data analysis tools have enabled accessibility assessments of parks and playgrounds at a neighborhood scale, yet the OSMnx approach has been only marginally explored and compared in the literature. This study addresses this gap by comparing three tools—the Quantum Geographic Information System (QGIS), OSMnx, and Space Syntax—for accessibility assessments of parks and playgrounds in Ward 60 of Kalyan Dombivli city, based on the 15-Minute City concept. Accessibility was evaluated using 25 m and 100 m grid resolutions under peak and non-peak conditions across public and private transportation modes. The findings show that QGIS offers highly consistent results at micro-scale (25 m), while OSMnx provides better accuracy at coarser scales (100 m+). The results were validated with space syntax through integration and choice values. The comparison highlights spatial disparities in accessibility across different tools and transportation modes, including Intermediate Public Transport (IPT), which remains underexplored despite its crucial role in last-mile connectivity. The presented approach can support municipal authorities in optimizing neighborhood mobility and is transferable for applying the SusTAIN framework in other urban contexts. Full article

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

► Show Figures

Figure 1

26 pages, 4176 KB

Open AccessFeature PaperArticle

An Effective Approach to Geometric and Semantic BIM/GIS Data Integration for Urban Digital Twin

by Peyman Azari, Songnian Li and Ahmed Shaker

ISPRS Int. J. Geo-Inf. 2025, 14(12), 478; https://doi.org/10.3390/ijgi14120478 - 2 Dec 2025

Viewed by 1000

Abstract

Urban Digital Twins (UDTs) demand both simplified geometry and rich semantic information from Building Information Models (BIM) to be effectively integrated into Geospatial Information Systems (GIS). However, current BIM-to-GIS conversion methods struggle with geometric complexity and semantic loss, particularly at scale. This paper [...] Read more.

Urban Digital Twins (UDTs) demand both simplified geometry and rich semantic information from Building Information Models (BIM) to be effectively integrated into Geospatial Information Systems (GIS). However, current BIM-to-GIS conversion methods struggle with geometric complexity and semantic loss, particularly at scale. This paper proposes a novel, scalable methodology for comprehensive BIM/GIS integration, addressing both geometric and semantic challenges. The approach introduces a geometry conversion workflow that transforms solid BIMs into valid, simplified CityGML representations through a level-by-level detection of building elements and outer surface extraction. To preserve semantic richness, all entities, attributes, and relationships—including implicit connections—are automatically extracted and stored in a Labeled Property Graph (LPG) database. The method is further extended with a new CityGML Application Domain Extension (ADE) that supports Multi-LoD4 representations, enabling selective interior visualization and efficient rendering. A web-based urban digital twin platform demonstrates the integration, allowing dynamic semantic querying and scalable 3D visualization. Results show a significant reduction in geometric complexity, full semantic retention, and robust performance in visualization and querying, offering a practical pathway for advanced UDT development. Full article

(This article belongs to the Topic The Geography of Digital Twin: Concepts, Architectures, Modeling, AI and Applications)

► Show Figures

Graphical abstract

20 pages, 5765 KB

Open AccessArticle

Infrared–Visible Fusion via Cross-Modality Attention and Small-Object Enhancement for Pedestrian Detection

by Jie Yang, Yanxuan Jiang, Dengyin Jiang and Zhichao Chen

ISPRS Int. J. Geo-Inf. 2025, 14(12), 477; https://doi.org/10.3390/ijgi14120477 - 2 Dec 2025

Cited by 1 | Viewed by 721

Abstract

Pedestrian detection under low illumination and complex environments remains a significant challenge for vision-based systems, particularly in safety-critical applications such as urban rail transit. To address the limitations of single-modality detection in adverse conditions, this paper proposes IVIFusion, a lightweight yet robust pedestrian [...] Read more.

Pedestrian detection under low illumination and complex environments remains a significant challenge for vision-based systems, particularly in safety-critical applications such as urban rail transit. To address the limitations of single-modality detection in adverse conditions, this paper proposes IVIFusion, a lightweight yet robust pedestrian detection framework that fuses infrared and visible images at the feature level. The method integrates a dual-branch Transformer-based backbone for modality-specific feature extraction and introduces a Cross-Modality Attention Fusion Module (CMAFM) to adaptively enhance cross-modal representations while suppressing noise. Furthermore, a dedicated small-object detection layer is incorporated to improve the recall of distant and occluded pedestrians. Extensive experiments conducted on the public LLVIP dataset and the custom HGPD dataset demonstrate the superior performance of IVIFusion, achieving mAP_0.5 scores of 98.6% and 97.2%, respectively. The results validate the effectiveness of the proposed architecture in handling challenging lighting conditions while maintaining real-time efficiency and low computational cost. Full article

(This article belongs to the Topic State-of-the-Art Object Detection, Tracking, and Recognition Techniques)

► Show Figures

Figure 1

17 pages, 5641 KB

Open AccessArticle

A Novel Smartphone PDR Framework Based on Map-Aided Adaptive Particle Filter with a Reduced State Space

by Mengchi Ai, Ilyar Asl Sabbaghian Hokmabadi and Xuan Zhao

ISPRS Int. J. Geo-Inf. 2025, 14(12), 476; https://doi.org/10.3390/ijgi14120476 - 2 Dec 2025

Viewed by 1583

Abstract

Accurate, reliable and infrastructure-free indoor positioning using a smartphone is considered an essential topic for applications such as indoor emergency response and indoor path planning. While the inertial measurement units (IMU) offer continuous and high-frequency motion data, pedestrian dead reckoning (PDR) based on [...] Read more.

Accurate, reliable and infrastructure-free indoor positioning using a smartphone is considered an essential topic for applications such as indoor emergency response and indoor path planning. While the inertial measurement units (IMU) offer continuous and high-frequency motion data, pedestrian dead reckoning (PDR) based on IMU data suffers from significant and accumulative errors. Map-aided particle filters (PFs) are important pose estimation frameworks that have exhibited capabilities to eliminate drifts by incorporating additional constraints from a pre-built floor map, without relying on other wireless or perception-based infrastructures. However, despite the recent approaches, a key challenging issue remains: existing map-aided PF-PDR solutions are computationally demanding, as they typically rely on a large number of particles and require map boundaries to eliminate non-matching particles. This process introduces substantial computational overhead, limiting efficiency and real-time performance on resource-constrained platforms such as smartphones. To address this key issue, this work proposes a novel map-aided PF-PDR framework that leverages a smartphone’s IMU data and a pre-built vectorized floor plan map. The proposed method introduces an adaptive PF-PDR solution that detects particle convergence using a cross-entropy distance of the particles and a Gaussian distribution. The number of particles is reduced significantly after a convergence is detected. Further, in order to reduce the computational cost, only the heading is included in particle attitude sampling. The heading is estimated accurately by levelling gyroscope measurements to a virtual plane, parallel to the ground. Experiments are performed using a dataset collected on a smartphone and the results demonstrate improved performance, especially in drift reduction, achieving an mean position error of 0.9 m and a processing rate of 37.0 Hz. Full article

(This article belongs to the Special Issue Indoor Mobile Mapping and Location-Based Knowledge Services)

► Show Figures

Figure 1

18 pages, 30685 KB

Open AccessArticle

Leveraging Explainable Artificial Intelligence for Place-Based and Quantitative Strategies in Urban Pluvial Flooding Management

by Chaorui Tan, Entong Ke and Haochen Shi

ISPRS Int. J. Geo-Inf. 2025, 14(12), 475; https://doi.org/10.3390/ijgi14120475 - 1 Dec 2025

Viewed by 415

Abstract

Reducing urban pluvial flooding susceptibility requires identifying dominant variables in different regions and offering quantitative management strategies, which remains a challenge for existing methodologies. To address this, this study delves into the characteristics of SHAP’s (Shapley Additive exPlanations) local interpretability and proposes a [...] Read more.

Reducing urban pluvial flooding susceptibility requires identifying dominant variables in different regions and offering quantitative management strategies, which remains a challenge for existing methodologies. To address this, this study delves into the characteristics of SHAP’s (Shapley Additive exPlanations) local interpretability and proposes a novel and concise framework based on explainable artificial intelligence (ensemble learning-SHAP) and applies it to the central urban area of Guangzhou as a case study. The research findings are as follows: (1) This framework captures the nonlinear and threshold effects of flood drivers, identifying specific inflection points where landscape features shift from mitigating to exacerbating flooding. (2) Anthropogenic variables, specifically impervious surface density (ISD) and vegetation (kNDVI), are identified as the dominant variables driving susceptibility in urban hotspots at the grid scale. (3) The interpretability results demonstrate high stability across model iterations. Finally, based on these findings, this study provides place-based and quantitative pluvial flooding management recommendations: for areas dominated by impervious surfaces and vegetation, maintaining the impervious surface density below 0.8 and the kNDVI above 0.25 can effectively reduce the susceptibility to urban flooding. This study provides a framework for achieving place-based and quantitative flooding management and offers valuable scientific insights for flooding management, urban planning, and sustainable urban development in the central district of Guangzhou, as well as in broader developing regions. Full article

(This article belongs to the Topic Natural Hazards Monitoring, Risk Assessment, Modelling and Management in the Artificial Intelligence Era)

► Show Figures

Figure 1

30 pages, 1800 KB

Open AccessArticle

A GIS-Native Framework for Qualitative Place Models: Implementation and Evaluation

by Abdurauf Satoti and Alia I. Abdelmoty

ISPRS Int. J. Geo-Inf. 2025, 14(12), 474; https://doi.org/10.3390/ijgi14120474 - 1 Dec 2025

Viewed by 397

Abstract

Humans typically describe spatial location using names, hierarchies, and relative positions (e.g., east of, inside), yet mainstream GIS represents places primarily through geometric coordinates, rendering qualitative spatial queries computationally challenging. We introduce the Qualitative Place Model (QPM), a GIS-native framework that transforms standard [...] Read more.

Humans typically describe spatial location using names, hierarchies, and relative positions (e.g., east of, inside), yet mainstream GIS represents places primarily through geometric coordinates, rendering qualitative spatial queries computationally challenging. We introduce the Qualitative Place Model (QPM), a GIS-native framework that transforms standard boundary datasets and place layers into structured knowledge bases of Qualitative Place Description (QPD). QPM provides a homogeneous representation whereby administrative units and physical places are treated uniformly as Place entities. The model materializes a compact set of local relations, hierarchical containment, directional neighbourhood, and optional proximity, that support rich inferences through sound logical operations (inverse relationships and per-predicate transitive closure). We implement QPM as an ArcGIS Pro toolbox that computes and persists QPDs within a geodatabase, with optional RDF export for SPARQL querying. This implementation enables natural-language-style spatial queries such as “Where is x?” or “Which places are north of x?” within standard GIS workflows. Evaluation on Wales (UK) administrative, postal, and electoral hierarchies plus a comprehensive place layer demonstrates robust performance: QPM generated 95.8% of expected basic-place statements (52,821 places) and achieved 89.7–96.5% coverage across administrative hierarchies. All QPDs proved unique under our deterministic signature. Despite compact storage requirements, directional relations expand by more than an order of magnitude (10.6× overall expansion) under logical closure, demonstrating substantial inferential power from a minimal stored representation. QPM complements geometric GIS with an explainable qualitative layer that aligns with human spatial cognition while remaining fully operational within standard GIS environments. Full article

► Show Figures

Figure 1

15 pages, 12075 KB

Open AccessArticle

Impact of Scanning Quality on Deep Learning-Based Contour Vectorization from Topographic Maps

by Jakub Vynikal and Jan Pacina

ISPRS Int. J. Geo-Inf. 2025, 14(12), 473; https://doi.org/10.3390/ijgi14120473 - 1 Dec 2025

Viewed by 438

Abstract

The quality of scanned topographic maps—including parameters such as image compression, scanning resolution, and bit depth—may strongly influence the performance of deep learning models for contour vectorization. In this study, we investigate this dependence by training eight U-Net models on the same map [...] Read more.

The quality of scanned topographic maps—including parameters such as image compression, scanning resolution, and bit depth—may strongly influence the performance of deep learning models for contour vectorization. In this study, we investigate this dependence by training eight U-Net models on the same map data but under varying input quality conditions. Each model is trained to segment contour lines from the raster input, followed by a postprocessing pipeline that converts segmented output into vector contours. We systematically compare the models with respect to topological error metrics (such as contour intersections and dangling ends) in the resulting vector output and overlay metrics of matched contour segments within given tolerance. Our experiments demonstrate that while the input data quality indeed matters, moderate lowering of quality parameters doesn’t introduce significant practical tradeoff, while storage and computational requirements remain low. We discuss implications for the preparation of archival map scans and propose guidelines for choosing scanning settings when the downstream goal is automated vectorization. Our results highlight that deep learning methods, though resilient against reasonable compression, remain measurably sensitive to degradation in input fidelity. Full article

► Show Figures

Figure 1

26 pages, 8979 KB

Open AccessArticle

Assessing the Multidimensionality of the 15-Min City in Seville Through Open Geospatial Data

by Joaquín Osorio-Arjona and José David Albarrán-Periáñez

ISPRS Int. J. Geo-Inf. 2025, 14(12), 472; https://doi.org/10.3390/ijgi14120472 - 1 Dec 2025

Viewed by 404

Abstract

This paper aims to map the degree of implementation of the 15-min city model in a medium-sized city like Seville and analyze the demographic, economic, and structural characteristics that affect the varying degree of implementation of the model. To this end, facility density [...] Read more.

This paper aims to map the degree of implementation of the 15-min city model in a medium-sized city like Seville and analyze the demographic, economic, and structural characteristics that affect the varying degree of implementation of the model. To this end, facility density was estimated from 15-min walking isochrones for each census tract, and a synthetic index was calculated from the coefficients obtained for each type of facility using a Geographically Weighted Regression (GWR) model that takes into account the spatial variation in infrastructure availability. A second GWR model was used to study the spatial impact of several demographic, socio-economic and structural variables on the calculated synthetic index. The main results show residential neighborhoods with greater accessibility and infrastructure diversity have a higher degree of compliance with the 15-min city model, while the city’s most marginalized and vulnerable neighborhoods have a negative index. It also highlights the fact that the processes of touristification and gentrification of the city’s historic center contribute to a lack of compliance with the model. These findings provide an empirical basis for designing urban policies aimed at reducing the territorial gap and towards equity in access to basic services. Full article

► Show Figures

Figure 1

33 pages, 24575 KB

Open AccessArticle

Street View Image-Based Emotional Perception Modeling of Old Residential Communities: An Explainable Framework Integrating Random Forest and SHAP

by Yanqing Xu and Xiaoxuan Fan

ISPRS Int. J. Geo-Inf. 2025, 14(12), 471; https://doi.org/10.3390/ijgi14120471 - 29 Nov 2025

Viewed by 522

Abstract

Understanding how the built environment shapes residents’ emotional perceptions in old residential communities (ORCs) is essential for enhancing livability and supporting people-oriented urban regeneration. This study proposes an explainable analytical framework that integrates community attributes, streetscape indicators, and subjective evaluations. Using random forest [...] Read more.

Understanding how the built environment shapes residents’ emotional perceptions in old residential communities (ORCs) is essential for enhancing livability and supporting people-oriented urban regeneration. This study proposes an explainable analytical framework that integrates community attributes, streetscape indicators, and subjective evaluations. Using random forest (RF) regression combined with Shapley Additive Explanations (SHAP), we conducted an empirical study on ten ORCs in Yangzhou, China. A total of 1240 street view images (SVIs) were processed to extract social attributes, including building age, building scale, and point-of-interest (POI) diversity, as well as visual indicators such as walkability, green view index (GVI), and colorfulness. Six emotional perception scores were obtained from the MIT Place Pulse 2.0 model and further calibrated through questionnaires. The results show that the proposed framework effectively captures the spatial determinants of residents’ perceptions, with the model predictions being highly consistent with survey evaluations. Specifically, GVI and street enclosure are positively associated with perceptions of beauty, safety, and vitality, while building aging and functional monotony intensify negative feelings such as oppression and boredom. Visual diversity (VD) enhances aesthetic and vitality perceptions, whereas facility visual entropy demonstrates a dual role—reinforcing safety but potentially inducing oppressive feelings. By integrating interpretable machine learning with geospatial analysis, this study provides both theoretical and practical insights for micro-scale community renewal, and the framework can be extended to multimodal analyses including soundscapes and behavioral pathways. 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 14, Issue 12 (December 2025) – 46 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI