[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Next Issue
Volume 13, May
Previous Issue
Volume 13, March
You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.9
2.8
Journals
IJGI
Volume 13
Issue 4
share announcement

ISPRS Int. J. Geo-Inf., Volume 13, Issue 4 (April 2024) – 35 articles

Cover Story (view full-size image): This study investigated the effectiveness of new point-of-interest pictograms on tourist maps to enhance the tourist experience in urban settings for individuals with specific needs, such as particular dietary, health, and clothing preferences. Six new pictogram designs showing healthcare, food, and apparel were assessed through a questionnaire involving 138 participants of diverse nationalities, ages, and educational backgrounds. The results revealed insights into the subtle cultural and lifestyle influences on pictogram perception. The findings provide a basis for considering the potential of the new pictogram designs in improving navigational experiences with geospatial information and encouraging sustainable tourist behaviors. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
18 pages, 5697 KiB  
Article
AED Inequity among Social Groups in Guangzhou
by Feng Gao, Siyi Lu, Shunyi Liao, Wangyang Chen, Xin Chen, Jiemin Wu, Yunjing Wu, Guanyao Li and Xu Han
ISPRS Int. J. Geo-Inf. 2024, 13(4), 140; https://doi.org/10.3390/ijgi13040140 - 22 Apr 2024
Viewed by 1663
Abstract
Automated external defibrillators (AEDs) are regarded as the most important public facility after fire extinguishers due to their importance to out-of-hospital cardiac arrest (OHCA) victims. Previous studies focused on the location optimization of the AED, with little attention to inequity among different social [...] Read more.
Automated external defibrillators (AEDs) are regarded as the most important public facility after fire extinguishers due to their importance to out-of-hospital cardiac arrest (OHCA) victims. Previous studies focused on the location optimization of the AED, with little attention to inequity among different social groups. To comprehensively investigate the spatial heterogeneity of the AED inequity, we first collected AED data from a WeChat applet. Then, we used the geographically weighted regression (GWR) model to quantify the inequity level and identify the socio-economic status group that faced the worst inequity in each neighborhood. Results showed that immigrants of all ages suffer a more severe AED inequity than residents after controlling population and road density. Immigrants face more severe inequity in downtown, while residents face more severe inequity in the peripheral and outer suburbs. AED inequity among youngsters tends to be concentrated in the center of each district, while inequity among the elderly tends to be distributed at the edge of each district. This study provides a new perspective for investigating the inequity in public facilities, puts forward scientific suggestions for future AED allocation planning, and emphasizes the importance of the equitable access to AED. Full article
(This article belongs to the Special Issue HealthScape: Intersections of Health, Environment, and GIS&T)
►▼ Show Figures

Figure 1

Figure 1
<p>Definition of AED inequity.</p> Full article ">Figure 2
<p>The theoretical framework of the AED inequity.</p> Full article ">Figure 3
<p>The process of the data collection and availability measurement of the AED.</p> Full article ">Figure 4
<p>The number of the six social groups in the study area.</p> Full article ">Figure 5
<p>Spatial distribution of AED availability.</p> Full article ">Figure 6
<p>Spatial distribution of the GWR coefficients.</p> Full article ">Figure 7
<p>Spatial distribution of AED inequity.</p> Full article ">Figure 8
<p>Spatial distribution of the worst type of AED inequity in each neighborhood.</p> Full article ">Figure 9
<p>Standardized coefficient statistics for each type of neighborhood.</p> Full article ">
22 pages, 4982 KiB  
Article
Research on the Spatial Network Structure of Tourist Flows in Hangzhou Based on BERT-BiLSTM-CRF
by Danfeng Qi, Bingbing Wang, Qiuhao Zhao and Pingbin Jin
ISPRS Int. J. Geo-Inf. 2024, 13(4), 139; https://doi.org/10.3390/ijgi13040139 - 21 Apr 2024
Cited by 1 | Viewed by 1690
Abstract
Tourist flows, crucial information within online travelogues, reveal the interactive relationships between different tourist destinations and serve as the nerve center and link of the tourism system. This study takes Hangzhou, China, as a case to investigate the spatial network structure of its [...] Read more.
Tourist flows, crucial information within online travelogues, reveal the interactive relationships between different tourist destinations and serve as the nerve center and link of the tourism system. This study takes Hangzhou, China, as a case to investigate the spatial network structure of its tourist flows. Firstly, a BERT-BiLSTM-CRF model and pan-attraction database are built to extract tourist attractions from online travelogues and create the tourist flow matrix. Then, this study uses social network analysis (SNA) to examine the structure of the tourist flow network from a county-level perspective. Additionally, GIS spatial analysis methods are applied to analyze the evolution of the tourist gravity center and standard deviation ellipse (SDE) of the network. The results reveal that the identification performances of the tourist flow extraction model this study proposed are significantly better than those of previous mainstream models, with an F1 value of 0.8752. Furthermore, the tourist flow network in Hangzhou displays a relatively sparse and unbalanced distribution, forming a “Core–Semi-Periphery–Periphery” structure. Lastly, from 2020 to 2022, the network’s gravity center experienced a shift towards the southwest, paralleled by an initial expansion and subsequent contraction of the SDE in the same southwest direction. These findings provide valuable insights into the spatial network structure of tourism in Hangzhou and can serve as a reference for policymakers to promote the “all-for-one” tourism. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Research area.</p> Full article ">Figure 2
<p>Research framework.</p> Full article ">Figure 3
<p>Framework of BERT-BiLSTM-CRF model.</p> Full article ">Figure 4
<p>Overall network structure of tourist flow in Hangzhou (threshold value = 7).</p> Full article ">Figure 5
<p>Original flow of tourism in Hangzhou. In the figure, dots represent the different county-level administrative divisions of Hangzhou. Larger, redder dots indicate stronger connections with other areas. Lines stand for the original tourism flow, with thicker, redder lines signifying heavier traffic.</p> Full article ">Figure 6
<p>Sankey diagram of Hangzhou’s tourism flow. The left column indicates the places where tourists originate, and the right column represents the destinations where tourists arrive.</p> Full article ">Figure 7
<p>The moving trajectory of the tourist gravity center in Hangzhou from 2020 to 2022.</p> Full article ">Figure 8
<p>The SDE changes in the tourist flow network in Hangzhou from 2020 to 2022.</p> Full article ">
15 pages, 2810 KiB  
Article
A Novel Address-Matching Framework Based on Region Proposal
by Yizhuo Quan, Yuanfei Chang, Linlin Liang, Yanyou Qiao and Chengbo Wang
ISPRS Int. J. Geo-Inf. 2024, 13(4), 138; https://doi.org/10.3390/ijgi13040138 - 21 Apr 2024
Viewed by 1177
Abstract
Geocoding is a fundamental component of geographic information science that plays a crucial role in various geographical studies and applications involving text data. Current mainstream geocoding methods fall into two categories: geodesic-grid prediction and address matching. However, the geodesic-grid-prediction method’s localization accuracy is [...] Read more.
Geocoding is a fundamental component of geographic information science that plays a crucial role in various geographical studies and applications involving text data. Current mainstream geocoding methods fall into two categories: geodesic-grid prediction and address matching. However, the geodesic-grid-prediction method’s localization accuracy is hindered by the density of grid partitioning, struggling to strike a balance between prediction accuracy and grid density. Address-matching methods mainly focus on the semantics of query text. However, they tend to ignore keyword information that can be used to distinguish candidates and introduce potential interference, which reduces matching accuracy. Inspired by the human map-usage process, we propose a two-stage address-matching approach that integrates geodesic-grid prediction and text-matching models. Initially, a multi-level text-classification model is used to generate a retrieval region proposal for an input query text. Subsequently, we search for the most relevant point of interest (POI) within the region-proposal area using a semantics-based text-retrieval model. We evaluated the proposed method using POI data from the Beijing Chaoyang District. The experimental results indicate that the proposed method provides high address-matching accuracy, increasing Recall@1 by 0.55 to 1.56 percentage points and MRR@5 by 0.54 to 1.68 percentage points. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Overview of region-proposal-based address matching.</p> Full article ">Figure 2
<p>Beijing’s Chaoyang district multi-level partitioning based on S2 geometry. Blue represents level 11, gray represents level 12, and green represents level 13.</p> Full article ">Figure 3
<p>Schematic diagram of PTMLG: (<b>a</b>) overall architecture and (<b>b</b>) details of a classification head.</p> Full article ">Figure 4
<p>Schematic of address matching based on a Bi-Encoder architecture.</p> Full article ">Figure 5
<p>(<b>a</b>) Line graph of loss changes during training and (<b>b</b>) line graph of learning-rate changes during training.</p> Full article ">Figure 6
<p>(<b>a</b>) Spatial distribution and (<b>b</b>) heat map of misclassified samples. In the heat map, red indicates a denser distribution and green indicates a more dispersed distribution.</p> Full article ">
16 pages, 2062 KiB  
Article
Comprehension of City Map Pictograms Designed for Specific Tourists’ Needs
by Dorotea Kovačević, Maja Brozović and Klementina Možina
ISPRS Int. J. Geo-Inf. 2024, 13(4), 137; https://doi.org/10.3390/ijgi13040137 - 18 Apr 2024
Viewed by 1609
Abstract
This study investigated the effectiveness of new point-of-interest (POI) pictograms on tourist maps within the Croatian and Slovenian contexts, focusing on enhancing the tourist experience in urban settings for individuals with specific needs. Despite the widespread use of tourist maps, there is a [...] Read more.
This study investigated the effectiveness of new point-of-interest (POI) pictograms on tourist maps within the Croatian and Slovenian contexts, focusing on enhancing the tourist experience in urban settings for individuals with specific needs. Despite the widespread use of tourist maps, there is a lack of research evaluating POI pictograms tailored to the needs of tourists with specific dietary, health-related, and sustainable clothing purchases. To fill this gap, we designed six new pictograms in three domains: healthcare, food, and apparel. The pictograms were evaluated using an online questionnaire involving 138 participants with a diverse range of ages and educational backgrounds. The results on comprehension and subjective assessments of the pictograms’ qualities revealed insights into the subtle cultural and lifestyle influences on pictogram perception. The findings provide a basis for considering the potential of new pictogram designs in improving navigational experiences with geospatial information and encouraging sustainable tourist behaviors. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Visual construction of the pictograms in the study; example with the pictogram for a medical supply store.</p> Full article ">Figure 2
<p>Pictograms used in the questionnaire: P1—a medical supply store; P2—a cobbler; P3—a second-hand clothing store; P4—an artisan bakery; P5—a gluten-free restaurant; P6—an herbal pharmacy.</p> Full article ">Figure 3
<p>The surroundings of each pictogram among other existing pictograms in the evaluation of the perceived pictogram noticeability.</p> Full article ">Figure 4
<p>Distribution of the correct interpretations of the pictograms (P1—a medical supply store; P2—a cobbler; P3—a second-hand clothing store; P4—an artisan bakery; P5—a gluten-free restaurant; P6—an herbal pharmacy) split by nation. The red line indicates a 67% minimum criterion for successful interpretation.</p> Full article ">Figure 5
<p>Ratings for the perceived noticeability of pictograms as evaluated by participants across three self-reported travel frequency levels (P1—a medical supply store; P3—a second-hand clothing store; P4—an artisan bakery). Boxes show median with interquartile range, whiskers show the range.</p> Full article ">
16 pages, 45757 KiB  
Article
Scale Distribution of Retail Formats in the Central Districts of Chinese Cities: A Study Analysis of Ten Cities
by Yi Shi, Yidian Wang, Yifan Ren, Chunyu Zhou and Xinyu Hu
ISPRS Int. J. Geo-Inf. 2024, 13(4), 136; https://doi.org/10.3390/ijgi13040136 - 18 Apr 2024
Cited by 1 | Viewed by 1335
Abstract
Analyses of urban hierarchy and scale distribution are crucial in urban research, as they examine the laws of urban development and the functional layout of urban spatial systems. However, previous studies have focused on the macro-spatial distribution of the economy, businesses, and population [...] Read more.
Analyses of urban hierarchy and scale distribution are crucial in urban research, as they examine the laws of urban development and the functional layout of urban spatial systems. However, previous studies have focused on the macro-spatial distribution of the economy, businesses, and population at the regional level, whereas systematic research on the scale distribution of retail formats in central urban areas is lacking. Therefore, this study investigated the hierarchical scale distribution of retail formats in the top ten cities in China by GDP, using the Public Service Facilities Index Method to define central district boundaries, using scale as an epistemological framework of order and analyzing the spatial distribution patterns of retail formats. The results revealed that the spatial hierarchical scale follows a power law within a certain range; the spatial distribution exhibits stage characteristics, providing a quantitative method for defining retail centres; and the dominant functions, development directions, and morphological characteristics of central districts influence the hierarchical scale distribution of retail formats. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Technical framework of the distribution dataset for the business type scale in urban central areas.</p> Full article ">Figure 2
<p>Index method for public service facilities.</p> Full article ">Figure 3
<p>Research areas and the corresponding information. (<b>A</b>) Shanghai Lujiazui, area: 27.17 km<sup>2</sup>; (<b>B</b>) Beijing Chaoyangmen, area: 88.35 km<sup>2</sup>; (<b>C</b>) Shenzhen Futian, area: 32.79 km<sup>2</sup>; (<b>D</b>) Guangzhou Tianhe, area: 20.73 km<sup>2</sup>; (<b>E</b>) Chongqing Jiangbei, area: 40.95 km<sup>2</sup>; (<b>F</b>) Suzhou Pingjiang, area: 28.11 km<sup>2</sup>; (<b>G</b>) Chengdu Tianfu, area: 35.94 km<sup>2</sup>; (<b>H</b>) Hangzhou Gongshu, area: 143.34 km<sup>2</sup>; (<b>I</b>) Wuhan Gongshu, area: 186.90 km<sup>2</sup>; (<b>J</b>) Nanjing Xinjiekou, area: 17.37 km<sup>2</sup>.</p> Full article ">Figure 4
<p>Spatial distribution of retail business levels in urban central areas.</p> Full article ">Figure 4 Cont.
<p>Spatial distribution of retail business levels in urban central areas.</p> Full article ">Figure 5
<p>Fitting results of power-law distribution for retail business types in urban central areas.</p> Full article ">Figure 6
<p>Schematic diagram of power; law layer.</p> Full article ">Figure 7
<p>Schematic diagram of power; law dataset.</p> Full article ">Figure 8
<p>Location of boundary circles in ten city centres.</p> Full article ">
20 pages, 3080 KiB  
Article
A Hierarchy-Aware Geocoding Model Based on Cross-Attention within the Seq2Seq Framework
by Linlin Liang, Yuanfei Chang, Yizhuo Quan and Chengbo Wang
ISPRS Int. J. Geo-Inf. 2024, 13(4), 135; https://doi.org/10.3390/ijgi13040135 - 17 Apr 2024
Cited by 3 | Viewed by 1533
Abstract
Geocoding converts unstructured geographic text into structured spatial data, which is crucial in fields such as urban planning, social media spatial analysis, and emergency response systems. Existing approaches predominantly model geocoding as a geographic grid classification task but struggle with the output space [...] Read more.
Geocoding converts unstructured geographic text into structured spatial data, which is crucial in fields such as urban planning, social media spatial analysis, and emergency response systems. Existing approaches predominantly model geocoding as a geographic grid classification task but struggle with the output space dimensionality explosion as the grid granularity increases. Furthermore, these methods generally overlook the inherent hierarchical structure of geographical texts and grids. In this paper, we propose a hierarchy-aware geocoding model based on cross-attention within the Seq2Seq framework, incorporating S2 geometry to model geocoding as a task for generating grid labels and predicting S2 tokens (labels of S2 grids) character-by-character. By incorporating a cross-attention mechanism into the decoder, the model dynamically perceives the address contexts at the hierarchical level that are most relevant to the current character prediction based on the input address text. Results show that the proposed model significantly outperforms previous approaches across multiple metrics, with a median and mean distance error of 41.46 m and 93.98 m, respectively. Furthermore, our method achieves superior results compared to others in regions with sparse data distribution, reducing the median and mean distance error by 16.27 m and 7.52 m, respectively, suggesting that our model has effectively mitigated the issue of insufficient learning in such regions. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Overall method framework.</p> Full article ">Figure 2
<p>HAGM architecture.</p> Full article ">Figure 3
<p>Examples of geocoding results visualization for (<b>a</b>) SLG, (<b>b</b>) MLG, (<b>c</b>) MLSG, and (<b>d</b>) HAGM (ours) at their optimal levels.</p> Full article ">Figure 4
<p>Visualization of performance comparison between SLG, MLG, MLSG, and HAGM. The evaluation results presented in the graph are, in clockwise order, overall, dense area, regular area, and sparse area. We have normalized the mean and median distance errors for intuitive comparison. A larger value on the radar chart indicates better performance on that metric.</p> Full article ">
23 pages, 15828 KiB  
Article
Spatiotemporal Analysis of Water Body in the Chongming Island Region over the Past Decade Based on the ISUNet Model
by Lizhi Miao, Xinkai Feng, Lijun Yang, Yanhui Ren, Yamei Deng and Tian Hang
ISPRS Int. J. Geo-Inf. 2024, 13(4), 134; https://doi.org/10.3390/ijgi13040134 - 17 Apr 2024
Viewed by 1290
Abstract
Chongming Island and its surrounding areas are highly significant coastal regions in China. However, the regions undergo continuous changes owing to various factors, such as the sedimentation from the Yangtze River, human activities, and tidal movements. Chongming Island is part of the Yangtze [...] Read more.
Chongming Island and its surrounding areas are highly significant coastal regions in China. However, the regions undergo continuous changes owing to various factors, such as the sedimentation from the Yangtze River, human activities, and tidal movements. Chongming Island is part of the Yangtze River Delta, which is one of the most economically developed regions in China. Studying the water body changes in this area is of great importance for decision making in water resource conservation, coastal resource management, and ecological environmental protection. In this study, we propose an improved ISUNet model by enhancing the skip-connection operations in the traditional UNet architecture. We extracted and analyzed the water bodies in Chongming Island and its surrounding areas from 2013 to 2022, providing a detailed spatiotemporal analysis of the water body area over the years. The results indicate that the water body area in the study area has decreased by 267.8 km2 over the past decade, showing a gradually fluctuating downward trend with an average annual reduction of nearly 27 km2. The analysis suggests that the reduction in the water body area is mainly attributed to sedimentation near river channels and ports, the formation of sandbars owing to channel erosion, and the artificial construction of ports and coastal areas. The influencing factors include human activities and sedimentation from the Yangtze River Estuary. Specifically, human activities such as land reclamation, port construction, and aquaculture play a major role in causing changes in the area. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Schematic of the study area.</p> Full article ">Figure 2
<p>Flowchart of the current study.</p> Full article ">Figure 3
<p>Distribution of image collection dates.</p> Full article ">Figure 4
<p>Schematic diagram of the rotated image. (<b>a</b>) Original image; (<b>b</b>) rotated 90°; (<b>c</b>) rotated 180°; (<b>d</b>) rotated 270°.</p> Full article ">Figure 5
<p>Structure of the ISUNet model.</p> Full article ">Figure 6
<p>Results of visualization of each model (The locations of the red circle show the extraction of the detailed features by each model).</p> Full article ">Figure 6 Cont.
<p>Results of visualization of each model (The locations of the red circle show the extraction of the detailed features by each model).</p> Full article ">Figure 7
<p>Changing trend of water body area in the study area from 2013 to 2022.</p> Full article ">Figure 8
<p>Results of the analysis of water body changes in 2013 and 2022. (<b>a</b>): Satellite observation images in 2010.05.01; (<b>b</b>): Satellite observation images in 2013.05.25; (<b>c</b>): Satellite observation images in 2022.05.18; (<b>d</b>): Comparison of Water Body Change Areas between 2013 and 2022. (The numbers 1, 2, 3, 4 represent the serial numbers of areas where notable changes have occurred.)</p> Full article ">Figure 9
<p>Comparison of changing trends in this research and JRC dataset.</p> Full article ">
18 pages, 5079 KiB  
Article
An LLM-Based Inventory Construction Framework of Urban Ground Collapse Events with Spatiotemporal Locations
by Yanan Hao, Jin Qi, Xiaowen Ma, Sensen Wu, Renyi Liu and Xiaoyi Zhang
ISPRS Int. J. Geo-Inf. 2024, 13(4), 133; https://doi.org/10.3390/ijgi13040133 - 16 Apr 2024
Cited by 2 | Viewed by 1860
Abstract
Historical news media reports serve as a vital data source for understanding the risk of urban ground collapse (UGC) events. At present, the application of large language models (LLMs) offers unprecedented opportunities to effectively extract UGC events and their spatiotemporal information from a [...] Read more.
Historical news media reports serve as a vital data source for understanding the risk of urban ground collapse (UGC) events. At present, the application of large language models (LLMs) offers unprecedented opportunities to effectively extract UGC events and their spatiotemporal information from a vast amount of news reports and media data. Therefore, this study proposes an LLM-based inventory construction framework consisting of three steps: news reports crawling, UGC event recognition, and event attribute extraction. Focusing on Zhejiang province, China, as the test region, a total of 27 cases of collapse events from 637 news reports were collected for 11 prefecture-level cities. The method achieved a recall rate of over 60% and a precision below 35%, indicating its potential for effectively and automatically screening collapse events; however, the accuracy needs to be improved to account for confusion with other urban collapse events, such as bridge collapses. The obtained UGC event inventory is the first open access inventory based on internet news reports, event dates and locations, and collapse co-ordinates derived from unstructured contents. Furthermore, this study provides insights into the spatial pattern of UGC frequency in Zhejiang province, effectively supplementing the statistical data provided by the local government. Full article
(This article belongs to the Special Issue Innovative GIS Models and Approaches for Large Environmental and Urban Applications in the Age of AI)
►▼ Show Figures

Figure 1

Figure 1
<p>Map of Zhejiang province, China.</p> Full article ">Figure 2
<p>The framework for UGC inventory construction.</p> Full article ">Figure 3
<p>Prompt templates for the LLM model.</p> Full article ">Figure 4
<p>Evaluation of UGC event recognition model for each city.</p> Full article ">Figure 5
<p>Statistic characteristics of UGC events from 2005 to 2022.</p> Full article ">Figure 5 Cont.
<p>Statistic characteristics of UGC events from 2005 to 2022.</p> Full article ">Figure 6
<p>Probability density risk evaluation results.</p> Full article ">Figure 7
<p>Examples of false-positive events (collapse-related events).</p> Full article ">Figure 8
<p>Geo-hazard frequency quantification of cities in Zhejiang province.</p> Full article ">
17 pages, 33515 KiB  
Article
Evaluating the Impact of Human Activities on Vegetation Restoration in Mining Areas Based on the GTWR
by Li Guo, Jun Li, Chengye Zhang, Yaling Xu, Jianghe Xing and Jingyu Hu
ISPRS Int. J. Geo-Inf. 2024, 13(4), 132; https://doi.org/10.3390/ijgi13040132 - 16 Apr 2024
Cited by 2 | Viewed by 1472
Abstract
The clarification of the impact of human activities on vegetation in mining areas contributes to the harmonization of mining and environmental protection. This study utilized Geographically and Temporally Weighted Regression (GTWR) to establish a quantitative relationship among the Normalized Difference Vegetation Index ( [...] Read more.
The clarification of the impact of human activities on vegetation in mining areas contributes to the harmonization of mining and environmental protection. This study utilized Geographically and Temporally Weighted Regression (GTWR) to establish a quantitative relationship among the Normalized Difference Vegetation Index (NDVI), temperature, precipitation, and Digital Elevation Model (DEM). Furthermore, residual analysis was performed to remove the impact of natural factors and separately assess the impact of human activities on vegetation restoration. The experiment was carried out in Shangwan Mine, China, and following results were obtained: (1) During the period of 2000 to 2020, intensified huan activities corresponded to positive vegetation changes (NDVI-HA) that exhibited an upward trend over time. (2) The spatial heterogeneity of vegetation restoration was attributed to the DEM. It is negatively correlated with NDVI in natural conditions, while under the environment of mining activities, there is a positive correlation between NDVI-HA and DEM. (3) The contribution of human activities to vegetation restoration in mining areas has been steadily increasing, surpassing the influences of temperature and precipitation since 2010. The results of this study can provide important references for the assessment of vegetation restoration to some extent in mining areas. Full article
(This article belongs to the Topic Advances in Earth Observation and Geosciences)
►▼ Show Figures

Figure 1

Figure 1
<p>Geographic location of the study area and the distribution of sample points.</p> Full article ">Figure 2
<p>Extraction process of vegetation changes caused by human activities.</p> Full article ">Figure 3
<p>Scattered distribution of observed <span class="html-italic">NDVI</span> and predicted <span class="html-italic">NDVI</span> for 1996 and 1997.</p> Full article ">Figure 4
<p>Interannual trends of observed <span class="html-italic">NDVI</span> and predicted <span class="html-italic">NDVI</span>.</p> Full article ">Figure 5
<p>Interannual trend of mean and standard deviation of <span class="html-italic">NDVI</span> from 1986–2020.</p> Full article ">Figure 6
<p>Trend changes of <span class="html-italic">NDVI</span> for 1986–2020, (<b>a</b>) is the spatial distribution of Slope, (<b>b</b>) is the classes of vegetation change trends.</p> Full article ">Figure 7
<p>The results of GTWR modelling for the years 1990, 1991, and 1995, (<b>a</b>,<b>b</b>) represent the spatial distribution of the coefficients for temperature (<span class="html-italic">β</span><sub>2</sub>) and precipitation(<span class="html-italic">β</span><sub>1</sub>) in the driving model, respectively, (<b>c</b>) are the driving equations of the predicted <span class="html-italic">NDVI</span> for some sample points.</p> Full article ">Figure 8
<p>Extraction results of <span class="html-italic">NDVI</span>-HA for 2010, (<b>a</b>–<b>c</b>) represent the observed <span class="html-italic">NDVI</span>, predicted <span class="html-italic">NDVI</span>, and the <span class="html-italic">NDVI</span>-HA.</p> Full article ">Figure 9
<p>Box plot of <span class="html-italic">NDVI</span>-HA for 2000−2020.</p> Full article ">Figure 10
<p>Spatial distribution of <span class="html-italic">NDVI</span>-HA in two stages.</p> Full article ">Figure 11
<p>Distribution of sample points for different restoration grades in two stages.</p> Full article ">Figure 12
<p>Negative correlation between DEM and predicted <span class="html-italic">NDVI</span>.</p> Full article ">Figure 13
<p>Positive correlation between DEM and <span class="html-italic">NDVI</span>-HA.</p> Full article ">Figure 14
<p>Relative contributions of temperature, precipitation, and human activities to vegetation growth for 2000−2020.</p> Full article ">
27 pages, 11739 KiB  
Article
Unveiling the Non-Linear Influence of Eye-Level Streetscape Factors on Walking Preference: Evidence from Tokyo
by Lu Huang, Takuya Oki, Sachio Muto and Yoshiki Ogawa
ISPRS Int. J. Geo-Inf. 2024, 13(4), 131; https://doi.org/10.3390/ijgi13040131 - 15 Apr 2024
Viewed by 1876
Abstract
Promoting walking is crucial for sustainable development and fosters individual health and well-being. Therefore, comprehensive investigations of factors that make walking attractive are vital. Previous research has linked streetscapes at eye-level to walking preferences, which usually focuses on simple linear relationships, neglecting the [...] Read more.
Promoting walking is crucial for sustainable development and fosters individual health and well-being. Therefore, comprehensive investigations of factors that make walking attractive are vital. Previous research has linked streetscapes at eye-level to walking preferences, which usually focuses on simple linear relationships, neglecting the complex non-linear dynamics. Additionally, the varied effects of streetscape factors across street segments and intersections and different street structures remain largely unexplored. To address these gaps, this study explores how eye-level streetscapes influence walking preferences in various street segments and intersections in Setagaya Ward, Tokyo. Using street view data, an image survey, and computer vision algorithms, we measured eye-level streetscape factors and walking preferences. The Extreme Gradient Boosting (XGBoost) model was then applied to analyze their non-linear relationships. This study identified key streetscape factors influencing walking preferences and uncovered non-linear trends within various factors, showcasing a variety of patterns, including upward, downward, and threshold effects. Moreover, our findings highlight the heterogeneity of the structural characteristics of street segments and intersections, which also impact the relationship between eye-level streetscapes and walking preferences. These insights can significantly inform decision-making in urban streetscape design, enhancing pedestrian perceptions. Full article
(This article belongs to the Special Issue Application of Geographical Information System in Urban Design, Management or Evaluation)
►▼ Show Figures

Figure 1

Figure 1
<p>Case study site.</p> Full article ">Figure 2
<p>(<b>a</b>) Rail transit network and stations; (<b>b</b>) land use zones.</p> Full article ">Figure 3
<p>(<b>a</b>) Mapping different categories of street segments and (<b>b</b>) street intersections.</p> Full article ">Figure 4
<p>Analysis framework.</p> Full article ">Figure 5
<p>(<b>a</b>) Image comparison survey interface (translated to English, original in Japanese); (<b>b</b>) a network to infer walking preference at street segments and intersections; (<b>c</b>) training dataset parameters and results.</p> Full article ">Figure 6
<p>Mapping preference scores for street segments. (<b>a</b>,<b>b</b>) Examples of preference predictions for arterial street segments, (<b>c</b>,<b>d</b>) collector street segments, and (<b>e</b>,<b>f</b>) local street segments.</p> Full article ">Figure 7
<p>Mapping preference scores for street intersections. (<b>a</b>,<b>b</b>) Examples of preference predictions for arterial street intersections, (<b>c</b>,<b>d</b>) collector street intersections, and (<b>e</b>,<b>f</b>) local street intersections.</p> Full article ">Figure 8
<p>(<b>a</b>) Example of panoptic segmentation at a street intersection using the Mapillary Vista v2.0 dataset; (<b>b</b>) panoptic segmentation at a street segment using the Mapillary Vista v2.0 dataset; (<b>c</b>) panoptic segmentation at a street segment using the ADE20K dataset; (<b>d</b>) panoptic segmentation at a street intersection using the ADE20K dataset.</p> Full article ">Figure 9
<p>Relative importance of streetscapes on walking preference (street segments).</p> Full article ">Figure 10
<p>Relative importance of streetscapes on the walking preference (street intersections).</p> Full article ">Figure 11
<p>(<b>a</b>,<b>b</b>) PDP of skeletal factors affecting walking preferences for street segments.</p> Full article ">Figure 12
<p>(<b>a</b>–<b>t</b>) PDP of detailed factors affecting walking preferences for street segments.</p> Full article ">Figure 12 Cont.
<p>(<b>a</b>–<b>t</b>) PDP of detailed factors affecting walking preferences for street segments.</p> Full article ">Figure 13
<p>(<b>a</b>,<b>b</b>) PDP of skeletal factors affecting walking preferences for street intersections.</p> Full article ">Figure 14
<p>(<b>a</b>–<b>p</b>) PDP of detailed factors affecting walking preferences for street intersections.</p> Full article ">Figure 14 Cont.
<p>(<b>a</b>–<b>p</b>) PDP of detailed factors affecting walking preferences for street intersections.</p> Full article ">
24 pages, 12210 KiB  
Article
Multi-Criteria Framework for Routing on Access Land: A Case Study on Dartmoor National Park
by Rafael Felipe Sprent, James Haworth, Stefano Cavazzi and Ilya Ilyankou
ISPRS Int. J. Geo-Inf. 2024, 13(4), 130; https://doi.org/10.3390/ijgi13040130 - 14 Apr 2024
Viewed by 1492
Abstract
Creating routes across open areas is challenging due to the absence of a defined routing network and the complexity of the environment, in which multiple criteria may affect route choice. In the context of urban environments, research has found Visibility and Spider-Grid subgraphs [...] Read more.
Creating routes across open areas is challenging due to the absence of a defined routing network and the complexity of the environment, in which multiple criteria may affect route choice. In the context of urban environments, research has found Visibility and Spider-Grid subgraphs to be effective approaches that generate realistic routes. However, the case studies presented typically focus on plazas or parks with defined entry and exit points; little work has been carried out to date on creating routes across open areas in rural settings, which are complex environments with varying terrain and obstacles and undefined entry or exit points. To address this gap, this study proposes a method for routing across open areas based on a Spider-Grid subgraph using queen contiguity. The method leverages a Weighted Sum–Dijkstra’s algorithm to allow multiple criteria such as surface condition, total time, and gradient to be considered when creating routes. The method is tested on the problem of routing across two areas of Dartmoor National Park, United Kingdom. The generated routes are compared with benchmark algorithms and real paths created by users of the Ordnance Survey’s Maps App. The generated routes are found to be more realistic than those of the benchmark methods and closer to the real paths. Furthermore, the routes are able to bypass hazards and obstacles while still providing realistic and flexible routes to the user. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Examples of different algorithms for producing a subgraph and the route suggested by each from the top left of the park to the bottom right: (<b>a</b>) Delaunay separates the space into triangles which are balanced in size and shape; (<b>b</b>) Voronoi tries to split the spaces into equal sized areas; (<b>c</b>,<b>d</b>) Grid divides the area into a grid at two different resolutions; (<b>e</b>,<b>f</b>) Spider adds additional complexity splitting the grids into triangles at the same resolutions; (<b>g</b>) Visibility divide the space by using lines of sight from entrances and exits of the park; (<b>h</b>) Visibility GCP is a modified version of (<b>g</b>) that removes connections that are not linked to the network; (<b>i</b>) Skeleton shrinks the edges of the area until they meet and then divides based on the meeting points; (<b>j</b>) Exterior Edges only uses the boundaries of the area to create the subgraph [<a href="#B8-ijgi-13-00130" class="html-bibr">8</a>].</p> Full article ">Figure 2
<p>Additional subgraph options on a different open area suggested by Graser [<a href="#B9-ijgi-13-00130" class="html-bibr">9</a>]: (<b>A</b>): Medial Axis, built from a set of points that have more than one closest neighbour on the polygon boundary (often approximated by the Voronoi diagram); (<b>B</b>): Straight Skeleton, built by step-wise shrinking of the polygon; (<b>C</b>): 5 m Grid, which is a simple square grid with a cell size of 5 m; (<b>D</b>): Visibility, where nodes that have visible (straight-line) connections are linked.</p> Full article ">Figure 3
<p>Steps involved in a Weighted Linear Combination process. Given three raster layers—Population density, Slope, and Cost—the raw values are first normalised (in this case, using inverse MinMax normalisation where minimum values of each layer become 1, and maximum values become 0). Then, values in each layer are multiplied by each layer’s normalised criteria weight, after which each criteria value is added for each cell to produce final raster values.</p> Full article ">Figure 4
<p>(<b>A</b>): An illustration of nodes created for a subgraph at 25 m resolution in both x and y axes. (<b>B</b>): The same subgraph, but with queen contiguity links.</p> Full article ">Figure 5
<p>(<b>A</b>): Example identification of intersecting points with subgraph. Points in red represent the intersecting points and lines in red represent the link they correspond with. (<b>B</b>): Fully integrated example of PN path into the subgraph.</p> Full article ">Figure 6
<p>Example of spatial intersection to only leave blue area (access land) with maroon objects signifying hazards, obstructions, or private land.</p> Full article ">Figure 7
<p>Images of different land covers at Haytor Down. (<b>A</b>): Acid grassland; (<b>B</b>): Braken; (<b>C</b>): Heathland; (<b>D</b>): Gorse.</p> Full article ">Figure 8
<p>Cost Maps for all the weightings in the Spider-Grid algorithm. © Crown copyright and/or database rights 2022 OS (Research Licence).</p> Full article ">Figure 9
<p>Ordnance Survey MasterMap extract of Haytor Study area. © Crown copyright and/or database rights 2022 OS (Research Licence).</p> Full article ">Figure 10
<p>Density Comparison of the routes generated and the user routes for Haytor. © Crown copyright and/or database rights 2022 OS (Research Licence).</p> Full article ">Figure 11
<p>Density Comparison of the routes generated and the user routes for Houndtor © Crown copyright and/or database rights 2022 OS (Research Licence).</p> Full article ">Figure A1
<p>Complete subgraph creation process for Haytor Down. (<b>A</b>): Node creation, (<b>B</b>): Link creation, (<b>C</b>): Detailed Path Network integration, (<b>D</b>): Non access land removal, (<b>E</b>): MasterMap polygon layer removal, (<b>F</b>): MasterMap line layer removal. © Crown copyright and/or database rights 2022 OS (Research Licence).</p> Full article ">Figure A1 Cont.
<p>Complete subgraph creation process for Haytor Down. (<b>A</b>): Node creation, (<b>B</b>): Link creation, (<b>C</b>): Detailed Path Network integration, (<b>D</b>): Non access land removal, (<b>E</b>): MasterMap polygon layer removal, (<b>F</b>): MasterMap line layer removal. © Crown copyright and/or database rights 2022 OS (Research Licence).</p> Full article ">
25 pages, 6480 KiB  
Article
Spatial Relationship of Inter-City Population Movement and Socio-Economic Determinants: A Case Study in China Using Multiscale Geographically Weighted Regression
by Sihan Liu and Xinyi Niu
ISPRS Int. J. Geo-Inf. 2024, 13(4), 129; https://doi.org/10.3390/ijgi13040129 - 12 Apr 2024
Cited by 1 | Viewed by 1546
Abstract
In the current field of regional studies, there is a growing focus on regional spatial relationships from the perspective of functional linkages between cities. Inter-city population movement serves as an embodiment of the integrated functionality of cities within a region, and this is [...] Read more.
In the current field of regional studies, there is a growing focus on regional spatial relationships from the perspective of functional linkages between cities. Inter-city population movement serves as an embodiment of the integrated functionality of cities within a region, and this is closely tied to the socio-economic development of urban areas. This study utilized Location-Based Services (LBSs) to collect the scale of inter-city population movement across 355 cities in China. Additionally, socio-economic data published by local governments were incorporated. By establishing a Multiscale Geographically Weighted Regression (MGWR) model, this research explores the spatial relationships between inter-city population movement and socio-economic influencing factors in China. This study aims to elucidate the spatial scales of the relationships between various variables. Our research findings indicate that the relationship between inter-city population movement and potential socio-economic determinants exhibits spatial non-stationarity. It is better to explore this spatial relationship through the MGWR model as there are different determinants operating on inter-city population movement at different spatial scales. The spatial distribution of the coefficient estimates shows significant regional differences and numerical variations. In China’s economically developed coastal regions, there is relatively balanced development among cities, with advanced manufacturing and producer service industries acting as significant drivers of mobility. In inland regions of China, city size is the most influential variable, directing a substantial flow of human and economic resources towards regional socio-economic hubs such as provincial capitals. The main contribution of this study is the re-examination of the relationship between inter-city population movement and socio-economic factors from the perspective of spatial scales. This approach will help China to consider the heterogeneity of different regions more extensively when formulating regional development policies, thereby facilitating the targeted promotion of regional element flow. Full article
(This article belongs to the Special Issue Application of Geographical Information System in Urban Design, Management or Evaluation)
►▼ Show Figures

Figure 1

Figure 1
<p>Data processing methods.</p> Full article ">Figure 2
<p>Spatial distribution of inter-city population movement scale.</p> Full article ">Figure 3
<p>(<b>a</b>) Spatial distribution of residuals of OLS; (<b>b</b>) spatial distribution of residuals of GWR; (<b>c</b>) spatial distribution of residuals of MGWR.</p> Full article ">Figure 4
<p>Comparison of root mean squared error from Geographically Weighted Regression (GWR, depicted in red) and Multiscale Geographically Weighted Regression (MGWR, depicted in blue) for each parameter surface.</p> Full article ">Figure 5
<p>(<b>a</b>) Spatial distribution of intercept coefficients of GWR model; (<b>b</b>) spatial distribution of GDP coefficients of GWR model; (<b>c</b>) spatial distribution of PSPC coefficients of GWR model; (<b>d</b>) spatial distribution of SSPC coefficients of GWR model; (<b>e</b>) spatial distribution of TSPC coefficients of GWR model; (<b>f</b>) spatial distribution of GPBEPC coefficients of GWR model; (<b>g</b>) spatial distribution of AW coefficients of GWR model.</p> Full article ">Figure 6
<p>(<b>a</b>) Spatial distribution of intercept coefficients of MGWR model; (<b>b</b>) spatial distribution of GDP coefficients of MGWR model; (<b>c</b>) spatial distribution of PSPC coefficients of MGWR model; (<b>d</b>) spatial distribution of SSPC coefficients of MGWR model; (<b>e</b>) spatial distribution of TSPC coefficients of MGWR model; (<b>f</b>) spatial distribution of GPBEPC coefficients of MGWR model. (The results of the AW parameter distribution in all cities are non-significant).</p> Full article ">Figure A1
<p>(<b>a</b>) Spatial distribution of average inter-city population movement scale on weekdays; (<b>b</b>) spatial distribution of average inter-city population movement scale on weekends; (<b>c</b>) spatial distribution of average inter-city population movement scale in all research periods.</p> Full article ">
16 pages, 2260 KiB  
Article
Search Engine for Open Geospatial Consortium Web Services Improving Discoverability through Natural Language Processing-Based Processing and Ranking
by Elia Ferrari, Friedrich Striewski, Fiona Tiefenbacher, Pia Bereuter, David Oesch and Pasquale Di Donato
ISPRS Int. J. Geo-Inf. 2024, 13(4), 128; https://doi.org/10.3390/ijgi13040128 - 12 Apr 2024
Viewed by 1467
Abstract
The improvement of search engines for geospatial data on the World Wide Web has been a subject of research, particularly concerning the challenges in discovering and utilizing geospatial web services. Despite the establishment of standards by the Open Geospatial Consortium (OGC), the implementation [...] Read more.
The improvement of search engines for geospatial data on the World Wide Web has been a subject of research, particularly concerning the challenges in discovering and utilizing geospatial web services. Despite the establishment of standards by the Open Geospatial Consortium (OGC), the implementation of these services varies significantly among providers, leading to issues in dataset discoverability and usability. This paper presents a proof of concept for a search engine tailored to geospatial services in Switzerland. It addresses challenges such as scraping data from various OGC web service providers, enhancing metadata quality through Natural Language Processing, and optimizing search functionality and ranking methods. Semantic augmentation techniques are applied to enhance metadata completeness and quality, which are stored in a high-performance NoSQL database for efficient data retrieval. The results show improvements in dataset discoverability and search relevance, with NLP-extracted information contributing significantly to ranking accuracy. Overall, the GeoHarvester proof of concept demonstrates the feasibility of improving the discoverability and usability of geospatial web services through advanced search engine techniques. Full article
(This article belongs to the Special Issue Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery)
►▼ Show Figures

Figure 1

Figure 1
<p>Frontend and backend conceptualization of the architecture used for the GeoHarvester PoC, including Scraper for OWS retrieval, NLP preprocessing, search engine logic in a first Docker container, and the Redis database in a second Docker container.</p> Full article ">Figure 2
<p>Use of OWS metadata in Switzerland of the investigated service providers. (<b>a</b>) Percentage of keyword fields filled. (<b>b</b>) Percentage of abstract fields filled. (<b>c</b>) Average number of words in filled keyword fields.</p> Full article ">Figure 3
<p>Steps of the query expansion process and resulting tokens for the search in the database for exact and similarity matches.</p> Full article ">Figure 4
<p>Two-phase query times on Redis database.</p> Full article ">Figure 5
<p>GeoHarvester user interface: (<b>a</b>) presentation of search results for the query &lt;bees&gt; in German, (<b>b</b>) drop-down menu with export and visualizations options of the same query.</p> Full article ">
21 pages, 11156 KiB  
Article
Map Reading and Analysis with GPT-4V(ision)
by Jinwen Xu and Ran Tao
ISPRS Int. J. Geo-Inf. 2024, 13(4), 127; https://doi.org/10.3390/ijgi13040127 - 11 Apr 2024
Cited by 3 | Viewed by 2532
Abstract
In late 2023, the image-reading capability added to a Generative Pre-trained Transformer (GPT) framework provided the opportunity to potentially revolutionize the way we view and understand geographic maps, the core component of cartography, geography, and spatial data science. In this study, we explore [...] Read more.
In late 2023, the image-reading capability added to a Generative Pre-trained Transformer (GPT) framework provided the opportunity to potentially revolutionize the way we view and understand geographic maps, the core component of cartography, geography, and spatial data science. In this study, we explore reading and analyzing maps with the latest version of GPT-4-vision-preview (GPT-4V), to fully evaluate its advantages and disadvantages in comparison with human eye-based visual inspections. We found that GPT-4V is able to properly retrieve information from various types of maps in different scales and spatiotemporal resolutions. GPT-4V can also perform basic map analysis, such as identifying visual changes before and after a natural disaster. It has the potential to replace human efforts by examining batches of maps, accurately extracting information from maps, and linking observed patterns with its pre-trained large dataset. However, it is encumbered by limitations such as diminished accuracy in visual content extraction and a lack of validation. This paper sets an example of effectively using GPT-4V for map reading and analytical tasks, which is a promising application for large multimodal models, large language models, and artificial intelligence. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
►▼ Show Figures

Figure 1

Figure 1
<p>Map image reading and analysis process using GPT-4V in OpenAI API.</p> Full article ">Figure 2
<p>Prompt 1.1 and answers from three LMMs regarding to the map of spotted owls and its predicted habitats in Oregon, retrieved from [<a href="#B24-ijgi-13-00127" class="html-bibr">24</a>], with proper answers highlighted in green, and incorrect answers highlighted in red.</p> Full article ">Figure 3
<p>Prompt 1.2 and answers from three LMMs regarding to the generated maps, with proper answers highlighted in green.</p> Full article ">Figure 4
<p>Prompt 1.2 and Answers from LMMs regarding to the map of four thematic maps (names are redacted), retrieved from [<a href="#B27-ijgi-13-00127" class="html-bibr">27</a>], with proper answers highlighted in green, answers that may be considered true under certain conditions highlighted in orange, and incorrect answers highlighted in red.</p> Full article ">Figure 5
<p>Prompt 2.1 and GPT-4V’s Answer regarding to the map of hardware store clusters in the Midwest of the United States, retrieved from [<a href="#B29-ijgi-13-00127" class="html-bibr">29</a>], color scheme used in this figure corresponds to the one described in <a href="#ijgi-13-00127-f004" class="html-fig">Figure 4</a>, indicating accuracy levels.</p> Full article ">Figure 6
<p>Prompt 2.2 and GPT-4V’s Answer after prompt engineering (adding additional information) on Prompt 2.1, with proper answers highlighted in green.</p> Full article ">Figure 7
<p>Prompt 2.3 and GPT-4V’s Answer regarding the map of bivariate point distributions (represented as green and red dots), retrieved from [<a href="#B34-ijgi-13-00127" class="html-bibr">34</a>], with proper answers highlighted in green.</p> Full article ">Figure 8
<p>Prompt 2.4 and GPT-4V’s Answer regarding the map of bivariate point distribution (burglary and theft) overlaid with income background layer, with crime data collected from <a href="https://data.cityofchicago.org/Public-Safety/Crimes-2022/9hwr-2zxp/data" target="_blank">https://data.cityofchicago.org/Public-Safety/Crimes-2022/9hwr-2zxp/data</a>, and income data collected from American Community Survey 2021 5-Year Estimates, both of which were accessed on 30 December 2023.</p> Full article ">Figure 9
<p>Prompt 2.5 and GPT-4V’s Answer regarding the map comparison between two NTL images in Houston on 7 February 2021 (before the winter storm) and 16 February 2021 (during the winter storm), NTL images retrieved from NASA (<a href="https://appliedsciences.nasa.gov/our-impact/news/extreme-winter-weather-causes-us-blackouts" target="_blank">https://appliedsciences.nasa.gov/our-impact/news/extreme-winter-weather-causes-us-blackouts</a>, accessed on 30 December 2023), additional insights identified by GPT-4V are highlighted in bold.</p> Full article ">Figure 10
<p>Prompt 2.6 and GPT-4V’s Answer regarding the map for time-series analysis using divisional precipitation data from 2000 to 2020 at a 5-year interval (i.e., 2000, 2005, 2010, 2015, 2020), retrieved from the interactive mapping platform, Climate at the Glance, under the Climate Monitoring product provided by NOAA NCEI (<a href="https://www.ncei.noaa.gov/access/monitoring/climate-at-a-glance/divisional/mapping" target="_blank">https://www.ncei.noaa.gov/access/monitoring/climate-at-a-glance/divisional/mapping</a>, accessed on 30 December 2023).</p> Full article ">Figure 11
<p>Prompt 2.7 and GPT-4V’s Answer regarding the map comparison across three spatial scales (statewide, divisional, and county) using annual precipitation data in 2022, retrieved from the interactive mapping platform, Climate at the Glance, under the Climate Monitoring product provided by NOAA NCEI (<a href="https://www.ncei.noaa.gov/access/monitoring/climate-at-a-glance/divisional/mapping" target="_blank">https://www.ncei.noaa.gov/access/monitoring/climate-at-a-glance/divisional/mapping</a>, accessed on 30 December 2023), with proper answers highlighted in green.</p> Full article ">Figure 12
<p>Prompt 2.8 and GPT-4V’s Answer following up the prompt response in Prompt 2.7, insights for different locations were highlighted in bold.</p> Full article ">
16 pages, 3853 KiB  
Article
Comparison of Different Green Space Measures and Their Impact on Dementia Cases in South Korea: A Spatial Panel Analysis
by Wulan Salle Karurung, Kangjae Lee and Wonhee Lee
ISPRS Int. J. Geo-Inf. 2024, 13(4), 126; https://doi.org/10.3390/ijgi13040126 - 9 Apr 2024
Cited by 1 | Viewed by 1796
Abstract
Dementia has become a profound public health problem due to the number of patients increasing every year. Previous studies have reported that environmental factors, including greenness, may influence the development and progression of dementia. Studies have found that exposure to green space is [...] Read more.
Dementia has become a profound public health problem due to the number of patients increasing every year. Previous studies have reported that environmental factors, including greenness, may influence the development and progression of dementia. Studies have found that exposure to green space is associated with a lower incidence of dementia. However, many definitions of green space exist, and the effects of its use may differ with the type of green space. Therefore, two types of green space measures were considered in this study to assess the differences in their impact on the prevalence of dementia among females and males. This study used five years of data (2017–2021) from 235 districts in South Korea. The two green space measures used were open space density and normalized difference vegetation index (NDVI), which were derived from satellite images. The analysis utilized a combination of traditional and spatial panel analyses to account for the spatial and temporal effects of independent variables on dementia prevalence. The spatial autocorrelation results revealed that both measures of greenness were spatially correlated with dementia prevalence. The spatial panel regression results revealed a significant positive association between NDVI and dementia prevalence, and open space had a negative association with dementia prevalence in both genders. The difference in the findings can serve as the basis for further research when choosing a greenspace measure, as it affects the analysis results, depending on the objective of the study. This study adds to the knowledge regarding improving dementia studies and the application of spatial panel analysis in epidemiological studies. Full article
(This article belongs to the Special Issue HealthScape: Intersections of Health, Environment, and GIS&T)
►▼ Show Figures

Figure 1

Figure 1
<p>Map of the study area.</p> Full article ">Figure 2
<p>Spatial distribution of prevalence of dementia from 2017 to 2021: (<b>a</b>) prevalence of female dementia; (<b>b</b>) prevalence of male dementia.</p> Full article ">Figure 3
<p>Spatial distribution of NDVI and open space from 2017 to 2021: (<b>a</b>) prevalence of open space; (<b>b</b>) NDVI value.</p> Full article ">Figure 4
<p>Boxplot of dementia prevalence in females and males from 2017 to 2021.</p> Full article ">Figure 5
<p>Statistics value of global Moran’s I of the dementia prevalence in female and male patients from 2017 to 2021.</p> Full article ">Figure 6
<p>Cluster map of the result of bivariate Moran’s I between dementia patients and NDVI from 2017 to 2021: (<b>a</b>) female dementia and NDVI; (<b>b</b>) male dementia and NDVI.</p> Full article ">Figure 7
<p>Cluster map of the result of bivariate Moran’s I between dementia patients and open space: (<b>a</b>) female dementia and open space; (<b>b</b>) male dementia and open space.</p> Full article ">
24 pages, 11609 KiB  
Article
Enhancing Adversarial Learning-Based Change Detection in Imbalanced Datasets Using Artificial Image Generation and Attention Mechanism
by Amel Oubara, Falin Wu, Reza Maleki, Boyi Ma, Abdenour Amamra and Gongliu Yang
ISPRS Int. J. Geo-Inf. 2024, 13(4), 125; https://doi.org/10.3390/ijgi13040125 - 9 Apr 2024
Cited by 2 | Viewed by 1629
Abstract
Deep Learning (DL) has become a popular method for Remote Sensing (RS) Change Detection (CD) due to its superior performance compared to traditional methods. However, generating extensive labeled datasets for DL models is time-consuming and labor-intensive. Additionally, the imbalance between changed and unchanged [...] Read more.
Deep Learning (DL) has become a popular method for Remote Sensing (RS) Change Detection (CD) due to its superior performance compared to traditional methods. However, generating extensive labeled datasets for DL models is time-consuming and labor-intensive. Additionally, the imbalance between changed and unchanged areas in object CD datasets, such as buildings, poses a critical issue affecting DL model efficacy. To address this issue, this paper proposes a change detection enhancement method using artificial image generation and attention mechanism. Firstly, the content of the imbalanced CD dataset is enhanced using a data augmentation strategy that synthesizes effective building CD samples using artificial RS image generation and building label creation. The created building labels, which serve as new change maps, are fed into a generator model based on a conditional Generative Adversarial Network (c-GAN) to generate high-resolution RS images featuring building changes. The generated images with their corresponding change maps are then added to the CD dataset to create the balance between changed and unchanged samples. Secondly, a channel attention mechanism is added to the proposed Adversarial Change Detection Network (Adv-CDNet) to boost its performance when training on the imbalanced dataset. The study evaluates the Adv-CDNet using WHU-CD and LEVIR-CD datasets, with WHU-CD exhibiting a higher degree of sample imbalance compared to LEVIR-CD. Training the Adv-CDNet on the augmented dataset results in a significant 16.5% F1-Score improvement for the highly imbalanced WHU-CD. Moreover, comparative analysis showcases the superior performance of the Adv-CDNet when complemented with the attention module, achieving a 6.85% F1-Score enhancement. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Adversarial learning of the change detection model.</p> Full article ">Figure 2
<p>Comprehensive workflow: building change augmentation and detection.</p> Full article ">Figure 3
<p>Visualization of the number of changed and unchanged pixels and images in the LEVIR-CD and WHU-CD datasets.</p> Full article ">Figure 4
<p>The architecture of the buildings generator.</p> Full article ">Figure 5
<p>Illustration of building label creation.</p> Full article ">Figure 6
<p>Building change detection model composed of generator and discriminator networks. The generator aims to generate a CM and the discriminator examines whether the generated CM is real or fake.</p> Full article ">Figure 7
<p>Channel attention module that can refine the detailed feature.</p> Full article ">Figure 8
<p>Comparative visualization of different methods on the LEVIR-CD and WHU-CD test sets. For easier comparison, some of the relevant detection errors have been marked with red circles for false positives (<math display="inline"><semantics> <mrow> <mi>F</mi> <mi>P</mi> </mrow> </semantics></math>) and blue circles for false negatives (<math display="inline"><semantics> <mrow> <mi>F</mi> <mi>N</mi> </mrow> </semantics></math>).</p> Full article ">Figure 9
<p>Comparative visualizations of WHU-CD and LEVIR-CD image generation. (<b>a</b>) Image at T<sub>0</sub>, (<b>b</b>) Original image at T<sub>1</sub>, (<b>c</b>) Created building label, (<b>d</b>) Created image at T<sub>1</sub> using Copy-Paste, and (<b>e</b>) Generated image at T<sub>1</sub> using our building generator.</p> Full article ">Figure 10
<p>Qualitative results of the impact of increasing the number of changed samples in the training dataset on the prformance of Adv-CDNet with and without attention. The results of testing on the WHU-CD and LEVIR-CD test sets are illustrated in three examples for each data. For easier comparison, some of the relevant detection errors have been marked with red circles for false positives (<math display="inline"><semantics> <mrow> <mi>F</mi> <mi>P</mi> </mrow> </semantics></math>) and blue circles for false negatives (<math display="inline"><semantics> <mrow> <mi>F</mi> <mi>N</mi> </mrow> </semantics></math>).</p> Full article ">Figure 11
<p>Training loss of different training configurations of Adv-CDNet model on WHU-CD dataset.</p> Full article ">
20 pages, 16280 KiB  
Article
Mapmaking Process Reading from Local Distortions in Historical Maps: A Geographically Weighted Bidimensional Regression Analysis of a Japanese Castle Map
by Naoto Yabe
ISPRS Int. J. Geo-Inf. 2024, 13(4), 124; https://doi.org/10.3390/ijgi13040124 - 9 Apr 2024
Viewed by 1433
Abstract
Shoho Castle Maps are maps of castle towns throughout Japan drawn by Kano School painters on the order of the shogun in 1644. The Shoho Castle Map of Takada, Joetsu City, Niigata Prefecture was used to visualize local distortions in historical maps and [...] Read more.
Shoho Castle Maps are maps of castle towns throughout Japan drawn by Kano School painters on the order of the shogun in 1644. The Shoho Castle Map of Takada, Joetsu City, Niigata Prefecture was used to visualize local distortions in historical maps and to scrutinize the mapmaking process. A novel method, geographically weighted bidimensional regression, was developed and applied to visualize the local distortions of the map. Exaggerated expressions by mapmakers that have not been identified in previous studies were revealed. That is, in addition to the castle being drawn enlarged, the town where the merchants and artisans lived was drawn larger than the castle. Therefore, the Takada Shoho Castle Map reflects mapmakers’ intentions, besides enlarging military facilities, which appear to have emphasized the pictorial composition of the map by placing the main gate to the castle at the center and drawing the map area evenly from the center in a well-balanced layout. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Historical and modern maps of Takada. Source: (<b>a</b>) “Takada Castle Town map (250 × 205 cm)” produced by Archives Center, Joetsu City; (<b>b</b>) “GSI Maps” produced by Geospatial Information Authority of Japan (GSI). Partly modified by the author.</p> Full article ">Figure 2
<p>Trace drawing of the Shoho Castle Map of Takada.</p> Full article ">Figure 3
<p>Distortions in Euclidean and affine transformations.</p> Full article ">Figure 4
<p>Tissot’s indicatrices at 115 control points. The background maps are displayed with 70% transparency. Source: (<b>a</b>) “Takada Castle Town map (250 × 205 cm)” produced by Archives Center, Joetsu City. (<b>b</b>) “GSI Maps” produced by Geospatial Information Authority of Japan (GSI). Partly modified by the author.</p> Full article ">Figure 5
<p>Local distortions at 115 control points in the Shoho Castle Map of Takada.</p> Full article ">Figure 6
<p>Differences between the shear angles along the <span class="html-italic">x</span>- and <span class="html-italic">y</span>-axes.</p> Full article ">Figure 7
<p>Ratios of the lengths of line segments from the center (main gate) of the maps. The numbers connected by arrows indicate ratios calculated with respect to the line segment with a value of 1.0. The line segments connect the corresponding edges on the two maps. The background maps are displayed with 70% transparency. Source: (<b>a</b>) “Takada Castle Town map (250 × 205 cm)” produced by Archives Center, Joetsu City. (<b>b</b>) “GSI Maps” produced by Geospatial Information Authority of Japan (GSI). Partly modified by the author.</p> Full article ">Figure 8
<p>Magnified view of the area around the main gate of historical and modern maps of Takada. Source: (<b>a</b>) “Takada Castle Town map (250 × 205 cm)” produced by Archives Center, Joetsu City; (<b>b</b>) “GSI Maps” produced by Geospatial Information Authority of Japan (GSI). Partly modified by the author.</p> Full article ">
23 pages, 5308 KiB  
Article
Variability of Extreme Climate Events and Prediction of Land Cover Change and Future Climate Change Effects on the Streamflow in Southeast Queensland, Australia
by Hadis Pakdel, Sreeni Chadalavada, Md Jahangir Alam, Dev Raj Paudyal and Majid Vazifedoust
ISPRS Int. J. Geo-Inf. 2024, 13(4), 123; https://doi.org/10.3390/ijgi13040123 - 8 Apr 2024
Viewed by 1635
Abstract
The severity and frequency of extremes are changing; thus, it is becoming necessary to evaluate the impacts of land cover changes and urbanisation along with climate change. A framework of the Generalised Extreme Value (GEV) method, Google Earth Engine (GEE), and land cover [...] Read more.
The severity and frequency of extremes are changing; thus, it is becoming necessary to evaluate the impacts of land cover changes and urbanisation along with climate change. A framework of the Generalised Extreme Value (GEV) method, Google Earth Engine (GEE), and land cover patterns’ classification including Random Forest (RF) and Support Vector Machine (SVM) can be useful for streamflow impact analysis. For this study, we developed a unique framework consisting of a hydrological model in line with the Process-informed Nonstationary Extreme Value Analysis (ProNEVA) GEV model and an ensemble of General Circulation Models (GCMs), mapping land cover patterns using classification methods within the GEE platform. We applied these methods in Southeast Queensland (SEQ) to analyse the maximum instantaneous floods in non-stationary catchment conditions, considering the physical system in terms of cause and effect. Independent variables (DEM, population, slope, roads, and distance from roads) and an integrated RF, SVM methodology were utilised as spatial maps to predict their influences on land cover changes for the near and far future. The results indicated that physical factors significantly influence the layout of landscapes. First, the values of projected evapotranspiration and rainfall were extracted from the multi-model ensemble to investigate the eight GCMs under two climate change scenarios (RCP4.5 and RCP8.5). The AWBM hydrological model was calibrated with daily streamflow and applied to generate historical runoff for 1990–2010. Runoff was projected under two scenarios for eight GCMs and by incorporating the percentage of each land cover into the hydrological model for two horizons (2020–2065 and 2066–2085). Following that, the ProNEVA model was used to calculate the frequency and magnitude of runoff extremes across the parameter space. The maximum peak flood differences under the RCP4.5 and RCP8.5 scenarios were 16.90% and 15.18%, respectively. The outcomes of this study suggested that neglecting the non-stationary assumption in flood frequency can lead to underestimating the amounts that can lead to more risks for the related hydraulic structures. This framework is adaptable to various geographical regions to estimate extreme conditions, offering valuable insights for infrastructure design, planning, risk assessment, and the sustainable management of future water resources in the context of long-term water management plans. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Flowchart of GCMs projections, hydrological model, GEE, and GEV model to estimate streamflow extremes.</p> Full article ">Figure 2
<p>The study’s area geographical position in Australia (<b>Left</b>) and hydro-meteorological stations are taken into consideration throughout the catchment (<b>Right</b>).</p> Full article ">Figure 3
<p>Land cover changes workflow chart (<b>a</b>) and spatial distribution of both training and validation polygons (<b>b</b>).</p> Full article ">Figure 4
<p>Land cover changes from 2000 to 2080 in the Lockyer catchment.</p> Full article ">Figure 4 Cont.
<p>Land cover changes from 2000 to 2080 in the Lockyer catchment.</p> Full article ">Figure 5
<p>Spatial variables applied to the landcover changes projection in the Lockyer catchment.</p> Full article ">Figure 6
<p>Scatter plot of observed and simulated daily runoff at the Lockyer valley over the calibration (1990–2002) and validation periods (2003–2010).</p> Full article ">Figure 7
<p>Observed and simulated daily runoff at the Lockyer Valley over the calibration (1990–2002) and validation periods (2003–2010).</p> Full article ">Figure 8
<p>Ensemble projections of long-term average daily inflow at Lockyer Creek at Rifle Range Road station for near future (2020–2065) and far future (2066–2085) periods under RCP 4.5 and RCP 8.5.</p> Full article ">Figure 9
<p>NEVA’s non-stationary GEV framework output, standard return levels with the likelihood of design exceedance for flood for future periods (2020–2086) under stationary and non-stationary assumption. (Figure generated using MATLAB R2020b).</p> Full article ">
25 pages, 9966 KiB  
Article
Balancing Flood Control and Economic Development in Flood Detention Areas of the Yangtze River Basin
by Siyuan Liao, Chao Wang, Renke Ji, Xiang Zhang, Zhifei Wang, Wei Wang and Nengcheng Chen
ISPRS Int. J. Geo-Inf. 2024, 13(4), 122; https://doi.org/10.3390/ijgi13040122 - 8 Apr 2024
Cited by 1 | Viewed by 2051
Abstract
Serving as a crucial part of the Yangtze River Basin (YRB)’s flood control system, Flood Detention Areas (FDAs) are vital in mitigating large-scale floods. Urbanization has led to the development of urban FDAs, but significant losses could ensue if these FDAs are activated. [...] Read more.
Serving as a crucial part of the Yangtze River Basin (YRB)’s flood control system, Flood Detention Areas (FDAs) are vital in mitigating large-scale floods. Urbanization has led to the development of urban FDAs, but significant losses could ensue if these FDAs are activated. With improved reservoirs and embankments, flood pressure in the middle reaches has lessened, posing challenges in balancing flood control and economic benefits. This paper presents a comparative analysis of land use, GDP, and population in FDAs and adjacent cities, enhancing our understanding of their disparities and interrelations. Using the Analytic Hierarchy Process (AHP)–Entropy Weight Method (EW)–Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) comprehensive evaluation method, we assess changes in flood control and economic values in FDAs. The results show a conflict between flood control and economic policies in FDAs, highlighting their underestimated economic potential, especially in urban areas. This study identifies differences in economic development across FDAs and a strong correlation between flood control value and inundation rates. Based on evaluations and simulations of the 1954 flood, we provide recommendations for the FDAs’ construction plan, which serves the development and flood management of the YRB and offer insights for similar assessments elsewhere. Full article
(This article belongs to the Special Issue Application of Geographical Information System in Urban Design, Management or Evaluation)
►▼ Show Figures

Figure 1

Figure 1
<p>Distribution of FDAs in the YRB and research areas of land use, GDP, and population change. (<b>a</b>) Description of the YRB in China; (<b>b</b>) Description of the YRMUA and the FDAs in the YRB; (<b>c</b>) The distribution of FDAs: 1, Jingjiang; 2, Woshi; 3, Renmindayuan; 4, Huxi; 5, Weidihu; 6, Liujiaoshan; 7, Jiuyuan; 8, Xiguan; 9, Anli; 10, Li’nan; 11, Anchang; 12, Anhua; 13, Nanding; 14, Hekang; 15, Nanhan; 16, Minzhu; 17, Gongshuangcha; 18, Chengxi; 19, Beihu; 20, Yihe; 21, Quyuan; 22, Jicheng’anhe; 23, Qianlianghu; 24, Jianshe; 25, Jianxin; 26, Junshan; 27, Datonghudong; 28, Jiangnanlucheng; 29, Honghu West; 30, Honghu Middle; 31, Honghu East; 32, Xilianghu; 33, Dongxihu; 34, Wuhu; 35, Zhangduhu; 36, Baitanhu; 37, Dujiatai; 38, Kangshan; 39, Zhuhu; 40, Huanghu; 41, Fangzhouxietang; 42, Huayanghe. More details can be found in <a href="#app1-ijgi-13-00122" class="html-app">Table S1</a>; (<b>d</b>) Description of the research areas of land use, GDP, and population change. Jingzhou_FDA, Jingzhou, Nanchang_FDA, Nanchang, Wuhan_FDA, Wuhan, and FDA in this figure represent the FDAs around Jingzhou City, the areas of Jingzhou City, the FDAs around Nanchang City, the areas of Nanchang City, the FDAs around Wuhan City, the areas of Wuhan City, and the FDAs in the YRB, respectively.</p> Full article ">Figure 2
<p>Flowchart of the research methodology: AHP–EW–TOPSIS.</p> Full article ">Figure 3
<p>The changes in proportion of impervious area. More details can be found in <a href="#app1-ijgi-13-00122" class="html-app">Table S2</a>.</p> Full article ">Figure 4
<p>The growth rate of impervious area. More details can be found in <a href="#app1-ijgi-13-00122" class="html-app">Table S3</a>.</p> Full article ">Figure 5
<p>The changes in GDP per unit area in nine comparative regions from 1995 to 2020, measured in CNY ten thousand per square kilometer. More details can be found in <a href="#app1-ijgi-13-00122" class="html-app">Table S4</a>.</p> Full article ">Figure 6
<p>The changes in GDP growth rate in nine comparative regions from 1995 to 2020. More details can be found in <a href="#app1-ijgi-13-00122" class="html-app">Table S5</a>.</p> Full article ">Figure 7
<p>The comparison of flood control value distribution of FDAs in the YRB. (<b>a</b>) The distribution of flood control value of each FDA in 2020; (<b>b</b>) The level distribution of each FDA; (<b>c</b>) The distribution of number of historical activations of each FDA; (<b>d</b>) The inundation losses under the economic development conditions of each FDA in 2020. More details can be found in <a href="#app1-ijgi-13-00122" class="html-app">Table S6</a>.</p> Full article ">Figure 7 Cont.
<p>The comparison of flood control value distribution of FDAs in the YRB. (<b>a</b>) The distribution of flood control value of each FDA in 2020; (<b>b</b>) The level distribution of each FDA; (<b>c</b>) The distribution of number of historical activations of each FDA; (<b>d</b>) The inundation losses under the economic development conditions of each FDA in 2020. More details can be found in <a href="#app1-ijgi-13-00122" class="html-app">Table S6</a>.</p> Full article ">Figure 8
<p>The change rate of flood control value per unit area in FDAs in the YRB from 1995 to 2020. (The explanation of the numbers can be seen in <a href="#ijgi-13-00122-f001" class="html-fig">Figure 1</a>).</p> Full article ">Figure 9
<p>The change of economic value per unit area in FDAs of the YRB from 1995 to 2020. (<b>a</b>–<b>f</b>) represent the distribution of economic value of each FDA in 1995, 2000, 2005, 2010, 2015, 2020, respectively. More details can be found in <a href="#app1-ijgi-13-00122" class="html-app">Table S7</a>.</p> Full article ">Figure 10
<p>Change rate of economic value per unit area in FDAs of the YRB (1995–2020). (The explanation of the numbers can be seen in <a href="#ijgi-13-00122-f001" class="html-fig">Figure 1</a>).</p> Full article ">Figure 11
<p>The results of flood inundation and flood control value validation in the FDAs of the YRB. (<b>a</b>,<b>c</b>,<b>e</b>) represent the historical flood inundation situations in 2010, 2016, and 2020, respectively; (<b>b</b>,<b>d</b>,<b>f</b>) show the validation accuracy of flood control values for each FDA in 2010, 2015, and 2020, respectively. The validation method involves comparing the closeness of the flood control value rankings and the inundation rate rankings for each FDA. A value closer to 1 indicates higher validation accuracy for the FDA. More details about the validation accuracy of FCV can be found in <a href="#app1-ijgi-13-00122" class="html-app">Table S8</a>.</p> Full article ">Figure 11 Cont.
<p>The results of flood inundation and flood control value validation in the FDAs of the YRB. (<b>a</b>,<b>c</b>,<b>e</b>) represent the historical flood inundation situations in 2010, 2016, and 2020, respectively; (<b>b</b>,<b>d</b>,<b>f</b>) show the validation accuracy of flood control values for each FDA in 2010, 2015, and 2020, respectively. The validation method involves comparing the closeness of the flood control value rankings and the inundation rate rankings for each FDA. A value closer to 1 indicates higher validation accuracy for the FDA. More details about the validation accuracy of FCV can be found in <a href="#app1-ijgi-13-00122" class="html-app">Table S8</a>.</p> Full article ">Figure 12
<p>Utilization of FDAs during the recurrence of the 1954 flood; we represent the FDAs required for activation in the four scheduling simulations on a single map, where the varying shades of different colors indicate the total number of times each FDA needs to be activated across the four simulated dispatches. (The explanation of the numbers can be seen in <a href="#ijgi-13-00122-f001" class="html-fig">Figure 1</a>).</p> Full article ">
38 pages, 19420 KiB  
Article
Mapping the CityGML Energy ADE to CityGML 3.0 Using a Model-Driven Approach
by Carolin Bachert, Camilo León-Sánchez, Tatjana Kutzner and Giorgio Agugiaro
ISPRS Int. J. Geo-Inf. 2024, 13(4), 121; https://doi.org/10.3390/ijgi13040121 - 4 Apr 2024
Cited by 1 | Viewed by 1785
Abstract
With the increasing adoption of semantic 3D city models, the relevance of applications in the field of Urban Building Energy Modelling (UBEM) has rapidly grown, as the building sector accounts for a large part of the total energy consumption. UBEM allows us to [...] Read more.
With the increasing adoption of semantic 3D city models, the relevance of applications in the field of Urban Building Energy Modelling (UBEM) has rapidly grown, as the building sector accounts for a large part of the total energy consumption. UBEM allows us to better understand the energy performance of the building stock and can contribute to defining refurbishment strategies. However, UBEM applications require lots of heterogeneous data, eventually advocating for standards for data interoperability. The Energy Application Domain Extension has been created to cope with UBEM data requirements and offers a standardised data model that builds upon the CityGML standard. The Energy ADE 1.0, released in 2018, creates new classes and adds new properties to existing classes of the CityGML 2.0 Core and Building modules. CityGML 3.0, released in 2021, has introduced several changes to the data model and its ADE mechanism. These changes render the Energy ADE incompatible with CityGML 3.0. This article presents how the Energy ADE has been ported to CityGML 3.0 to allow, on the one hand, for a lossless data conversion and, on the other hand, to exploit the new characteristics of CityGML 3.0 while keeping a logical symmetry between the ADE classes of both CityGML versions. The article describes the chosen methodology, the mapping strategies, the implementation steps, as well as the data conversion tests to check the validity of the “new” Energy ADE for CityGML 3.0. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Schematic workflow to map and convert the Energy ADE to CityGML 3.0. Image adapted from [<a href="#B9-ijgi-13-00121" class="html-bibr">9</a>].</p> Full article ">Figure 2
<p>Package overview of the Energy ADE 1.0 for CityGML 2.0. The colours representing the different packages will be used throughout the article.</p> Full article ">Figure 3
<p>The modules in CityGML 3.0. Image adapted from [<a href="#B10-ijgi-13-00121" class="html-bibr">10</a>].</p> Full article ">Figure 4
<p>Overview of the classes making up the space concept in the CityGML 3.0 Core module. Image adapted from [<a href="#B7-ijgi-13-00121" class="html-bibr">7</a>].</p> Full article ">Figure 5
<p>Representation of the classes <span class="html-italic">AbstractSpace</span> (orange) and <span class="html-italic">AbstractSpaceBoundary</span> (blue) using the example of a building. Image adapted from [<a href="#B10-ijgi-13-00121" class="html-bibr">10</a>].</p> Full article ">Figure 6
<p>Representation of the classes <span class="html-italic">AbstractPhysicalSpace</span> (green) and <span class="html-italic">AbstractLogicalSpace</span> (brown) using the example of a building. Image adapted from [<a href="#B10-ijgi-13-00121" class="html-bibr">10</a>].</p> Full article ">Figure 7
<p>Representation of the classes <span class="html-italic">OccupiedSpace</span> and <span class="html-italic">UnoccupiedSpace</span> using the example of a building. Image taken from [<a href="#B10-ijgi-13-00121" class="html-bibr">10</a>].</p> Full article ">Figure 8
<p>Example of extending the existing CityGML 3.0 class <span class="html-italic">AbstractBuilding</span> by means of the ADE hook mechanism (<span class="html-italic">EnergyProperties</span>, via <span class="html-italic">ADEOfAbstractBuilding</span>) and by deriving a new class (<span class="html-italic">ThermalHull</span>) from the existing class <span class="html-italic">AbstractLogicalSpace</span>.</p> Full article ">Figure 9
<p>The Core module of the Energy ADE for CityGML 2.0.</p> Full article ">Figure 10
<p>The Core module of the Energy ADE for CityGML 3.0.</p> Full article ">Figure 11
<p>Mapping the volume attribute of _<span class="html-italic">AbstractBuilding</span> in the Energy ADE for CityGML 2.0 (on the left) to the volume attribute of <span class="html-italic">AbstractSpace</span> in CityGML 3.0 (on the right). The corresponding complex data types are matched accordingly.</p> Full article ">Figure 12
<p>The Building physics module in the Energy ADE for CityGML 2.0.</p> Full article ">Figure 13
<p>Option to map the Building Physics module classes to CityGML 3.0 by deriving them all from <span class="html-italic">AbstractCityObject</span> and, thus, keeping them closer together within the UML class diagram.</p> Full article ">Figure 14
<p>Option to map the Building physics module classes to CityGML 3.0 by their best semantic match.</p> Full article ">Figure 15
<p>Example of several options for the parent class of <span class="html-italic">AbstractThermalZone</span>. Eventually, <span class="html-italic">AbstractBuildingSubdivision</span> is chosen.</p> Full article ">Figure 16
<p>Excerpt of the CityGML 3.0 Construction module showing the different thematic surfaces.</p> Full article ">Figure 17
<p>The Building physics module in the Energy ADE for CityGML 3.0.</p> Full article ">Figure 18
<p>The Occupant behaviour module in the Energy ADE for CityGML 2.0.</p> Full article ">Figure 19
<p>Example of a problematic mapping scenario. When rigidly sticking to the mapping principles, <span class="html-italic">UsageZone</span> and <span class="html-italic">ThermalZone</span> should both be derived from CityGML 3.0’s <span class="html-italic">BuildingUnit</span>. As <span class="html-italic">BuildingUnit</span> is extended by the ADE properties of class <span class="html-italic">BuildingUnitOccupancy</span>, the ADE properties would also be inherited by <span class="html-italic">UsageZone</span> and <span class="html-italic">ThermalZone</span>, which is not desired. If both classes are derived instead from <span class="html-italic">AbstractBuildingSubdivision</span>, the mapping does not adhere to the “integrate as much as possible” principle, however, it solves the aforementioned problem of undesired class inheritance.</p> Full article ">Figure 20
<p>Excerpt of the Occupant behaviour module in the Energy ADE for CityGML 3.0. The full module is depicted in [<a href="#B15-ijgi-13-00121" class="html-bibr">15</a>].</p> Full article ">Figure 21
<p>Class <span class="html-italic">EnergyDemand</span> in the Energy ADE for CityGML 2.0 with the property <span class="html-italic">energyAmount</span> which references a time series through its property type <span class="html-italic">AbstractTimeSeries</span>.</p> Full article ">Figure 22
<p>The time series classes in the Energy ADE for CityGML 2.0.</p> Full article ">Figure 23
<p>Excerpt of the Energy ADE for CityGML 3.0, showcasing the UML modelling of time-varying properties.</p> Full article ">Figure 24
<p>The Dynamizer module of CityGML 3.0 (in cyan) extended with the mapped time series of the Energy ADE (in yellow).</p> Full article ">Figure 25
<p>The Schedule classes in the Energy ADE for CityGML 2.0.</p> Full article ">Figure 26
<p>The <span class="html-italic">Schedule</span> classes of the Energy ADE for CityGML 3.0.</p> Full article ">Figure 27
<p>The property <span class="html-italic">occupancyRate</span> represented in-line and highlighted in red (left) equals the by-reference representation (right).</p> Full article ">Figure 28
<p>Excerpt of the CityGML 3.0 Dynamizer module.</p> Full article ">Figure 29
<p>Excerpt of the CityGML 3.0 Dynamizer module (in cyan) with the added properties (in yellow) to map the DailyPatternSchedule.</p> Full article ">Figure 30
<p>Visualisation of the test dataset in the FZK ModelViewer. Upper picture: the CityModel with its LOD2 buildings and properties. Lower picture: the <span class="html-italic">UsageZone</span> of Building “Yoda’s Hut” with its properties and own geometry.</p> Full article ">Figure 31
<p>Schematic overview of the data conversion from Energy ADE for CityGML 2.0 to Energy ADE for CityGML 3.0 in FME. The “Input A” block stands for input class A, e.g., <span class="html-italic">ThermalZone</span>, and the “Output A” block for the respective output after the conversion. Unlike in CityGML 2.0, the <span class="html-italic">Schedule</span> and <span class="html-italic">Dynamizer</span> now have their own classes in the Energy ADE for CityGML 3.0, which is why they also have their own blocks to write the final output.</p> Full article ">
27 pages, 12972 KiB  
Article
How Does the 2D/3D Urban Morphology Affect the Urban Heat Island across Urban Functional Zones? A Case Study of Beijing, China
by Shouhang Du, Yuhui Wu, Liyuan Guo, Deqin Fan and Wenbin Sun
ISPRS Int. J. Geo-Inf. 2024, 13(4), 120; https://doi.org/10.3390/ijgi13040120 - 4 Apr 2024
Cited by 5 | Viewed by 2035
Abstract
Studying driving factors of the urban heat island phenomenon is vital for enhancing urban ecological environments. Urban functional zones (UFZs), key for planning and management, have a substantial impact on the urban thermal environment through their two-dimensional (2D)/three-dimensional (3D) morphology. Despite prior research [...] Read more.
Studying driving factors of the urban heat island phenomenon is vital for enhancing urban ecological environments. Urban functional zones (UFZs), key for planning and management, have a substantial impact on the urban thermal environment through their two-dimensional (2D)/three-dimensional (3D) morphology. Despite prior research on land use and landscape patterns, understanding the effects of 2D/3D urban morphology in different UFZs is lacking. This study employs Landsat-8 remote sensing data to retrieve the land surface temperature (LST). A method combining supervised and unsupervised classification is proposed for UFZ mapping, utilizing multi-source geospatial data. Subsequently, parameters defining the 2D/3D urban morphology of UFZs are established. Finally, the Pearson correlation analysis and GeoDetector are used to analyze the driving factors. The results indicate the following: (1) In the Fifth Ring Road area of Beijing, the residential zones exhibit the highest LST, followed by the industrial zones. (2) In 2D urban morphology, the percentage of built-up landscape (built-PLAND) and Shannon’s diversity index (SHDI) are the main factors influencing LST. In 3D urban morphology, building density, the sky view factor (SVF), and the area-weighted mean shape index (shape index) are the main factors influencing LST. Therefore, low-density buildings with simple and dispersed shapes contribute to mitigating LST, while fragmented distributions of trees, grasslands, and water bodies also play important roles in alleviating LST. (3) In the interactive detection results, all UFZs show the highest interaction detection results with the built-PLAND. (4) Spatial variations are observed in the impact of different UFZs on LST. For instance, in the residential zones, industrial zones, green space zones, and public service zones, the SVF is negatively correlated with LST, while in the commercial zones, the SVF exhibits a positive correlation with LST. Full article
(This article belongs to the Special Issue Application of Geographical Information System in Urban Design, Management or Evaluation)
►▼ Show Figures

Figure 1

Figure 1
<p>Study Area. (<b>a</b>) Beijing-Tianjin-Hebei region; (<b>b</b>) Fifth Ring Road of Beijing; (<b>c</b>) land cover map of the area within the Beijing Fifth Ring Road (data sourced from the European Space Agency: <a href="https://dataspace.copernicus.eu/" target="_blank">https://dataspace.copernicus.eu/</a> (accessed on 15 July 2023); (<b>d</b>) Sentinel-2 image.</p> Full article ">Figure 2
<p>Workflow of this study.</p> Full article ">Figure 3
<p>(<b>a</b>) Building height distribution within the Fifth Ring Road in Beijing. According to the “Chinese Civil Building Design Code”, buildings are divided into four categories: low-rise (&lt;10 m), mid-rise (10–24 m), high-rise (24–90 m) and super high-rise (&gt;90 m). (<b>b</b>) Building height of a sample area and (<b>c</b>) SVF.</p> Full article ">Figure 4
<p>UFZ mapping results.</p> Full article ">Figure 5
<p>Accuracy evaluation of UFZ mapping results.</p> Full article ">Figure 6
<p>LST inversion results within the Fifth Ring Road in Beijing.</p> Full article ">Figure 7
<p>LST of different UFZs (low temperature (≤29.85 °C), sub-low temperature (29.86–30.70 °C), medium temperature (30.71–31.43 °C), sub-high temperature (31.44–32.10 °C), high temperature (≥32.11 °C)).</p> Full article ">Figure 8
<p>LST distribution of UFZs.</p> Full article ">Figure 9
<p>Violin plot and box plot of LST in UFZs (the white point is the middle value, the middle rectangle represents the mean value, the box limits represent the upper and lower quartiles, respectively, the box error bar represents the range within 1.5 IQR, and the black line shows distribution of data).</p> Full article ">Figure 10
<p>Differences in the influence degree of 2D factors on different UFZs.</p> Full article ">Figure 11
<p>Differences in the influence degree of 3D factors on different UFZs.</p> Full article ">Figure 12
<p>Three-dimensional factor interaction detection results in UFZs ((<b>a</b>) residential zone; (<b>b</b>) commercial zone; (<b>c</b>) industrial zone; (<b>d</b>) green space; (<b>e</b>) public service zone).</p> Full article ">Figure 13
<p>Two-dimensional factor interaction detection results in UFZs ((<b>a</b>) residential zone; (<b>b</b>) commercial zone; (<b>c</b>) industrial zone; (<b>d</b>) green space; (<b>e</b>) public service zone).</p> Full article ">Figure 14
<p>Two-dimensional/three-dimensional factor interaction detection results in UFZs ((<b>a</b>) residential zone; (<b>b</b>) commercial zone; (<b>c</b>) industrial zone; (<b>d</b>) green space; (<b>e</b>) public service zone).</p> Full article ">
20 pages, 5721 KiB  
Article
Low-Cost Data, High-Quality Models: A Semi-Automated Approach to LOD3 Creation
by Harshit, Pallavi Chaurasia, Sisi Zlatanova and Kamal Jain
ISPRS Int. J. Geo-Inf. 2024, 13(4), 119; https://doi.org/10.3390/ijgi13040119 - 3 Apr 2024
Cited by 3 | Viewed by 2340
Abstract
In the dynamic realm of digital twin modeling, where advancements are swiftly unfolding, users now possess the unprecedented ability to capture and generate geospatial data in real time. This article delves into a critical exploration of this landscape by presenting a meticulously devised [...] Read more.
In the dynamic realm of digital twin modeling, where advancements are swiftly unfolding, users now possess the unprecedented ability to capture and generate geospatial data in real time. This article delves into a critical exploration of this landscape by presenting a meticulously devised workflow tailored for the creation of Level of Detail 3 (LOD3) models. Our research methodology capitalizes on the integration of Apple LiDAR technology alongside photogrammetric point clouds acquired from Unmanned Aerial Vehicles (UAVs). The proposed process unfolds with the transformation of point cloud data into Industry Foundation Classes (IFC) models, which are subsequently refined into LOD3 Geographic Information System (GIS) models leveraging the Feature Manipulation Engine (FME) workbench 2022.1.2. This orchestrated synergy among Apple LiDAR, UAV-derived photogrammetric point clouds, and the transformative capabilities of the FME culminates in the development of precise LOD3 GIS models. Our proposed workflow revolutionizes this landscape by integrating multi-source point clouds, imbuing them with accurate semantics derived from IFC models, and culminating in the creation of valid CityGML LOD3 buildings through sophisticated 3D geometric operations. The implications of this technical innovation are profound. Firstly, it elevates the capacity to produce intricate infrastructure models, unlocking new vistas for modeling digital twins. Secondly, it extends the horizons of GIS applications by seamlessly integrating enriched Building Information Modeling (BIM) components, thereby enhancing decision-making processes and facilitating more comprehensive spatial analyses. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Representation of the IFC structure as graph (<a href="https://blenderbim.org/" target="_blank">https://blenderbim.org/</a> accessed on 24 November 2023).</p> Full article ">Figure 2
<p>Representation of the same real-world building in Levels of Detail 0–3 [<a href="#B26-ijgi-13-00119" class="html-bibr">26</a>].</p> Full article ">Figure 3
<p>Workflow acquired for the current study.</p> Full article ">Figure 4
<p>(<b>a</b>) Geomatics building used for this study. (<b>b</b>) Photogrammetric point cloud of the Geomatics building.</p> Full article ">Figure 5
<p>(<b>a</b>) Apple iPad Pro used for corridor scanning. (<b>b</b>) Corridor point cloud scanned through Apple LiDAR.</p> Full article ">Figure 6
<p>(<b>a</b>) Scan of the first-floor corridor. (<b>b</b>) Scan of the ground floor corridor. (<b>c</b>) Outdoor point cloud registered with indoor point cloud.</p> Full article ">Figure 7
<p>Building information model recreated in Revit and visualized in BlenderBIM [<a href="#B52-ijgi-13-00119" class="html-bibr">52</a>] without any texture information.</p> Full article ">Figure 8
<p>FME workflow for converting IFC to CityGML.</p> Full article ">Figure 9
<p>Creation of the exterior shell of the building.</p> Full article ">Figure 10
<p>Joining with parent GML IDs and filtering into single features.</p> Full article ">Figure 11
<p>Roof, wall, and floor surface in CityGML.</p> Full article ">Figure 12
<p>Extraction of doors and windows.</p> Full article ">Figure 13
<p>Visualization and validation of CityGML schema in the FZK viewer [<a href="#B54-ijgi-13-00119" class="html-bibr">54</a>].</p> Full article ">Figure 14
<p>Visualization of the CityJSON schema in the NINJA viewer [<a href="#B57-ijgi-13-00119" class="html-bibr">57</a>].</p> Full article ">
15 pages, 6373 KiB  
Article
Animating Cartographic Meaning: Unveiling the Impact of Pictorial Symbol Motion Speed in Preattentive Processing
by Paweł Cybulski
ISPRS Int. J. Geo-Inf. 2024, 13(4), 118; https://doi.org/10.3390/ijgi13040118 - 3 Apr 2024
Cited by 2 | Viewed by 1469
Abstract
The primary objective of this study is to assess how the motion of dynamic point symbols impacts preattentive processing on a map. Specifically, it involves identifying the motion velocity parameters for cartographic animated pictorial symbols that contribute to the preattentive perception of the [...] Read more.
The primary objective of this study is to assess how the motion of dynamic point symbols impacts preattentive processing on a map. Specifically, it involves identifying the motion velocity parameters for cartographic animated pictorial symbols that contribute to the preattentive perception of the target symbols. We created five pictorial symbols, each accompanied by a unique animation tailored to convey the meaning associated with each symbol. The animation dynamics of symbols on the administrative map were distributed across arithmetic, logarithmic, and exponential scales. Eye-tracking technology was utilized to explain the user’s visual attention. The key findings reveal that, although movement does not uniformly hold the same designation in cartographic communication, it could guide user attention to identify the value peaks in quantitative map visualization. Motion velocity enhances the salience of animated symbols, making them stand out, not only against static elements but also against other animated distractors. Additionally, motion distributions between symbol classes based on exponential or arithmetic scales were identified as the most successful. Nevertheless, certain types of motion, such as rotational, do not perform well with pictorial symbols, even on the most effective motion distribution scale. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Individual frames of each dynamic pictorial symbol. In brackets, next to each symbol name, there is the actual size on the display monitor.</p> Full article ">Figure 2
<p>Fifteen administrative border maps with 20 randomly distributed dynamic pictorial symbols were used in the experiment. Different administrative boundaries were used to support stimuli randomization. Actual map examples can be seen in <a href="#app1-ijgi-13-00118" class="html-app">Supplementary Videos S1–S5</a>.</p> Full article ">Figure 3
<p>Experimental procedure scheme, starting from the calibration process to the display of the map with the target symbol.</p> Full article ">Figure 4
<p>Success rate (percentage) of all pictorial symbols in various motion distribution schemes. The difference between bottom-up (the group that did not see the target symbol) and top-down (the group that was presented the target symbol before the actual map stimuli) search was distinguished by the outline of the charts.</p> Full article ">Figure 5
<p>Differences between symbols and motion distribution scales in the number of fixations on the target, taking into account successful and unsuccessful target search.</p> Full article ">Figure 6
<p>Overall distribution of the number of fixations on the target and the time to the first fixation on the target.</p> Full article ">Figure 7
<p>Average dwell time (time spent on the target symbol during stimuli display) was measured across all motion distribution scales and for all analyzed pictorial symbols.</p> Full article ">
18 pages, 8333 KiB  
Article
Analysis of Spatiotemporal Dynamics of Land Desertification in Qilian Mountain National Park Based on Google Earth Engine
by Xiaowen Chen, Naiang Wang, Simin Peng, Nan Meng and Haoyun Lv
ISPRS Int. J. Geo-Inf. 2024, 13(4), 117; https://doi.org/10.3390/ijgi13040117 - 1 Apr 2024
Cited by 3 | Viewed by 3022
Abstract
Notwithstanding the overall improvement in the ecological condition of the Qilian Mountains, there are localized occurrences of grassland degradation, desertification, and salinization. Moreover, timely and accurate acquisition of desertification information is a fundamental prerequisite for effective monitoring and prevention of desertification. Leveraging the [...] Read more.
Notwithstanding the overall improvement in the ecological condition of the Qilian Mountains, there are localized occurrences of grassland degradation, desertification, and salinization. Moreover, timely and accurate acquisition of desertification information is a fundamental prerequisite for effective monitoring and prevention of desertification. Leveraging the Google Earth Engine (GEE) platform in conjunction with machine learning techniques, this study aims to identify and extract the spatiotemporal dynamics of desertification in the Qilian Mountain National Park (QMNP) and its surroundings (QMNPs) spanning from 1988 to 2023. Results show that based on the random forest algorithm, the multi-index inversion methodology achieves a commendable overall accuracy of 91.9% in desertification extraction. From 1988 to 2023, the gravity center of light desertification shifts southeastward, while centers characterized by moderate, severe, and extremely severe desertification display a westward retreat with fluctuations. The area of sandy land shows an expansion trend in the medium term, but after 2018, desertification in QMNPs reversed. As of 2023, the sandy land area measured 16,897.35 km2, accounting for 18.29% of the total area of QMNPs. The insights garnered from this study provide a valuable reference for regional desertification prevention and control in the future. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Study area and fieldwork. (<b>a</b>) the location of QMNP; (<b>b</b>) the defined study area in this study based on QMNP; (<b>c</b>) distribution of field sampling points.</p> Full article ">Figure 2
<p>Workflow of spatiotemporal dynamics extraction and analysis of land desertification.</p> Full article ">Figure 3
<p>Accuracy evaluation of six classifiers under different combinations of features.</p> Full article ">Figure 4
<p>Classification results of RF, CART, and GTB algorithms in 2023. a (Halten River), b (Danghe River), c (Hala Lake), d (upper reaches of Shule River), and e (non-desertification area) represent the typical cases for regional comparison.</p> Full article ">Figure 5
<p>Regional comparison of model classification results. (<b>a</b>) Halten River; (<b>b</b>) Danghe River; (<b>c</b>) Hala Lake; (<b>d</b>) upper reaches of Shule River; (<b>e</b>) non-desertification area.</p> Full article ">Figure 6
<p>Spatial distribution of land desertification from 1988 to 2023.</p> Full article ">Figure 7
<p>Proportion of land desertification area in different degrees from 1988 to 2023.</p> Full article ">Figure 8
<p>Spatial change trends of land desertification in various periods.</p> Full article ">Figure 9
<p>The Sankey map showing the area of transition between different degrees of desertification (unit: km<sup>2</sup>) in each period drawn by the “Origin 2022 SR1” software.</p> Full article ">Figure 10
<p>Gravity center migration of different desertification levels. (<b>a</b>) Light. (<b>b</b>) Moderate. (<b>c</b>) Severe. (<b>d</b>) Extremely severe.</p> Full article ">
21 pages, 12915 KiB  
Article
An Integrated Duranton and Overman Index and Local Duranton and Overman Index Framework for Industrial Spatial Agglomeration Pattern Analysis
by Yupu Huang, Li Zhuo and Jingjing Cao
ISPRS Int. J. Geo-Inf. 2024, 13(4), 116; https://doi.org/10.3390/ijgi13040116 - 29 Mar 2024
Viewed by 1573
Abstract
Accurately measuring industrial spatial agglomeration patterns is crucial for promoting regional economic development. However, few studies have considered both agglomeration degrees and cluster locations of industries. Moreover, the traditional multi-scale cluster location mining (MCLM) method still has limitations in terms of accuracy, parameter [...] Read more.
Accurately measuring industrial spatial agglomeration patterns is crucial for promoting regional economic development. However, few studies have considered both agglomeration degrees and cluster locations of industries. Moreover, the traditional multi-scale cluster location mining (MCLM) method still has limitations in terms of accuracy, parameter setting, calculation efficiency, etc. This study proposes a new framework for analyzing industrial spatial agglomeration patterns, which uses the Duranton and Overman (DO) index for estimating agglomeration degrees and a newly developed local DO (LDO) index for mining cluster locations. The MCLM-LDO method was proposed by incorporating the LDO index into the MCLM method, and it was validated via comparisons with three baseline methods based on two synthetic datasets. The results proved that the MCLM-LDO method can achieve accuracies of 0.945 and 1 with computational times of 0.15 s and 0.11 s on two datasets, which are superior to existing MCLM methods. The proposed framework was further applied to analyze the spatial agglomeration patterns of the industry of computer, communication, and other electronic equipment manufacturing in Guangdong Province, China. The results showed that the framework gives a more holistic perspective of spatial agglomeration patterns, which can serve as more meaningful references for industrial sustainable development. Full article
(This article belongs to the Special Issue Application of Geographical Information System in Urban Design, Management or Evaluation)
►▼ Show Figures

Figure 1

Figure 1
<p>The overall structure of the proposed integrated Duranton and Overman (DO) index and Local Duranton and Overman (LDO) index (DO-LDO) framework. Note that MCLM-LDO refers to the Multi-scale Cluster Location Mining method based on LDO index, <math display="inline"><semantics> <mrow> <msub> <mi>h</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> </mrow> </semantics></math> and <math display="inline"><semantics> <mrow> <msub> <mi>h</mi> <mi>i</mi> </msub> </mrow> </semantics></math> represent boundary distance parameters for global and local spatial scales, respectively, <math display="inline"><semantics> <mrow> <mo>Γ</mo> <mrow> <mo>(</mo> <mi>A</mi> <mo>)</mo> </mrow> </mrow> </semantics></math> denotes the sum over all distances of the agglomeration degree, <math display="inline"><semantics> <mrow> <msub> <mrow> <mi>LDO</mi> </mrow> <mrow> <mi>mean</mi> </mrow> </msub> </mrow> </semantics></math> denotes the average density of firms in the cluster, and <math display="inline"><semantics> <mrow> <msub> <mi>P</mi> <mi>n</mi> </msub> </mrow> </semantics></math> denotes the percentage of the number of firms in the cluster to the total number of firms in the industry.</p> Full article ">Figure 2
<p>Examples of localization index curves of industries A, B, C, and D.</p> Full article ">Figure 3
<p>Diagram of the evaluation scheme for the MCLM-LDO method. Note that green rectangles represent improved steps while orange rectangles represent steps of the MCLM-LK method.</p> Full article ">Figure 4
<p>The industrial spatial distributions of multiple clusters in (<b>a</b>) Synthetic Dataset 1 and (<b>b</b>) Synthetic Dataset 2.</p> Full article ">Figure 5
<p>Spatial distribution of firms in the C39 industry in Guangdong Province, China, in 2022. Note that the Dongsha Islands of China are not shown considering that there are no firms.</p> Full article ">Figure 6
<p>The localization index <math display="inline"><semantics> <mrow> <mo>Γ</mo> <mrow> <mo>(</mo> <mrow> <mi>A</mi> <mo>,</mo> <mi>d</mi> </mrow> <mo>)</mo> </mrow> </mrow> </semantics></math> of Synthetic Dataset 1.</p> Full article ">Figure 7
<p>Spatial distribution of estimated firm types on Synthetic Dataset 1 by inputting <math display="inline"><semantics> <mrow> <mover accent="true"> <mi>h</mi> <mo stretchy="false">^</mo> </mover> <mo>=</mo> <mn>11</mn> </mrow> </semantics></math> to (<b>a</b>) MCLM-LDO method, (<b>b</b>) baseline method 1, (<b>c</b>) baseline method 2, and (<b>d</b>) baseline method 3.</p> Full article ">Figure 7 Cont.
<p>Spatial distribution of estimated firm types on Synthetic Dataset 1 by inputting <math display="inline"><semantics> <mrow> <mover accent="true"> <mi>h</mi> <mo stretchy="false">^</mo> </mover> <mo>=</mo> <mn>11</mn> </mrow> </semantics></math> to (<b>a</b>) MCLM-LDO method, (<b>b</b>) baseline method 1, (<b>c</b>) baseline method 2, and (<b>d</b>) baseline method 3.</p> Full article ">Figure 8
<p>The localization index <math display="inline"><semantics> <mrow> <mo>Γ</mo> <mrow> <mo>(</mo> <mrow> <mi>A</mi> <mo>,</mo> <mi>d</mi> </mrow> <mo>)</mo> </mrow> </mrow> </semantics></math> of Synthetic Dataset 2.</p> Full article ">Figure 9
<p>Spatial distribution of estimated firm types on Synthetic Dataset 2 by inputting <math display="inline"><semantics> <mrow> <mover accent="true"> <mi>h</mi> <mo stretchy="false">^</mo> </mover> <mo>=</mo> <mn>6</mn> </mrow> </semantics></math> to (<b>a</b>) MCLM-LDO method, (<b>b</b>) baseline method 1, (<b>c</b>) baseline method 2, and (<b>d</b>) baseline method 3.</p> Full article ">Figure 10
<p>The evolution of the localization index <math display="inline"><semantics> <mrow> <mo>Γ</mo> <mrow> <mo>(</mo> <mrow> <mi>A</mi> <mo>,</mo> <mi>d</mi> </mrow> <mo>)</mo> </mrow> </mrow> </semantics></math> of the C39 industry in Guangdong Province from 2000 to 2022.</p> Full article ">Figure 11
<p>The evolution of cluster locations of the C39 industry in Guangdong Province from 2000 to 2022: (<b>a</b>) global agglomeration boundary and center and (<b>b</b>) local cluster (inside the gray dotted line in (<b>a</b>)).</p> Full article ">Figure 12
<p>Spatial distribution of estimated firm types on Synthetic Dataset 2 by inputting <math display="inline"><semantics> <mrow> <mover accent="true"> <mi>h</mi> <mo stretchy="false">^</mo> </mover> <mo>=</mo> <mn>4</mn> </mrow> </semantics></math> to the (<b>a</b>) MCLM-LDO method, (<b>b</b>) baseline method 1, (<b>c</b>) baseline method 2, and (<b>d</b>) baseline method 3.</p> Full article ">Figure 12 Cont.
<p>Spatial distribution of estimated firm types on Synthetic Dataset 2 by inputting <math display="inline"><semantics> <mrow> <mover accent="true"> <mi>h</mi> <mo stretchy="false">^</mo> </mover> <mo>=</mo> <mn>4</mn> </mrow> </semantics></math> to the (<b>a</b>) MCLM-LDO method, (<b>b</b>) baseline method 1, (<b>c</b>) baseline method 2, and (<b>d</b>) baseline method 3.</p> Full article ">Figure 13
<p>Spatial distribution of estimated firm types on Synthetic Dataset 2 by inputting <math display="inline"><semantics> <mrow> <mover accent="true"> <mi>h</mi> <mo stretchy="false">^</mo> </mover> <mo>=</mo> <mn>8</mn> </mrow> </semantics></math> to the (<b>a</b>) MCLM-LDO method, (<b>b</b>) baseline method 1, (<b>c</b>) baseline method 2, and (<b>d</b>) baseline method 3.</p> Full article ">Figure 14
<p>Spatial distribution of estimated firm types by using the MCLM-LDO method on Synthetic Dataset 2 by inputting (<b>a</b>) the first curve crest (<math display="inline"><semantics> <mrow> <mover accent="true"> <mi>d</mi> <mo stretchy="false">^</mo> </mover> <mo>=</mo> <mn>3</mn> <mo>,</mo> <mo> </mo> <mover accent="true"> <mi>h</mi> <mo stretchy="false">^</mo> </mover> <mo>=</mo> <mn>2</mn> </mrow> </semantics></math>), (<b>b</b>) second curve crest (<math display="inline"><semantics> <mrow> <mover accent="true"> <mi>d</mi> <mo stretchy="false">^</mo> </mover> <mo>=</mo> <mn>9</mn> <mo>,</mo> <mo> </mo> <mover accent="true"> <mi>h</mi> <mo stretchy="false">^</mo> </mover> <mo>=</mo> <mn>2</mn> </mrow> </semantics></math>), and (<b>c</b>) third curve crest (<math display="inline"><semantics> <mrow> <mover accent="true"> <mi>d</mi> <mo stretchy="false">^</mo> </mover> <mo>=</mo> <mn>20</mn> <mo>,</mo> <mo> </mo> <mover accent="true"> <mi>h</mi> <mo stretchy="false">^</mo> </mover> <mo>=</mo> <mn>2</mn> </mrow> </semantics></math>).</p> Full article ">
23 pages, 2698 KiB  
Article
Analyzing the Influence of Visitor Types on Location Choices and Revisit Intentions in Urban Heritage Destinations
by Sevim Sezi Karayazi, Gamze Dane and Theo Arentze
ISPRS Int. J. Geo-Inf. 2024, 13(4), 115; https://doi.org/10.3390/ijgi13040115 - 28 Mar 2024
Viewed by 1731
Abstract
Understanding visitors’ spatial choice behavior is important in developing effective policies to counteract overcrowdedness in attractive urban heritage areas. This research presents a comprehensive analysis of visitor location choice behavior, aiming to address two primary objectives. First, this paper investigates the relationship between [...] Read more.
Understanding visitors’ spatial choice behavior is important in developing effective policies to counteract overcrowdedness in attractive urban heritage areas. This research presents a comprehensive analysis of visitor location choice behavior, aiming to address two primary objectives. First, this paper investigates the relationship between visitor segments and the choice of particular Points of Interest (POIs). Second, this paper explores the impacts of visitors’ experiences and visitor segments on their revisit intentions. We used a sample of 320 visitors who had been to Amsterdam within the last five years to collect data about their location choice behavior and intention to revisit after a recent visit to the city. Combining the revealed choices and intentions of pre-defined visitor segments obtained from a stated choice experiment, association rules are extracted to reveal differences in the patterns of behaviors related to the segment. The findings identify associations between various POIs, including museums such as the Rijksmuseum and Madame Tussauds, and visitor classes, which include “cultural attraction seekers”, “selective sightseers”, and “city-life lovers”. Furthermore, binary logistic regression analysis reveals that affective experiences, such as feelings of comfort, happiness, and annoyance, have a significant influence on visitors’ intentions to revisit the destination in the future. This research found that “cultural attraction seekers” and “selective sightseers” display a higher likelihood of considering a return visit to the city. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>The interactive map-based part of the questionnaire.</p> Full article ">Figure 2
<p>Reported locations by respondents.</p> Full article ">Figure 3
<p>Spatial segmentation of visited POIs across different visitor classes: (<b>a</b>) all classes; (<b>b</b>) cultural attraction seekers (LC1); (<b>c</b>) selective sightseers (LC2); (<b>d</b>) city-life lovers (LC3).</p> Full article ">
15 pages, 2426 KiB  
Article
Mapping Street Patterns with Network Science and Supervised Machine Learning
by Cai Wu, Yanwen Wang, Jiong Wang, Menno-Jan Kraak and Mingshu Wang
ISPRS Int. J. Geo-Inf. 2024, 13(4), 114; https://doi.org/10.3390/ijgi13040114 - 28 Mar 2024
Viewed by 1991
Abstract
This study introduces a machine learning-based framework for mapping street patterns in urban morphology, offering an objective, scalable approach that transcends traditional methodologies. Focusing on six diverse cities, the research employed supervised machine learning to classify street networks into gridiron, organic, hybrid, and [...] Read more.
This study introduces a machine learning-based framework for mapping street patterns in urban morphology, offering an objective, scalable approach that transcends traditional methodologies. Focusing on six diverse cities, the research employed supervised machine learning to classify street networks into gridiron, organic, hybrid, and cul-de-sac patterns with the street-based local area (SLA) as the unit of analysis. Utilising quantitative street metrics and GIS, the study analysed the urban form through the random forest method, which reveals the predictive features of urban patterns and enables a deeper understanding of the spatial structures of cities. The findings showed distinctive spatial structures, such as ring formations and urban cores, indicating stages of urban development and socioeconomic narratives. It also showed that the unit of analysis has a major impact on the identification and study of street patterns. Concluding that machine learning is a critical tool in urban morphology, the research suggests that future studies should expand this framework to include more cities and urban elements. This would enhance the predictive modelling of urban growth and inform sustainable, human-centric urban planning. The implications of this study are significant for policymakers and urban planners seeking to harness data-driven insights for the development of cities. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Methodology flowchart.</p> Full article ">Figure 2
<p>Example of different units of analysis division (in red line) of the street network in Chengdu.</p> Full article ">Figure 3
<p>The mapping of street patterns in the six case study cities.</p> Full article ">
11 pages, 462 KiB  
Article
Connection of Conic and Cylindrical Map Projections
by Miljenko Lapaine
ISPRS Int. J. Geo-Inf. 2024, 13(4), 113; https://doi.org/10.3390/ijgi13040113 - 27 Mar 2024
Viewed by 1431
Abstract
In previous papers that have dealt with cylindrical map projections as limiting cases of conical projections, standard or equidistant parallels were used in the derivations. This paper shows that this is not necessary and that it is sufficient to use parallels that preserve [...] Read more.
In previous papers that have dealt with cylindrical map projections as limiting cases of conical projections, standard or equidistant parallels were used in the derivations. This paper shows that this is not necessary and that it is sufficient to use parallels that preserve length. In addition, unlike other approaches, in this article the limiting cases of conic projections are derived in the most natural way, by deriving the equations of cylindrical projections from the equations of conic projections in a rectangular system in the projection plane using a mathematical concept of limits. It is shown that such an approach is possible, but not always, so it should be used carefully, or even better, avoided in teaching and studying map projections. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Cone in the middle and limiting cases that should correspond to the Mercator (<b>left</b>) and stereographic projection (<b>right</b>), according to [<a href="#B14-ijgi-13-00113" class="html-bibr">14</a>].</p> Full article ">
18 pages, 3573 KiB  
Article
Measuring the Spatial-Temporal Heterogeneity of Helplessness Sentiment and Its Built Environment Determinants during the COVID-19 Quarantines: A Case Study in Shanghai
by Yuhao He, Qianlong Zhao, Shanqi Sun, Wenjing Li and Waishan Qiu
ISPRS Int. J. Geo-Inf. 2024, 13(4), 112; https://doi.org/10.3390/ijgi13040112 - 27 Mar 2024
Cited by 2 | Viewed by 1826
Abstract
The COVID-19 outbreak followed by the strict citywide lockdown in Shanghai has sparked negative emotion surges on social media platforms in 2022. This research aims to investigate the spatial–temporal heterogeneity of a unique emotion (helplessness) and its built environment determinants. First, we scraped [...] Read more.
The COVID-19 outbreak followed by the strict citywide lockdown in Shanghai has sparked negative emotion surges on social media platforms in 2022. This research aims to investigate the spatial–temporal heterogeneity of a unique emotion (helplessness) and its built environment determinants. First, we scraped about twenty thousand Weibo posts and utilized their sentiments with natural language processing (NLP) to extract helplessness emotion and investigated its spatial–temporal variations. Second, we tested whether “helplessness” was related with urban environment attributes when other real estate economic and demographic variables were controlled using the ordinary least squares (OLS) model. Our results confirmed that helplessness emotion peaked in early April when the lockdown started. Second, residents in neighborhoods characterized by higher rents and property management fees, higher population density, lower housing prices, lower plot ratios, or surrounded by less tree view and higher perceived visual complexity, are found to exhibit higher degree of “helplessness”. This study provides an effective data-driven framework to utilize social media data for public sentiments monitoring. The helplessness emotion identified is a unique mental distress under strict quarantine measures, which expands the growing literature of urban governance in the post-pandemic era. Decision makers should pay attention to public opinions and design tailored management measures with reference to civic emotion dynamics to facilitate social sustainability and resilience in face of future crises. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Method and workflow.</p> Full article ">Figure 2
<p>The 9-week trajectory of helplessness on Shanghai’s Weibo posts.</p> Full article ">Figure 3
<p>Number of new cases in Shanghai 2022.</p> Full article ">Figure 4
<p>Map of helplessness. (<b>a</b>) Helplessness mapping in April (<b>b</b>) Helplessness mapping in May. (<b>c</b>) Helplessness difference (May minus April).</p> Full article ">Figure 5
<p>The spatial distribution of the independent variables.</p> Full article ">Figure 6
<p>The impact ranking of independent variables in May (by standardized coefficient).</p> Full article ">Figure A1
<p>The boundary of Shanghai central area in both vector map.</p> Full article ">
15 pages, 2989 KiB  
Article
Spatial Analysis of Exposure of Roads to Flooding and Its Implications for Mobility in Urban/Peri-Urban Accra
by Gerald Albert Baeribameng Yiran, Martin Oteng Ababio, Albert Nii Moe Allotey, Richard Yao Kofie and Lasse Møller-Jensen
ISPRS Int. J. Geo-Inf. 2024, 13(4), 111; https://doi.org/10.3390/ijgi13040111 - 27 Mar 2024
Viewed by 2373
Abstract
Climate change seriously threatens human systems, properties and livelihoods. Global projections suggest a continuous increase in the frequency and severity of weather events, with severe outcomes. Although the trends and impacts are highly variable depending on location, most studies tend to concentrate on [...] Read more.
Climate change seriously threatens human systems, properties and livelihoods. Global projections suggest a continuous increase in the frequency and severity of weather events, with severe outcomes. Although the trends and impacts are highly variable depending on location, most studies tend to concentrate on either the urban or rural areas, with little focus on peri-urban areas. Yet, in Sub-Saharan Africa, peri-urban areas display unique characteristics: inadequate infrastructure, unplanned development, weak governance, and environmental degradation, all of which exacerbate flood impact and thus need academic attention. This study contributes to filling this gap by assessing the flood vulnerability of roads in peri-urban Accra and its implications for mobility. Based on the fieldwork, the study delineated and analysed potential zones within the research locations. The researchers calculated roads’ absolute and relative lengths, using a spatial overlay (intersection) of potentially flooded roads with the total road network within the grid cells of 500 m by 500 m. These measures were adopted and used as exposure measures. The findings revealed that over 80% of roads with lengths between 100 m and 500 m were exposed to floods. Some areas had higher exposure indices, with absolute road lengths ranging from 1.5 km to 3.2 km and relative road lengths between 0.8 and 1.0. There were significant variations in road exposure between and within neighbourhoods. Depending on the depth and duration of the floodwater, residents may be unable to access their homes or carry out their daily activities. In conclusion, this study highlights the differential vulnerability of peri-urban areas to road flooding and recommends targeted provision of flood-resilient infrastructure to promote sustainable development. Full article
►▼ Show Figures

Figure 1

Figure 1
<p>Map of the study neighbourhoods. Source: Modified from [<a href="#B46-ijgi-13-00111" class="html-bibr">46</a>].</p> Full article ">Figure 2
<p>Topographic Wetness Index Map.</p> Full article ">Figure 3
<p>Exposure of roads to floods. Source: Authors.</p> Full article ">Figure 4
<p>Traffic building up in Antiaku neighbourhood due to flood. Courtesy Stephen Fiatornu, a Ph.D. student.</p> Full article ">Figure 5
<p>Road exposure indices in potentially flooded zones.</p> Full article ">Figure 6
<p>Nature of roads in peri-urban Accra. Source: Stephen Fiatornu, a Ph.D. student.</p> Full article ">Figure 7
<p>Mobility challenges due to road flooding. (<b>a</b>) A man trying to wade through water on the road in front of his house; (<b>b</b>) Flooded Road used by vehicles.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-35
Previous Issue
Next Issue
Back to TopTop