ISPRS International Journal of Geo-Information

26 pages, 6977 KiB

Open AccessArticle

Exploring the Nonlinear Impacts of Built Environment on Urban Vitality from a Spatiotemporal Perspective at the Block Scale in Chongqing

by Jiayu Yang and Enxu Wang

ISPRS Int. J. Geo-Inf. 2025, 14(6), 225; https://doi.org/10.3390/ijgi14060225 (registering DOI) - 7 Jun 2025

Abstract

Examining the relationship between built environment (BE) and urban vitality (UV) is beneficial for promoting urban planning, as it deepens the understanding of how spatial design shapes urban life and activity patterns. However, the nonlinear effects of BE on UV from a spatiotemporal [...] Read more.

Examining the relationship between built environment (BE) and urban vitality (UV) is beneficial for promoting urban planning, as it deepens the understanding of how spatial design shapes urban life and activity patterns. However, the nonlinear effects of BE on UV from a spatiotemporal perspective have not been fully explored. In this study, the central urban area of Chongqing at the block scale is selected as a research case. The Gradient Boosting Decision Tree with SHapley Additive exPlanations (GBDT-SHAP) model is used to examine the nonlinear impacts of BE on UV. The results show the following: (1) The BE has a stronger overall impact on UV during holidays. Road intersection density (RID) has the greatest impact on UV on weekdays and holidays, building density (BD) has the greatest impact on weekend mornings, cultural and leisure accessibility (CLA) has the greatest impact on weekend afternoons, and commercial accessibility (CA) has the most significant impact on weekend evenings; (2) the impacts of the BE on UV exhibit significant nonlinear characteristics, with BD and park and square accessibility (PSA) showing a first increasing and then inhibiting effect on UV; lower CA, CLA, and MSA have inhibitory effects on UV, with higher normalized difference vegetation index (NDVI) values similarly demonstrating such effects; building height (BH), bus stop density (BSD), road network density (RD), and RID have enhancing effects on UV; functional mix degree (FMD) and water proximity index (WPI) show different trends in different time periods; (3) there are significant interactive effects among BE such as BD and BH, CA; RD and WPI, MSA; FMD and BH, PSA; PSA and CLA. A comprehensive understanding of these interactive relationships is crucial for optimizing the BE to enhance UV. This study provides a theoretical basis for urban planners to develop more effective, time-sensitive strategies. Future research should explore these nonlinear and interactive effects across different cities and scales to further generalize the findings. Full article

(This article belongs to the Topic Sustainable Development and Coordinated Governance of Urban and Rural Areas Under the Guidance of Ecological Wisdom—2nd Edition)

13 pages, 2203 KiB

Open AccessArticle

Evaluating Spatio-Temporal Kriging with Machine Learning Considering the Sources of Spatio-Temporal Variation

by Min Jeong and Hyeongmo Koo

ISPRS Int. J. Geo-Inf. 2025, 14(6), 224; https://doi.org/10.3390/ijgi14060224 - 5 Jun 2025

Abstract

Integrating spatio-temporal kriging with machine learning improves estimation accuracy by addressing complex spatial and temporal variations in spatio-temporal phenomena. The improvement can be attributed to the enhanced flexibility of machine learning in capturing non-linear global trends, which traditional methods struggle to model, while [...] Read more.

Integrating spatio-temporal kriging with machine learning improves estimation accuracy by addressing complex spatial and temporal variations in spatio-temporal phenomena. The improvement can be attributed to the enhanced flexibility of machine learning in capturing non-linear global trends, which traditional methods struggle to model, while kriging remains effective in representing spatio-temporal interactions. However, differences in the estimated global trends and spatio-temporal interactions resulting from applying machine learning may influence the spatio-temporal variation patterns of the kriging results. Therefore, this study evaluates the effectiveness of machine learning in spatio-temporal kriging using NO₂ concentrations in Seoul, focusing on its impact on overall accuracy and the contributions to global trends and spatio-temporal interactions. The results show that integrating machine learning enhances overall accuracy relative to ordinary spatio-temporal kriging. Global trend estimates differ by the models, with polynomial regression producing smoother patterns but larger errors, while random forest and boosting yield more abrupt patterns with smaller errors. These differences lead to smoother kriging outcomes in the polynomial model and more discrete patterns in the ensemble-based models. This study highlights the importance of considering both overall estimation accuracy and spatio-temporal patterns when selecting kriging methods. Full article

► Show Figures

Figure 1

18 pages, 6877 KiB

Open AccessArticle

Machine Learning-Enhanced 3D GIS Urban Noise Mapping with Multi-Modal Factors

by Jianping Pan, Yuzhe He, Wei Ma, Shengwang An, Lu Li, Dan Huang and Dunxin Jia

ISPRS Int. J. Geo-Inf. 2025, 14(6), 223; https://doi.org/10.3390/ijgi14060223 - 4 Jun 2025

Abstract

Geographic Information System (GIS)-based noise management is crucial in urban environments as it provides precise spatial analysis, helping to identify noise hotspots and optimize noise control measures. By integrating noise propagation models with GIS technology, dynamic simulation and visualization of noise distribution can [...] Read more.

Geographic Information System (GIS)-based noise management is crucial in urban environments as it provides precise spatial analysis, helping to identify noise hotspots and optimize noise control measures. By integrating noise propagation models with GIS technology, dynamic simulation and visualization of noise distribution can be achieved, offering scientific support for urban planning and noise management. Most existing noise prediction models fail to fully account for three-dimensional (3D) spatial information and a wide range of environmental factors. As a result, there are often discrepancies between the actual noise measurements at monitoring points and the predicted values generated by these models. Furthermore, there is a lack of a system that can effectively integrate noise data with three-dimensional scenes for simulation. This paper proposes a new method to simulate urban noise propagation, aiming to achieve more accurate noise prediction and visualization in a three-dimensional environment. First, we computed the preliminary noise propagation based on a traffic noise model. Next, machine learning techniques were applied to analyze the relationship between noise discrepancies and multi-modal factors, thereby improving the accuracy of environmental noise level estimation. Based on this, we developed an urban noise simulation system. The system integrates functions such as noise simulation, traffic simulation, and weather changes, enabling accurate noise visualization within a three-dimensional virtual environment. Experimental results demonstrate that this method enhances the accuracy of urban noise prediction and visualization, providing users with a more comprehensive understanding of the spatial distribution of urban noise. Full article

► Show Figures

Figure 1

22 pages, 7036 KiB

Open AccessArticle

Clustering Method for Edge and Inner Buildings Based on DGI Model and Graph Traversal

by Hesheng Huang, Yijun Zhang and Aidong Ye

ISPRS Int. J. Geo-Inf. 2025, 14(6), 222; https://doi.org/10.3390/ijgi14060222 - 3 Jun 2025

Abstract

Accurate clustering of buildings is a prerequisite for map generalization in densely populated urban data. Edge buildings at the edge of building groups, identified through human-eye recognition, may serve as boundary constraints for clustering. This paper proposes the use of seven Gestalt factors [...] Read more.

Accurate clustering of buildings is a prerequisite for map generalization in densely populated urban data. Edge buildings at the edge of building groups, identified through human-eye recognition, may serve as boundary constraints for clustering. This paper proposes the use of seven Gestalt factors to distinguish edge buildings from other buildings. Employing the DGI model to produce high-quality node embeddings, optimize the mutual information between the local node representation and the global summary vector. We then conduct training to identify edge buildings in the two test datasets using eight feature combinations. This research introduces a modified distance metric called the ‘m_dis’ feature, which is used to describe the closeness between two adjacent buildings. Finally, the clusters of edge and inner buildings are determined through a constrained graph traversal that is based on the ‘m_dis’ feature. This method is capable of effectively identifying and distinguishing densely distributed building groups in Chengdu City, China, as demonstrated by experimental results. It offers novel concepts for edge building recognition in dense urban areas, confirms the significance of the LOF factor and the ‘m_dis’ feature, and achieves superior clustering results in comparison to other methods. Additionally, this semi-supervised clustering method (DGI-EIC) has the potential to achieve an ARI index of approximately 0.5. Full article

► Show Figures

Figure 1

23 pages, 8631 KiB

Open AccessArticle

Revealing Spatiotemporal Urban Activity Patterns: A Machine Learning Study Using Google Popular Times

by Mikel Barrena-Herrán, Itziar Modrego-Monforte and Olatz Grijalba

ISPRS Int. J. Geo-Inf. 2025, 14(6), 221; https://doi.org/10.3390/ijgi14060221 - 3 Jun 2025

Abstract

Extensive scientific evidence underscores the importance of identifying spatiotemporal patterns for investigating urban dynamics. The recent proliferation of location-based social networks (LBSNs) facilitates the measurement of urban rhythms through geotemporal information, providing deeper insights into the underlying causes of urban vibrancy. This study [...] Read more.

Extensive scientific evidence underscores the importance of identifying spatiotemporal patterns for investigating urban dynamics. The recent proliferation of location-based social networks (LBSNs) facilitates the measurement of urban rhythms through geotemporal information, providing deeper insights into the underlying causes of urban vibrancy. This study presents a methodology for analyzing the spatiotemporal use of cities and identifying occupancy patterns taking into consideration urban form and function. The analysis relies on data obtained from Google Popular Times (GPT), transforming the relative occupancy of a large number of points of interest (POI) classified into five categories, for estimating the number of people aggregated within urban nodes during a typical day. As a result, this research assesses the utility of this data source for evaluating the changing dynamics of a city across both space and time. The methodology employs geographic information system (GIS) tools and artificial intelligence techniques. The results demonstrate that by analyzing geotemporal data, we can classify urban nodes according to their hourly activity patterns. These patterns, in turn, relate to city form and urban activities, showing a certain spatial concentration. This research contributes to the growing body of knowledge on machine learning (ML) methods for spatiotemporal modeling, laying the groundwork for future studies that can further explore the complexity of urban phenomena. Full article

► Show Figures

Figure 1

15 pages, 3095 KiB

Open AccessArticle

A Deep Learning Method for the Automated Mapping of Archaeological Structures from Geospatial Data: A Case Study of Delos Island

by Pavlos Fylaktos, George P. Petropoulos and Ioannis Lemesios

ISPRS Int. J. Geo-Inf. 2025, 14(6), 220; https://doi.org/10.3390/ijgi14060220 - 2 Jun 2025

Abstract

The integration of artificial intelligence (AI), specifically through convolutional neural networks (CNNs), is paving the way for significant advancements in archaeological research. This study explores the innovative application of the so-called Mask Region-based convolutional neural network (Mask R-CNN) algorithm in a GIS environment, [...] Read more.

The integration of artificial intelligence (AI), specifically through convolutional neural networks (CNNs), is paving the way for significant advancements in archaeological research. This study explores the innovative application of the so-called Mask Region-based convolutional neural network (Mask R-CNN) algorithm in a GIS environment, utilizing high-resolution satellite imagery from the WorldView-3 system. By combining these state-of-the-art technologies, this study demonstrates the algorithm’s effectiveness at recognizing and segmenting the ancient structures within the archaeological site of Delos, Greece. Despite the computational constraints, the outcomes are promising, with around 25.91% of the initial vector data (434 out of 1675 polygons) successfully identified. The algorithm achieved an impressive F1 Score of 0.93% at a threshold of 0.9, indicating its high precision in differentiating specific features from their environments. This research highlights AI’s crucial role in archaeology, enabling the remote analysis of vast areas through automated or semi-automated techniques. Although these technologies cannot supplant essential on-site investigations, they can significantly enhance traditional methodologies by minimizing costs and fieldwork duration. This study also points out obstacles, such as the complexity of and variability in archaeological remains, which complicate the creation of standardized data libraries. Nevertheless, as AI technologies progress, their applications in archaeology are anticipated to broaden, fostering further innovation within the discipline. Full article

► Show Figures

Figure 1

17 pages, 3458 KiB

Open AccessArticle

Viewpoint Selection for 3D Scenes in Map Narratives

by Shichuan Liu, Yong Wang, Qing Tang and Yaoyao Han

ISPRS Int. J. Geo-Inf. 2025, 14(6), 219; https://doi.org/10.3390/ijgi14060219 - 31 May 2025

Abstract

Narrative mapping, an advanced geographic information visualization technology, presents spatial information episodically, enhancing readers’ spatial understanding and event cognition. However, during 3D scene construction, viewpoint selection is heavily reliant on the cartographer’s subjective interpretation of the event. Even with fixed-angle settings, the task [...] Read more.

Narrative mapping, an advanced geographic information visualization technology, presents spatial information episodically, enhancing readers’ spatial understanding and event cognition. However, during 3D scene construction, viewpoint selection is heavily reliant on the cartographer’s subjective interpretation of the event. Even with fixed-angle settings, the task of ensuring that selected viewpoints align with the narrative theme remains challenging. To address this, an automated viewpoint selection method constrained by narrative relevance and visual information is proposed. Narrative relevance is determined by calculating spatial distances between each element and the thematic element within the scene. Visual information is quantified by assessing the visual salience of elements as the ratio of their projected area on the view window to their total area. Pearson’s correlation coefficient is used to evaluate the relationship between visual salience and narrative relevance, serving as a constraint to construct a viewpoint fitness function that integrates the visual salience of the convex polyhedron enclosing the scene. The chaotic particle swarm optimization (CPSO) algorithm is utilized to locate the viewpoint position while maximizing the fitness function, identifying a viewpoint meeting narrative and visual salience requirements. Experimental results indicate that, compared to the maximum projected area method and fixed-value method, a higher viewpoint fitness is achieved by this approach. The narrative views generated by this method were positively recognized by approximately two-thirds of invited professionals. This process aligns effectively with narrative visualization needs, enhances 3D narrative map creation efficiency, and offers a robust strategy for viewpoint selection in 3D scene-based narrative mapping. Full article

► Show Figures

Figure 1

19 pages, 8169 KiB

Open AccessArticle

Exploring the Application of NeRF in Enhancing Post-Disaster Response: A Case Study of the Sasebo Landslide in Japan

by Jinge Zhang, Yan Du, Yujing Jiang, Sunhao Zhang, Hongbin Chen and Dongqi Shang

ISPRS Int. J. Geo-Inf. 2025, 14(6), 218; https://doi.org/10.3390/ijgi14060218 - 30 May 2025

Abstract

Rapid acquisition of 3D reconstruction models of landslides is crucial for post-disaster emergency response and rescue operations. This study explores the application potential of Neural Radiance Fields (NeRF) technology for rapid post-disaster site modeling and performs a comparative analysis with traditional photogrammetry methods. [...] Read more.

Rapid acquisition of 3D reconstruction models of landslides is crucial for post-disaster emergency response and rescue operations. This study explores the application potential of Neural Radiance Fields (NeRF) technology for rapid post-disaster site modeling and performs a comparative analysis with traditional photogrammetry methods. Taking a landslide induced by heavy rainfall in Sasebo City, Japan, as a case study, this research utilizes drone-acquired video imagery data and employs two different 3D reconstruction techniques to create digital models of the landslide area. Visual realism and point cloud detail were compared. The results indicate that the high-capacity NeRF model (NeRF 24G) approaches or even surpasses traditional photogrammetry in visual realism under certain scenarios; however, the generated point clouds are inferior in terms of detail compared to those produced by traditional photogrammetry. Nevertheless, NeRF significantly reduces the modeling time. NeRF 6G can generate a point cloud of engineering-useful accuracy in only 45 min, providing a 3D overview of the disaster site to support emergency response efforts. In the future, integrating the advantages of both methods could enable rapid and precise post-disaster 3D reconstruction. Full article

(This article belongs to the Topic Geotechnics for Hazard Mitigation)

► Show Figures

Figure 1

22 pages, 25402 KiB

Open AccessArticle

Site Selection Analysis and Prediction of New Retail Stores from an Urban Commercial Space Perspective: A Case Study of Luckin Coffee and Starbucks in Shanghai

by Zhengxu Zhao, Gang Chen, Jianshu Duan and Youheng Xu

ISPRS Int. J. Geo-Inf. 2025, 14(6), 217; https://doi.org/10.3390/ijgi14060217 - 30 May 2025

Abstract

In the context of digital transformation, examining the differences in commercial site selection and the factors influencing these decisions holds significant practical value for understanding market adaptation strategies across varying business models and predicting future industry trends. This study divides the research area [...] Read more.

In the context of digital transformation, examining the differences in commercial site selection and the factors influencing these decisions holds significant practical value for understanding market adaptation strategies across varying business models and predicting future industry trends. This study divides the research area into 100 m × 100 m grids and employs a random forest model and related interpretability methods to conduct an empirical analysis of the site selection and influencing factors of Luckin Coffee and Starbucks stores in Shanghai. By integrating the prediction results with existing planning documents, this study achieves a coupling between urban spatial structure and location strategies. The findings indicate the following: (1) The random forest model demonstrates high accuracy in predicting new retail store locations, with an accuracy rate of 90.0% for Luckin Coffee and 92.2% for Starbucks. (2) The influence of traditional factors on the expansion of new retail coffee stores is declining, while Luckin Coffee’s layout demonstrates a stronger reliance on urban functional zones. (3) Relative suitability is derived by calculating the difference between the predicted probability values and the normalized kernel density values. In the central activity areas of the city, the relationship between site selection probability and suitability exhibits an inverse correlation, with Starbucks generally showing higher relative suitability overall. (4) Suitable areas for both brands’ site selections are spatially contiguous and integrated within the urban fabric, which suggests significant growth potential for both brands in the main urban areas. This study not only focuses on commercial optimization but also offers theoretical and methodological insights by exploring how different retail models interact with urban spatial structures, thereby contributing to the fields of retail geography and spatial governance. Full article

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

► Show Figures

Figure 1

21 pages, 20433 KiB

Open AccessArticle

Micro-Terrain Recognition Method of Transmission Lines Based on Improved UNet++

by Feng Yi and Chunchun Hu

ISPRS Int. J. Geo-Inf. 2025, 14(6), 216; https://doi.org/10.3390/ijgi14060216 - 30 May 2025

Abstract

Micro-terrain recognition plays a crucial role in the planning, design, and safe operation of transmission lines. To achieve intelligent and automatic recognition of micro-terrain surrounding transmission lines, this paper proposes an improved semantic segmentation model based on UNet++. This model expands the single [...] Read more.

Micro-terrain recognition plays a crucial role in the planning, design, and safe operation of transmission lines. To achieve intelligent and automatic recognition of micro-terrain surrounding transmission lines, this paper proposes an improved semantic segmentation model based on UNet++. This model expands the single encoder into multiple encoders to accommodate the input of multi-source geographic features and introduces a gated fusion module (GFM) to effectively integrate the data from diverse sources. Additionally, the model incorporates a dual attention network (DA-Net) and a deep supervision strategy to enhance performance and robustness. The multi-source dataset used for the experiment includes the Digital Elevation Model (DEM), Elevation Coefficient of Variation (ECV), and profile curvature. The experimental results of the model comparison indicate that the improved model outperforms common semantic segmentation models in terms of multiple evaluation metrics, with pixel accuracy (PA) and intersection over union (IoU) reaching 92.26% and 85.63%, respectively. Notably, the performance in identifying the saddle and alpine watershed types has been enhanced significantly by the improved model. The ablation experiment results confirm that the introduced modules contribute to enhancing the model’s segmentation performance. Compared to the baseline network, the improved model enhances PA and IoU by 1.75% and 2.96%, respectively. Full article

► Show Figures

Figure 1

26 pages, 4590 KiB

Open AccessArticle

Hierarchical Data Visualization Based on Rectangular Cartograms

by Lina Wang, Haoxun Yuan, Xiang Li, Yaru Li, Danfei Zhang and Haoqi Hu

ISPRS Int. J. Geo-Inf. 2025, 14(6), 215; https://doi.org/10.3390/ijgi14060215 - 30 May 2025

Abstract

As the diversity and complexity of geographic statistical data continue to increase, it becomes increasingly important to present multi-level information in order to meet a broader range of needs. In response to the limitations of existing visualization methods in representing the geographic distribution [...] Read more.

As the diversity and complexity of geographic statistical data continue to increase, it becomes increasingly important to present multi-level information in order to meet a broader range of needs. In response to the limitations of existing visualization methods in representing the geographic distribution of statistical data, this paper proposes a geographical hierarchical data visualization method based on rectangular cartograms. First, a new rectangular cartograms construction algorithm is adopted in this paper, which can effectively preserve relatively accurate orientation and adjacency relationships between geographic regions, while also effectively preserving the statistical data features. Then, a treemap layout algorithm is applied within the rectangular cartogram to further partition the geographic regions, thereby visualizing the hierarchical structure of the data. Through experimental validation using real datasets and usability testing, the results demonstrate that the method presented in this paper excels in geographic distribution representation, hierarchical relationship visualization, and information readability. Compared to traditional thematic map methods, this approach demonstrates significant advantages in terms of information transmission efficiency and shows promising performance in expressive effectiveness, providing strong support for the analysis and decision making of geographical hierarchical data. Full article

► Show Figures

Figure 1

22 pages, 8463 KiB

Open AccessArticle

GeoFAN: Point Pattern Recognition in Spatial Vector Data

by Zhuoyi Yang, Zeyi Li, Haitao Zhang, Wei Zhang, Yanwei Wang and Yihang Huang

ISPRS Int. J. Geo-Inf. 2025, 14(6), 214; https://doi.org/10.3390/ijgi14060214 - 29 May 2025

Abstract

The recognition of point patterns in spatial vector data has important applications in geographic mapping and formation recognition. However, the application of traditional methods to spatial vector data faces two difficulties. Firstly, these data are low signal-to-noise ratio data in which the point [...] Read more.

The recognition of point patterns in spatial vector data has important applications in geographic mapping and formation recognition. However, the application of traditional methods to spatial vector data faces two difficulties. Firstly, these data are low signal-to-noise ratio data in which the point patterns are mixed with a large number of normal point clusters; thus, it is difficult to recognize point patterns from these unstructured data using traditional clustering or machine learning methods. Secondly, the lack of edge connectivity relationships in spatial vector data directly hinders the application of graph models. Few studies have systematically solved the above difficulties. In this article, we propose a geometric feature attention scheme to overcome the above challenges. We also present an implementation of the scheme based on the graph method, termed GeoFAN, to extract and classify point patterns simultaneously in spatial vector data. Firstly, the raw data are transformed into a graph structure consisting of adjacency and attribute matrices. Secondly, a geometric feature attention module is proposed to enhance the feature representation of point patterns. Finally, the recognition results of all points are output via GeoFAN. The macro precision, recall, and

F_{1}

score of five simulated point pattern types with different attributes and point numbers are 92.8%, 90.3%, and 91.5%, respectively, and GeoFAN is trained with simulated data to recognize real location-based point patterns successfully. The proposed GeoFAN showed superior performance and generalization ability in point pattern recognition. Full article

► Show Figures

Figure 1

24 pages, 4868 KiB

Open AccessArticle

Flow-Based Community Search Approach for Functionally Cohesive Building Group Recognition: A Case Study on Commercial Complexes

by Taiyang Yang, Pengxin Zhang, Daozhu Xu, Pengcheng Liu and Min Yang

ISPRS Int. J. Geo-Inf. 2025, 14(6), 213; https://doi.org/10.3390/ijgi14060213 - 29 May 2025

Abstract

Recognizing functionally cohesive building groups is crucial for urban analysis, geospatial intelligence, and smart city applications. Traditional methods rely heavily on geometric information and often overlook the functional and semantic coherence of buildings, leading to their incorrect recognition. To overcome these challenges, this [...] Read more.

Recognizing functionally cohesive building groups is crucial for urban analysis, geospatial intelligence, and smart city applications. Traditional methods rely heavily on geometric information and often overlook the functional and semantic coherence of buildings, leading to their incorrect recognition. To overcome these challenges, this study introduces a flow-based community search approach, which models morphological, functional, and spatial relationships with a graph-based representation. The approach consists of graph representation learning, flow-based community generation, and community quality assessment, enabling adaptive building group recognition based on both structural coherence and functional similarity. Experimental results on commercial complex recognition demonstrate that our approach consistently outperforms traditional methods, achieving an improvement of over 5.4% in F1 score compared to the second-best method. Furthermore, its strong performance on limited training datasets highlights its robustness. These findings establish the proposed approach as an effective and reliable tool for recognizing functionally cohesive building groups, with practical viability in urban planning and policy formulation. Full article

(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation (2nd Edition))

► Show Figures

Figure 1

25 pages, 24232 KiB

Open AccessArticle

Topology-Aware Multi-View Street Scene Image Matching for Cross-Daylight Conditions Integrating Geometric Constraints and Semantic Consistency

by Haiqing He, Wenbo Xiong, Fuyang Zhou, Zile He, Tao Zhang and Zhiyuan Sheng

ISPRS Int. J. Geo-Inf. 2025, 14(6), 212; https://doi.org/10.3390/ijgi14060212 - 29 May 2025

Abstract

While deep learning-based image matching methods excel at extracting high-level semantic features from remote sensing data, their performance degrades significantly under cross-daylight conditions and wide-baseline geometric distortions, particularly in multi-source street-view scenarios. This paper presents a novel illumination-invariant framework that synergistically integrates geometric [...] Read more.

While deep learning-based image matching methods excel at extracting high-level semantic features from remote sensing data, their performance degrades significantly under cross-daylight conditions and wide-baseline geometric distortions, particularly in multi-source street-view scenarios. This paper presents a novel illumination-invariant framework that synergistically integrates geometric topology and semantic consistency to achieve robust multi-view matching for cross-daylight urban perception. We first design a self-supervised learning paradigm to extract illumination-agnostic features by jointly optimizing local descriptors and global geometric structures across multi-view images. To address extreme perspective variations, a homography-aware transformation module is introduced to stabilize feature representation under large viewpoint changes. Leveraging a graph neural network with hierarchical attention mechanisms, our method dynamically aggregates contextual information from both local keypoints and semantic topology graphs, enabling precise matching in occluded regions and repetitive-textured urban scenes. A dual-branch learning strategy further refines similarity metrics through supervised patch alignment and unsupervised spatial consistency constraints derived from Delaunay triangulation. Finally, a topology-guided multi-plane expansion mechanism propagates initial matches by exploiting the inherent structural regularity of street scenes, effectively suppressing mismatches while expanding coverage. Extensive experiments demonstrate that our framework outperforms state-of-the-art methods, achieving a 6.4% improvement in matching accuracy and a 30.5% reduction in mismatches under cross-daylight conditions. These advancements establish a new benchmark for reliable multi-source image retrieval and localization in dynamic urban environments, with direct applications in autonomous driving systems and large-scale 3D city reconstruction. Full article

(This article belongs to the Topic 3D Computer Vision and Smart Building and City, 3rd Edition)

► Show Figures

Figure 1

32 pages, 20803 KiB

Open AccessArticle

Synergistic Mechanisms Between Elderly Oriented Community Activity Space Morphology and Microclimate Performance: An Integrated Learning and Multi-Objective Optimization Approach

by Fang Wen, Lu Zhang, Ling Jiang, Rui Tang and Bo Zhang

ISPRS Int. J. Geo-Inf. 2025, 14(6), 211; https://doi.org/10.3390/ijgi14060211 - 28 May 2025

Abstract

This study collected site and spatial morphological data from 63 typical aging community activity spaces and extracted 12 spatial types through statistical analysis. A parametric modeling tool was used to generate spatial models. Based on clearly defined design variables and constraints, the NSGA-II [...] Read more.

This study collected site and spatial morphological data from 63 typical aging community activity spaces and extracted 12 spatial types through statistical analysis. A parametric modeling tool was used to generate spatial models. Based on clearly defined design variables and constraints, the NSGA-II multi-objective optimization algorithm was applied to minimize summer thermal discomfort, maximize winter thermal comfort, and maximize annual average sunlight duration, resulting in 342 Pareto optimal solutions. The study first explored the linear relationships between spatial morphology and environmental performance using the Spearman method. It then integrated ensemble learning and the interpretable machine learning model SHAP to reveal nonlinear relationships and boundary effects. The results of the two methods complemented and reinforced each other. Based on a comparison of these two approaches, morphological indicators showing significant differences were selected for attribution and sensitivity analyses, clarifying the mechanisms by which spatial morphological parameters influence environmental performance and identifying their critical thresholds. Key findings include the following: (1) the UTCI-S exhibits significant negative linear correlations with the open space ratio (OSR) and spatial crowding density (SCD); the UTCI-W shows negative linear correlations with canopy coverage (CVH) and wind speed (WS); and a positive linear correlation exists between the sky view factor (SVF) and AV.SH. (2) Boundary effects and threshold intervals of critical morphological parameters were identified as follows. The open space ratio should be controlled to 10–15%, the shrub–tree layer coverage to 0.013–0.0165%, and the average building height to 3.1–3.8 m. (3) Spatial layout principles demonstrate that placing fully enclosed spaces (E-2) and semi-enclosed spaces (S-1/S-3) on the northern side, as well as semi-enclosed spaces (S-1/S-2) and circulation spaces (C-3) on the southern side, significantly enhance microclimatic performance. These findings provide quantitative guidelines for community space design in cold regions and offer data support for creating outdoor environments that meet the comfort needs of the elderly. Full article

► Show Figures

Figure 1

25 pages, 5086 KiB

Open AccessArticle

A Playful Participatory Planning System (P-PPS): A Framework for Collecting and Analyzing Player-Generated Spatial Data from Minecraft Worlds

by Ítalo Sousa de Sena, Lasith Niroshan, Jonáš Rosecký, Vojtěch Brůža, Micheál Butler and Chiara Cocco

ISPRS Int. J. Geo-Inf. 2025, 14(6), 210; https://doi.org/10.3390/ijgi14060210 - 24 May 2025

Abstract

Digital tools, especially games, are increasingly important for enabling citizen participation in urban planning. Among these, Minecraft has been widely utilized to engage children, leveraging its virtual environment to represent geospatial data. However, systematic methods for collecting and analyzing player-generated data within Minecraft [...] Read more.

Digital tools, especially games, are increasingly important for enabling citizen participation in urban planning. Among these, Minecraft has been widely utilized to engage children, leveraging its virtual environment to represent geospatial data. However, systematic methods for collecting and analyzing player-generated data within Minecraft remain underexplored. Playful Participatory Planning System (P-PPS) framework that transforms player actions (e.g., building, removing, planting) within Minecraft, using OpenStreetMap (OSM) data to create game environments, back into geospatial data for analysis. The framework’s applicability was demonstrated through two case studies, one with 58 schoolchildren and 18 adults in Ireland. The results reveal that schoolchildren, while highly engaged, demonstrated a high density of actions within limited areas, suggesting a need for guidance on spatial distribution and ecological considerations. In contrast, adults prioritized the urban context and exhibited greater spatial consistency in their actions. Challenges emerged in managing online interactions, emphasizing the need for clear guidelines and moderation strategies. This research demonstrates the potential of Minecraft as a platform for participatory urban planning, exploring its use as a collaborative immersive mapping tool. Full article

► Show Figures

Figure 1

32 pages, 11121 KiB

Open AccessArticle

Construction of a Cold Island Spatial Pattern from the Perspective of Landscape Connectivity to Alleviate the Urban Heat Island Effect

by Qianli Ouyang, Bohong Zheng, Junyou Liu, Xi Luo, Shengyan Wu and Zhaoqian Sun

ISPRS Int. J. Geo-Inf. 2025, 14(6), 209; https://doi.org/10.3390/ijgi14060209 - 23 May 2025

Abstract

This study presents an innovative approach to mitigating the urban heat island (UHI) effect by constructing a cold island spatial pattern (CSP) from the perspective of landscape connectivity, integrating three-dimensional (3D) urban morphology and meteorological factors for the first time. Unlike traditional studies [...] Read more.

This study presents an innovative approach to mitigating the urban heat island (UHI) effect by constructing a cold island spatial pattern (CSP) from the perspective of landscape connectivity, integrating three-dimensional (3D) urban morphology and meteorological factors for the first time. Unlike traditional studies that focus on isolated patches or single-city scales, we propose a hierarchical framework for urban agglomerations, combining morphological spatial pattern analysis (MSPA), landscape connectivity assessment, and circuit theory to a construct CSP at the scale of urban agglomeration. By incorporating wind environment data and 3D building features (e.g., height, density) into the resistance surface, we enhance the accuracy of cooling network identification, revealing 39 cold island sources, 89 cooling corridors, and optimal corridor widths (600 m) in the Changsha–Zhuzhou–Xiangtan urban agglomeration (CZXUA). Ultimately, a three-tiered heat island mitigation framework for urban agglomerations was established based on the CSP. This study offers an innovative perspective on urban climate adaptability planning within the context of contemporary urbanization. Our methodology and findings provide critical insights for future studies to integrate multiscale, multidimensional, and climate-adaptive approaches in urban thermal environment governance, fostering sustainable urbanization under escalating climate challenges. Full article

(This article belongs to the Topic Climate Change Impacts and Adaptation: Interdisciplinary Perspectives, 2nd Edition)

► Show Figures

Figure 1

21 pages, 4062 KiB

Open AccessArticle

Comprehensive Assessment and Obstacle Factor Recognition of Waterlogging Disaster Resilience in the Historic Urban Area

by Fangjie Cao, Qianxin Wang, Yun Qiu and Xinzhuo Wang

ISPRS Int. J. Geo-Inf. 2025, 14(6), 208; https://doi.org/10.3390/ijgi14060208 - 23 May 2025

Abstract

As climate change intensifies, cities are experiencing more severe rainfall and frequent waterlogging. When rainfall exceeds the carrying capacity of urban drainage networks, it poses a significant risk to urban facilities and public safety, seriously affecting sustainable urban development. Compared with general urban [...] Read more.

As climate change intensifies, cities are experiencing more severe rainfall and frequent waterlogging. When rainfall exceeds the carrying capacity of urban drainage networks, it poses a significant risk to urban facilities and public safety, seriously affecting sustainable urban development. Compared with general urban built-up areas, they demonstrate greater vulnerability to rainfall-induced waterlogging due to their obsolete infrastructure and high heritage value, making it imperative to comprehensively enhance their waterlogging resilience. In this study, Qingdao’s historic urban area is selected as a sample case to analyze the interaction between rainfall intensity, the built environment, and population and business characteristics and the mechanism of waterlogging disaster in the historic urban area by combining with the concept of resilience; then construct a resilience assessment system for waterlogging in the historic urban area in terms of dangerousness, vulnerability, and adaptability; and carry out a measurement study. Specifically, the CA model is used as the basic model for simulating the possibility of waterlogging, and the waterlogging resilience index is quantified by combining the traditional research data and the emerging open-source geographic data. Furthermore, the waterlogging resilience and obstacle factors of the 293 evaluation units were quantitatively evaluated by varying the rainfall characteristics. The study shows that the low flooding resilience in the historic city is found in the densely built-up areas within the historic districts, which are difficult to penetrate, because of the high vulnerability of the buildings themselves, their adaptive capacity to meet the high intensity of tourism and commercial activities, and the relatively weak resilience of the built environment to disasters. Based on the measurement results, targeted spatial optimization strategies and planning adjustments are proposed. Full article

(This article belongs to the Special Issue Advances in Remote Sensing and GIS for Natural Hazards Monitoring and Management)

► Show Figures

Figure 1

25 pages, 12494 KiB

Open AccessArticle

Grid Partition-Based Dynamic Spatial–Temporal Graph Convolutional Network for Large-Scale Traffic Flow Forecasting

by Lifeng Gao, Liujia Chen, Agen Qiu, Qinglian Wang, Jianlong Wang, Cai Chen, Fuhao Zhang and Geli Ou’er

ISPRS Int. J. Geo-Inf. 2025, 14(5), 207; https://doi.org/10.3390/ijgi14050207 - 19 May 2025

Abstract

Accurate forecasting of city-level large-scale traffic flow is crucial for efficient traffic management and effective transport planning. However, previously proposed traffic flow prediction methods model dynamic spatial correlations across entire traffic networks, leading to high computational complexity, elevated memory usage, and model overfitting. [...] Read more.

Accurate forecasting of city-level large-scale traffic flow is crucial for efficient traffic management and effective transport planning. However, previously proposed traffic flow prediction methods model dynamic spatial correlations across entire traffic networks, leading to high computational complexity, elevated memory usage, and model overfitting. Therefore, a novel grid partition-based dynamic spatial–temporal graph convolutional network was developed in this study to capture correlations within a large-scale traffic network. It includes the following: a dynamic graph convolution module to divide the traffic network into grid regions and thereby effectively capture the local spatial dependencies inherent in large-scale traffic topologies, an attention-based dynamic graph convolutional network to capture the local spatial correlations within each region, a global spatial dependency aggregation module to model inter-regional correlation weights using sequence similarity methods and comprehensively reflect the overall state of the traffic network, and multi-scale gated convolutions to capture both long- and short-term temporal correlations across varying time ranges. The performance of the proposed model was compared with that of different baseline models using two large-scale real-world datasets; the proposed model significantly outperformed the baseline models, demonstrating its potential effectiveness in managing large-scale traffic networks. Full article

(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation (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