ISPRS International Journal of Geo-Information

31 pages, 23750 KB

Open AccessArticle

Spatial Allocation of Elderly Care Resources in High-Density Urban Areas Under the Guidance of Efficiency and Equity

by Siyu Zhao, Shaohua Wang, Haojian Liang, Jingyi Zhou, Hao Wang, Ning Zhang, Chang Liu and Hong Gao

ISPRS Int. J. Geo-Inf. 2026, 15(8), 376; https://doi.org/10.3390/ijgi15080376 - 21 Aug 2026

Viewed by 367

Abstract

Rapid urban population aging and increasing land constraints pose significant challenges for improving both service coverage and spatial equity in elderly care facility planning. This study develops an integrated optimization framework that simultaneously addresses accessibility, efficiency, and equity in the spatial allocation of [...] Read more.

Rapid urban population aging and increasing land constraints pose significant challenges for improving both service coverage and spatial equity in elderly care facility planning. This study develops an integrated optimization framework that simultaneously addresses accessibility, efficiency, and equity in the spatial allocation of elderly care facilities. First, an improved Gaussian Two-Step Floating Catchment Area (G2SFCA) method is employed to evaluate accessibility patterns across multiple facility types under both walking and driving scenarios. Second, resource allocation equity is quantified using Lorenz curves and spatial Gini coefficients to identify mismatches between elderly care supply and population demand. Building upon these analyses, a fairness-oriented maximum covering location model—termed the Equity Maximum Covering Location Problem (EMCLP)—is formulated and further transformed into a Markov Decision Process. A deep reinforcement learning-based algorithm is subsequently designed to solve the EMCLP under complex spatial constraints. Experiment results demonstrate that the proposed approach achieves improved computational efficiency while maintaining robust solution quality, and effectively enhances service provision in underserved areas through differentiated functional allocation strategies. Full article

(This article belongs to the Special Issue Novel Theories and Applications on Geo-Spatial Databases, Models and AI in Urban Science, Planning, Development and Governance)

► Show Figures

Figure 1

34 pages, 22759 KB

Open AccessArticle

Persistence-Based Analysis of Urban Growth Regimes, Spatial Drivers, and Growth-Pressure Screening: A Case Study of Tehran 2016–2030

by SeyedMasoud Hamed Seyedbeiglou, Andreas Rienow and Ata Ghaffari Gilandeh

ISPRS Int. J. Geo-Inf. 2026, 15(8), 375; https://doi.org/10.3390/ijgi15080375 - 19 Aug 2026

Viewed by 364

Abstract

Urban expansion is often tracked with annual land-cover data, yet year-to-year classification noise can masquerade as persistent urban growth. Previous work has usually treated detection, morphology, spatial structure, driver analysis, and forward-looking modelling separately. Here we follow urban growth in Tehran County from [...] Read more.

Urban expansion is often tracked with annual land-cover data, yet year-to-year classification noise can masquerade as persistent urban growth. Previous work has usually treated detection, morphology, spatial structure, driver analysis, and forward-looking modelling separately. Here we follow urban growth in Tehran County from 2016 to 2025 within one linked workflow and then extend the analysis to a 2025–2030 growth-pressure screening under static covariates. Annual 10 m built-up composites from Dynamic World were passed through a temporal stability filter to retain persistent change. Stable growth was classified into four regimes, tested for clustering and interaction scale, and examined using a Spatial Durbin Model and multiscale geographically weighted regression. A two-stage machine-learning branch then produced a ranked growth-pressure surface. In this study, growth-pressure screening means identifying where recent spatial conditions are most compatible with continued growth under unchanged covariates; it is intended for relative spatial ranking under stated assumptions rather than deterministic estimation of future urbanization. Stable new built-up area totaled 107.64 km², most of it ribbon growth (57.60%) and edge expansion (32.77%). A stratified local validation of 300 samples returned a weighted overall accuracy of 97.30%, and a 27-scenario threshold test retained ribbon growth as the largest regime and edge expansion as the second largest in every case. Clustering was significant (Global Moran’s I = 0.326), with a dominant interaction range of about 8–10 km. Historical backtesting showed strong discrimination and ranking (ROC AUC = 0.979; PR AUC = 0.984; Spearman ρ = 0.902), while exact growth-magnitude performance was more moderate (R² = 0.341). The growth-pressure surface is therefore more useful for hotspot identification and relative ranking than for estimating exact future growth magnitude. Full article

► Show Figures

Figure 1

25 pages, 29061 KB

Open AccessArticle

Geospatial Big Data Integration for Near-Real-Time Multimodal Urban Mobility Analysis

by Boban Davidovic and Dusan Barac

ISPRS Int. J. Geo-Inf. 2026, 15(8), 374; https://doi.org/10.3390/ijgi15080374 - 19 Aug 2026

Viewed by 237

Abstract

Urban mobility systems generate large volumes of heterogeneous geospatial data that differ in temporal resolution, spatial coverage, update frequency, and semantic structure, making integrated near-real-time analysis difficult. This paper presents a geospatial big-data framework for integrating and analyzing multimodal urban mobility data from [...] Read more.

Urban mobility systems generate large volumes of heterogeneous geospatial data that differ in temporal resolution, spatial coverage, update frequency, and semantic structure, making integrated near-real-time analysis difficult. This paper presents a geospatial big-data framework for integrating and analyzing multimodal urban mobility data from the Norwegian transport ecosystem, including public transport, micromobility, road infrastructure, weather sensing, and civil aviation. The framework is implemented as a modular pipeline for data ingestion, source-specific normalization, temporal alignment, and analytical processing, enabling minute-level comparison across heterogeneous operational feeds. The proposed approach preserves source-level semantics while supporting unified spatiotemporal analysis across transport modes with different operational characteristics. The framework is evaluated through analytical scenarios focused on peak and off-peak mobility dynamics, weather-related multimodal variability, and spatial autocorrelation of public transport activity and delay across four analysis windows and six Norwegian cities. The results show that mobility–weather relationships vary across transport modes and temporal windows, particularly in public transport activity, cycling behavior, and delay patterns, and that spatial clustering of public transport activity and delay is itself city- and window-dependent, with some cities showing strong, stable clustering and others showing none. The findings indicate that multimodal urban mobility should be interpreted as a context-dependent and interconnected spatiotemporal system rather than through isolated modal indicators. The study demonstrates how geospatial big-data integration can support near-real-time urban mobility monitoring and operational analytics in smart-city environments. Full article

(This article belongs to the Special Issue Innovative Mobility Services for Smart Cities)

► Show Figures

Figure 1

22 pages, 13031 KB

Open AccessArticle

Uncertainty Reduction in Flood Susceptibility Mapping: Integrating Information Value Model and Machine Learning in the Yellow River Basin

by Jiahan Li, Huilin Yang, Rui Yao, Guodong Qu, Ran Gu, Yayi Zhang and Peng Sun

ISPRS Int. J. Geo-Inf. 2026, 15(8), 373; https://doi.org/10.3390/ijgi15080373 - 19 Aug 2026

Viewed by 205

Abstract

Flood susceptibility mapping in the Yellow River Basin remains challenging due to uncertainties in sample selection and model generalization. This study develops a novel two-step coupling framework that integrates an information value (IV) model with machine learning (ML) to improve reliability. The IV [...] Read more.

Flood susceptibility mapping in the Yellow River Basin remains challenging due to uncertainties in sample selection and model generalization. This study develops a novel two-step coupling framework that integrates an information value (IV) model with machine learning (ML) to improve reliability. The IV model first identifies stable low-susceptibility zones to select robust non-flood samples, which are then combined with historical flood inventories to train ML models. The SHAP method is applied to quantify factor contributions and interpret outputs. The results show that the IV-RF model achieves the highest predictive performance, while a stacking ensemble further reduces uncertainty. Sensitivity analyses confirm that model outcomes remain stable across random data splits and repeated non-flood point selections. High-risk areas are primarily located in the Hetao Plain, the Weihe River Basin, and sections of the lower Yellow River Basin, where susceptibility is driven by drainage density, anthropogenic and urban–mining soils, a high topographic wetness index, and gentle slopes. This work provides a transferable methodology that enhances physically consistent sample selection and model interpretability for flood risk assessment. 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

15 pages, 1646 KB

Open AccessArticle

TARA: Task-Adaptive Rank Allocation for Efficient Large Language Model Fine-Tuning in Geo-Information Text Classification

by Canhui Wang, Juntao Shen, Yicong Feng, Jin Huang, Yanwu Jing, Weiwei Chen, Wanqiang Zhang and Min Wang

ISPRS Int. J. Geo-Inf. 2026, 15(8), 372; https://doi.org/10.3390/ijgi15080372 - 18 Aug 2026

Viewed by 246

Abstract

Geo-information texts, including geospatial data-use regulations and Earth observation metadata, are central to data governance and compliance auditing in remote sensing ecosystems. Full fine-tuning of large pre-trained language models is often computationally impractical, while standard LoRA reduces cost but assigns a fixed rank [...] Read more.

Geo-information texts, including geospatial data-use regulations and Earth observation metadata, are central to data governance and compliance auditing in remote sensing ecosystems. Full fine-tuning of large pre-trained language models is often computationally impractical, while standard LoRA reduces cost but assigns a fixed rank to all adapted modules, ignoring differences across layers and projection types. This paper proposes TARA, a task-adaptive rank allocation method for LoRA-based fine-tuning. TARA assigns learnable importance scores to rank dimensions and uses Gumbel–Sigmoid sampling with the Straight-Through Estimator to learn discrete rank masks under a global sparsity constraint. We further construct RSRegulation, a geospatial regulatory compliance benchmark containing 4032 English-language samples derived from 168 clauses across seven regulatory and policy sources with clause-level data isolation. Across five random seeds, TARA achieves 95.30 ± 0.10% accuracy and 95.44 ± 0.10% F1 with a maximum trainable adapter budget of 1.57 M parameters. The learned soft allocation corresponds to approximately 0.38 M effective adapter parameters and 75.8% soft rank compression. Physical hard pruning reduces the deployed adapter to 0.086 M parameters while retaining 95.12 ± 0.11% accuracy and 95.21 ± 0.10% F1. Layer-wise analysis shows that value projections retain higher ranks than query projections under the current task and backbone, revealing a task-dependent non-uniform allocation pattern. Full article

► Show Figures

Figure 1

31 pages, 19287 KB

Open AccessArticle

Simulating Sustainable County-Level Land Use by Integrating the Mechanical Equilibrium Model with the Multi-Objective Genetic Algorithm

by Yuan Meng, Long Zhou, Mahyar Arefi and Guoqiang Shen

ISPRS Int. J. Geo-Inf. 2026, 15(8), 371; https://doi.org/10.3390/ijgi15080371 - 17 Aug 2026

Viewed by 225

Abstract

Multifunctional land use has gained increasing attention for reconciling societal (life function), economic (production function), and environmental (ecological function) development needs and addressing sustainable land use challenges in rapidly urbanizing regions. Consistent with mainstream international land use functions (LUFs), this study’s production-living-ecological (PLE) [...] Read more.

Multifunctional land use has gained increasing attention for reconciling societal (life function), economic (production function), and environmental (ecological function) development needs and addressing sustainable land use challenges in rapidly urbanizing regions. Consistent with mainstream international land use functions (LUFs), this study’s production-living-ecological (PLE) framework covers three key land functions, matching global research paradigms. To develop a sustainable county-level land use quantitative structure optimization model, this study innovatively integrates a mechanical equilibrium model with the multi-objective genetic algorithm (NSGA-II), overcoming the limitations of conventional qualitative production-living-ecological spaces (PLES) optimization. Furthermore, by establishing a mapping relationship between urbanization drivers and PLES functional evolution, it also enables structural optimization across urbanization subsystems. The optimization results indicate the following adjustment directions: southern coastal and southwestern counties require targeted population and socioeconomic urbanization improvements, while northern counties demand differentiated ecological urbanization regulation, and southeastern coastal areas should prioritize ecological protection. Most counties exhibit cropland and construction land expansion alongside woodland shrinkage, featuring expanded production and living spaces but contracted ecological functions. In contrast, certain counties achieve coordinated sustainability by eliminating inefficient construction land. This study operationalizes macroscopic PLE coordination into feasible quantitative strategies, enriching optimization methodologies and providing transferable insights for territorial spatial governance. Full article

(This article belongs to the Special Issue Novel Theories and Applications on Geo-Spatial Databases, Models and AI in Urban Science, Planning, Development and Governance)

► Show Figures

Figure 1

28 pages, 2752 KB

Open AccessArticle

CGD-QCSF: A Code Generation-Driven Query–Computation Separation Framework for Natural Language Geospatial Analysis

by Zhiyuan Le, Hao Li, Yuanxun Mei, Miaomiao Ren, Haizhen Chen, Yinying Zhou and Lu Li

ISPRS Int. J. Geo-Inf. 2026, 15(8), 370; https://doi.org/10.3390/ijgi15080370 - 16 Aug 2026

Viewed by 305

Abstract

Geospatial data provide an important basis for urban governance, resource management, disaster assessment, and public health analysis by linking spatial locations, attribute information, and dynamic processes. However, complex geospatial analysis still requires substantial expertise in spatial databases, spatial SQL, and GIS computation tools. [...] Read more.

Geospatial data provide an important basis for urban governance, resource management, disaster assessment, and public health analysis by linking spatial locations, attribute information, and dynamic processes. However, complex geospatial analysis still requires substantial expertise in spatial databases, spatial SQL, and GIS computation tools. Although large language model-based Text-to-SQL methods have lowered the barrier to natural language-driven data querying, most existing approaches rely on single-step SQL generation and remain unstable for spatial tasks that involve attribute retrieval, spatial relationship evaluation, geometric operations, and statistical aggregation. To address this limitation, this paper proposes a Code Generation-Driven Query–Computation Separation Framework (CGD-QCSF). The framework is based on the separation of query and computation, and decomposes complex geospatial analysis into a staged execution process. CGD-QCSF coordinates intent understanding, schema pre-filtering, planning, execution state management, SQL generation, and spatiotemporal computation. A structured planner and an execution state manager coordinate task decomposition, capability-aware routing, and evidence-based recovery. A SQL Code Generation Agent (SCGA) handles database access, attribute filtering, and intermediate data extraction, while a Spatiotemporal Computation Agent (STCA) performs out-of-database spatial computation and statistical aggregation in an isolated Python sandbox. We construct a benchmark of 200 tasks, covering easy, medium, and hard spatial tasks. In the main experiment with Qwen3.7-Plus as the foundation model, CGD-QCSF achieves a Strict Structured Accuracy (SSA) of 90.5%. Removing the Planner reduces SSA to 84.5%, while removing the STCA reduces it to 70.5%. The ablation experiments show that removing either the Python sandbox or the Planner Agent degrades performance on complex tasks. These results indicate that CGD-QCSF extends complex geospatial analysis from single-step SQL generation into a multi-staged execution process. By explicitly separating query and computation, the framework reduces interference between spatial computation logic and database schema information, thereby improving the stability and success rate of natural language-driven geospatial analysis. Full article

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

► Show Figures

Figure 1

24 pages, 55593 KB

Open AccessArticle

Color Palette Identification and Intelligent Knowledge Extraction for Natural Disaster Mapping

by Weiyao Guo, An Zhang and Yi Cao

ISPRS Int. J. Geo-Inf. 2026, 15(8), 369; https://doi.org/10.3390/ijgi15080369 - 16 Aug 2026

Viewed by 271

Abstract

Natural disaster emergency cartography requires high semantic accuracy in color design and efficient visual communication. However, existing studies still lack systematic palette analysis and knowledge organization methods based on real-world emergency maps. To address this gap, this study proposes a framework for palette [...] Read more.

Natural disaster emergency cartography requires high semantic accuracy in color design and efficient visual communication. However, existing studies still lack systematic palette analysis and knowledge organization methods based on real-world emergency maps. To address this gap, this study proposes a framework for palette analysis and knowledge organization that uses publicly available Emergency Response Coordination Centre (ERCC)’s emergency maps as the primary data source. The framework extracts disaster types and thematic mapping indicators. It performs palette identification, matching, and statistical analysis using color information from legend regions in the RGB, HSV, and CIELab color spaces, together with the ColorBrewer palette system. Based on the statistical matching results, we constructed a structured knowledge graph that links disaster types, thematic mapping indicators, and palettes, enabling organized retrieval of palette knowledge. Results show that color extraction from legend regions effectively reduces interference from non-thematic elements and improves the accuracy of palette identification. In addition, palette usage in ERCC emergency maps exhibits clear statistical associations and shared and differentiated patterns, indicating stable yet non-unique associations among disaster themes, thematic mapping indicators, and color palettes. The proposed knowledge graph provides a structured framework for organizing palette knowledge and analyzing semantic relationships in ERCC emergency cartography. Full article

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

► Show Figures

Figure 1

27 pages, 7061 KB

Open AccessArticle

Spatiotemporal Differentiation and Cross-Scale Correlates of Tourist Perception in Mountain-Type and Rural Comprehensive Destinations: VGI Evidence from Shangrao, China

by Zongrong Liu and Yu Xia

ISPRS Int. J. Geo-Inf. 2026, 15(8), 368; https://doi.org/10.3390/ijgi15080368 - 15 Aug 2026

Viewed by 315

Abstract

As tourism shifts from sightseeing to experience-oriented consumption, understanding how tourist perception differs across heterogeneous destination types and spatial scales remains challenging. Using 23,439 Volunteered Geographic Information (VGI) reviews archived for six destinations in Shangrao, China, this study compares mountain-type and rural comprehensive [...] Read more.

As tourism shifts from sightseeing to experience-oriented consumption, understanding how tourist perception differs across heterogeneous destination types and spatial scales remains challenging. Using 23,439 Volunteered Geographic Information (VGI) reviews archived for six destinations in Shangrao, China, this study compares mountain-type and rural comprehensive destination products. These are operational dominant-function categories rather than mutually exclusive geomorphological classes. The archive supports fine-grained sentiment, topic, and semantic-network analyses; annual temporal comparisons use the full 23,439-review corpus covering 2019–2025, whereas a separate subset of reviews posted from 1 August 2022 with official IP labels, aggregated into 2022–2024 province–year observations, supports Pooled Ordinary Least Squares (Pooled OLS) estimation. A hybrid lexicon–XLM-RoBERTa workflow, BERTopic, semantic co-occurrence analysis, and Pooled OLS are integrated in a cross-scale framework. Static results reveal shared strengths and weaknesses—high scenery and overall-experience evaluations but low price evaluations—alongside type-specific structures: mountain reviews concentrate on natural scenery, climbing effort, and accessibility, whereas rural reviews span village landscapes, cultural activities, accommodation, and nighttime experiences. Temporally, mountain demand retains a stable scenic core while accessibility concerns become more salient; rural demand shifts from traditional agricultural landscapes toward nighttime performances and other experience-oriented products. Cross-scale regressions identify destination- and dimension-specific correlates rather than causal drivers: urbanization is positively associated with several rural evaluations, while ecological contrast, climatic difference, and competing scenic resources are associated with more critical assessments in selected dimensions. The findings show that perception differences arise from the interaction of destination product structures and origin-region contexts, supporting differentiated accessibility management for mountain destinations and balanced product innovation, service improvement, and commercialization control for rural destinations. Full article

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

► Show Figures

Figure 1

31 pages, 15025 KB

Open AccessFeature PaperArticle

Effects of Low-Altitude Urban Landscapes on Pilot Cognitive Load in Urban Air Mobility: An Explainable Machine Learning Approach

by Yupeng Jiang, Jie Song, Yukun Jiang, Yu Liu, Chengfeng Cai, Bolun Li and Bingchen Gou

ISPRS Int. J. Geo-Inf. 2026, 15(8), 367; https://doi.org/10.3390/ijgi15080367 - 14 Aug 2026

Viewed by 248

Abstract

Whereas environmental effects on driver cognition have been extensively studied in ground transportation, research linking low-altitude visual environment characteristics to pilot cognitive load (CL) in urban air mobility (UAM) remains scarce. This study combines multimodal physiological data with explainable machine learning to elucidate [...] Read more.

Whereas environmental effects on driver cognition have been extensively studied in ground transportation, research linking low-altitude visual environment characteristics to pilot cognitive load (CL) in urban air mobility (UAM) remains scarce. This study combines multimodal physiological data with explainable machine learning to elucidate how low-altitude visual environments influence pilots’ CL. First, a CL quantification framework integrating electroencephalography (EEG) and eye-tracking data is developed to capture real-time cognitive dynamics during flight. Second, multidimensional visual environment indicators are extracted from low-altitude urban landscape images captured during simulated flights using computer vision techniques. These indicators, combined with flight dynamics features, serve as input variables for constructing pilot CL prediction models via machine learning approaches. The results demonstrate that a Bayesian-optimized XGBoost model achieves superior predictive performance. Further interpretability analysis based on SHAP reveals that environmental contrast and the visibility of buildings and water bodies are key factors influencing pilot CL. Additionally, significant interaction effects are also identified among spatial morphology, color characteristics, and landscape typology, with certain landscape elements exhibiting marked variations in both importance and directional influence across different low-altitude flight scenarios. These findings inform low-altitude route optimization, urban morphological regulation, and blue-green infrastructure configuration, advancing an air-ground synergistic planning paradigm. Full article

(This article belongs to the Special Issue Innovative Mobility Services for Smart Cities)

► Show Figures

Figure 1

34 pages, 28222 KB

Open AccessArticle

Geoinformation-Based Simulation of Policy-Oriented Land-Use Scenarios for SDG-Oriented Spatial Planning in a Resource-Depleted City: Evidence from Huangshi, China

by Zirui Zhan and Suhui Zhang

ISPRS Int. J. Geo-Inf. 2026, 15(8), 366; https://doi.org/10.3390/ijgi15080366 - 14 Aug 2026

Viewed by 244

Abstract

Rapid urban development has intensified conflicts between land development and ecological conservation, making spatially explicit land-use planning increasingly important for resource-depleted cities. This study develops a geoinformation-based decision-support framework for Huangshi, China, by integrating multi-scenario land-use modeling, production–living–ecological space analysis, landscape pattern assessment, [...] Read more.

Rapid urban development has intensified conflicts between land development and ecological conservation, making spatially explicit land-use planning increasingly important for resource-depleted cities. This study develops a geoinformation-based decision-support framework for Huangshi, China, by integrating multi-scenario land-use modeling, production–living–ecological space analysis, landscape pattern assessment, and SDG 15 diagnostics. Four 2035 policy-oriented scenarios were compared: Business-as-Usual (BAU), Ecological Restoration Priority (ERP), Economic Development Priority (EDP), and Sustainable Development (SD). The results show that ERP delivers the strongest ecological performance, with ecological space reaching 46.47%, forest cover increasing from 35.40% to 36.80%, water area rising to 9.65%, net land degradation declining to −2.04%, and mean habitat quality reaching 0.484. SD provides a more balanced pathway, with ecological space of 44.80%, living space of 8.93%, a land-use stability rate of 96.36%, and a relatively low net degradation rate of 1.33%. BAU and EDP show higher ecological risks. The framework demonstrates how multi-source geospatial data and spatially explicit SDG diagnostics can support adaptive planning in resource-depleted cities. Full article

► Show Figures

Figure 1

27 pages, 3687 KB

Open AccessArticle

A Cloud-Native Python GIS Framework for Flood Susceptibility Screening and Critical Facility Exposure Analysis: A Reproducible Methodological Demonstration for Miami, Florida

by Princewill Odum and Zirui Wang

ISPRS Int. J. Geo-Inf. 2026, 15(8), 365; https://doi.org/10.3390/ijgi15080365 - 13 Aug 2026

Viewed by 348

Abstract

Urban coastal cities face compounded flood hazards driven by sea-level rise, intense precipitation, and dense impervious surfaces. This study develops and demonstrates a cloud-native Python 3.12 GIS framework for flood susceptibility screening and critical facility exposure analysis in Miami, Florida, one of the [...] Read more.

Urban coastal cities face compounded flood hazards driven by sea-level rise, intense precipitation, and dense impervious surfaces. This study develops and demonstrates a cloud-native Python 3.12 GIS framework for flood susceptibility screening and critical facility exposure analysis in Miami, Florida, one of the most flood-exposed coastal cities in the United States. Defined here as a geospatial workflow that retrieves data dynamically from cloud-hosted APIs and executes entirely within a hosted computing environment, the framework integrates three open-source spatial indicators: terrain elevation from the USGS 3D Elevation Programme via py3dep; Euclidean distance to water bodies from OpenStreetMap via OSMnx; and building footprint density as an impervious surface proxy, also from OpenStreetMap. Indicators were standardised and combined using literature-informed MCDA weights (water proximity: 0.40; elevation: 0.35; building density: 0.25) into a continuous flood susceptibility index, classified at the 33rd- and 66th-percentile thresholds. In this proof-of-concept application, high-susceptibility zones cover 48.66 km² (34.0%) of the city, concentrated along coastal waterfronts and inland canal corridors. Overlaying critical facility locations on the classified surface indicates that 9 of 16 hospitals (56.2%), 61 of 244 schools (25.0%), and 5 of 17 fire stations (29.4%) fall within high-susceptibility zones; because this overlay uses centroid-based facility points that have not been cross-checked against official municipal or state facility registries, these counts should be read as indicative rather than definitive. Exact binomial testing shows that the school exposure deficit is statistically significant (p = 0.00), while elevated hospital exposure, although substantively notable, does not reach significance at the current sample size (p = 0.07). The susceptibility surface itself has not been quantitatively validated against external benchmarks such as FEMA flood maps or historical inundation records, the MCDA weights have not been sensitivity-tested, and spatial autocorrelation in the index has not been assessed; concrete protocols for each of these steps are specified as subsequent calibration work rather than as prerequisites for the architecture demonstrated here. The contribution of this paper is the reproducible, cloud-native workflow architecture and its proof-of-concept application, not a validated operational assessment tool; we present it explicitly as a methodological protocol and workflow demonstration, not as an evaluation of flood risk. The framework is fully reproducible, low-cost, and transferable to other US coastal cities. Full article

(This article belongs to the Topic Applications of Algorithms in Risk Assessment and Evaluation)

► Show Figures

Figure 1

22 pages, 8530 KB

Open AccessArticle

Trajectory Recovery via Global Spatial Dependencies and Local Multi-Factor Semantics

by Cheng Jin, Daozhu Xu and Xinlei Zhang

ISPRS Int. J. Geo-Inf. 2026, 15(8), 364; https://doi.org/10.3390/ijgi15080364 - 13 Aug 2026

Viewed by 316

Abstract

Trajectory data may suffer from missing locations due to environmental and equipment constraints, which impact the performance of downstream tasks. Trajectory recovery aims to enhance the utility of mobility data by reconstructing high-quality trajectories. However, existing methods face two significant limitations. First, most [...] Read more.

Trajectory data may suffer from missing locations due to environmental and equipment constraints, which impact the performance of downstream tasks. Trajectory recovery aims to enhance the utility of mobility data by reconstructing high-quality trajectories. However, existing methods face two significant limitations. First, most existing methods rely on individual historical trajectories, making it difficult to exploit global spatial dependencies across the population. Second, current approaches ignore the role of local multi-factor semantics in personalized trajectory recovery. To address the above challenges, we propose a joint trajectory recovery method named GLTrajRec, which integrates global spatial dependencies and local multi-factor semantics. Specifically, global trajectory flow graph modeling is proposed to capture shared mobility patterns from all users’ trajectories, which can provide effective spatial transition constraints even when individual historical data is insufficient. Then, multi-factor local semantics embedding is designed to comprehensively encode multi-dimensional personalized mobility information from multiple aspects, enabling more accurate personalized recovery results. In addition, a Transformer-based encoder–decoder framework is developed to bidirectionally encode the embedded global dependencies and local semantics and to decode multi-class information. Finally, we construct a transition matrix based on the global trajectory flow graph to improve the accuracy of the recovery output. Extensive experiments conducted on two real-world datasets demonstrate that the proposed method achieves mean average precision (MAP) scores of 0.7181 and 0.7345, respectively, representing an improvement of approximately 5% to 7% over traditional trajectory recovery methods. Full article

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

► Show Figures

Figure 1

22 pages, 10177 KB

Open AccessArticle

A Visual-Attention-Driven Framework for Quantifying Wayfinding Cue Strength for Pedestrians in Urban Scenes: A Pilot Study of Older Adults in Hong Kong

by Yijia Liu, Wenzhong Shi, Shuyu Zhang, Anshu Zhang and Linya Peng

ISPRS Int. J. Geo-Inf. 2026, 15(8), 363; https://doi.org/10.3390/ijgi15080363 - 12 Aug 2026

Viewed by 280

Abstract

In urban environments, wayfinding is a fundamental task through which individuals access essential services. Quantifying the strength of perceived cues that facilitate wayfinding can inform urban design interventions aimed at reducing potential wayfinding difficulties. This study develops a visual-attention-driven computational framework to measure [...] Read more.

In urban environments, wayfinding is a fundamental task through which individuals access essential services. Quantifying the strength of perceived cues that facilitate wayfinding can inform urban design interventions aimed at reducing potential wayfinding difficulties. This study develops a visual-attention-driven computational framework to measure such cue strength from street-view images. In implementation, the framework adopts an image-inpainting-based strategy and incorporates a task-specific eye-tracking fine-tuning procedure to improve the strength of visual saliency extraction. A POI-based cognitive weighting scheme is then introduced to integrate the extracted visual values with cognitive information into a composite measure of wayfinding cue strength. Due to the lack of available data, a self-collected dataset integrating eye-tracking data from older adults, cognitive data, and ground-truth annotations for 30 intersections in Hong Kong was constructed to evaluate the framework and provide a data foundation for future work. The results revealed a significant positive correlation between the computed scores and the mean human ratings on a 1–5 Likert scale, while the linear regression model yielded an

R^{2}

of 0.62, providing preliminary evidence for the effectiveness of the proposed computational framework. The findings suggest that the cognitive attributes of spatially extensive environmental entities, such as neighborhood parks, could be considered in future site-selection processes, as they may enhance pedestrians’ spatial understanding and thereby facilitate wayfinding. Full article

(This article belongs to the Special Issue Novel Theories and Applications on Geo-Spatial Databases, Models and AI in Urban Science, Planning, Development and Governance)

► Show Figures

Figure 1

23 pages, 17354 KB

Open AccessArticle

Reframing Historical GIS: From Tools and Infrastructure Toward Value-Oriented Knowledge Production

by Lijin Zhang and Changsong Wang

ISPRS Int. J. Geo-Inf. 2026, 15(8), 362; https://doi.org/10.3390/ijgi15080362 - 12 Aug 2026

Viewed by 518

Abstract

Historical geographic information systems (HGIS) have evolved from auxiliary tools for digitizing historical materials and displaying maps into infrastructural research environments that connect multidisciplinary forms of historical spatial knowledge production. Yet infrastructure alone does not fully capture the field’s value-oriented epistemic goals. Building [...] Read more.

Historical geographic information systems (HGIS) have evolved from auxiliary tools for digitizing historical materials and displaying maps into infrastructural research environments that connect multidisciplinary forms of historical spatial knowledge production. Yet infrastructure alone does not fully capture the field’s value-oriented epistemic goals. Building on existing research on HGIS and historical spatial data infrastructures (HSDIs), this integrative literature review proposes Historical Geomatics as an agenda-setting heuristic framework organized around the core question of how HGIS can restructure knowledge production in historical geography. It synthesizes the field’s knowledge traditions, workflows, analytical paradigms, and future directions. First, it clarifies that HGIS function across research traditions as a tool, a method, and an environment that can use HSDIs to organize heterogeneous historical materials. Second, it conceptualizes spatialization as a continuous workflow of spatial element recognition, geographic attribute assignment, standardized modeling, and validation and revision. Standardization and explicit uncertainty representation are treated as prerequisites for research quality, while platform-based and public HGISs extend the lifecycle of historical spatial data. Third, the review groups existing scholarship into four analytical paradigms: spatiotemporal reconstruction; urban morphology and spatial structure; networks, mobility, and social space; and place, landscape, and memory. Finally, it examines how geospatial artificial intelligence (GeoAI) is reshaping HGIS knowledge production and argues that Historical Geomatics may serve as an agenda-setting heuristic for the next stage of HGIS. The principal opportunities lie not in accumulating additional cases, but in strengthening HSDIs, improving multimodal automation, representing uncertainty explicitly, and rebalancing space and place, models and narratives, and technical efficiency and historical context. Full article

► Show Figures

Figure 1

22 pages, 786 KB

Open AccessArticle

Geographic Uncertainty in Multimodal Logistics and Supply Chain Management: A Systematic Literature Review

by Matthias Winter, Sarah Pfoser and Johannes Scholz

ISPRS Int. J. Geo-Inf. 2026, 15(8), 361; https://doi.org/10.3390/ijgi15080361 - 11 Aug 2026

Viewed by 385

Abstract

Geographic uncertainty is an underexplored but increasingly relevant dimension of uncertainty in multimodal logistics and supply chain management. This systematic literature review synthesizes research at the intersection of logistics, supply chain uncertainty, and geography, with particular attention to multimodal freight transportation. Based on [...] Read more.

Geographic uncertainty is an underexplored but increasingly relevant dimension of uncertainty in multimodal logistics and supply chain management. This systematic literature review synthesizes research at the intersection of logistics, supply chain uncertainty, and geography, with particular attention to multimodal freight transportation. Based on a PRISMA-guided search in Scopus and Web of Science, 38 peer-reviewed journal and conference articles were analyzed to examine how geographic uncertainty is conceptualized, modeled, and applied in the literature. This review shows that geographic uncertainty is predominantly represented through network-based structures, especially at the node and arc levels, rather than through continuous spatial representations. Transportation-, transshipment-, and demand-related uncertainty dominate the literature, while environmental and emission-related uncertainty remain comparatively scarce. With respect to the geographic dimension, most studies focus on individual locations and routes, whereas regions, countries, and climate- or policy-relevant spatial units are rarely considered. In addition, many models treat uncertainty homogeneously across space, limiting their ability to capture location-specific patterns. To address these gaps, this paper proposes a conceptual distinction between locational and distance-based geographic uncertainty, grounded in the notion of friction of distance. This review highlights conceptual, methodological, and empirical research gaps and provides a foundation for improved modeling and management of geographic uncertainty in logistics systems. Full article

► Show Figures

Figure 1

21 pages, 4292 KB

Open AccessArticle

Social Sensing and Geospatial Visual Analytics of Tourist Destination Image and Town-Scale Gravity

by Weixing Xu, Kangkang Gu, Jinxuan Li, Zhenyu Wang, Nuojun Wang, Xiaotong Ren, Jiehui Geng and Beibei Liu

ISPRS Int. J. Geo-Inf. 2026, 15(8), 360; https://doi.org/10.3390/ijgi15080360 - 11 Aug 2026

Viewed by 274

Abstract

Tourism has become a critical pathway for town construction, everyday-life improvement, and cultural revitalization. Yet, the mechanisms through which destination image is associated with town attraction remain insufficiently understood, particularly at the fine-grained town scale. Drawing on social media photographs and check-in records [...] Read more.

Tourism has become a critical pathway for town construction, everyday-life improvement, and cultural revitalization. Yet, the mechanisms through which destination image is associated with town attraction remain insufficiently understood, particularly at the fine-grained town scale. Drawing on social media photographs and check-in records from 26 characteristic towns in Tianjin, China, this study deconstructs tourist destination image into image genes and examines their associations with town gravity. A VGG19-based image-recognition model was used to identify and aggregate 68 scene types into nine image-gene categories, while check-in data from Weibo and Little Red Book were used to measure destination gravity. The results show that uniqueness image, cultural custom genes, public space genes, sidewalk density, and POI mix are significantly and positively associated with town gravity, whereas animal genes exhibit a significant negative association. These findings provide an empirical basis for policymakers and planners to strengthen distinctive cultural representation, optimize public-space systems and service diversity, and promote the sustainable attractiveness of town destinations. Full article

► Show Figures

Graphical abstract

18 pages, 34635 KB

Open AccessArticle

Temporally Weighted Land Surface Temperature: From Multiyear Observations to a Target-Year-Referenced Thermal Surface

by Jiahui Qin, Qianxin Wang, Xinyu Dong, Suqin Wu and Angela Lausch

ISPRS Int. J. Geo-Inf. 2026, 15(8), 359; https://doi.org/10.3390/ijgi15080359 - 10 Aug 2026

Viewed by 428

Abstract

Accurate characterization of land surface temperature (LST) is essential for urban thermal environment analysis. However, commonly used LST representations have their inherent limitations. For example, single-year LST may be influenced by year-specific anomalies, whereas multiyear means may obscure recent changes. Neither representation addresses [...] Read more.

Accurate characterization of land surface temperature (LST) is essential for urban thermal environment analysis. However, commonly used LST representations have their inherent limitations. For example, single-year LST may be influenced by year-specific anomalies, whereas multiyear means may obscure recent changes. Neither representation addresses how relevance to the target year and persistent historical information can be balanced within a single spatial LST surface. This study therefore proposes a temporally weighted land surface temperature (TWLST) method, which uses temporal decay weights and a half-life parameter to achieve the above balance and produce a continuous LST surface for spatial analysis. The framework was applied at regional and city scales in the Beijing–Tianjin–Hebei region and Beijing city, respectively, to examine its applicability. Spatial overlap between TWLST high-temperature (HT) areas and reference LST HT areas ranged from 0.577 to 0.733 and from 0.666 to 0.863 in the two applications. Historical annual LST anomalies were higher in TWLST-specific HT areas than in target-year-specific HT areas, with median paired differences of 1.16 °C and 2.49 °C, respectively. These results indicated that TWLST preferentially identified persistently warm locations while preserving major high-temperature patterns. The modeling and interpretation analyses further indicated that changes in LST representation could influence model performance and the relative importance of explanatory variables. Full article

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

► Show Figures

Figure 1

43 pages, 24447 KB

Open AccessArticle

An Intelligent Incremental Update Method for Building Data Across Multiple Scales Supported by Categorical Boosting

by Xinyu Niu, Haizhong Qian, Xiao Wang, Limin Xie, Xianyong Gong, Chengyi Liu and Jinghan Li

ISPRS Int. J. Geo-Inf. 2026, 15(8), 358; https://doi.org/10.3390/ijgi15080358 - 9 Aug 2026

Viewed by 344

Abstract

Leveraging larger-scale data with higher currency to incrementally update smaller-scale data, thereby upholding consistency across multiple scale databases, has become a core focus of contemporary map production tasks centered on data updates. Existing methods rely on rule-based constraints to extract change information and [...] Read more.

Leveraging larger-scale data with higher currency to incrementally update smaller-scale data, thereby upholding consistency across multiple scale databases, has become a core focus of contemporary map production tasks centered on data updates. Existing methods rely on rule-based constraints to extract change information and identify update-required objects, which have notable limitations in terms of method generalization and constraints on results. To address the above issues, we propose an intelligent incremental updating method for different scale building datasets supported by Categorical Boosting (CatBoost). The proposed method forms a general incremental updating framework for buildings through three steps: change information extraction, change information classification, and change information updating. Experiments conducted on different scale datasets from Ningbo, China, demonstrate that the proposed method can effectively identify update-required objects and generate more reasonable updated smaller-scale data than the comparative methods. Full article

► Show Figures

Figure 1

30 pages, 4646 KB

Open AccessArticle

3D-Geo-Vis: A Web-Based Environment for Interactive 3D Thematic Geovisualisation and Its Usability Evaluation

by Jakub Zejdlik, Tomas Vanicek and Vit Vozenilek

ISPRS Int. J. Geo-Inf. 2026, 15(8), 357; https://doi.org/10.3390/ijgi15080357 - 8 Aug 2026

Viewed by 575

Abstract

3D geovisualisation is increasingly used to represent spatial phenomena in engaging and interactive ways. However, 3D thematic methods and their user-centred evaluation remain challenging due to issues such as view distortion, variable scale, and complex interactions. Previous research emphasises that effective 3D thematic [...] Read more.

3D geovisualisation is increasingly used to represent spatial phenomena in engaging and interactive ways. However, 3D thematic methods and their user-centred evaluation remain challenging due to issues such as view distortion, variable scale, and complex interactions. Previous research emphasises that effective 3D thematic design requires careful treatment of visual variables and interactive camera control to mitigate overlap and occlusion. Building on this foundation, we present 3D-Geo-Vis, a web-based application with open-source code. The application visualises air temperature using seven methods of 3D geovisualisation and supports real-time adjustment of method-specific visual variables through a dedicated side panel. We report a usability study with 54 participants that combines (i) eye-tracking (Tobii Pro Spark, 60 Hz), (ii) interaction logging using our MapLogger tool, and (iii) a post-test questionnaire including the User Experience Questionnaire (UEQ) and open-ended feedback. Participants completed a structured scenario comprising free exploration and targeted analytical tasks. Across all sessions, MapLogger captured 15,457 interactions. The success rate of fully completed tasks was generally high for tasks involving the search for a specific value or modification of interface parameters (Task 2: 87.0%; Task 3: 85.2%), while the voxel-based analytical task showed slightly lower completion (Task 4: 77.8%), reflecting higher cognitive and interaction demands. UEQ results indicate a slightly positive overall user experience, with speed-related items rated most negatively. Triangulating gaze behaviour, interaction logs, and subjective feedback reveals key usability issues (e.g., insufficient salience of method switching, attention concentration on the side panel, and performance limitations of voxel rendering) and yields concrete recommendations for improving onboarding, feedback, and control discoverability in interactive 3D visualisation environments. These findings and resulting recommendations informed the development of the revised 3D-Geo-Vis 2.0 application. Full article

► Show Figures

Figure 1

13 pages, 727 KB

Open AccessArticle

Controllable Spatio-Temporal Modeling of Pedestrian Spawn Dynamics for Urban Crowd Geosimulation

by Yan Lyu, Bo Ling, Weiwei Wu, Xiangxiang Xing and Peng Wang

ISPRS Int. J. Geo-Inf. 2026, 15(8), 356; https://doi.org/10.3390/ijgi15080356 - 7 Aug 2026

Viewed by 301

Abstract

Realistic modeling of pedestrian flow in dense public spaces is important for urban crowd geosimulation, mobility analysis, and indoor public-space geo-information modeling. Although prior research has emphasized microscopic agent interactions, higher-level spawn dynamics—governing when and where pedestrians appear—remain less explored, despite their fundamental [...] Read more.

Realistic modeling of pedestrian flow in dense public spaces is important for urban crowd geosimulation, mobility analysis, and indoor public-space geo-information modeling. Although prior research has emphasized microscopic agent interactions, higher-level spawn dynamics—governing when and where pedestrians appear—remain less explored, despite their fundamental role in shaping crowd density and flow. Existing approaches often decouple spatial and temporal generation, limiting their ability to capture rich spatio-temporal correlations, and they lack controllability for user-specific scenarios such as high-density environments. In this paper, we propose a Guided Joint Spatio-Temporal Diffusion framework for pedestrian spawn simulation. Our objective is to develop and evaluate a controllable joint spatio-temporal generative model that produces each pedestrian spawn event—its inter-arrival time, origin, and destination—consistent with observed spawn dynamics and a user-specified normalized local spawn-intensity condition. The model addresses the upstream initialization of a crowd simulation, rather than complete trajectory prediction or microscopic interaction simulation, and is evaluated through both next-event accuracy and fixed-horizon controllability. The method leverages spatio-temporal diffusion point processes to jointly model spatial and temporal spawn events, capturing dependencies overlooked by classical and neural point-process-based methods. To support controllable pedestrian-flow generation for geosimulation and downstream applications, we integrate a conditional denoising network with classifier-free guidance, enabling user-specified factors such as crowd density to steer generation. Experiments on the Grand Central dataset demonstrate that our method outperforms strong baselines, reducing temporal error (T-RMSE) by 38% and achieving consistent improvements in spatial and spatio-temporal accuracy. These results show the potential of diffusion-based spatio-temporal modeling for controllable urban crowd geosimulation and pedestrian mobility data generation. Full article

► Show Figures

Figure 1

24 pages, 1817 KB

Open AccessArticle

Spatial Methods for Identifying Undocumented Historical Earthquake Damage

by Adi Ofir and Motti Zohar

ISPRS Int. J. Geo-Inf. 2026, 15(8), 355; https://doi.org/10.3390/ijgi15080355 - 6 Aug 2026

Viewed by 509

Abstract

Historical earthquake records are inherently incomplete: many sites that were likely damaged were never documented, leaving spatial gaps in the macroseismic record. This study evaluates whether intensity values at unreported sites can be estimated from the spatial relationships of surrounding reports, framing the [...] Read more.

Historical earthquake records are inherently incomplete: many sites that were likely damaged were never documented, leaving spatial gaps in the macroseismic record. This study evaluates whether intensity values at unreported sites can be estimated from the spatial relationships of surrounding reports, framing the task as a spatial data imputation problem. Three spatial imputation methods, Linear regression, K-Nearest Neighbors (KNN), and Kriging, were applied to eight macroseismic datasets, comprising two historical Dead Sea Transform earthquakes (1927 Dead Sea, 1837 South Lebanon) and six instrumental events from major strike-slip fault systems. Model performance was assessed with 5-fold cross-validation under random and spatial-block designs, using Mean Squared Error (MSE) and success rate, defined as the percentage of predictions falling within ±0.5 and ±1.0 intensity units of observed values. Under random cross-validation, simple and locally focused models performed on par with the complex geostatistical approaches. For the geographically concentrated historical data, success rates reached up to 90% within ±1.0 intensity units. San Andreas events yielded the strongest results among instrumental datasets, while Caribbean events showed the weakest performance due to spatial reporting biases. Under spatial-block cross-validation, performance declined across all models, with linear regression and Universal Kriging proving most robust to spatial extrapolation. These findings provide a methodological basis for estimating intensity at undocumented sites. While continuous intensity mapping from sparse data remains inadvisable, point-based imputation offers a practical tool for enriching historical earthquake records, with direct implications for seismic research along poorly documented fault systems. 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

28 pages, 8709 KB

Open AccessArticle

Causal–Semantic Spatiotemporal Traffic Flow Forecasting for Expressway UAV Pre-Deployment Using ETC Gantry Networks

by Zeen Yang, Zhuoer Wang, Hongjuan Zhang and Bijun Li

ISPRS Int. J. Geo-Inf. 2026, 15(8), 354; https://doi.org/10.3390/ijgi15080354 - 6 Aug 2026

Viewed by 402

Abstract

Expressway unmanned aerial vehicle (UAV) pre-deployment is a geospatial decision-support task that requires reliable road-segment-level traffic flow prediction based on spatial sensing networks. However, existing spatiotemporal forecasting models remain limited in characterizing cross-segment propagation relationships, long-lag causal dependencies, and atypical traffic evolution patterns. [...] Read more.

Expressway unmanned aerial vehicle (UAV) pre-deployment is a geospatial decision-support task that requires reliable road-segment-level traffic flow prediction based on spatial sensing networks. However, existing spatiotemporal forecasting models remain limited in characterizing cross-segment propagation relationships, long-lag causal dependencies, and atypical traffic evolution patterns. In addition, complex models often fail to meet the computational requirements of edge-device deployment. Based on electronic toll collection (ETC) gantry data, this study proposes a causal–semantic spatiotemporal forecasting framework for long-term traffic flow prediction with a 24 h forecasting horizon. First, conditional Granger causality analysis is used to construct a directed causal prior graph that characterizes traffic propagation relationships among expressway segments. Second, scenario-semantic priors generated by a large language model are introduced to describe atypical traffic conditions. Then, causal structural priors and scenario-semantic priors are integrated into a teacher model and transferred to a lightweight student model through response-level and feature-level knowledge distillation. Experiments using expressway data from Hubei Province, China, show that the proposed model achieves the best overall performance in the typical scenario and competitive performance in the atypical scenario. The results indicate that the proposed framework can provide day-scale decision support for expressway law-enforcement UAV pre-deployment and enhance the spatial intelligence of traffic emergency management. Full article

(This article belongs to the Topic Digital and Intelligent Technologies and Application in Urban Construction, Operation, Maintenance, and Renewal)

► Show Figures

Figure 1

28 pages, 44648 KB

Open AccessArticle

A Terrain-Factor-Constrained GAN Model for Feature Preservation in DEM Downscaling

by Yanchen Wan, Haowen Jiang, Wenping Jiang, Yue Wang and Xinyue Lyu

ISPRS Int. J. Geo-Inf. 2026, 15(8), 353; https://doi.org/10.3390/ijgi15080353 - 4 Aug 2026

Viewed by 382

Abstract

Geographic information generalization underpins multi-scale spatial databases and cartography, and reliable DEM downscaling is critical to maintaining geomorphological consistency across map scales. Traditional DEM simplification and resampling methods rely on local geometric filtering and overlook global terrain structures, frequently causing structural distortions such [...] Read more.

Geographic information generalization underpins multi-scale spatial databases and cartography, and reliable DEM downscaling is critical to maintaining geomorphological consistency across map scales. Traditional DEM simplification and resampling methods rely on local geometric filtering and overlook global terrain structures, frequently causing structural distortions such as broken ridges and deformed slopes. This study proposes DD-GAN, a generative adversarial network constrained by terrain morphological factors for high-fidelity DEM downscaling. Built on a GAN architecture, the model embeds local relief and gradient as physical loss terms to prioritize major geomorphic skeletons and suppress trivial micro-terrain during resolution reduction, avoiding the indiscriminate over-smoothing of conventional sampling approaches. Multi-scale experiments covering downscaling factors ranging from 2× to 5× are conducted using mountainous datasets from Chongqing, Alaska, and Colorado. Quantitative and visual comparisons against raster interpolation, TIN-based simplification, and ordinary CNN show that DD-GAN mitigates terrain structural distortion and better retains elevation extremes and slope features, with more prominent strengths under large downscaling multiples. This physics-constrained deep learning paradigm provides an automated DEM downscaling solution that facilitates multi-scale terrain representation, supporting cartographic production and geomorphometric analysis. Full article

► Show Figures

Figure 1

30 pages, 4494 KB

Open AccessArticle

From Spatial Evolution to Low-Carbon Transition: Regional Heterogeneity and Stage Diagnosis of Carbon Emissions Across 19 Urban Agglomerations in China

by Ye Duan, Minghan Yang, Zhaowei Hou, Hongye Wang, Albert Fekete and Dongge Ning

ISPRS Int. J. Geo-Inf. 2026, 15(8), 352; https://doi.org/10.3390/ijgi15080352 - 4 Aug 2026

Viewed by 405

Abstract

Understanding the spatiotemporal dynamics of carbon emissions and developing differentiated governance strategies for urban agglomerations are essential for achieving regional low-carbon transformation. This study aims to identify the spatiotemporal patterns, driving mechanisms, and development-stage differences of carbon emissions across China’s urban agglomerations and [...] Read more.

Understanding the spatiotemporal dynamics of carbon emissions and developing differentiated governance strategies for urban agglomerations are essential for achieving regional low-carbon transformation. This study aims to identify the spatiotemporal patterns, driving mechanisms, and development-stage differences of carbon emissions across China’s urban agglomerations and to establish a type-specific governance framework. Based on multi-source geospatial and socioeconomic data from 19 urban agglomerations for the period 2006–2023, this study integrates spatial autocorrelation analysis, standard deviation ellipse analysis, hotspot analysis, random forest regression with SHAP interpretation, K-medoid clustering, and the Environmental Kuznets Curve (EKC) model to systematically examine emission evolution, influencing factors, and governance pathways. The results indicate the following: (1) carbon emissions in China’s urban agglomerations increased continuously during the study period and exhibited significant spatial heterogeneity, characterized by a “high east–low west” pattern, expanding eastern emission hotspots, and a gradual southwest shift in the emission centroid; (2) industrial structure and economic development level were identified as the dominant factors associated with carbon-emission differences, while energy efficiency, urbanization, and population density showed heterogeneous relationships across regions; (3) five carbon-emission development types were identified, including high-carbon high-development, transition-pressure, resource-dependent, stable-development, and low-carbon potential agglomerations, each exhibiting distinct development characteristics and governance requirements; and (4) EKC analysis revealed differentiated development stages among these types, suggesting that carbon governance should be tailored according to regional development conditions, dominant drivers, and emission-transition stages. This study provides an integrated geospatial modeling framework for understanding carbon-emission heterogeneity and offers scientific support for differentiated low-carbon planning and collaborative governance of urban agglomerations. Full article

(This article belongs to the Special Issue Novel Theories and Applications on Geo-Spatial Databases, Models and AI in Urban Science, Planning, Development and Governance)

► Show Figures

Figure 1

23 pages, 14928 KB

Open AccessArticle

A Direction-Aware Lightweight Network for Camera-Based Underground Mine Track Region Segmentation

by Haijun Li, Baolong Ma, Jianjun Gong, Dengyin Jiang, Jie Yang, Kuangang Fan and Zhichao Chen

ISPRS Int. J. Geo-Inf. 2026, 15(8), 351; https://doi.org/10.3390/ijgi15080351 - 4 Aug 2026

Viewed by 331

Abstract

Accurate localization of the visible track region is essential for perception using front-mounted cameras on underground rail-guided mine vehicles. The task is difficult because the track foreground occupies only a small image area, and its boundary appearance changes with illumination, water, dust, and [...] Read more.

Accurate localization of the visible track region is essential for perception using front-mounted cameras on underground rail-guided mine vehicles. The task is difficult because the track foreground occupies only a small image area, and its boundary appearance changes with illumination, water, dust, and scene clutter. This study formulates local perception of the track corridor as binary semantic segmentation of the surface bounded by the two visible rails. RailDLA is a lightweight encoder–decoder network. It combines track context preconditioning, RDLA directional strip propagation, context-guided feature fusion, and track axis proxy decoding. On a self-constructed dataset of underground mine vehicle imagery, RailDLA achieves 96.50% mIoU, 92.10% track IoU, 97.50% track accuracy, and 99.70% pixel accuracy. On the working split, its track IoU exceeds those of FastSCNN, PIDNet-S, DDRNet-23-slim, and SegNeXt-S by absolute margins of 6.06, 1.70, 1.56, and 0.37 percentage points, respectively. Under the unified runtime protocol, RailDLA reaches 120.00 FPS on an NVIDIA GeForce RTX 3070 Laptop GPU. These results demonstrate accurate, real-time inference for underground mine vehicle perception. Full article

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

► Show Figures

Figure 1

57 pages, 7105 KB

Open AccessArticle

Fine-Grained Cultural Perception and Evaluation of Beijing’s Capital Culture Integrating Large Language Models with Higher-Order Tensor Decomposition

by Shihao Xi, Zhiyuan Ou, Bin Meng and Xiaohang Li

ISPRS Int. J. Geo-Inf. 2026, 15(8), 350; https://doi.org/10.3390/ijgi15080350 - 3 Aug 2026

Viewed by 638

Abstract

Fine-grained urban cultural perception is critical for GIScience, yet traditional social media studies struggle with complex cultural semantics and heterogeneous factor integration. Addressing Beijing’s “Capital Culture,” this study couples LLM agents with higher-order tensor decomposition. Using 2019 full-sample geotagged Sina Weibo data, we [...] Read more.

Fine-grained urban cultural perception is critical for GIScience, yet traditional social media studies struggle with complex cultural semantics and heterogeneous factor integration. Addressing Beijing’s “Capital Culture,” this study couples LLM agents with higher-order tensor decomposition. Using 2019 full-sample geotagged Sina Weibo data, we developed a four-agent collaborative architecture with Chain-of-Thought prompting and human-in-the-loop mechanisms via a locally deployed Qwen3-32B model. A four-way tensor (“Cultural Type–Evaluation Aspect–Sentiment Polarity–Spatial Carrier”) was constructed and integrated with kernel density estimation to characterize spatial differentiation. We address three questions: whether LLMs can reliably classify fine-grained cultural perceptions, how cultural types associate with evaluation dimensions, sentiments, and spatial carriers, and whether tensor decomposition reveals latent patterns beyond marginal frequencies. The agentic workflow achieves over 90% accuracy in cultural and sentiment classification, and the tensor decomposition attains a 94.87% goodness-of-fit, successfully identifying latent patterns. Spatially, Beijing’s capital culture exhibits an unbalanced hierarchical structure—“high coupling in the core area with differentiated expansion at the periphery.” This study validates the transition from “data-driven” to “AI + data dual-driven” spatial analysis, providing a quantifiable pathway for LLM-supported urban cultural governance. Full article

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

► Show Figures

Figure 1

30 pages, 4122 KB

Open AccessArticle

Spatial Differentiation and Driving Mechanisms of County-Level Tourism Accessibility in Gansu Based on Multi-Dimensional Travel Cost Perspective

by Ruhu Gao, Wenkai Shi, Yuwei Wang, Zhennan Qi and Liangzhi Li

ISPRS Int. J. Geo-Inf. 2026, 15(8), 349; https://doi.org/10.3390/ijgi15080349 - 3 Aug 2026

Viewed by 436

Abstract

Tourism accessibility is an important indicator for assessing the coordinated development of transport and tourism. Using counties and districts in Gansu Province as the units of analysis, this study developed a three-dimensional evaluation framework comprising temporal accessibility, economic accessibility, and balanced accessibility, based [...] Read more.

Tourism accessibility is an important indicator for assessing the coordinated development of transport and tourism. Using counties and districts in Gansu Province as the units of analysis, this study developed a three-dimensional evaluation framework comprising temporal accessibility, economic accessibility, and balanced accessibility, based on real-world travel data between county and district centres and China’s A-rated tourist attractions obtained from the Amap API. Spatial autocorrelation analysis, the Geographical Detector, the Spatial Durbin Model (SDM), and Multiscale Geographically Weighted Regression (MGWR) were employed to systematically investigate the spatial patterns and driving mechanisms of tourism accessibility in Gansu Province. The results indicate that: (1) tourism accessibility exhibits significant spatial clustering, with high-value areas primarily concentrated in the Hexi Corridor and low-value areas mainly distributed in the mountainous regions of central and southern Gansu; (2) distance to the provincial capital, elevation, and the number of adjacent counties constitute the core determinants of tourism accessibility, while interactions among factors generally exhibit bi-factor enhancement or nonlinear enhancement effects; and (3) tourism accessibility exhibits significant spatial spillover effects and spatial heterogeneity, with the effects of different driving factors varying considerably across space. The findings provide a theoretical basis for optimising tourism transport and promoting balanced regional tourism development in Gansu Province. Full article

► Show Figures

Figure 1

64 pages, 28857 KB

Open AccessFeature PaperArticle

FCEND: A Fuzzy Cross-Efficiency GIS-DEA Framework for Equitable Logistics Network Design Under Deep Uncertainty

by Hossein Zangooei Dovom, Mir Saman Pishvaee and Hadi Sahebi

ISPRS Int. J. Geo-Inf. 2026, 15(8), 348; https://doi.org/10.3390/ijgi15080348 - 1 Aug 2026

Viewed by 323

Abstract

This study develops the Fuzzy Cross-Efficiency Network Design (FCEND) framework—an integrated Geographic Information System (GIS) and Data Envelopment Analysis (DEA) approach for logistics network design under deep uncertainty. Unlike conventional methods that ignore spatial equity and data credibility, FCEND combines GIS-based suitability mapping [...] Read more.

This study develops the Fuzzy Cross-Efficiency Network Design (FCEND) framework—an integrated Geographic Information System (GIS) and Data Envelopment Analysis (DEA) approach for logistics network design under deep uncertainty. Unlike conventional methods that ignore spatial equity and data credibility, FCEND combines GIS-based suitability mapping (30 m resolution, incorporating slope, land use, and floodplains), hybrid efficiency scores (

Φ_{j}

) integrating Cross-Efficiency DEA (CEDEA) peer evaluation with Fuzzy DEA (FDEA) uncertainty modeling, and a multi-objective function Z(S) = α·Efficiency(S) + β·H(S) − γ·Gini(S) that balances demand-weighted efficiency, portfolio-dependent criterion diversity (represented by the entropy term H(S)), and spatial equity. Applied to Iran’s staple food commodity network—85 million people across 1.65 million km²—FCEND identifies an optimal 15-node portfolio spanning 15 provinces with 74% direct population coverage within 150 km. The portfolio achieves a Gini coefficient of 0.298, and 9 of 15 nodes with excellent rail connectivity, while capturing strategically vital nodes (Borujerd, Bandar Abbas, Zahedan) overlooked by conventional approaches. Nine core sites with stability scores (f_j = 1.0) demonstrate perfect stability across all uncertainty scenarios. The framework’s modular architecture is conceptually transferable to emerging economies, as illustrated through adaptation to Vietnam (70% parameter swap). By integrating GIS-based spatial analysis, peer evaluation, fuzzy uncertainty, portfolio-dependent entropy, and equity constraints within a unified optimization framework, FCEND offers a transferable methodology for evidence-based logistics infrastructure planning—contributing directly to the United Nations Sustainable Development Goals (SDGs): SDG 2 (Zero Hunger), SDG 9 (Resilient Infrastructure), SDG 10 (Reduced Inequalities), and SDG 13 (Climate Action). Full article

► Show Figures

Figure 1

51 pages, 9273 KB

Open AccessArticle

Sustainable Urban Forms and Climate Adaptation Policy: A Sparsity-Responsiveness Framework Based on Chinese Cities

by Zhihan Zhang, Junyan Yang, Xilong Chen, Zhixiang Lin, Yuyue Huang, Qingxin Yang and Huaxing Sheng

ISPRS Int. J. Geo-Inf. 2026, 15(8), 347; https://doi.org/10.3390/ijgi15080347 - 1 Aug 2026

Viewed by 447

Abstract

Sustainability is recognized as a key driver for the formation and evolution of sustainable urban forms, serving as a critical approach for guiding and assessing urban sustainability. In the context of global warming, climate adaptation has become a pressing concern in shaping sustainable [...] Read more.

Sustainability is recognized as a key driver for the formation and evolution of sustainable urban forms, serving as a critical approach for guiding and assessing urban sustainability. In the context of global warming, climate adaptation has become a pressing concern in shaping sustainable urban forms. However, the complex mechanisms linking sustainability, urban form, and climate adaptation are difficult to identify and track due to variations in data precision, research scales, and stakeholder needs. This study first re-views the relevant literature to clarify the current state and trends in this field. It then employs locally weighted regression to analyze the relationships between sustainability principles, urban form, and climate adaptation from 2005 to 2024. Based on the “mitigation-adaptation” framework, sparsity-responsiveness indicators are constructed to define four types of climate adaptation. These types are used to classify 31 representative cities in China. Considering the cities’ developmental stages, the study proposes design strategies that prioritize sustainability. Full article

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

► Show Figures

Figure 1

Journal Menu

Journal Browser

ISPRS Int. J. Geo-Inf., Volume 15, Issue 8 (August 2026) – 39 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI