Proceedings

Editorial

Jump to: Other

2 pages, 130 KiB

Open AccessEditorial

Statement of Peer Review

by Dongmei Chen, Yuhong He and Songnian Li

Proceedings 2024, 110(1), 33; https://doi.org/10.3390/proceedings2024110033 - 18 Feb 2025

Viewed by 308

Abstract

In submitting conference proceedings to Proceedings, the volume editors of the proceedings certify to the publisher that all papers published in this volume have been subjected to peer review administered by the volume editors [...] Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

5 pages, 1509 KiB

Open AccessEditorial

A Preface of the 31st International Conference on Geoinformatics

by Dongmei Chen, Yuhong He and Songnian Li

Proceedings 2024, 110(1), 34; https://doi.org/10.3390/proceedings2024110034 - 18 Feb 2025

Viewed by 331

Abstract

The International Conference on Geoinformatics is an official conference of the International Association of Chinese Professionals in Geographic Information Sciences (CPGIS) and has attracted not only CPGIS community members but also researchers, professionals, and students from broad communities [...] Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

Other

Jump to: Editorial

8 pages, 2806 KiB

Open AccessProceeding Paper

Constructing Rasterized Covariates from LiDAR Point Cloud Data via Structured Query Language

by Rory Pittman and Baoxin Hu

Proceedings 2024, 110(1), 1; https://doi.org/10.3390/proceedings2024110001 - 3 Dec 2024

Cited by 2 | Viewed by 725

Abstract

For point cloud data compiled over larger spatial domains, the rasterization of features is effectively streamlined by means of structured query language (SQL). This comprises enhanced control with filtering data and implementing specific metrics for summarization to derive environmental covariates. LiDAR (light detection [...] Read more.

For point cloud data compiled over larger spatial domains, the rasterization of features is effectively streamlined by means of structured query language (SQL). This comprises enhanced control with filtering data and implementing specific metrics for summarization to derive environmental covariates. LiDAR (light detection and ranging) point cloud data were analyzed via SQL to generate rasterized covariates of the digital terrain model (DTM), canopy height model (CHM), and a gap fraction for a boreal study region in Northern Ontario, Canada. These features, along with topographic covariates computed from the DTM, were later ascertained as important for subsequent tree species classification research. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

7 pages, 3886 KiB

Open AccessProceeding Paper

Event/Visual/IMU Integration for UAV-Based Indoor Navigation

by Ahmed Elamin and Ahmed El-Rabbany

Proceedings 2024, 110(1), 2; https://doi.org/10.3390/proceedings2024110002 - 2 Dec 2024

Viewed by 1085

Abstract

Unmanned aerial vehicle (UAV) navigation in indoor environments is challenging due to varying light conditions, the dynamic clutter typical of indoor spaces, and the absence of GNSS signals. In response to these complexities, emerging sensors, such as event cameras, demonstrate significant potential in [...] Read more.

Unmanned aerial vehicle (UAV) navigation in indoor environments is challenging due to varying light conditions, the dynamic clutter typical of indoor spaces, and the absence of GNSS signals. In response to these complexities, emerging sensors, such as event cameras, demonstrate significant potential in indoor navigation with their low latency and high dynamic range characteristics. Unlike traditional RGB cameras, event cameras mitigate motion blur and operate effectively in low-light conditions. Nevertheless, they exhibit limitations in terms of information output during scenarios of limited motion, in contrast to standard cameras that can capture detailed surroundings. This study proposes a novel event-based visual–inertial odometry approach for precise indoor navigation. In the proposed approach, the standard images are leveraged for feature detection and tracking, while events are aggregated into frames to track features between consecutive standard frames. The fusion of IMU measurements and feature tracks facilitates the continuous estimation of sensor states. The proposed approach is evaluated and validated using a controlled office environment simulation developed using Gazebo, employing a P230 simulated drone equipped with an event camera, an RGB camera, and IMU sensors. This simulated environment provides a testbed for evaluating and showcasing the proposed approach’s robust performance in realistic indoor navigation scenarios. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

8 pages, 4314 KiB

Open AccessProceeding Paper

Exploitation of Class Activation Map to Improve Land Cover and Land Use Classification Using Deep Learning

by Taewoong Ham and Baoxin Hu

Proceedings 2024, 110(1), 3; https://doi.org/10.3390/proceedings2024110003 - 2 Dec 2024

Viewed by 780

Abstract

This study investigates the potential of gradient-weighted class activation mapping (Grad-CAM++) in enhancing land cover and land use (LCLU) classification using deep learning models. A U-Net and an Attention U-Net model were trained on Sentinel-2 imagery to classify 10 LCLU classes in a [...] Read more.

This study investigates the potential of gradient-weighted class activation mapping (Grad-CAM++) in enhancing land cover and land use (LCLU) classification using deep learning models. A U-Net and an Attention U-Net model were trained on Sentinel-2 imagery to classify 10 LCLU classes in a study area in Northern Ontario, Canada (centered at 49.17° N, 83.03° W). The classes included water, wetland, deciduous forest, mixed forest, coniferous forest, barren, urban/development, agriculture, shrubland, and no data (masked areas). The U-Net model achieved overall accuracy of 70.68%, a mean intersection over union (IoU) of 0.4852, and an F1 score of 0.7150, slightly outperforming the Attention U-Net model. Grad-CAM++ visualizations revealed that both models correctly focused on relevant features for each LCLU class, enhancing the interpretability of deep learning models in remote sensing applications. The findings suggest that integrating Grad-CAM++ with deep learning architectures can improve model transparency and guide future enhancements in LCLU classification tasks. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

8 pages, 1242 KiB

Open AccessProceeding Paper

Subtropical Tree Species Identification Based on Domain Generalization with Hyperspectral Images

by Xu Wang, Wenmei Li, Lei Zhao and Yuhong He

Proceedings 2024, 110(1), 4; https://doi.org/10.3390/proceedings2024110004 - 2 Dec 2024

Viewed by 550

Abstract

Subtropical tree species identification is a crucial aspect of forest resource monitoring, and the advancement of deep learning has introduced new opportunities for subtropical tree species identification. But, its performance often relies heavily on the availability of sufficient training samples. In this study, [...] Read more.

Subtropical tree species identification is a crucial aspect of forest resource monitoring, and the advancement of deep learning has introduced new opportunities for subtropical tree species identification. But, its performance often relies heavily on the availability of sufficient training samples. In this study, we propose a method for tree species identification via domain generalization with hyperspectral images. The network comprises a generator and a discriminator; the former produces similar samples, and the latter outputs predicted probabilities and classification loss to guide model optimization. The results demonstrate its superiority over traditional CNN-based algorithms. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

7 pages, 5004 KiB

Open AccessProceeding Paper

How to Understand Carbon Intensity? A Comparative Study of China and Europe Regarding the Relationship Between Rural Development Regimes and Carbon Emission Intensity

by Jiaqi Li and Yishao Shi

Proceedings 2024, 110(1), 5; https://doi.org/10.3390/proceedings2024110005 - 2 Dec 2024

Cited by 1 | Viewed by 682

Abstract

Background: China’s rural revitalisation policy has promoted the transformation of rural industries, which always neglect the “dual-carbon” goal in rural. Rural industrial upgrading in Europe can inspire sustainable rural development in China. Methods: Based on EDGAR and NEP data, the carbon emission intensity [...] Read more.

Background: China’s rural revitalisation policy has promoted the transformation of rural industries, which always neglect the “dual-carbon” goal in rural. Rural industrial upgrading in Europe can inspire sustainable rural development in China. Methods: Based on EDGAR and NEP data, the carbon emission intensity of rural ecosystems was calculated in terms of area. By Isodata cluster algorithm and k-means, the Chinese and European rural regions were classified based on agricultural areas. Pearson’s coefficient and geographical convergent cross-mapping (GCCM) were used to explore the correlation and causality between carbon intensity and development patterns in rural China and Europe. Results: The expansion of the land share of the primary industry and land consolidation will lead to more carbon emissions in the study areas. The proportion of land used for tertiary industry increases carbon emission intensity in rural China, but not in European study areas. The area carbon emission intensity shows that the fragmented industrial layout may hinder the development of rural industries in Europe, but not in China, from a productivity perspective. Conclusions: Carbon emission distribution and industrial development patterns vary spatially. GCCM can help identify the interactions for this variation between China and Europe, providing insights into China’s sustainable development. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

7 pages, 4765 KiB

Open AccessProceeding Paper

Spatiotemporal Analysis of Carbon Emissions and Uptake Changes from Land-Use in the Yangtze River Delta Region

by Cuiheng Ye, Jie Jiang and Yan Jin

Proceedings 2024, 110(1), 6; https://doi.org/10.3390/proceedings2024110006 - 3 Dec 2024

Viewed by 629

Abstract

Land use change and energy consumption caused by human activities is the primary source of carbon emissions and a driver of climate change. The study focused on the Yangtze River Delta (YRD), using the China Land Cover Dataset (CLCD) to calculate the region’s [...] Read more.

Land use change and energy consumption caused by human activities is the primary source of carbon emissions and a driver of climate change. The study focused on the Yangtze River Delta (YRD), using the China Land Cover Dataset (CLCD) to calculate the region’s carbon emissions from 1990 to 2020. Based on the Natural Segment Method, the spatial distribution of carbon emissions in the YRD region were constructed by dividing them into three categories: heavy, medium, and light. The results indicate that: (1) Carbon emissions of the YRD region was 594.02 million tons at the end of 2020, an increase of 468.53 million tons compared with that of 1990. The impervious surface was the major source of carbon emissions, accounting for more than 98.51% of the total, and woodland was the most important carbon sink, accounting for more than 91.32% of the total carbon uptake. (2) The carbon emissions increase rate over the 30-year period has risen from rapid to gradual, with the fastest rate of increase occurring between 2000 and 2010. (3) Differences in economic development and land type lead to spatial variability in carbon emissions. Regions with substantial emissions were predominantly located in coastal areas, indicating a trend toward shifting inland. The assessment of carbon emissions is helpful for designing emissions mitigation policies. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

11 pages, 5505 KiB

Open AccessProceeding Paper

Combining Deep Learning and Street View Images for Urban Building Color Research

by Wenjing Li, Qian Ma and Zhiyong Lin

Proceedings 2024, 110(1), 7; https://doi.org/10.3390/proceedings2024110007 - 3 Dec 2024

Viewed by 961

Abstract

The color of a cityscape plays a significant role in its atmosphere; however, the traditional city color analysis methods cover a wide range but are not precise enough, requiring field sampling, a lot of manual comparisons, and lacking quantitative analysis of color. With [...] Read more.

The color of a cityscape plays a significant role in its atmosphere; however, the traditional city color analysis methods cover a wide range but are not precise enough, requiring field sampling, a lot of manual comparisons, and lacking quantitative analysis of color. With the development of artificial intelligence, deep learning and computer vision technology show great potential in urban environment research. In this document, we focus on “building color” and present a deep learning-based framework that combines geospatial big data with AI technology to extract and analyze urban color information. The framework is composed of two phases: “deep learning” and “quantitative analysis.” In the “deep learning” phase, a deep convolutional neural network (DCNN)-based color extraction model is designed to automatically learn building color information from street view images; in the “quantitative analysis” phase, building color is quantitatively analyzed at the overall and local levels, and a color clustering model is designed to quantitatively display the color relationship to comprehensively understand the current status of urban building color. The research method and results of this paper are one of the effective ways to combine geospatial big data with GeoAI, which is helpful to the collection and analysis of urban color and provides direction for the construction of urban color information management. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

9 pages, 6603 KiB

Open AccessProceeding Paper

Spatially Seamless Downscaling of a SMAP Soil Moisture Product Through a CNN-Based Approach with Integrated Multi-Source Remote Sensing Data

by Yan Jin, Haoyu Fan, Zeshuo Li and Yaojie Liu

Proceedings 2024, 110(1), 8; https://doi.org/10.3390/proceedings2024110008 - 3 Dec 2024

Viewed by 847

Abstract

Surface soil moisture (SSM) is crucial for understanding terrestrial hydrological processes. Despite its widespread use since 2015, the Soil Moisture Active and Passive (SMAP) SSM dataset faces challenges due to its inherent low spatial resolution and data gaps. This study addresses these limitations [...] Read more.

Surface soil moisture (SSM) is crucial for understanding terrestrial hydrological processes. Despite its widespread use since 2015, the Soil Moisture Active and Passive (SMAP) SSM dataset faces challenges due to its inherent low spatial resolution and data gaps. This study addresses these limitations through a deep learning approach aimed at interpolating missing values and downscaling soil moisture data. The result is a seamless, daily 1 km resolution SSM dataset for China, spanning from 1 January 2016 to 31 December 2022. For the original 9 km daily SMAP products, a convolutional neural network (CNN) with residual connections was employed to achieve the spatially seamless 9 km SSM data, integrating multi-source remote sensing data. Subsequently, auxiliary data including land cover, land surface temperatures, vegetation indices, vegetation temperature drought indices, elevation, and soil texture were integrated into the CNN-based downscaling model to generate the spatially seamless 1 km SSM. Comparative analysis of the spatially seamless 9 km and 1 km SSM datasets with ground observations yielded unbiased root mean square error values of 0.09 cm³/cm³ for both, demonstrating the effectiveness of the downscaling method. This approach provides a promising solution for generating high-resolution, spatially seamless soil moisture data to meet the needs of hydrological, meteorological, and agricultural applications. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

7 pages, 4626 KiB

Open AccessProceeding Paper

Construction and Application of an Ecological Quality Evaluation System Based on a PIE-Engine

by Pengdu Li, Cuiheng Ye, Lei Li and Jie Jiang

Proceedings 2024, 110(1), 9; https://doi.org/10.3390/proceedings2024110009 - 3 Dec 2024

Viewed by 656

Abstract

Ecosystem services, including climate regulation and biodiversity maintenance, are vital for human well-being and sustainable development. The ecological quality evaluation system, based on the three dimensions of ecological function, ecological stability, and ecological stress, was established using the Pixel Information Expert Engine (PIE-Engine) [...] Read more.

Ecosystem services, including climate regulation and biodiversity maintenance, are vital for human well-being and sustainable development. The ecological quality evaluation system, based on the three dimensions of ecological function, ecological stability, and ecological stress, was established using the Pixel Information Expert Engine (PIE-Engine) and Moderate Resolution Imaging Spectroradiometer (MODIS) products to assess the ecological quality of the Taihu Basin from 2001 to 2020. The findings reveal that (1) the average Ecological Function Index (EFI) of the Taihu Basin showed a trend of initially decreasing and then increasing, with significant spatial differences. The highest EFI was observed in the western and southwestern regions of the Taihu Basin, which are mainly covered by forest and grassland, while the relatively lower EFI was found in the densely urbanized northeastern part of the basin. (2) The average Ecological Stability Index (ESI) of the Taihu Basin showed a similar trend to the EFI, with the rate of increase higher than the rate of decrease. The ESI was higher in the southwestern part, while in the southeastern and western parts of cropland and wetlands, the ESI was relatively low. (3) The Ecological Threat Index (ETI) of the Taihu Basin showed a fluctuating decrease followed by an increase, with the rate of increase higher than the rate of decrease. The reduction in grassland and the expansion of urban space are the main factors contributing to the increase in ecological stress. The research results of this paper will provide an important reference value for the coordinated and sustainable development of the economy and ecosystem in the Taihu Basin. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

8 pages, 4795 KiB

Open AccessProceeding Paper

Unsupervised Domain Adaptive Transfer Learning for Urban Built-Up Area Extraction

by Feifei Peng, Shuai Yao, Yixiang Chen and Wenmei Li

Proceedings 2024, 110(1), 10; https://doi.org/10.3390/proceedings2024110010 - 3 Dec 2024

Viewed by 718

Abstract

Built-up areas are the main gathering place for human activities. The widespread availability of various satellite sensors provides a rich data source for mapping built-up areas. Deep learning can automatically learn multi-level features of targets from sample data in an end-to-end manner, overcoming [...] Read more.

Built-up areas are the main gathering place for human activities. The widespread availability of various satellite sensors provides a rich data source for mapping built-up areas. Deep learning can automatically learn multi-level features of targets from sample data in an end-to-end manner, overcoming the limitations of traditional methods based on handcrafted features. However, existing deep-learning-based methods rely on the quantity and distribution of sample data, and the trained models often exhibit limited generalization ability when faced with image data from novel scenarios. To effectively tackle this issue, this study proposes an unsupervised domain adaptive transfer learning method based on adversarial machine learning. This method aims to utilize the feature information of the source domain to train a classifier suitable for target domain feature discrimination without requiring a target domain label, and achieve built-up area extraction of different sensor images. The model comprises a feature extraction module, a label classification module, and a domain discrimination module. Through adversarial training, the feature knowledge from the source domain is transferred to the target domain, achieving feature alignment and efficient discrimination of built-up areas. The Gaofen-2 (GF-2) and Sentinel-2 datasets were employed for experimental evaluation. The results show that the proposed method, trained on the GF-2 image dataset (source domain), can be transferred unsupervised to the Sentinel-2 image dataset (target domain), demonstrating robust detection performance. Further comparative experiments have also demonstrated the superiority of our method in extracting built-up areas through transfer learning. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

8 pages, 11999 KiB

Open AccessProceeding Paper

Sustainable Urbanization in the Yangtze River Basin Through Built-Up Area Extraction

by Zeshuo Li, Haoyu Fan and Yan Jin

Proceedings 2024, 110(1), 11; https://doi.org/10.3390/proceedings2024110011 - 3 Dec 2024

Viewed by 744

Abstract

The Yangtze River Economic Belt (YREB), spanning nine provinces and cities in eastern, central, and western China, is a key region for China’s urbanization. This study utilizes the Google Earth Engine (GEE) platform to integrate four land cover and impervious surface datasets, constructing [...] Read more.

The Yangtze River Economic Belt (YREB), spanning nine provinces and cities in eastern, central, and western China, is a key region for China’s urbanization. This study utilizes the Google Earth Engine (GEE) platform to integrate four land cover and impervious surface datasets, constructing built-up area datasets for the YREB at five-year intervals from 1985 to 2020. The employed random forest model achieved an overall accuracy (OA) and kappa coefficient both exceeding 90%, demonstrating high reliability and precision in the generated datasets. Using this dataset, we then calculated the United Nations Sustainable Development Goal 11.3.1 (SDG11.3.1) index for the YREB and its nine constituent provinces, which includes the land consumption rate (LCR), population growth rate (PGR), and ratio of land consumption rate to population growth rate (LCRPGR). The results show that the LCRPGR index for the entire region over the 35-year period is −0.006, 4.84, 0.44, 0.77, 5.15, 0.09, and 2.13, respectively. These values suggest that the land consumption rate significantly outpaced the population growth rate during 1990–1995, 2005–2010, and 2015–2020, reflecting periods of rapid urban development. This study offers important insights into urban expansion in the YREB, offering valuable data to inform sustainable urbanization practices. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

9 pages, 1927 KiB

Open AccessProceeding Paper

UAV-Based Multi-Sensor Data Fusion for 3D Building Detection

by Mohsen Shahraki, Ahmed El-Rabbany and Ahmed Elamin

Proceedings 2024, 110(1), 12; https://doi.org/10.3390/proceedings2024110012 - 3 Dec 2024

Viewed by 760

Abstract

Three-dimensional building extraction is crucial for urban planning, environmental analysis, and autonomous navigation. One method for data collection involves using unmanned aerial vehicles (UAVs), which allow for flexible and rapid data acquisition. However, accurate 3D building extraction from these data remains challenging due [...] Read more.

Three-dimensional building extraction is crucial for urban planning, environmental analysis, and autonomous navigation. One method for data collection involves using unmanned aerial vehicles (UAVs), which allow for flexible and rapid data acquisition. However, accurate 3D building extraction from these data remains challenging due to the abundance of information in high-resolution datasets. To tackle this problem, a novel UAV-based multi-sensor data fusion model is developed, which utilizes deep neural networks (DNNs) to enhance point cloud segmentation. Urban datasets, acquired by a UAV equipped with a Zenmuse L1 payload, are collected and used to train, validate, and test the DNNs. It is shown that most building extraction results have precision, accuracy, and F-score values greater than 0.96. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

6 pages, 1354 KiB

Open AccessProceeding Paper

The Point Cloud Reduction Algorithm Based on the Feature Extraction of a Neighborhood Normal Vector and Fuzzy-c Means Clustering

by Hongxiao Xu, Donglai Jiao and Wenmei Li

Proceedings 2024, 110(1), 13; https://doi.org/10.3390/proceedings2024110013 - 3 Dec 2024

Viewed by 849

Abstract

The three-dimensional model of geographic elements serves as the primary medium for digital visualization. However, the original point cloud model is often vast and includes considerable redundant data, resulting in inefficiencies during the three-dimensional modeling process. To address this issue, this paper proposes [...] Read more.

The three-dimensional model of geographic elements serves as the primary medium for digital visualization. However, the original point cloud model is often vast and includes considerable redundant data, resulting in inefficiencies during the three-dimensional modeling process. To address this issue, this paper proposes a point cloud reduction algorithm that leverages domain normal vectors and fuzzy-c means (FCM) clustering for feature extraction. The algorithm first extracts the edge points of the model and then utilizes domain normal vectors to extract the overall feature points of the model. Next, utilizing point cloud curvature, coordinate information, and geometric attributes, the algorithm applies the FCM clustering method to isolate local feature points. Non-feature points are then sampled using an enhanced farthest point sampling technique. Finally, the algorithm integrates edge points, feature points, and non-feature points to generate simplified point cloud data. This paper compares the proposed algorithm with traditional methods, including the uniform grid method, random sampling method, and curvature sampling method, and evaluates the simplified point cloud in terms of reduction level and reconstruction time. This approach effectively preserves critical feature information from the majority of point cloud data, thereby addressing the complexities inherent in original point cloud models. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

7 pages, 1105 KiB

Open AccessProceeding Paper

Spatial Interpolation Methods of Temperature Data Based on Geographic Information System—Taking Jiangxi Province as an Example

by Zihao Feng, Runjie Wang, Xianglei Liu, Ming Huang and Liang Huo

Proceedings 2024, 110(1), 14; https://doi.org/10.3390/proceedings2024110014 - 3 Dec 2024

Cited by 1 | Viewed by 691

Abstract

The comfort level of air temperature in a region is one of the influencing factors that affect tourists’ choice of tourism purpose. As a national red cultural mecca, the study of air temperature in Jiangxi Province can provide an important scientific reference for [...] Read more.

The comfort level of air temperature in a region is one of the influencing factors that affect tourists’ choice of tourism purpose. As a national red cultural mecca, the study of air temperature in Jiangxi Province can provide an important scientific reference for the development of tourism and the dissemination of red culture. Temperature is one of the most important indicators for climate comfort studies. Thus, in this paper, the average air temperature in Jiangxi Province in 2018 was studied. Three interpolation methods of Kriging interpolation, the inverse distance weight method, and the spline function method were used to spatially interpolate the data from 26 weather stations to obtain the spatial distribution map of air temperature for comparative study. At the same time, the method of cross-validation was adopted, and the average error and the root-mean-square error were quoted as the evaluation indexes for accuracy assessment. The conclusions of this paper are as follows: (1) the ME of IDW and spline method can reach 0.02–1.82 °C and the RMSE can reach 1.22–2.72 °C; (2) Kriging interpolation improves the RMSE by 27% and 55% compared to IDW and spline function methods, respectively; (3) considering the relatively sparse distribution of meteorological stations in Jiangxi Province, Kriging interpolation can avoid the extreme value phenomenon due to the influence of distance by reasonably choosing the shape and size associated with the surface space in the process of solving. Moreover, the results of this experimental study show that the accuracy of the kriging interpolation method is higher, so this method is more suitable for the spatial interpolation of the temperature in Jiangxi Province. In conclusion, this study provides a reference for the study of temperature comfort in Jiangxi Province. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

9 pages, 2175 KiB

Open AccessProceeding Paper

Geographical Spatial Characteristics and Low-Carbon Sustainable Paths of Coal Resource-Exhausted Cities

by Xiaotong Feng, Min Tan, Jihong Dong and Thomas Kienberger

Proceedings 2024, 110(1), 15; https://doi.org/10.3390/proceedings2024110015 - 3 Dec 2024

Viewed by 576

Abstract

Resource-exhausted cities are cities where the ratio of exploited reserves to recoverable reserves exceeds 70%. Long-term energy extraction and consumption lead to weak economic growth, idle industrial land, and ecological imbalances. It is imperative to explore sustainable development paths that are green and [...] Read more.

Resource-exhausted cities are cities where the ratio of exploited reserves to recoverable reserves exceeds 70%. Long-term energy extraction and consumption lead to weak economic growth, idle industrial land, and ecological imbalances. It is imperative to explore sustainable development paths that are green and low-carbon. The spatial characteristics of cities and the structure of energy networks are crucial foundations for low-carbon development and energy security in cities. The main research content includes three aspects: (1) The first involves the identification of the distribution characteristics of typical resource- exhausted cities worldwide. This mainly includes coal, oil, metallurgy, forestry, and non-metallic minerals. Among them, coal resource-exhausted cities are the most numerous, mainly distributed in China, Australia, the United States, etc. (2) The second includes an analysis of the spatial characteristics of resource-exhausted cities in China. This involves taking 24 resource-exhausted prefecture-level cities in China as the research objects, integrating geographic data such as Points of Interest (POIs), and using machine learning for accurate quantitative identification and spatial delineation of urban functions. The production space and ecological space of cities show an aggregated distribution pattern, while the living space is randomly distributed. (3) The third is based on urban energy consumption data, utilizing the modified gravity model and social network analysis (SNA), and analyzing the centrality/relevance, relationship density and frequency, and accessibility. The average degree of centrality of the 17 coal-related industries is 5.529, demonstrating the energy network structure of resource-exhausted cities. This paper provides data foundations and technical methods for achieving urban energy renewal, ecosystem stability, and optimized spatial structures. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

8 pages, 10782 KiB

Open AccessProceeding Paper

Analysis of Cultivated Land Fragmentation and Its Influencing Factors in Northern China

by Qianyu Nie, Shuang Zhao, Zhiheng Wang and Dingyang Zhang

Proceedings 2024, 110(1), 16; https://doi.org/10.3390/proceedings2024110016 - 3 Dec 2024

Viewed by 795

Abstract

Revealing the spatial distribution patterns and driving factors of cultivated land fragmentation is of great significance for optimizing the utilization and management of cultivated land resources and promoting moderate-scale agricultural operations. Based on the 2020 Landsat8 Collection2 surface reflectance data from Changping District, [...] Read more.

Revealing the spatial distribution patterns and driving factors of cultivated land fragmentation is of great significance for optimizing the utilization and management of cultivated land resources and promoting moderate-scale agricultural operations. Based on the 2020 Landsat8 Collection2 surface reflectance data from Changping District, Binhai New Area, and Hulin City, this study comprehensively utilized the landscape pattern index method and the moving window method was used to evaluate the spatial distribution characteristics of cultivated land fragmentation. Furthermore, the Geodetector was employed to analyze the factors which influenced cultivated land fragmentation. The results indicated that the comprehensive indices of cultivated land fragmentation in the three research areas are 0.133, 0.132, and 0.140, respectively, suggesting that the degree of fragmentation is highest in Binhai New Area and lowest in Hulin City. Apart from topographical factors, there are differences in the secondary driving factors of cultivated land fragmentation across the different study areas. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

7 pages, 11708 KiB

Open AccessProceeding Paper

Urban Functional Zone Mapping by Integrating Multi-Source Data and Spatial Relationship Characteristics

by Daoyou Zhu, Xu Dang, Wenjia Shi, Yixiang Chen and Wenmei Li

Proceedings 2024, 110(1), 17; https://doi.org/10.3390/proceedings2024110017 - 4 Dec 2024

Cited by 1 | Viewed by 899

Abstract

Timely and precise acquisition of urban functional zone (UFZ) information is crucial for effective urban planning, management, and resource allocation. However, current UFZ mapping approaches primarily focus on individual functional units’ visual and semantic characteristics, often overlooking the crucial spatial relationships between them, [...] Read more.

Timely and precise acquisition of urban functional zone (UFZ) information is crucial for effective urban planning, management, and resource allocation. However, current UFZ mapping approaches primarily focus on individual functional units’ visual and semantic characteristics, often overlooking the crucial spatial relationships between them, resulting in classification inaccuracies. To address this limitation, our study presents a novel framework for UFZ classification that seamlessly integrates visual image features, Points of Interest (POI) semantic attributes, and spatial relationship information. This framework leverages the OpenStreetMap (OSM) road network to partition the study area into functional units, employs a graph model to represent urban functional nodes and their intricate spatial topological relationships, and harnesses the capabilities of Graph Convolutional Network (GCN) to fuse these multi-dimensional features through end-to-end learning for accurate urban function discrimination. Experimental evaluations utilizing Gaofen-2 (GF-2) satellite imagery, POI data, and OSM road network information from Shenzhen, China have yielded remarkable results. Our method has achieved significant improvements in classification accuracy across all functional categories, surpassing approaches that rely solely on visual or semantic features. Notably, the overall classification accuracy reached an impressive 87.92%, marking a significant 2.08% increase over methods that disregard spatial relationship features. Furthermore, our method has demonstrated superior performance when compared to similar techniques, underscoring its effectiveness and potential for widespread application in UFZ classification. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

7 pages, 3543 KiB

Open AccessProceeding Paper

Spatial Optimization for Facilities with Anisotropic Coverage

by Enbo Zhou, Alan T. Murray, Jiwon Baik and Jing Xu

Proceedings 2024, 110(1), 18; https://doi.org/10.3390/proceedings2024110018 - 5 Dec 2024

Viewed by 650

Abstract

Locating facilities such as directional sensors and lights represents a challenging problem given their anisotropic coverage. This paper proposes a spatial optimization model to locate and orient facilities simultaneously. A finite dominating set approach considering occlusion is presented to reformulate the problem as [...] Read more.

Locating facilities such as directional sensors and lights represents a challenging problem given their anisotropic coverage. This paper proposes a spatial optimization model to locate and orient facilities simultaneously. A finite dominating set approach considering occlusion is presented to reformulate the problem as an integer programming problem. The model is then solved exactly using branch and bound. Applications to surveillance camera deployment in a university context demonstrate the performance of the proposed approach. The results show a pivotal enhancement in the estimation of coverage provided by the facility system. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

8 pages, 3075 KiB

Open AccessProceeding Paper

Detecting Polder Water Surface Dynamics Using Multi-Source Remote Sensing Data

by Heng Yu, Dawei Zhu, Sicheng Wan, Yuting Jiang, Chao Lu, Rui Zhang and Yan Jia

Proceedings 2024, 110(1), 19; https://doi.org/10.3390/proceedings2024110019 - 5 Dec 2024

Cited by 1 | Viewed by 726

Abstract

The flow of water in plain river network areas is significantly influenced by various factors, including human activities, upstream water influx, downstream tidal forces, and local rainfall. This leads to a complex situation where poor drainage and flooding are frequent occurrences. Polders play [...] Read more.

The flow of water in plain river network areas is significantly influenced by various factors, including human activities, upstream water influx, downstream tidal forces, and local rainfall. This leads to a complex situation where poor drainage and flooding are frequent occurrences. Polders play a crucial role in water management and agriculture in China by facilitating drainage and flood control, as well as supporting irrigation and aquaculture. As agriculture and water resource management continue to modernize, the monitoring and analysis of changes in water bodies and levels within polders become increasingly important. This paper primarily focuses on the detection of open water features in polder regions, mainly employing Sentinel-2 satellite imagery. By analyzing these data, we can effectively monitor the changes in the surface areas of water bodies within the polders. For our study, we have selected the Lixiahe region in China as it frequently experiences both flooding and drought conditions and houses a considerable number of polder zones. This region provides an ideal case study to explore the intricate relationship between water management infrastructure and natural hydrological phenomena. The importance of this research is manifold and significant. It advances the capabilities of remote sensing technologies and provides valuable insights for improved water level management in complex agricultural landscapes. The research introduces new methods and technical support for the remote sensing of water level changes in polders, contributing scientific support for enhanced water management and agricultural water conservation. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

9 pages, 1422 KiB

Open AccessProceeding Paper

Utilizing CYGNSS Data for Flood Monitoring and Analysis of Influencing Factors

by Yan Jia, Quan Liu, Dawei Zhu, Heng Yu, Yuting Jiang and Junjie Wang

Proceedings 2024, 110(1), 20; https://doi.org/10.3390/proceedings2024110020 - 5 Dec 2024

Cited by 1 | Viewed by 809

Abstract

Flood disasters are among the most severe natural calamities worldwide and typically occur in densely populated areas with abundant lakes and high rainfall. These disasters cause significant damage to the environment and human settlements. Therefore, accurately monitoring and understanding the occurrence and evolution [...] Read more.

Flood disasters are among the most severe natural calamities worldwide and typically occur in densely populated areas with abundant lakes and high rainfall. These disasters cause significant damage to the environment and human settlements. Therefore, accurately monitoring and understanding the occurrence and evolution of floods, as well as studying the influencing factors, is of great importance. This study employs CYGNSS satellite data from a constellation of small satellites equipped with reflective radar, which observe the Earth’s surface with high spatial and temporal resolution. Such systems effectively monitor the distribution of water bodies and hydrological processes on land surfaces. By collecting and analyzing CYGNSS data, we can map the distribution of water bodies during flood events to assess the extent and severity of the flooding. Additionally, this study examines various factors influencing flooding, including rainfall, land use, and topography. By compiling relevant meteorological, geographical, and hydrological data, we aim to develop a model that elucidates the impacts of these factors on the initiation and progression of floods. Ultimately, this research offers a comprehensive analysis based on CYGNSS data for monitoring floods and their influencing factors. The goal is to yield significant insights and explore the potential of using CYGNSS data in flood monitoring efforts. In the context of global climate change and the increasing frequency of flood disasters, these findings are expected to provide a crucial scientific basis for improving flood prevention and management strategies, thereby helping to mitigate losses and enhance our warning and disaster response capabilities. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

7 pages, 2576 KiB

Open AccessProceeding Paper

The Design of a Mobile Sensing Framework for Road Surfaces Based on Multi-Modal Sensors

by Haiyang Lyu, Yu Huang, Jianchun Hua, Wenmei Li, Tianju Wu, Hanru Zhang and Wangta Ma

Proceedings 2024, 110(1), 21; https://doi.org/10.3390/proceedings2024110021 - 11 Dec 2024

Viewed by 797

Abstract

Road surface information, encompassing aspects like road surface damages and facility distributions, is vital for maintaining and updating roads in smart cities. The proposed mobile sensing framework uses multi-modal sensors, including a GPS, gyroscope, accelerometer, camera, and Wi-Fi, integrated into a Jetson Nano [...] Read more.

Road surface information, encompassing aspects like road surface damages and facility distributions, is vital for maintaining and updating roads in smart cities. The proposed mobile sensing framework uses multi-modal sensors, including a GPS, gyroscope, accelerometer, camera, and Wi-Fi, integrated into a Jetson Nano to collect comprehensive road surface information. The collected data are processed, stored, and analyzed on the server side, with results accessible via RESTful APIs. This system enables the detection of road conditions, which are visualized through the web mapping technique. Based on this concept, the Mobile Sensor Framework for Road Surface analysis (MSF4RS) is designed, and its use significantly enhances road surface data acquisition and analysis. Key contributions include (1) the integration of multi-modal IoT sensors to capture comprehensive road surface data; (2) the development of a software environment that facilitates robust data processing; and (3) the execution of experiments using the MSF4RS, which synergistically combines hardware and software components. The framework leverages advanced sensor technologies and server-based computational methods and offers a user-friendly web interface for the dynamic visualization and interactive exploration of road surface conditions. Experiments confirm the framework’s effectiveness in capturing and visualizing road surface data, demonstrating significant potential for smart city applications. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

10 pages, 2345 KiB

Open AccessProceeding Paper

A Landslide Susceptibility Mapping Method Based on Geographic Information System and Data Enhancement Techniques: A Case Study of Guangzhou City, China

by Long Chen, Yizhao Wang, Wenfeng Bai, Fei Wang, Qinglun He, Juncai Jiang, Yuming Qiao, Shiyang Xu and Zhi Wang

Proceedings 2024, 110(1), 22; https://doi.org/10.3390/proceedings2024110022 - 12 Dec 2024

Viewed by 803

Abstract

Landslides are one of the most widespread and hazardous geologic hazards in the world. Landslide susceptibility mapping (LSM) is an effective way to identify landslide-prone areas to prevent and reduce landslide hazards. However, the accuracy of LSM is greatly limited by the balance [...] Read more.

Landslides are one of the most widespread and hazardous geologic hazards in the world. Landslide susceptibility mapping (LSM) is an effective way to identify landslide-prone areas to prevent and reduce landslide hazards. However, the accuracy of LSM is greatly limited by the balance of landslide data. The collection of high-quality landslide inventories is labor-intensive. In this paper, four data enhancement techniques are used to correct the unbalanced landslide dataset based on GIS. The method is applied to LSM in Guangzhou City. And the difference in the accuracy of the enhancement is compared with two assessment models, SVM and RF. The experimental results show that the data enhancement technique helps to improve the accuracy of the evaluated models, and the evaluation results of all models show the best performance by GAN-RF. This study shows that the balance of landslide data greatly affects the accuracy of the assessment model. And the data enhancement technique enhances the robustness of the assessment model and improves the accuracy of the prediction results. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

11 pages, 4179 KiB

Open AccessProceeding Paper

A Methodology for Predicting the Stability Trend of Ground Collapse Under the Water Flow

by Qinglun He, Yizhao Wang, Wenfeng Bai, Fei Wang, Xing Min, Zhi Wang, Long Chen, Juncai Jiang and Yuming Qiao

Proceedings 2024, 110(1), 23; https://doi.org/10.3390/proceedings2024110023 - 12 Dec 2024

Viewed by 727

Abstract

Ground collapse is one of the common geological hazards in modern cities. With the development of urbanization, the risk of ground collapse increases, which has a great impact on urban public safety. Ground collapse accidents typically occur due to the presence of unstable [...] Read more.

Ground collapse is one of the common geological hazards in modern cities. With the development of urbanization, the risk of ground collapse increases, which has a great impact on urban public safety. Ground collapse accidents typically occur due to the presence of unstable cavities under the surface, or the generation and expansion of cavities induced by triggering factors. Investigating the stability of cavities in the strata is significant for identifying subsidence risks and mitigating the consequences of subsidence. This study proposed a method for predicting ground subsidence settlement based on the ARMA model. Firstly, CFD-DEM coupled simulation is employed to simulate the mechanism of cavity changes in the soil layers under the influence of triggering factors and to calculate the safety coefficient for ground subsidence stability. Subsequently, the safety coefficient data at different time points are fitted to predict the subsequent stability of the subsidence. We selected a subway permeable collapse accident in Foshan City, Guangdong Province for experimental verification, and compared the predicted results with the actual situation. The result shows that this method can effectively predict the changes in ground collapse safety factor and the collapse time point. With 40% of the data, high accuracy prediction can be achieved, improving the efficiency of collapse evolution prediction and providing strong support for ground collapse risk prevention and control. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

8 pages, 3869 KiB

Open AccessProceeding Paper

Urban Road Collapse Risk Assessment Study Based on InSAR Spatiotemporal Data

by Juncai Jiang, Wenfeng Bai, Yizhao Wang, Fei Wang, Qinglun He, Long Chen, Yuming Qiao, Zhi Wang and Haitao Luo

Proceedings 2024, 110(1), 24; https://doi.org/10.3390/proceedings2024110024 - 12 Dec 2024

Viewed by 946

Abstract

Urban road collapse is a common disaster in modern cities, posing a severe threat to the safety of life and property of urban residents. Effective risk assessment is crucial for preventing collapses. This study proposes a novel method for assessing the risk of [...] Read more.

Urban road collapse is a common disaster in modern cities, posing a severe threat to the safety of life and property of urban residents. Effective risk assessment is crucial for preventing collapses. This study proposes a novel method for assessing the risk of urban road collapse by integrating Interferometric Synthetic Aperture Radar (InSAR) technology with Long Short-Term Memory (LSTM) networks. We conduct experimental analysis using collapse incidents and corresponding subsidence maps from five areas in Guangzhou. The results demonstrate that the proposed model successfully establishes a mapping relationship between the temporal features of InSAR data and the risk of road collapse, enabling a risk assessment of specific areas solely based on InSAR data. This model overcomes the difficulty of obtaining numerous assessment indicators in traditional risk assessment methods, providing strong support for the prevention and control of regional road collapse risks. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

8 pages, 1118 KiB

Open AccessProceeding Paper

Geospatial Analytics to Support District Efficiency, Fairness and Equity

by Jiwon Baik, Alan T. Murray, Enbo Zhou and Jing Xu

Proceedings 2024, 110(1), 25; https://doi.org/10.3390/proceedings2024110025 - 6 Dec 2024

Viewed by 593

Abstract

Districting is essential in establishing efficient, fair, and equitable boundaries across various domains such as trade and service provision, land-use development, school attendance, and political representation. This paper introduces a robust spatial optimization model tailored to delineate a districting strategy that accounts for [...] Read more.

Districting is essential in establishing efficient, fair, and equitable boundaries across various domains such as trade and service provision, land-use development, school attendance, and political representation. This paper introduces a robust spatial optimization model tailored to delineate a districting strategy that accounts for issues of equinumerosity, compactness, and contiguity, among others. The model is designed to ensure an even distribution of population across districts while ensuring compact and contiguous boundaries. By integrating advanced GIScience and spatial optimization techniques, the model aims to maximize compactness metrics and balance population, producing districts that are both geometrically efficient and demographically representative. Explicit contiguity constraints are imposed to guarantee geographical connectedness among districts. To assess the efficacy of the proposed methodology, application to a school district in California is considered. Our findings highlight GIScience capabilities to identify district boundaries that outperform traditional districting schemes in addressing population balance and compactness. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

14 pages, 2783 KiB

Open AccessProceeding Paper

Research on the Spatial Distribution and Influencing Factors of Digital Creative Industry—Take Shenzhen as an Example

by Zhiyi Gan, Yan Zhang, Nengjun Chen and Ruipeng Li

Proceedings 2024, 110(1), 26; https://doi.org/10.3390/proceedings2024110026 - 13 Dec 2024

Viewed by 860

Abstract

In recent years, the digital creative industry has manifested a vigorous growth trend along with the continuous upgrading of the Internet and the leap of the national economy. This research identifies the spatial distribution characteristics of digital creative enterprises in Shenzhen, employs big [...] Read more.

In recent years, the digital creative industry has manifested a vigorous growth trend along with the continuous upgrading of the Internet and the leap of the national economy. This research identifies the spatial distribution characteristics of digital creative enterprises in Shenzhen, employs big data of spatial information of various facilities such as transportation and commerce as the driving factor to construct a model, takes 1 km grid as the fundamental research unit, and explores the influence mechanism of enterprise location selection through methods like OLS and MGWR. The results are as follows: (1) The overall spatial distribution characteristics of digital creative industry are characterized by “widely distributed throughout the city, with a high concentration within the customs and a weak dispersion outside the customs”. (2) The factors of park foundation, production service, public service and life service exert a significant influence on the spatial distribution of digital creative industries in Shenzhen. Among them, the density of shopping facilities, staff, hotel and bus station exhibits a highly obvious spatial heterogeneity in terms of the influence on enterprise location. (3) The correlation of local scale factors is high and the influence range is precise, which frequently presents complex correlation outcomes in small scales such as streets or communities. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

8 pages, 8451 KiB

Open AccessProceeding Paper

Monitoring, Inspection and Early Warning System in Electrical Distribution Networks Using Satellite Images

by Erick Armando Sedeño Bueno, José Luis Capote Fernández, René González Rodríguez and Nelson Ivan Escalona Macides

Proceedings 2024, 110(1), 27; https://doi.org/10.3390/proceedings2024110027 - 11 Dec 2024

Viewed by 828

Abstract

Timely identification of problems in electrical distribution networks is crucial to preventing major failures, reducing costs, and ensuring a reliable power supply. This paper presents a monitoring, inspection, and early warning system designed specifically for electrical networks, utilizing satellite imagery to complement traditional [...] Read more.

Timely identification of problems in electrical distribution networks is crucial to preventing major failures, reducing costs, and ensuring a reliable power supply. This paper presents a monitoring, inspection, and early warning system designed specifically for electrical networks, utilizing satellite imagery to complement traditional inspections. The system uses spectral indices derived from satellite images to monitor environmental factors such as humidity, vegetation, snow cover, and burned areas, offering a comprehensive view of the grid’s surroundings. Collected daily, this information detects changes that may pose risks to power lines and infrastructure. The system also allows users to include custom indices, ensuring flexibility in various environmental and network contexts. An integrated AI model estimates vegetation height from Sentinel-2 images, identifying potential risk areas where vegetation could threaten power lines. One key advantage of the system is the reduced reliance on costly, frequent manual inspections, lowering operational expenses compared to other methods like aerial photography or LiDAR scanners. Additionally, it provides early alerts to grid operators when potential issues are detected, enabling timely intervention and proactive maintenance. This improves network efficiency and reliability by enhancing the response to critical situations and facilitating preventive risk management. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

7 pages, 386 KiB

Open AccessProceeding Paper

Overview and Prospects of Visibility Analysis Approaches

by Jianghong Zhao, Ailin Xu, Xueqing Zhang, Yunhui Zhang, Yihong Zhang, Mengtian Cao and Ming Huang

Proceedings 2024, 110(1), 28; https://doi.org/10.3390/proceedings2024110028 - 17 Dec 2024

Viewed by 1148

Abstract

This paper conducts a systematic literature review on visibility analysis, aiming to develop a comprehensive classification framework. Visibility analysis is categorized into 2D, 2.5D, and 3D analyses, summarizing its extensive application fields and research dimensions. Chronologically, this paper reviews various algorithms, comparing their [...] Read more.

This paper conducts a systematic literature review on visibility analysis, aiming to develop a comprehensive classification framework. Visibility analysis is categorized into 2D, 2.5D, and 3D analyses, summarizing its extensive application fields and research dimensions. Chronologically, this paper reviews various algorithms, comparing their advantages and limitations in terms of processing speed, accuracy, and applicability. It highlights current challenges, such as dynamic scene analysis and high-resolution data processing, and proposes optimization strategies like employing data dimensionality reduction, integrating eye-tracking data, and using deep learning to enhance robustness. This review offers a practical classification framework and insights for future research trends in visibility analysis. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

13 pages, 4207 KiB

Open AccessProceeding Paper

Methane Dynamics in Inner Mongolia: Unveiling Spatial and Temporal Variations and Driving Factors

by Sirui Yan, Yichun Xie, Ge Han, Xiaoliang Meng and Ziwei Li

Proceedings 2024, 110(1), 29; https://doi.org/10.3390/proceedings2024110029 - 23 Dec 2024

Cited by 1 | Viewed by 767

Abstract

Methane (CH₄), the second-largest greenhouse gas contributing to global warming, has a high warming potential despite its short atmospheric lifespan. Inner Mongolia, due to its high carbon and energy consumption industries, faces significant methane emission challenges. This study uses TROPOMI satellite [...] Read more.

Methane (CH₄), the second-largest greenhouse gas contributing to global warming, has a high warming potential despite its short atmospheric lifespan. Inner Mongolia, due to its high carbon and energy consumption industries, faces significant methane emission challenges. This study uses TROPOMI satellite data (February 2019 to December 2022) to analyze the long-term trends and spatial distribution of methane in Inner Mongolia. The results indicate significant spatial heterogeneity in the methane concentration distribution in Inner Mongolia, China. Higher methane concentrations are observed in the southeastern regions, whereas the central regions exhibit relatively lower concentrations. Temporally, the methane concentrations show an increasing trend with seasonal peaks from late August to early September. Using multiple stepwise regression and geographically weighted regression (GWR) methods, the study identifies the key factors influencing methane concentrations. Increased precipitation and soil temperature, along with intensified human activity, contribute to higher methane levels, while rising surface temperatures and increased vegetation suppress methane concentrations. The GWR model provides a better fit compared to the traditional methods, especially in regions with higher methane levels. This research offers insights for developing strategies to mitigate methane emissions and supports China’s emission control targets. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

10 pages, 2010 KiB

Open AccessProceeding Paper

Learnable Weight Graph Neural Network for River Ice Classification

by Yifan Qu, Armina Soleymani, Denise Sudom and Katharine Andrea Scott

Proceedings 2024, 110(1), 30; https://doi.org/10.3390/proceedings2024110030 - 13 Jan 2025

Viewed by 661

Abstract

Monitoring river ice is crucial for planning safe navigation routes, with ice–water classification being one of the most important tasks in ice mapping. While high-resolutions satellite imagery, such as synthetic aperture radar (SAR), is well-suited to this task, manual interpretation of these data [...] Read more.

Monitoring river ice is crucial for planning safe navigation routes, with ice–water classification being one of the most important tasks in ice mapping. While high-resolutions satellite imagery, such as synthetic aperture radar (SAR), is well-suited to this task, manual interpretation of these data is challenging due to the large data volume. Machine learning approaches are suitable methods to overcome this; however, training the models might not be time-effective when the desired result is a narrow structure, such as a river, within a large image. To address this issue, we proposed a model incorporating a graph neural network (GNN), called learnable weights graph convolution network (LWGCN). Focusing on the winters of 2017–2021 with emphasis on the Beauharnois Canal and Lake St Lawrence regions of the Saint Lawrence River. The model first converts the SAR image into graph-structured data using simple linear iterative clustering (SLIC) to segment the SAR image, then connecting the centers of each superpixel to form graph-structured data. For the training model, the LWGCN learns the weights on each edge to determine the relationship between ice and water. By using the graph-structured data as input, the proposed model training time is eight times faster, compared to a convolution neural network (CNN) model. Our findings also indicate that the LWGCN model can significantly enhance the accuracy of ice and water classification in SAR imagery. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

9 pages, 4576 KiB

Open AccessProceeding Paper

Spatial–Temporal Evolution of Land Desertification Sensitivity in Mu Us Desert Ecological Function Reserve

by Yahao Wu, Xianglei Liu, Runjie Wang, Ming Huang and Liang Huo

Proceedings 2024, 110(1), 31; https://doi.org/10.3390/proceedings2024110031 - 13 Feb 2025

Viewed by 432

Abstract

Land desertification management in the Mu Us Desert has received widespread attention. Assessing land desertification sensitivity is crucial for desertification monitoring and management. This study constructed a comprehensive evaluation index system using four factors: dryness index, the number of windy and sandy days [...] Read more.

Land desertification management in the Mu Us Desert has received widespread attention. Assessing land desertification sensitivity is crucial for desertification monitoring and management. This study constructed a comprehensive evaluation index system using four factors: dryness index, the number of windy and sandy days in the winter and spring, soil texture, and vegetation cover. Land sand sensitivity was divided into five grades, and multi-source data from the Ecological Functional Reserve of the Mu Us Desert from 2002 to 2022 were used to study spatial distribution and dynamic changes. The results show the following: (1) the overall land desertification sensitivity in the Mu Us Desert Ecological Functional Reserve decreased from 2002 to 2022, with the proportion of highly sensitive land decreasing from 92.39% to 82.75%, and the proportion of medium-, medium–low-, and low-sensitivity areas increasing from 0.63% to 1.70%. (2) Low-sensitivity areas were concentrated in Jingbian County, Hengshan District, and southern Uxin Banner. Southeast Otog Banner and northern Jingbian County saw the most significant decreases in land desertification sensitivity since 2002. (3) The four selected factors interacted, with increased vegetation cover being the most crucial factor. This study provides a reference for future ecological restoration in the Mu Us Desert area. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

9 pages, 11286 KiB

Open AccessProceeding Paper

Dynamic Evacuation Shelter Allocation in Response to Human Mobility: A Case Study of Taipei City

by Chang-Hung Shih, Cheng-Yun Wu, Shu-Ping Tseng, Yi-Lin Huang, Rong-Pu Jhuang, Yi-Chung Chen, Tien-Yi Yang and Wei-Ting Chen

Proceedings 2024, 110(1), 32; https://doi.org/10.3390/proceedings2024110032 - 18 Feb 2025

Viewed by 659

Abstract

Natural disasters often occur unexpectedly, catching people off guard, such as the Hualien earthquake on 3 April 2024. Many of the evacuation-monitoring systems currently in place lack real-time updates of shelter capacities, which raises the risk of overcrowding under wartime scenarios. This study [...] Read more.

Natural disasters often occur unexpectedly, catching people off guard, such as the Hualien earthquake on 3 April 2024. Many of the evacuation-monitoring systems currently in place lack real-time updates of shelter capacities, which raises the risk of overcrowding under wartime scenarios. This study developed a system for the targeted assignment of evacuation sites during air raids. The DBSCAN algorithm was used to group data based on pedestrian flow patterns and an LSTM model was used to enhance the prediction speed and accuracy. Weighted Voronoi diagrams delineated regions to identify optimal evacuation points, while real-time SMS notifications through base station positioning disseminated evacuation information to the public. The experiment results demonstrated the effectiveness of the proposed system in facilitating safe evacuations across a broad range of geographic regions while reducing the number of LSTM models. Dynamic updates on the shelter capacities make it possible for citizens to make informed decisions during air raid emergencies. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

8 pages, 4437 KiB

Open AccessProceeding Paper

Enhancing Youbike Redistribution System: A Study on Station Recommendation Using a Genetic Algorithm

by Yang-Chou Juan, Yi-Chung Chen, Wei-Ting Chen, Chieh Yang, Chia-Tzu Liu, Yi-Ci Hou and Yi-Hsuan Tsai

Proceedings 2024, 110(1), 35; https://doi.org/10.3390/proceedings2024110035 - 20 Feb 2025

Viewed by 665

Abstract

Governments are encouraging public transportation and bicycle-sharing systems to promote sustainable development and reduce greenhouse gas emissions. Despite the expansion of Taipei’s YouBike program, many stations frequently run out of bikes or docking spaces, and current redistribution strategies are suboptimal. This study proposes [...] Read more.

Governments are encouraging public transportation and bicycle-sharing systems to promote sustainable development and reduce greenhouse gas emissions. Despite the expansion of Taipei’s YouBike program, many stations frequently run out of bikes or docking spaces, and current redistribution strategies are suboptimal. This study proposes a novel approach to optimize YouBike allocation under resource constraints. We first used K-means clustering to group stations with similar rental profiles, reducing the number of models needed. A random forest model selected key crowd grid factors as input variables for a long short-term memory (LSTM) prediction model to accurately predict demand patterns, including during special events or weather changes. A genetic algorithm then determined optimal station configurations and provided return station recommendations, considering user destinations and station dock ratios, while minimizing manual redistribution. Simulations demonstrated that the proposed system meets user needs, enhances operational efficiency, and significantly reduces manual redistribution costs. Our methods have practical applicability for YouBike managers, indicating that user compliance with recommendations can offset the need for manual redistribution and support the current policy of recommending stations within 600 m of the user’s destination. Full article

(This article belongs to the Proceedings of The 31st International Conference on Geoinformatics)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Proceedings, 2024, Geoinformatics'2024

Editorial

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI