ISPRS International Journal of Geo-Information

21 pages, 18118 KiB

Open AccessArticle

How Hydrological Extremes Affect the Chlorophyll-a Concentration in Inland Water in Jiujiang City, China: Evidence from Satellite Remote Sensing

by Wei Jiang, Xiaohui Ding, Fanping Kong, Gan Luo, Tengfei Long, Zhiguo Pang, Shiai Cui, Jie Liu and Elhadi Adam

ISPRS Int. J. Geo-Inf. 2025, 14(2), 85; https://doi.org/10.3390/ijgi14020085 (registering DOI) - 15 Feb 2025

Abstract

From 2020 to 2022, hydrological extremes such as severe floods and droughts occurred successively in Jiujiang city, Poyang Lake Basin, posing a threat to regional water quality safety. The chlorophyll-a (Chl-a) concentration is a key indicator of river eutrophication. Until now, there has [...] Read more.

From 2020 to 2022, hydrological extremes such as severe floods and droughts occurred successively in Jiujiang city, Poyang Lake Basin, posing a threat to regional water quality safety. The chlorophyll-a (Chl-a) concentration is a key indicator of river eutrophication. Until now, there has been a lack of empirical research exploring the Chl-a trend in inland water in Jiujiang in the context of hydrological extremes. In this study, Sentinel-2 satellite remote sensing data sourced from the Google Earth Engine (GEE) cloud platform, along with hourly water quality data collected from monitoring stations in Jiujiang city, Jiangxi Province, China, are utilized to develop a quantitative inversion model for the Chl-a concentration. The Chl-a concentrations for various inland water types were estimated for each quarter from 2020 to 2022, and the spatiotemporal distribution was analyzed. The main findings are as follows: (1) the quantitative inversion model for the Chl-a concentration was validated via in situ measurements, with a coefficient of determination of 0.563; (2) the spatial estimates of the Chl-a concentration revealed a slight increasing trend, increasing by 0.1193 μg/L from 2020 to 2022, closely aligning with the monitoring-station data; (3) an extreme drought in 2022 led to less water in inland water bodies, and consequently, the Chl-a concentration displayed a significant upward trend, especially in Poyang Lake, where the mean Chl-a concentration increased by approximately 1 μg/L from Q1 to Q2 in 2022. These findings revealed the seasonal changes in the Chl-a concentrations in inland waters in the context of extreme hydrological events, thus providing valuable information for the sustainable management of water quality in Jiujiang city. Full article

(This article belongs to the Special Issue Geographic Information Systems and Cartography for a Sustainable World)

28 pages, 10152 KiB

Open AccessArticle

A Multi-Scale Hybrid Scene Geometric Similarity Measurement Method Using Heterogeneous Graph Neural Network

by Chongya Gong, Tinghua Ai, Shiyu Chen, Tianyuan Xiao and Huafei Yu

ISPRS Int. J. Geo-Inf. 2025, 14(2), 84; https://doi.org/10.3390/ijgi14020084 - 14 Feb 2025

Abstract

Geographic features in maps consist of a mixture of points, polylines, and polygons, generally including POIs, roads, buildings, and other geographic features. Due to the differing dimensionality of these various types of geographic data, traditional geometric similarity measurement methods that rely on a [...] Read more.

Geographic features in maps consist of a mixture of points, polylines, and polygons, generally including POIs, roads, buildings, and other geographic features. Due to the differing dimensionality of these various types of geographic data, traditional geometric similarity measurement methods that rely on a single type of feature are not applicable to mixed scenes. The traditional solution to this issue is to treat points as projections of polylines and polylines as projections of polygons. Through neural networks, projection matrices can be learned to convert points, polylines, and polygons into the same type of object, thereby enabling the use of single-scene geometric measurement methods (e.g., Graph Neural Networks) to solve the problem. However, the key challenge in using Graph Neural Networks for similarity measurement is learning the adjacency relationships between geometric features. It is evident that the adjacency relationships between different feature pairs, such as polyline–polygon, polyline–polyline, and polygon–polygon, require different approaches for measurement, and these diverse relationships cannot be captured by a simple GNN. Heterogeneous Graph Neural Networks (HGNNs) are suited to address this problem: different adjacency relationships between feature pairs can be learned using distinct embedded networks, the new node characteristics can be calculated through the information aggregation and propagation framework of HGNNs, and these new characteristics can be used for geometric similarity measurement. Finally, the effectiveness of the proposed method was verified through practical experiments. Full article

18 pages, 2500 KiB

Open AccessArticle

4SIM: A Novel Description Model for the Ternary Spatial Relation “Between” of Buildings

by Hanxue Zhang, Xianyong Gong, Chengyi Liu, Fang Wu, Yue Qiu, Andong Wang and Yuyang Qi

ISPRS Int. J. Geo-Inf. 2025, 14(2), 83; https://doi.org/10.3390/ijgi14020083 - 13 Feb 2025

Abstract

Natural language spatial relations are often ambiguous and polysemic. They are also pluralistic and subjective in nature. Their descriptive methods are crucial but difficult in cartography, geographic information science, and map generalization. “Between” is a context-concerned spatial concept which is widely used to [...] Read more.

Natural language spatial relations are often ambiguous and polysemic. They are also pluralistic and subjective in nature. Their descriptive methods are crucial but difficult in cartography, geographic information science, and map generalization. “Between” is a context-concerned spatial concept which is widely used to describe the arrangement of spatial objects. It involves the spatial distribution of at least three spatial objects and describes a scenario in which one (or more) object(s) is surrounded by objects on both sides. Existing models based on RCC and the n-intersection model are mainly used to describe binary spatial logic and are inadequate in describing the “between” ternary relation effectively. At present, although existing models can describe and reason about such ternary spatial relations, their limitations still exist. The description capability of ternary spatial relations is unspecific and polysemic, and certain results are inconsistent with spatial cognition and perception and application requirements. Therefore, this paper proposes a 4 Sides Intersection Model (4SIM) to express the spatial relation among ternary buildings in detail. Theoretically, 4SIM can effectively describe 45 spatial relations among ternary objects through the topological distances among the four boundaries of the region formed by the intermediate object and the two adjacent objects. The 4SIM has been demonstrated to offer a superior degree of accuracy in the depiction of spatial relations in comparison to the extant RIM method, thus providing new possibilities for map generalization. Full article

► Show Figures

Figure 1

19 pages, 1220 KiB

Open AccessArticle

Spatial Network Analysis of CO₂ Emissions in Major Cities in China: Regional Structures and Influencing Factors

by Yue Zhao, Yuning Feng, Mingyi Du, Klaus Fraedrich and Zehao Shen

ISPRS Int. J. Geo-Inf. 2025, 14(2), 82; https://doi.org/10.3390/ijgi14020082 - 13 Feb 2025

Abstract

China’s rapid industrialization and urbanization have led to significant and imbalanced CO₂ emissions, putting pressure on achieving sustainable development goals. This study analyzed the CO₂ emissions of 31 major cities in China from different sectors (total, power, industry, and transport) from [...] Read more.

China’s rapid industrialization and urbanization have led to significant and imbalanced CO₂ emissions, putting pressure on achieving sustainable development goals. This study analyzed the CO₂ emissions of 31 major cities in China from different sectors (total, power, industry, and transport) from 2019 to 2022. This study constructs a city-scale CO₂ emission correlation model to achieve nationwide and urban fine-scale research on CO₂ emission spatial networks from different sectors. This study revealed the following: (i) there is an increasing correlation among regions in China, and collaborative governance is crucial; (ii) there are differences in the structure, characteristics, and roles of CO₂ emission networks from different sectors; (iii) China’s CO₂ emission network is mainly concentrated in the northern and eastern regions, which play an important role in emission reduction; and (iv) the impact factors have different effects on CO₂ emissions from different sectors, and we should actively contribute to promoting emission reduction. Correctly understanding the spatial characteristics and influencing factors of CO₂ emissions can help us formulate targeted and efficient emission reduction policies. Full article

(This article belongs to the Special Issue Geographic Information Systems and Cartography for a Sustainable World)

16 pages, 2163 KiB

Open AccessArticle

Developing a Spatial Analysis-Based Model for Assessing Investment Potential in Local Self-Government Using the Analytic Hierarchy Process

by Josip Lisjak, Hrvoje Tomić, Ante Rončević and Vlado Cetl

ISPRS Int. J. Geo-Inf. 2025, 14(2), 81; https://doi.org/10.3390/ijgi14020081 - 13 Feb 2025

Abstract

The paper presents research on investigating the possible impact of spatial characteristics of a certain location on its investment potential, in a general sense. By applying multi-criteria decision analysis with the AHP method, a model for the investment potential assessment at the level [...] Read more.

The paper presents research on investigating the possible impact of spatial characteristics of a certain location on its investment potential, in a general sense. By applying multi-criteria decision analysis with the AHP method, a model for the investment potential assessment at the level of local self-government units in Republic of Croatia is developed and presented. By applying the model, the investment potential index is calculated for sample LGUs in Croatia. The model is tested using a calculated and published development index of each LGU in Croatia and the calculated investment potential index. The development index is observed to be a measure of the success of previous investments and economic action in the LGU. The statistical tests returned positive results, confirming the statistical significance and validity of the model. Full article

► Show Figures

Figure 1

19 pages, 8912 KiB

Open AccessArticle

Revealing Spatial Patterns and Environmental Influences on Jogging Volume and Speed: Insights from Crowd-Sourced GPS Trajectory Data and Random Forest

by Xiao Yang, Chengbo Zhang and Linzhen Yang

ISPRS Int. J. Geo-Inf. 2025, 14(2), 80; https://doi.org/10.3390/ijgi14020080 - 13 Feb 2025

Abstract

Outdoor jogging plays a critical role in active mobility and transport-related physical activity (TPA), contributing to both urban health and sustainability. While existing studies have primarily focused on jogging participation volumes through survey data, they often overlook the real-time dynamics that shape jogging [...] Read more.

Outdoor jogging plays a critical role in active mobility and transport-related physical activity (TPA), contributing to both urban health and sustainability. While existing studies have primarily focused on jogging participation volumes through survey data, they often overlook the real-time dynamics that shape jogging experiences. This study seeks to provide a data-driven analysis of both jogging volume and speed, exploring how environmental factors influence these behaviors. Utilizing a dataset of over 1000 crowd-sourced jogging trajectories in Shenzhen, we spatially linked these trajectories to road-section-level units to map the distribution of jogging volume and average speed. By depicting a bivariate map of both behavioral characteristics, we identified spatial patterns in jogging behavior, elucidating variations in the distribution of volume and speed. A random forest regression model was validated and employed to capture nonlinear relationships and assess the differential impacts of various environmental factors on jogging volume and speed. The results reveal distinct jogging patterns across the city, where jogging volume is shaped by the mixed interplay of natural, visual, and built environment factors, while jogging speed is primarily influenced by visual factors. Additionally, the analysis highlights nonlinear effects, particularly identifying a threshold beyond which incremental environmental improvements provide diminishing returns in jogging speed. These findings clarify the distinct roles of environmental factors in influencing jogging volume and speed, offering insights into the dynamics of active mobility. Ultimately, this study provides data-informed implications for urban planners seeking to create environments that support TPA and promote active lifestyles. Full article

(This article belongs to the Topic The Use of Big Data in Public Health Research and Practice)

► Show Figures

Figure 1

Figure 1
Study area of Shenzhen and the distribution of jogging volume and speed. Full article ">Figure 2
Bivariate map of jogging volume and jogging speeds with representative environment photos of each pattern. Full article ">Figure 3
Relative variable importance of environmental variables on jogging volume (a) and speed (b). Variables from three categories are ranked by their average contributions to each metric. Full article ">Figure 4
Nonlinear effects of natural environment variables on jogging volume (left—a,c,e,g,i) and speed (right—b,d,f,h,j). Full article ">Figure 5
Nonlinear effects of built environment variables on jogging volume (left—a,c,e,g,i,k) and speed (right—b,d,f,h,j,l). Full article ">Figure 6
Nonlinear effects of visual environment variables on jogging volume (left—a,c,e,g) and speed (right—b,d,f,h). Full article ">

25 pages, 13626 KiB

Open AccessArticle

Fine-Tuning LLM-Assisted Chinese Disaster Geospatial Intelligence Extraction and Case Studies

by Yaoyao Han, Jiping Liu, An Luo, Yong Wang and Shuai Bao

ISPRS Int. J. Geo-Inf. 2025, 14(2), 79; https://doi.org/10.3390/ijgi14020079 - 11 Feb 2025

Abstract

The extraction of disaster geospatial intelligence (DGI) from social media data with spatiotemporal attributes plays a crucial role in real-time disaster monitoring and emergency decision-making. However, conventional machine learning approaches struggle with semantic complexity and limited Chinese disaster corpus. Recent advancements in large [...] Read more.

The extraction of disaster geospatial intelligence (DGI) from social media data with spatiotemporal attributes plays a crucial role in real-time disaster monitoring and emergency decision-making. However, conventional machine learning approaches struggle with semantic complexity and limited Chinese disaster corpus. Recent advancements in large language models (LLMs) offer new opportunities to overcome these challenges due to their enhanced semantic comprehension and multi-task learning capabilities. This study investigates the potential application of LLMs in disaster intelligence extraction and proposes an efficient, scalable method for multi-hazard DGI extraction. Building upon a unified ontological framework encompassing core natural disaster elements, this method employs parameter-efficient low-rank adaptation (LoRA) fine-tuning to optimize open-source Chinese LLMs using a meticulously curated instruction-tuning dataset. It achieves simultaneous identification of multi-hazard intelligence cues and extraction of disaster spatial entity attributes from unstructured Chinese social media texts through unified semantic parsing and structured knowledge mapping. Compared to pre-trained models such as BERT and ERNIE, the proposed method was shown to achieve state-of-the-art evaluation results, with the highest recognition accuracy (F1-score: 0.9714) and the best performance in structured information generation (BLEU-4 score: 92.9649). Furthermore, we developed and released DGI-Corpus, a Chinese instruction-tuning dataset covering various disaster types, to support the research and application of LLMs in this field. Lastly, the proposed method was applied to analyze the spatiotemporal evolution patterns of the Zhengzhou “7.20” flood disaster. This study enhances the efficiency of natural disaster monitoring and emergency management, offering technical support for disaster response and mitigation decision-making. Full article

(This article belongs to the Topic Machine Learning and Big Data Analytics for Natural Disaster Reduction and Resilience)

► Show Figures

Figure 1

37 pages, 6361 KiB

Open AccessArticle

Development of a Fifteen-Minute City Index Using Walkability Scores and Age-Classified Population: The Case of Pasig City, Metro Manila, Philippines

by Carlo Angelo R. Mañago, Marielle G. Nasalita, Cesar V. Saveron, Ynah Andrea D. Sunga and Alexis Richard C. Claridades

ISPRS Int. J. Geo-Inf. 2025, 14(2), 78; https://doi.org/10.3390/ijgi14020078 - 11 Feb 2025

Abstract

The 15-min city (FMC) is a people-oriented urban development strategy that aims to provide a higher quality of life by manifesting the people’s right to the city. This study proposes an FMC index that measures how close a specific area is to achieving [...] Read more.

The 15-min city (FMC) is a people-oriented urban development strategy that aims to provide a higher quality of life by manifesting the people’s right to the city. This study proposes an FMC index that measures how close a specific area is to achieving the 15-min accessibility to the six social functions (living, working, supplying, caring, learning, and enjoying). In the case of Pasig City, social function service areas were generated in terms of walkability and walking speeds per age group. Grid-based and population-based FMCI were calculated based on the established weights of points of interest and social functions, as well as the barangay population distribution per age group. The results show that 90% of the barangays achieved an FMCI of 0.5 or higher. This study presents an in-depth yet replicable approach using open-source data, considering facilities in each social function based on necessity of each age group, as well as utilizing pedestrian walkability as an impedance. Further, high population-based FMCI barangays cluster in the southern-central part of the city. The developed FMCI offers a compelling rationale for other HUCs to assess urban planning strategies, such as zoning strategies in the context of the weighted importance of amenities, walkability, and population distribution. Full article

► Show Figures

Figure 1

2 pages, 176 KiB

Open AccessCorrection

Correction: Lee, J.; Kang, Y. A Dynamic Algorithm for Measuring Pedestrian Congestion and Safety in Urban Alleyways. ISPRS Int. J. Geo-Inf. 2024, 13, 434

by Jiyoon Lee and Youngok Kang

ISPRS Int. J. Geo-Inf. 2025, 14(2), 77; https://doi.org/10.3390/ijgi14020077 - 11 Feb 2025

Abstract

We would like to address and correct errors found in the original publication of our article [...] Full article

(This article belongs to the Topic Technological Innovation and Emerging Operational Applications in Digital Earth)

13 pages, 5129 KiB

Open AccessArticle

Evaluating Digital Map Utilization and Interpretation Skills of Students

by Hiroyuki Yamauchi, Jiali Song, Takashi Oguchi, Takuro Ogura and Kotaro Iizuka

ISPRS Int. J. Geo-Inf. 2025, 14(2), 76; https://doi.org/10.3390/ijgi14020076 - 11 Feb 2025

Abstract

In recent years, secondary schools and university departments related to geography have begun to teach various topics using Geographic Information Systems (GIS). In particular, WebGIS, available online without installing additional software, is recognized as a powerful educational tool for educators and students. However, [...] Read more.

In recent years, secondary schools and university departments related to geography have begun to teach various topics using Geographic Information Systems (GIS). In particular, WebGIS, available online without installing additional software, is recognized as a powerful educational tool for educators and students. However, research on how students perceive and utilize digital maps to understand geographical objects and investigate the complexity of such learning is insufficient. Therefore, we initiated a study to clarify these research questions by implementing Disaster Risk Reduction (DRR) education using a digital hazard map developed with WebGIS technology, focusing on young people in Japan, including secondary school and university students. The results indicate that DRR education using a simple digital map is helpful for a wide range of students regardless of age. Still, some perceive difficulty in learning to use a digital hazard map. Map representation strongly affects students’ interpretation of vulnerable areas. The maps’ layers and functions are more useful when added gradually, corresponding to students’ ability and familiarity with GIS in the initial stage of geography education using maps to prevent students’ negative impressions caused by complex issues and technical problems. Full article

► Show Figures

Figure 1

21 pages, 7417 KiB

Open AccessArticle

Strategies for Glacier Retreat Communication with 3D Geovisualization and Open Data Sharing

by Federica Gaspari, Federico Barbieri, Rebecca Fascia, Francesco Ioli, Livio Pinto and Federica Migliaccio

ISPRS Int. J. Geo-Inf. 2025, 14(2), 75; https://doi.org/10.3390/ijgi14020075 - 10 Feb 2025

Abstract

Images of melting ice have become powerful symbols of climate change, attracting both public attention and scientific interest. This research uses web technologies to document and communicate the ongoing retreat of the Belvedere Glacier in the Italian Alps. By combining historical and contemporary [...] Read more.

Images of melting ice have become powerful symbols of climate change, attracting both public attention and scientific interest. This research uses web technologies to document and communicate the ongoing retreat of the Belvedere Glacier in the Italian Alps. By combining historical and contemporary 2D and 3D geospatial data, the paper presents a comprehensive digital platform that allows visualization of long-term changes of the Belvedere Glacier. To increase public understanding and engagement, we develop a user-friendly web platform that provides interactive tools for exploring glacier data. By fostering a deeper understanding of the complex processes involved in glacier retreat by different audiences (students, general public, and technical experts), this work aims to inspire further research and cooperation, also thanks to the reproducibility of the open-source code. Full article

(This article belongs to the Special Issue Geographic Information Systems and Cartography for a Sustainable World)

► Show Figures

Graphical abstract

24 pages, 2969 KiB

Open AccessArticle

Research on the Evaluation and Spatial Distribution Optimization of the Field Intensity Effect of Rural Basic Education Infrastructure in Wuhan’s New Urban District: A Case Study of Liji Township

by Liang Jiang, Jie Chen, Jing Luo and Guanghui Tian

ISPRS Int. J. Geo-Inf. 2025, 14(2), 74; https://doi.org/10.3390/ijgi14020074 - 10 Feb 2025

Abstract

Education infrastructure is a critical public service facility in rural areas. The evaluation of rural education infrastructure could have important implications for the spatial distribution optimization of public educational services in countryside regions. Based on the elementary education data and survey data of [...] Read more.

Education infrastructure is a critical public service facility in rural areas. The evaluation of rural education infrastructure could have important implications for the spatial distribution optimization of public educational services in countryside regions. Based on the elementary education data and survey data of Liji Town in 2022, this paper built an index evaluation system for Liji Township to explore the optimized spatial distribution mode of rural education infrastructure using models of MCR and field intensity. This system consisted of the potential energy of rural basic education infrastructure, as well as district and service thresholds. The results show the following: (1) The resistance of the rural education infrastructure in Liji Township was lower in the eastern and western parts of the township, as well as along the northern–southern county highway; however, the resistance was higher in the southern and northeastern areas. (2) There were significant differences in the potential energy component of education field intensity, showing a gradual decreasing tendency from the central villages to the peripheral villages. The spatial distribution of the central villages’ potential energy component was consistent with the component of the service threshold. However, the components of both district and service thresholds showed higher values for the suburban villages and lower values for the peripheral villages. (3) The rural basic education infrastructure can be divided into three types, and the corresponding development path is proposed in combination with different types. The optimization result is easy to explain and has potential applications in public education evaluation and facility layout planning. These modes can facilitate the allocation and spatial distribution optimization of basic education infrastructure in rural regions of metropolitan areas. Full article

► Show Figures

Figure 1

25 pages, 14056 KiB

Open AccessArticle

A System for Analysis and Simulating Hydraulic and Hydrogeological Risks Through WebGIS 3D Digital Platforms

by Mauro Mazzei and Davide Quaroni

ISPRS Int. J. Geo-Inf. 2025, 14(2), 73; https://doi.org/10.3390/ijgi14020073 - 10 Feb 2025

Abstract

The present research activity carried out demonstrated how simulation tools developed through WebGIS 3D digital platforms are capable of producing approximate forecasts of the effects of potentially catastrophic meteorological phenomena that may affect riverbeds in the territories observed. This work presents an analysis [...] Read more.

The present research activity carried out demonstrated how simulation tools developed through WebGIS 3D digital platforms are capable of producing approximate forecasts of the effects of potentially catastrophic meteorological phenomena that may affect riverbeds in the territories observed. This work presents an analysis and simulation platform with graphic representation of the results in the form of three-dimensional animation. This methodology may represent a useful tool for all bodies and organizations that need to create hypothetical scenarios for the management of emergencies related to flooding events in watercourses, especially in areas of maximum hydrogeological vulnerability in the Italian territory. These scenarios are particularly useful in cases where watercourses are located near inhabited centers, industrial areas or strategic infrastructures, where the risk of material damage and danger to the population is greater. The simulation is based on the morphology of the land adjacent to the bed of an affected watercourse, taking elevation into account to determine the direction of the expansion of the water mass. An important aspect of the platform is the extreme speed of simulation resolution, which allows the tool to be used even in real time. This real-time forecasting approach is crucial for making quick and informed decisions, thus reducing reaction times and improving emergency management on the ground, with a potential positive impact on the safety of the population and the protection of infrastructure. Full article

(This article belongs to the Topic Advances in Multi-Scale Geographic Environmental Monitoring: Theory, Methodology and Applications)

► Show Figures

Figure 1

27 pages, 3542 KiB

Open AccessArticle

Segmentation of Transaction Prices Submarkets in Vienna, Austria Using Multidimensional Spatiotemporal Change–DBSCAN (MDSTC-DBSCAN)

by Lorenz Treitler and Ourania Kounadi

ISPRS Int. J. Geo-Inf. 2025, 14(2), 72; https://doi.org/10.3390/ijgi14020072 - 10 Feb 2025

Abstract

This study delineates transaction price submarkets of dwellings in Vienna by performing spatiotemporal clustering and analysing the change in purchasing prices in these clusters between 2018 and 2022. The submarkets are created using a novel spatiotemporal clustering method referred to as Multidimensional Spatiotemporal [...] Read more.

This study delineates transaction price submarkets of dwellings in Vienna by performing spatiotemporal clustering and analysing the change in purchasing prices in these clusters between 2018 and 2022. The submarkets are created using a novel spatiotemporal clustering method referred to as Multidimensional Spatiotemporal Change–DBSCAN (MDSTC-DBSCAN), which incorporates the temporal change in transaction prices along with spatial proximity to identify spatial areas with similar transaction prices. It represents an advancement over MDST-DBSCAN for this use case, as it considers the change over time as valuable information rather than a constraint that further splits the clustering groups. The results of the case study in Vienna indicate variations in price growth rates among the submarkets (i.e., contiguous regions with similar prices and price growth rates) that confirm the importance of considering the temporal changes in transaction prices. With respect to the Viennese case study, a lower Moran’s I value was observed for 2022 compared to previous years (2018 to 2021), indicating a higher level of homogeneity in transaction prices. This finding was also supported by the cluster analysis, as less expensive clusters demonstrated higher rates of price increase compared to more expensive clusters. Future research can enhance the algorithm’s usability and broaden its potential use cases to other multidimensional spatiotemporal event data. Full article

► Show Figures

Figure 1

21 pages, 12882 KiB

Open AccessArticle

An Efficient Route Planning Algorithm for Special Vehicles with Large-Scale Road Network Data

by Ting Tian, Huijing Wu, Haitao Wei, Fang Wu and Mingliang Xu

ISPRS Int. J. Geo-Inf. 2025, 14(2), 71; https://doi.org/10.3390/ijgi14020071 - 10 Feb 2025

Abstract

During natural disasters such as earthquakes, fires, or landslides, the timely passage of special vehicles (primarily oversized vehicles) is crucial for successful emergency rescue operations. Efficient route planning algorithms capable of handling large-scale road networks are essential to facilitate this. This paper focuses [...] Read more.

During natural disasters such as earthquakes, fires, or landslides, the timely passage of special vehicles (primarily oversized vehicles) is crucial for successful emergency rescue operations. Efficient route planning algorithms capable of handling large-scale road networks are essential to facilitate this. This paper focuses on the rapid dispatch of special vehicles to their destinations within large-scale national road networks during emergency rescue operations. Using China’s national road network as a case study, a dual-layer road network data model was proposed to separate high-grade expressways from low-grade ordinary roadways to optimize data storage and access. A two-level spatial grid framework is also introduced to efficiently segment, extract, and store road network data. An improved algorithm constrained by a shortest-route planning objective function is proposed to improve route planning efficiency. This algorithm optimizes data access by loading high-grade road network data into memory once and only loading the necessary grid segments of low-grade road network data during route planning. The objective function incorporates constraints such as bridge weight and tunnel height limitations to ensure the safe passage of special vehicles. A parallelized bidirectional Dijkstra algorithm was proposed to further accelerate route planning. This approach simultaneously searches for optimal routes from both the starting and ending points, significantly improving efficiency for large-scale, cross-regional route planning. Experimental results demonstrate that our improved road network model and algorithm reduce search time by 1.69 times compared to conventional methods. The parallelized bidirectional Dijkstra algorithm further accelerates route planning by a factor of 3.75, achieving comparable performance to commercial software. The proposed road network model, route planning algorithm, and related findings offer valuable insights for optimizing emergency rescue operations and ensuring cost-effective resource allocation. Full article

► Show Figures

Figure 1

27 pages, 24272 KiB

Open AccessArticle

A Data Model and Method Framework for Cyberspace Map Visualization

by Zheng Zhang, Chenghu Zhou, Minjie Chen, Yibing Cao and Shaojing Fan

ISPRS Int. J. Geo-Inf. 2025, 14(2), 70; https://doi.org/10.3390/ijgi14020070 - 9 Feb 2025

Abstract

Integrating cyberspace and geographic space through map visualization is a valuable approach for revealing distribution patterns and relational dynamics in cyberspace. The interdisciplinary integration of network science and geographic science has gained increasing attention in recent years. However, current geographic information data models [...] Read more.

Integrating cyberspace and geographic space through map visualization is a valuable approach for revealing distribution patterns and relational dynamics in cyberspace. The interdisciplinary integration of network science and geographic science has gained increasing attention in recent years. However, current geographic information data models are not suitable for representing cyberspace features and their relations, and there is a lack of general and systematic cyberspace map visualization methods. To address these problems, this paper introduces an integrated data model that aligns spatial and cyberspace features based on a “proxy mode”. This model is designed to support both the visualization of data maps and the analysis of complex networks and graph layouts. In addition, a framework for cyberspace map visualization is introduced, comprising three main stages: “cyberspace data processing”, “cyberspace data rendering”, and “base map processing and map layout”. Using the Routers, BrightKite, and Cables datasets, we developed a web-based CMV system and generated a statistical map, a node-link map, an edge bundling map, a flow map, and a feature distribution map. The experimental results showed that the proposed data model and method framework can be effectively applied to represent the distribution and relations of cyberspace features and help reveal the interaction patterns between cyberspace and geographic space. Full article

► Show Figures

Figure 1

22 pages, 8143 KiB

Open AccessArticle

STPam: Software for Intelligently Analyzing and Mining Spatiotemporal Processes Based on Multi-Source Big Data

by Rongjun Xiong, Zeqiang Chen, Huiwen Pan, Dongyang Liu, Aiguo Sun and Nengcheng Chen

ISPRS Int. J. Geo-Inf. 2025, 14(2), 69; https://doi.org/10.3390/ijgi14020069 - 9 Feb 2025

Abstract

Analyzing and mining spatiotemporal processes refers to the extraction of geographic phenomena from spatiotemporal data and the analysis of available geographic knowledge and patterns. It finds applications in various fields such as natural disaster evolution, environmental pollution, and human behavior prediction. However, training [...] Read more.

Analyzing and mining spatiotemporal processes refers to the extraction of geographic phenomena from spatiotemporal data and the analysis of available geographic knowledge and patterns. It finds applications in various fields such as natural disaster evolution, environmental pollution, and human behavior prediction. However, training spatiotemporal models based on big data is time-consuming, and the traditional physical models and static objects used in existing geographic data analysis software have limitations in mining efficiency and simulation accuracy for dynamic spatiotemporal processes. In this paper, we develop an intelligent spatiotemporal process analysis and mining software tool, called STPam, which integrates a plug-and-play artificial intelligence model by a service-oriented method, distributed deep learning framework, and multi-source big data adaptation. The floods in the middle reaches of the Yangtze River have perennially affected safety and property in surrounding cities and communities. Therefore, this article applies the software to simulate the flooding process in the basin in 2022. The experimental results correspond to the rare drought phenomenon in the basin, demonstrating the practicality of the STPam software. In summary, STPam aids researchers in visualizing and analyzing geospatial processes and also holds potential application value in assisting regional management authorities in making disaster prevention and mitigation decisions. Full article

► Show Figures

Figure 1

20 pages, 4283 KiB

Open AccessArticle

A Dynamic and Timely Point-of-Interest Recommendation Based on Spatio-Temporal Influences, Timeliness Feature and Social Relationships

by Jun Zhu, Haifeng Lin, Zhinan Gou, Yiqing Xu, Hongying Liu, Ming Tang, Li Wang, Shu Li and Bing Hu

ISPRS Int. J. Geo-Inf. 2025, 14(2), 68; https://doi.org/10.3390/ijgi14020068 - 8 Feb 2025

Abstract

Point-of-interest (POI) recommendation is highly sensitive to temporal factors, including fluctuations in user preferences, variation in user similarity, and decay in the attraction of locations. However, current studies overlook the temporal dynamics of user similarity and the timeliness of POIs, resulting in a [...] Read more.

Point-of-interest (POI) recommendation is highly sensitive to temporal factors, including fluctuations in user preferences, variation in user similarity, and decay in the attraction of locations. However, current studies overlook the temporal dynamics of user similarity and the timeliness of POIs, resulting in a disconnect between recommendations and users’ recent preferences. This paper proposes a new framework for dynamic and timely POI recommendation by integrating spatio-temporal influences and social relationships. Dynamic prediction is achieved through an enhanced user-based collaborative filtering approach. A time slot clustering technique was designed based on the statistical check-in features in each time slot. Ratings within the same cluster were shared to address data sparsity. To reflect user similarity drift, we took the time variable as a crucial parameter to dynamically calculate user similarity. Moreover, timely prediction was achieved by integrating the timeliness, popularity, and spatial features of POIs. We introduce a novel method to evaluate the timeliness of POI recommendation, aimed at assessing whether the recommendations align with users’ recent preferences. Comprehensive experiments are performed on Brightkite and Gowalla datasets, with the data divided into workdays and weekends. The experimental results reveal that our algorithm outperforms seven state-of-the-art recommenders in terms of prediction accuracy and system timeliness. Full article

► Show Figures

Figure 1

18 pages, 4334 KiB

Open AccessArticle

In the Footsteps of Grandtourists: Envisioning Itineraries in Inner Areas for Literary and Responsible Tourism

by Paolo Zatelli, Nicola Gabellieri and Angelo Besana

ISPRS Int. J. Geo-Inf. 2025, 14(2), 67; https://doi.org/10.3390/ijgi14020067 - 7 Feb 2025

Abstract

In recent years, various scholars have called for the development of new forms of cultural tourism aimed at enhancing inland areas. Following this, this paper presents a method for semi-automatically constructing itineraries for cultural tourism, utilizing a geo-dataset of literary quotations, including quotes [...] Read more.

In recent years, various scholars have called for the development of new forms of cultural tourism aimed at enhancing inland areas. Following this, this paper presents a method for semi-automatically constructing itineraries for cultural tourism, utilizing a geo-dataset of literary quotations, including quotes and itineraries that can offer ideas for new storytelling, envisioning landscapes and cultural references for territorial valorization. This pilot case study focuses on the Dolomite area of the Fiemme and Fassa valleys, a well-known tourist destination also famous for its historic wood production. This study is based on a dataset of geolocated travel reports from 11 different 19th-century authors. These descriptions are classified into Points of Interest (POIs), and the point layer is integrated with a linear layer of the road and path network. Variables such as bus stops and travel time are also considered. The entire process is automated through a script that generates maps of optimal routes for each author, along with corresponding tables of travel times. This method enables the use of this dataset to design and develop specific cultural routes considering different variables. As a result, a cartography of multiple itineraries is proposed, which can serve as a tool for promoting cultural, sustainable and slow tourism development in an alpine inland area. Full article

► 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