ISPRS International Journal of Geo-Information

23 pages, 4649 KB

Open AccessArticle

Multi-Source Geospatial Data for Parking Space Discovery for Hospitals in Densely Urban Areas

by Yimeng Zhang, Yirui Wei, Ruishuan Zhu, Yuhao Liu, Kunliang Xiao, Sheng Zhang and Xiran Zhou

ISPRS Int. J. Geo-Inf. 2026, 15(3), 117; https://doi.org/10.3390/ijgi15030117 - 11 Mar 2026

Abstract

Amid rapid urbanization, the rapid increase in urban vehicles has exacerbated parking scarcity, particularly in areas surrounding hospitals. As the core city of the Huaihai Economic Zone, Xuzhou’s medical institutions serve a broad region spanning 178,000 square kilometers. The pronounced mismatch between parking [...] Read more.

Amid rapid urbanization, the rapid increase in urban vehicles has exacerbated parking scarcity, particularly in areas surrounding hospitals. As the core city of the Huaihai Economic Zone, Xuzhou’s medical institutions serve a broad region spanning 178,000 square kilometers. The pronounced mismatch between parking supply and demand in these areas severely impacts traffic efficiency and public service quality. To address this challenge, this study proposes a data-driven parking resource planning methodology for the identification and planning of informal/shared parking spaces (utilizing underutilized idle spaces) in hospital vicinities, integrating multi-source geospatial data from OpenStreetMap, remote sensing imagery, and field surveys. The methodology involves data preprocessing (e.g., format conversion, building boundary calibration), parking space identification and classification (e.g., buffer zone delineation, vacant land categorization, shape-based division), and layout optimization using a genetic algorithm combined with manual refinement. Applied within a 1 km radius around two hospitals in Xuzhou, the results demonstrate significant improvements in space utilization and provide a scientific basis for temporary parking facility planning. The results provide practical decision support for urban spatial management and temporary parking governance in high-demand public service areas. Full article

► Show Figures

Figure 1

38 pages, 2441 KB

Open AccessArticle

Geo-Information Driven Multi-Criteria Decision Analysis for Precision Agriculture Technologies Using Neutrosophic Entropy-DEMATEL and Hybrid TOPSIS

by Venkata Prasanna Nagari and Vinoth Subbiah

ISPRS Int. J. Geo-Inf. 2026, 15(3), 116; https://doi.org/10.3390/ijgi15030116 - 11 Mar 2026

Abstract

Precision agriculture employs advanced technologies to enhance farm productivity and sustainability; however, selecting the most appropriate tools can be challenging for small and medium-sized farms. This study conducts a comparative analysis of ten key precision agriculture technologies (PATs): remote sensing, GPS, GIS, VRT, [...] Read more.

Precision agriculture employs advanced technologies to enhance farm productivity and sustainability; however, selecting the most appropriate tools can be challenging for small and medium-sized farms. This study conducts a comparative analysis of ten key precision agriculture technologies (PATs): remote sensing, GPS, GIS, VRT, soil & crop sensors, DSS, UAVs/Drones, AI & ML-based precision farming, autonomous agricultural machinery, and IoT-based smart farming. The analysis employs a neutrosophic set-based multi-criteria decision-making (MCDM) framework. Domain experts evaluated ten representative technologies using a structured questionnaire based on ten critical criteria, including spatial-temporal accuracy, data acquisition latency, scalability, robustness, interoperability, environmental resilience, economic feasibility, and agro-ecological impact. A hybrid MCDM methodology was employed, integrating neutrosophic entropy and DEMATEL to construct criterion weights. Furthermore, we utilized neutrosophic DEMATEL to identify inter-criterion causal relationships. Neutrosophic TOPSIS, enhanced by a newly proposed hybrid Cosine-Jaccard similarity measure, was introduced to rank the alternatives under conditions of uncertainty. The findings reveal that IoT-based smart farming solutions achieved the highest overall score, followed by remote sensing and decision-support system (DSS) platforms. At the same time, variable-rate technology and sensor networks received lower rankings. The findings underscore the appropriateness of particular PATs for small and medium-scale farming contexts and illustrate the effectiveness of neutrosophic MCDM in addressing ambiguity and indeterminacy. The comparative insights provide direction for researchers, policymakers, and practitioners in prioritizing precision agriculture technologies and strategies to enhance sustainable practices in small and medium-scale farming. Full article

► Show Figures

Figure 1

21 pages, 3982 KB

Open AccessArticle

Spatio-Temporal Analysis of Regional Fire Service Accessibility for Underground Parking Garages

by Leng Liang, Diping Yuan, Dingli Liu, Weijun Liu, Lei Zou and Guohua Wu

ISPRS Int. J. Geo-Inf. 2026, 15(3), 115; https://doi.org/10.3390/ijgi15030115 - 9 Mar 2026

Abstract

Underground parking garages in high-density megacities are high-risk environments where strong confinement and large fire loads pose severe safety threats. In this study, an evaluation model is proposed based on the entropy weight method combined with dynamic traffic conditions to determine the regional [...] Read more.

Underground parking garages in high-density megacities are high-risk environments where strong confinement and large fire loads pose severe safety threats. In this study, an evaluation model is proposed based on the entropy weight method combined with dynamic traffic conditions to determine the regional fire service accessibility index

C_{j}

. Taking Shenzhen, a megacity in China, as the study area, POI data were used to identify 510 fire stations as supply points and 3378 underground parking garages as demand points, yielding 165,522 samples across 49 evaluation scenarios. The results show that the overall average travel time, distance, and velocity are 388.17 s, 2217.95 m, and 5.84 m/s.

C_{j}

fluctuates between 0.572 and 0.813, demonstrating clear time-of-day differences. The overall average

C_{j}

for all 49 scenarios is 0.697, corresponding to Grade “C”, representing the general level of regional fire service accessibility. It is recommended that additional fire resources be deployed during peak hours and that fire station layouts in peripheral areas be optimized to improve fire safety in underground parking garages. Full article

► Show Figures

Figure 1

21 pages, 14922 KB

Open AccessArticle

GeoPPO—A Location-Allocation Method of Superstores Based on Deep Reinforcement Learning—A Case Study of Xi’an

by Yuxuan Hu, Kun Qin and Shaohua Wang

ISPRS Int. J. Geo-Inf. 2026, 15(3), 114; https://doi.org/10.3390/ijgi15030114 - 9 Mar 2026

Abstract

Urban commercial restructuring, driven by the closure of traditional supermarkets and the expansion of new-format superstores, creates a large-scale spatial reallocation challenge requiring scientific location-allocation methods. Traditional heuristic algorithms such as Genetic Algorithm (GA) struggle with discrete spatial optimization under 400+ candidate sites [...] Read more.

Urban commercial restructuring, driven by the closure of traditional supermarkets and the expansion of new-format superstores, creates a large-scale spatial reallocation challenge requiring scientific location-allocation methods. Traditional heuristic algorithms such as Genetic Algorithm (GA) struggle with discrete spatial optimization under 400+ candidate sites and complex geographic mask constraints: they converge slowly and easily fall into local optima. This study proposes a Deep Reinforcement Learning (DRL) framework named GeoPPO (Geospatial Proximal Policy Optimization) to address this gap. Using Xi’an’s retail restructuring as a case setting—427 candidate locations and multidimensional geographic features—the approach models spatial constraints via a gridded environment encoded as a five-channel state tensor. Key innovations include a dynamic action-constraint mechanism that masks invalid actions based on boundary rules and competition avoidance, and a curriculum learning strategy that enables stable convergence. The framework fills the need for methods that handle hard spatial constraints in large-scale location-allocation. Tests demonstrate rapid convergence within 1,000 epochs, achieving 75% average demand coverage—2.7% and 5.5% higher than GA and Particle Swarm Optimization (PSO), respectively. Ablation experiments confirm that Vanilla PPO without dynamic action masking fails to produce feasible solutions. The framework offers a feasible technical path for handling highly dynamic urban facility spatial configuration with geographic mask constraints. Full article

► Show Figures

Figure 1

23 pages, 12310 KB

Open AccessArticle

Multi-Scenario Simulation of Low-Carbon Land Use Using an Integrated NSGA-III–PLUS Framework in Coastal Urban Agglomerations

by Tingting Pan and Fenzhen Su

ISPRS Int. J. Geo-Inf. 2026, 15(3), 113; https://doi.org/10.3390/ijgi15030113 - 8 Mar 2026

Abstract

Rapid urban expansion poses growing challenges for balancing carbon emissions (CE), economic development, and ecological protection, particularly in coastal urban agglomerations. Although optimization–simulation approaches have been widely applied, explicit consideration of low-carbon objectives remains limited. To address this gap, this study proposes an [...] Read more.

Rapid urban expansion poses growing challenges for balancing carbon emissions (CE), economic development, and ecological protection, particularly in coastal urban agglomerations. Although optimization–simulation approaches have been widely applied, explicit consideration of low-carbon objectives remains limited. To address this gap, this study proposes an integrated non-dominated sorting genetic algorithm III (NSGA-III)–patch-generating land use simulation (PLUS) framework that combines multi-objective optimization with spatially explicit land-use simulation. Using multi-temporal land-use datasets (2000–2020) from the Guangdong–Hong Kong–Macao Greater Bay Area (GBA), this research examined spatiotemporal land-use transitions and their co-evolution with CE, ecosystem services value (ESV), and GDP under five development scenarios. The results show that construction land expanded by 78% from 2000 to 2020, largely through cropland conversion, which pushed CE upward to 335.4 Mt. For 2030, the Low Carbon Emission scenario reduces CE by 11.8 Mt compared with the natural development scenario. The Balanced Development scenario maintains economic growth while limiting CE increases and stabilizing ESV. Spatially, scenario differences are limited in extent. Over 93% of areas remain unchanged, and variations are mainly concentrated in peri-urban corridors around the Guangzhou–Foshan core. Overall, the NSGA-III–PLUS framework provides a structured approach for coordinating carbon mitigation and land-use planning in rapidly urbanizing coastal areas. Full article

► Show Figures

Figure 1

24 pages, 3793 KB

Open AccessArticle

More Effort Is Needed to Mitigate Spatial Inequality in Rural China’s Healthcare Accessibility: Evidence from a High-Resolution, Multi-Scale and Time-Sensitive Assessment

by Ying Gao, Xiaoran Wu, Mingxiao Xu, Yanlei Ye and Na Zhao

ISPRS Int. J. Geo-Inf. 2026, 15(3), 112; https://doi.org/10.3390/ijgi15030112 - 8 Mar 2026

Abstract

This study aims to address gaps in understanding healthcare accessibility inequality in rural China, where traditional distance-based assessments and urban-centric biases are insufficient. By integrating real-time travel data from Amap and the two-step floating catchment area (2SFCA) method, we conducted a high-resolution (1 [...] Read more.

This study aims to address gaps in understanding healthcare accessibility inequality in rural China, where traditional distance-based assessments and urban-centric biases are insufficient. By integrating real-time travel data from Amap and the two-step floating catchment area (2SFCA) method, we conducted a high-resolution (1 km grid) analysis across transportation modes, administrative scales, and time-sensitive populations. Results reveal that driving enables more stable, equitable access (characterized by higher supply–demand ratios and lower variability) than public transport, which distorts ratios due to limited coverage. Accessibility disparities are most pronounced at the county scale, with eastern rural counties (e.g., Yangtze River Delta) showing far higher accessibility (log₁₀(A-value) > 5.0) than remote western counties (log₁₀(A-value) < 1.5). High time-sensitive populations (urgent care) face extreme accessibility gaps, with only 15% of counties providing optimal access. In contrast, low time-sensitive groups benefit from extended travel time thresholds, achieving 62% coverage of optimal access. Targeted interventions—investing in rural high-tier hospitals, enhancing transit frequency, and county-specific policies—are needed to advance health equity. The findings of this study provide the first nationwide high-resolution healthcare accessibility map for rural China, improve assessment accuracy via real-time data, and identify county-level gaps—offering data-driven insights for targeted policies to advance health equity and support rural revitalization. Full article

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

► Show Figures

Figure 1

19 pages, 6051 KB

Open AccessArticle

Knowledge-Driven Adaptive Direct Sampling for Reconstructing Geochemical Fields Under Sampling Bias

by Yameng Liu, Jiali Zi, Yanqi Dong, Nuo Xu, Qing Zhang and Feixiang Chen

ISPRS Int. J. Geo-Inf. 2026, 15(3), 111; https://doi.org/10.3390/ijgi15030111 - 6 Mar 2026

Abstract

Deriving meaningful mineralization information from raw geospatial datasets is fundamental to the sustainable evaluation and management of mineral resources. As a cornerstone of mineral resource evaluation, identifying geochemical anomalies often faces the significant challenge of sampling bias in practical applications. Strong spatial unevenness [...] Read more.

Deriving meaningful mineralization information from raw geospatial datasets is fundamental to the sustainable evaluation and management of mineral resources. As a cornerstone of mineral resource evaluation, identifying geochemical anomalies often faces the significant challenge of sampling bias in practical applications. Strong spatial unevenness often leads to information loss in traditional geostatistical models, where critical anomaly structures may be over-smoothed or obscured. To address this limitation, this study proposes a knowledge-driven adaptive direct sampling (KD-ADS) framework. This approach functions as a geospatial context-aware reconstruction engine. It integrates a multi-factor knowledge-driven weighting system to prioritize regions with high information value and incorporates a dynamic context-aware neighborhood module that adapts to local statistical characteristics. Using 1268 samples from the Jiulian Mountains tungsten metallogenic belt, ablation studies demonstrate the individual contributions of the knowledge-driven weighting and adaptive neighborhood modules to improving reconstruction accuracy and spatial connectivity. Comparative experiments with the traditional direct sampling (DS) algorithm demonstrate that KD-ADS achieves a more accurate reconstruction of geochemical fields and better preserves discrete high-value mineralization anomalies and spatial heterogeneity under sampling-bias conditions. This approach improves the reproducibility of mineralization enrichment patterns and enhances computational efficiency, providing data science-driven support for sustainable mineral exploration and resource allocation. Full article

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

► Show Figures

Figure 1

24 pages, 4302 KB

Open AccessArticle

Adapted Route Instructions for Navigation Technologies in Support of Wheelchair Mobility in Urban Areas: Online Survey

by Sanaz Azimi, Mir Abolfazl Mostafavi, Krista L. Best, Aurélie Dommes and Angélique Montuwy

ISPRS Int. J. Geo-Inf. 2026, 15(3), 110; https://doi.org/10.3390/ijgi15030110 - 5 Mar 2026

Abstract

Wheelchair users face environmental barriers that limit their mobility and social participation. Although existing navigation tools support urban mobility, they often lack clear orientation and confirmation cues, and information on accessible and safe routes to meet wheelchair users’ needs. This study aims to [...] Read more.

Wheelchair users face environmental barriers that limit their mobility and social participation. Although existing navigation tools support urban mobility, they often lack clear orientation and confirmation cues, and information on accessible and safe routes to meet wheelchair users’ needs. This study aims to identify the most adapted route instructions for wheelchair users, examine characteristics’ (sociodemographic information and profiles) impact on their instructions’ choices, and evaluate instruction’s delivery modalities. An online questionnaire collected participants’ characteristics and agreement with the proposed route instruction formulations (different combinations of information like turn-by-turn instructions, landmarks, and accessibility information) regarding clarity, sufficiency, adaptability, and safety criteria. Formulations were evaluated across 14 navigation situations involving accessibility and safety challenges. Participants also rated communication modalities. 32 wheelchair-users (19 males, 13 females; mean age = 45.8 years; mean wheelchair experience = 23.5 years) participated. Data analysis reveals the importance of enriched turn-by-turn instructions, including non-turning actions, alerts, landmarks, and/or street names for participants. Alert-based formulations were favored in most situations, like uneven sidewalks, slopes and intersections. More enriched instructions were significantly acceptable among women and participants with greater wheelchair experience. Multimodal delivery, particularly visual and audio information, was also preferred. These findings help develop adaptive navigation tools, improving wheelchair users’ safe, confident mobility, autonomy, and social participation. Full article

► Show Figures

Figure 1

33 pages, 4521 KB

Open AccessArticle

Land Use, Street Design, and Older Adults’ Active Travel: Uncovering Nonlinear Effects in Multi-Scale Convenient Living Circles

by Chang Liu, Yu Zhang, Shuo Yang, Liang Guo, Hui He and Xiaoli Sun

ISPRS Int. J. Geo-Inf. 2026, 15(3), 109; https://doi.org/10.3390/ijgi15030109 - 4 Mar 2026

Abstract

Promoting older adults’ active travel (AT) is important for healthy ageing, yet the optimal spatial units and scales for built environment (BE) interventions remain unclear. Existing studies often ignore the Modifiable Areal Unit Problem and fail to distinguish macro-scale land-use patterns from micro-scale [...] Read more.

Promoting older adults’ active travel (AT) is important for healthy ageing, yet the optimal spatial units and scales for built environment (BE) interventions remain unclear. Existing studies often ignore the Modifiable Areal Unit Problem and fail to distinguish macro-scale land-use patterns from micro-scale street design under potentially nonlinear behavior–environment relationships. This study aims to clarify how multi-scale BE influences older adults’ AT and to identify the most effective intervention scale. Using survey data from 2494 older adults in Wuhan, China, we construct six behaviorally meaningful sliding units (5, 10, and 15 min walking network buffers and distance-equivalent Euclidean buffers), derive macro- and micro-scale indicators from GIS, census data, and street view images, and build separate Extreme Gradient Boosting (XGBoost) models with Accumulated Local Effects plots for interpretation. A model comparison reveals pronounced scale effects: network-based buffers systematically outperform circular buffers, and the 15 min walking network buffer emerges as the optimal intervention unit. Across all scales, BE variables contribute more to model performance than socio-demographic factors, and macro-scale attributes (e.g., land-use mix, facility density, and transit access) consistently outweigh micro-scale street features. Nonlinear effects and thresholds are identified for key density, accessibility, and streetscape indicators. These findings underscore the necessity of multi-scale analysis and support planning “15 min life circles” for older adults that prioritize macro-scale land-use and facility optimization, complemented by targeted, context-specific street-level improvements to create safe, age-friendly walking environments. Full article

(This article belongs to the Topic Applications of Intelligent Technologies in the Life Cycle of Transportation Infrastructure)

► Show Figures

Figure 1

26 pages, 4960 KB

Open AccessArticle

TGR-T: Truncated-Gaussian-Weighted Reliability for Adaptive Dynamic Thresholding in Weakly Supervised Indoor 3D Point Cloud Segmentation

by Ziwei Luo, Xinyue Liu, Jun Jiang, Hanyu Qi, Chen Wang, Zhong Xie and Tao Zeng

ISPRS Int. J. Geo-Inf. 2026, 15(3), 108; https://doi.org/10.3390/ijgi15030108 - 4 Mar 2026

Abstract

Indoor 3D point cloud semantic segmentation is a fundamental task for fine-grained scene understanding and intelligent perception. Due to the prohibitive cost of dense point-wise annotations, weakly supervised learning has emerged as a promising alternative for indoor point cloud segmentation. However, existing weakly [...] Read more.

Indoor 3D point cloud semantic segmentation is a fundamental task for fine-grained scene understanding and intelligent perception. Due to the prohibitive cost of dense point-wise annotations, weakly supervised learning has emerged as a promising alternative for indoor point cloud segmentation. However, existing weakly supervised methods commonly rely on fixed confidence thresholds for pseudo-label selection, which exhibit limited generalization caused by threshold sensitivity, underutilization of informative low-confidence regions, and progressive noise accumulation during self-training. To address these issues, we propose TGR-T, a weakly supervised framework for indoor 3D point cloud semantic segmentation that incorporates truncated-Gaussian-weighted reliability with adaptive dynamic thresholding. Specifically, a reliability-adaptive dynamic thresholding strategy is introduced to guide pseudo-label selection based on the evolving confidence statistics of unlabeled mini-batches, with exponential moving average smoothing employed to produce stable global estimates and robust separation of reliable and ambiguous regions. To further exploit uncertain regions, a learnable truncated Gaussian weighting function is designed to explicitly model prediction uncertainty within the ambiguous set, providing soft supervision by assigning adaptive weights to low-confidence predictions during optimization. Extensive experimental results demonstrate that the proposed framework significantly enhances the exploitation of unlabeled data under extremely limited supervision: extensive experiments conducted on standard indoor 3D scene benchmarks demonstrate that TGR-T achieves competitive or superior segmentation performance under extremely sparse supervision and can even outperform several fully supervised baselines trained with dense annotations while using only 1% labeled points, thereby substantially narrowing the performance gap between weakly supervised and fully supervised 3D semantic segmentation methods. Full article

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

► Show Figures

Figure 1

15 pages, 5501 KB

Open AccessArticle

User Preferences for Cartographic Presentation in Tourist Information Search Across Geographic Scales

by Beata Medyńska-Gulij and Marek Krajewski

ISPRS Int. J. Geo-Inf. 2026, 15(3), 107; https://doi.org/10.3390/ijgi15030107 - 3 Mar 2026

Abstract

This study touches upon the issue of searching for tourist information in the context of preferred forms of cartographic presentation in different geographic scales. The main objective of our research was to examine the link between the type of tourist information that is [...] Read more.

This study touches upon the issue of searching for tourist information in the context of preferred forms of cartographic presentation in different geographic scales. The main objective of our research was to examine the link between the type of tourist information that is searched for and the graphical level of abstraction, as well as geographic scale. We used the method of the online survey on twelve maps to study users’ preferences in two respondent groups: geographers and sociologists. Based on the map rankings obtained, we have drawn conclusions on the informative value of realistic and conventional sources of tourist information. The study has demonstrated the globalization of social behavior that significantly favors global web map services over other online sources. The most important factor in choosing a map is whether it contains the information the user is currently seeking. It is impossible to clearly indicate a preferred level of abstraction for presenting tourist information at every geographical scale. However, consistently high rankings were observed for maps using pictorial and symbolic signs. The map type preferences of geographers and sociologists were very similar, although geographers showed a slightly stronger preference for maps with conventional symbols. All respondents rated traditional hypsometric maps highly. Full article

► Show Figures

Figure 1

23 pages, 760 KB

Open AccessArticle

Trajectory Data Publishing Scheme Based on Transformer Decoder and Differential Privacy

by Haiyong Wang and Wei Huang

ISPRS Int. J. Geo-Inf. 2026, 15(3), 106; https://doi.org/10.3390/ijgi15030106 - 3 Mar 2026

Abstract

The proliferation of Location-Based Services (LBSs) has generated vast trajectory datasets that offer immense analytical value but pose critical privacy risks. Achieving an optimal balance between data utility and privacy preservation remains a challenge, a difficulty compounded by the limitations of existing methods [...] Read more.

The proliferation of Location-Based Services (LBSs) has generated vast trajectory datasets that offer immense analytical value but pose critical privacy risks. Achieving an optimal balance between data utility and privacy preservation remains a challenge, a difficulty compounded by the limitations of existing methods in modeling complex, long-term spatiotemporal dependencies. To address this, this paper proposes a trajectory data publishing scheme combining a Transformer decoder with differential privacy. Unlike traditional single-layer approaches, the proposed method establishes a systematic generation–generalization framework. First, a Transformer decoder is integrated into a Generative Adversarial Network (GAN). This architecture mitigates the gradient vanishing issues common in RNN-based models, generating high-fidelity synthetic trajectories that capture long-range correlations while decoupling them from sensitive source data. Second, to provide rigorous privacy guarantees, a clustering-based generalization strategy is implemented, utilizing Exponential and Laplace mechanisms to ensure

ϵ

-differential privacy. Experiments on the Geolife and Foursquare NYC datasets demonstrate that the scheme significantly outperforms leading baselines, achieving a superior trade-off between privacy protection and data utility. Full article

(This article belongs to the Topic Recent Advances in Security, Privacy, and Trust)

► Show Figures

Figure 1

17 pages, 1296 KB

Open AccessArticle

SSKEM: A Global Pointer Network Model for Joint Entity and Relation Extraction in Storm Surge Texts

by Yebin Chen, Mingjie Xie, Yongli Chen, Zhenduo Dou and Weihong Li

ISPRS Int. J. Geo-Inf. 2026, 15(3), 105; https://doi.org/10.3390/ijgi15030105 - 3 Mar 2026

Abstract

Storm surges are catastrophic marine disasters that pose severe threats to coastal populations, making the rapid extraction of key information from multi-source texts critical for effective emergency response. However, existing extraction methods often struggle with complex linguistic challenges, such as identifying nested entities [...] Read more.

Storm surges are catastrophic marine disasters that pose severe threats to coastal populations, making the rapid extraction of key information from multi-source texts critical for effective emergency response. However, existing extraction methods often struggle with complex linguistic challenges, such as identifying nested entities (e.g., overlapping geographic names), capturing relationships across long texts, and handling the disparity between formal official reports and unstructured social media data. To address these limitations, this study proposes a Storm Surge Knowledge Extraction Model (SSKEM) based on Global Pointer Networks. By constructing a domain-specific dataset of 4000 records from government bulletins, news reports, and social media, the proposed model utilizes a unified matrix decoding mechanism to treat entity and relation extraction as a holistic task. Experimental results demonstrate that the model achieves an F1-score of 88.4%, outperforming robust baseline models by 5.5%. Notably, it improves the recognition accuracy of complex nested entities by 13.7% and enhances the recall rate for cross-sentence relations by 18.2%. Furthermore, the model exhibits high computational efficiency, processing speed suitable for real-time applications, and effectively bridges the performance gap between standardized and fragmented data sources. This research provides a robust technical solution for transforming heterogeneous disaster big data into actionable knowledge for decision-support systems. Full article

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

► Show Figures

Figure 1

26 pages, 14594 KB

Open AccessArticle

Mix-Persona Comment Generation and Geographically Enhanced Context Retrieval for LLM Fine-Tuning in Multimodal Crisis Post Classification

by Tong Bie, Yongli Hu, Yu Fu, Linjia Hao, Tengfei Liu, Kan Guo, Huajie Jiang, Junbin Gao, Yanfeng Sun and Baocai Yin

ISPRS Int. J. Geo-Inf. 2026, 15(3), 104; https://doi.org/10.3390/ijgi15030104 - 2 Mar 2026

Abstract

Social media has become a vital source for humanitarian organizations to gather information during crises. However, existing multimodal classification methods operate primarily as isolated systems, while neglecting external references crucial for accurate judgment. Furthermore, while user comments can provide valuable context, they are [...] Read more.

Social media has become a vital source for humanitarian organizations to gather information during crises. However, existing multimodal classification methods operate primarily as isolated systems, while neglecting external references crucial for accurate judgment. Furthermore, while user comments can provide valuable context, they are often scarce during the early stages of a crisis. To address these limitations, we propose a framework named Mix-Persona Comment Generation with Geographically Enhanced Context Retrieval for LLM Instruction Fine-tuning (MPCG-GECR). To mitigate comment scarcity, we employ a Synthetic Persona Generator (SPG) that prompts LLMs to adopt diverse mix-personas, generating synthetic comments that simulate multi-perspective public discourse. To incorporate external references, we introduce a Geographically Enhanced Context Retrieval (GECR) module. Unlike standard retrieval approaches, GECR utilizes a hybrid re-ranking strategy to identify samples that are both multimodally similar and geographically consistent, serving as reliable reference anchors for the LLM. By integrating these social perspectives and geographic references into a unified instruction-tuning format, we transform the classification task into a context-aware text generation problem and fine-tune the LLM using Low-Rank Adaptation (LoRA). Extensive experiments on the CrisisMMD and DMD datasets demonstrate that MPCG-GECR effectively overcomes data scarcity and context isolation, significantly outperforming existing methods. Full article

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

► Show Figures

Graphical abstract

22 pages, 4608 KB

Open AccessArticle

Enhancing Ecosystem Service Value Through Land Use Optimization: A Multi-Objective Particle Swarm Optimization (PSO) Approach in Wuhan, China

by Yan Zhang, Lu Wei, Yasi Tian, Yiheng Wang, Fanjie Kong, Yang Zhang, Yiyun Chen and Xu Zhou

ISPRS Int. J. Geo-Inf. 2026, 15(3), 103; https://doi.org/10.3390/ijgi15030103 - 1 Mar 2026

Abstract

Integrating ecosystem service value (ESV) into land use optimization is crucial for achieving sustainable development goals. Unlike traditional “post-evaluation” approaches that assess ESV after generating land use plans, this study pioneers a “goal-oriented” method by embedding ESV as an objective to guide land [...] Read more.

Integrating ecosystem service value (ESV) into land use optimization is crucial for achieving sustainable development goals. Unlike traditional “post-evaluation” approaches that assess ESV after generating land use plans, this study pioneers a “goal-oriented” method by embedding ESV as an objective to guide land use optimization. A multi-objective particle swarm optimization (PSO) framework, which incorporates ESV with land quantity error, spatial aggregation of farmland and construction land, and economic benefits, was constructed for the research study. Applied to Wuhan, China, for the periods of 2005–2015 and 2010–2020, the results demonstrate the feasibility of the proposed framework in: (1) reducing construction land area while increasing farmland and ecological land; (2) spatially aggregating construction land towards urban functional areas while protecting farmland and ecological land in peri-urban and outer suburban areas; (3) improving spatial aggregation of farmland, construction land, and ecological land; and (4) slightly increasing ESV, particularly in peri-urban and outer suburban areas. The proposed PSO framework provides a valuable tool for optimizing land use layout, enhancing ecosystem service provision, and promoting balanced socio-ecological development. Full article

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

► Show Figures

Figure 1

20 pages, 14553 KB

Open AccessArticle

Spatiotemporal Characteristics and Hazard Assessment of Drought in Inner Mongolia Based on the MCI

by Yanmin Li, Jinghui Liu, Xinxu Li, Zixuan Wang and Chenxu Liu

ISPRS Int. J. Geo-Inf. 2026, 15(3), 102; https://doi.org/10.3390/ijgi15030102 - 1 Mar 2026

Abstract

This study identifies and extracts two typical drought characteristics, drought frequency and drought severity, based on the Meteorological Drought Composite Index (MCI), and systematically analyzes their spatiotemporal evolution in Inner Mongolia. Using a two-stage geographical detector approach, the dominant factors of drought characteristics [...] Read more.

This study identifies and extracts two typical drought characteristics, drought frequency and drought severity, based on the Meteorological Drought Composite Index (MCI), and systematically analyzes their spatiotemporal evolution in Inner Mongolia. Using a two-stage geographical detector approach, the dominant factors of drought characteristics and their spatial variations are quantitatively identified across different drought grades and subregions, and the weights of drought indicators are determined accordingly. Finally, a multi-level drought hazard assessment is conducted using a drought hazard index model, providing scientific support for drought risk management and disaster prevention in Inner Mongolia. The results indicate that (1) drought characteristics exhibit significant spatial heterogeneity. Drought frequency presents a distinct east–high to west–low gradient, while high values of drought severity are concentrated in the central and southwestern regions. Temporally, drought frequency shows an increasing trend, whereas drought severity demonstrates periodic fluctuations and relative stability. (2) Results from factor and interaction detection reveal that light, moderate, and extreme drought levels are primarily influenced by the combined effects of regions with extremely high drought frequency and drought severity. In contrast, severe drought is mainly driven by regions with extremely high frequency and high severity. Moreover, the interaction between multiple factors significantly enhances the explanatory power for drought severity levels compared to individual factors. (3) The drought hazard assessment shows that high-hazard areas are mainly concentrated in Alxa League, Tongliao City, and other regions. The spatial distribution of hazard levels is highly consistent with historical drought statistics, thereby validating the rationality and practical applicability of the proposed model. Full article

► Show Figures

Figure 1

26 pages, 4766 KB

Open AccessArticle

A Novel Wind-Aware Dynamic Graph Neural Network for Urban Ground-Level Ozone Concentration Prediction

by Wenjie Wu, Xinyue Mo and Huan Li

ISPRS Int. J. Geo-Inf. 2026, 15(3), 101; https://doi.org/10.3390/ijgi15030101 - 28 Feb 2026

Abstract

Ground-level ozone pollution poses significant risks to public health and ecosystems and remains a major environmental challenge worldwide. Accurate forecasting is difficult due to the nonlinear formation mechanisms of ozone and its strong dependence on meteorological conditions. This study proposes a Wind Speed [...] Read more.

Ground-level ozone pollution poses significant risks to public health and ecosystems and remains a major environmental challenge worldwide. Accurate forecasting is difficult due to the nonlinear formation mechanisms of ozone and its strong dependence on meteorological conditions. This study proposes a Wind Speed and Direction-Based Dynamic Spatiotemporal Graph Attention Network (WSDST-GAT) for multi-step hourly ground-level ozone prediction. The model integrates a wind-aware dynamic graph to represent anisotropic pollutant transport and a Transformer-based temporal encoder to capture long-range dependencies. Meteorological variables are incorporated to enhance physical interpretability and predictive robustness. A co-kriging module is further employed to reconstruct continuous spatial ozone fields with quantified uncertainty. Using hourly observations from 35 monitoring stations in Beijing, WSDST-GAT achieves a Coefficient of Determination of 0.957, with a Mean Absolute Error of 5.25 μg/m³, and a Root Mean Square Error of 9.58 μg/m³. The prediction intervals demonstrate strong reliability with a Prediction Interval Coverage Probability of 94.01% and a Prediction Interval Normalized Average Width of 0.174. These results indicate that the proposed framework provides an accurate and physically informed solution for ozone forecasting and air quality management. Full article

(This article belongs to the Topic Innovative Approaches in Geospatial Analysis and Modeling of Urban Environments)

► Show Figures

Figure 1

35 pages, 1627 KB

Open AccessReview

Shedding Light on Explainable AI: Insights, Challenges, and the Future of Infrastructure Management

by Youwen Hu, Zunaira Atta, Tariq Ur Rahman, Shi Qiu, Jin Wang, Wei Wei, Zhiyu Liang and Qasim Zaheer

ISPRS Int. J. Geo-Inf. 2026, 15(3), 100; https://doi.org/10.3390/ijgi15030100 - 28 Feb 2026

Abstract

This study presents a systematic review of Explainable Artificial Intelligence (XAI) applications in Transportation Infrastructure Management (TIM), focusing on predictive maintenance of safety-critical assets such as railways and bridges. A predefined review protocol was implemented, and peer-reviewed literature was systematically retrieved from Web [...] Read more.

This study presents a systematic review of Explainable Artificial Intelligence (XAI) applications in Transportation Infrastructure Management (TIM), focusing on predictive maintenance of safety-critical assets such as railways and bridges. A predefined review protocol was implemented, and peer-reviewed literature was systematically retrieved from Web of Science and Scopus covering the period 2015 to March 2025. Using structured Boolean search logic and clearly defined inclusion and exclusion criteria—requiring explicit integration of explainability within AI-driven infrastructure maintenance—450 records were initially identified, screened in multiple stages, and refined to 163 eligible studies for detailed analysis. Through structured data extraction and thematic synthesis, the review develops a taxonomy of model-specific, model-agnostic, hybrid, and human-centered XAI approaches while identifying recurring challenges including heterogeneous multi-modal data environments, lack of standardized interpretability metrics, computational constraints in real-time deployment, limited robustness validation under field conditions, and unresolved performance–interpretability trade-offs. The findings demonstrate systematic growth in XAI-driven predictive maintenance research and highlight the need for domain-specific benchmarks, hybrid interpretable architectures, digital twin-assisted validation, and edge-enabled explainable systems to enable scalable, transparent, and regulation-ready infrastructure management aligned with Industry 5.0. Full article

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

► Show Figures

Figure 1

27 pages, 2254 KB

Open AccessArticle

GeoJed: A Geospatial Grid Model for Data Acquisition and Spatial–Quality Assessment of Healthcare Services in Jeddah

by Saud Althabiti

ISPRS Int. J. Geo-Inf. 2026, 15(3), 99; https://doi.org/10.3390/ijgi15030099 - 27 Feb 2026

Abstract

The limited availability of structured and consistent health-facility information poses challenges for assessing service accessibility and quality in rapidly growing cities, particularly in the Middle East. Although digital map platforms provide extensive public data, such information is often fragmented and not directly suitable [...] Read more.

The limited availability of structured and consistent health-facility information poses challenges for assessing service accessibility and quality in rapidly growing cities, particularly in the Middle East. Although digital map platforms provide extensive public data, such information is often fragmented and not directly suitable for systematic spatial analysis. This study presents GeoJed, a framework designed to automate the collection, organisation, and spatial analysis of healthcare facility information from digital map platforms. The framework is demonstrated through a case study in Jeddah, Saudi Arabia, highlighting its applicability for large-scale and reproducible spatial analysis of healthcare services. Using the resulting GeoJedHF dataset, a baseline analysis was conducted to illustrate the analytical value of the collected data, including the construction of an initial Patient Satisfaction Index (PSI) that integrates service availability with user-reported quality indicators derived from a multilingual sentiment model (XLM-RoBERTa). The results reveal clear spatial variations between districts in both facility distribution and perceived service quality. Overall, GeoJed establishes a reusable and extensible process for facility-level spatial data acquisition and analysis, with potential applications in accessibility assessment, urban planning, and service evaluation. Full article

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

► Show Figures

Figure 1

Journal Description

ISPRS International Journal of Geo-Information

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Further Information

Guidelines

MDPI Initiatives

Follow MDPI