Article
Computer Science, Information Systems
Liang Kong, Zhengwei He, Zhongsheng Chen, Mingliang Luo, Zhong Du, Fuquan Zhu, Li He
Summary: This study focuses on measuring and presenting urban spatial forms in rapidly urbanizing China by identifying urban territorial scopes through extracting urban settlements and expansion curves. The optimal distance thresholds for urban settlements in cities like Guangzhou, Chengdu, Nanjing, and Shijiazhuang were determined, showing consistency with the built-up areas.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2021)
Article
Ecology
Mathieu Chevalier, Olivier Broennimann, Josselin Cornuault, Antoine Guisan
Summary: This study investigated the impact of spatial niche truncation on SDMs projections and the performance of different methods in addressing this issue. Findings revealed that certain approaches integrating information from larger-scale data sets could reduce bias, with performance varying based on the level of truncation and data combination.
ECOLOGICAL APPLICATIONS
(2021)
Article
Geography, Physical
Quan Qin, Shishuo Xu, Mingyi Du, Songnian Li
Summary: This paper developed an integrated geo-corpus construction approach to identify Urban Functional Zones (UFZs). By extracting multi-spatial distribution patterns of Points of Interest (POIs), UFZs were classified with a high accuracy.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2022)
Article
Environmental Studies
Waldemar A. Gorzym-Wilkowski, Karolina Trykacz
Summary: As development level increases, spatial planning becomes more important in public management. This study compares the enforcement mechanisms of public interest in the spatial planning systems of Poland and Portugal, revealing significant differences between the two countries' approaches to achieving public goals.
Article
Transportation Science & Technology
Linbo Li, Mengfei Cao, Jiajun Yin, Yanli Wang, Yahua Zhang
Summary: The study reveals that the length of activity chain and the proportion of multi-activity travels increase with the distance between residence and activity center, while the distribution density of POIs and activity destinations have strong positive correlations. These findings are important in urban planning for inducing activities through reasonable combinations and spatial interconnections of POIs.
PROMET-TRAFFIC & TRANSPORTATION
(2021)
Article
Construction & Building Technology
Mohammad Reza Dehbozorgi, Mohammad Rastegar, Ashkan Sami
Summary: This paper proposes a data-mining based approach to identify the most probable causes of momentary outages in electric power distribution systems. By analyzing outage dataset, load, and weather historical data, association rules and frequent itemsets are derived to find similarities with permanent outages, thereby reducing the probability of permanent outages.
SUSTAINABLE CITIES AND SOCIETY
(2022)
Article
Remote Sensing
Wenhao Yu, Jiaxin Chen, Cheng Wei
Summary: This paper proposes a neural network prediction method based on multi-level POI category organization, which improves prediction performance by aggregating small sample categories hierarchically while ensuring a balanced data volume.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2022)
Article
Environmental Studies
Wei Chien Benny Chin, Yuming Fu, Kwan Hui Lim, Thomas Schroepfer, Lynette Cheah
Summary: Understanding urban form and function is crucial for urban planning and redevelopment. This study proposes a comprehensive analysis framework using point-of-interest data to identify and characterize urban functional zones and amenities. The framework utilizes geocoded user-generated content to capture the spatial structure of human activities. Case studies in Singapore demonstrate the effectiveness of the framework in identifying urban functional zone shapes and examining associated amenities. The findings reveal a diversity in amenity distribution, challenging the homogeneity of intended land-use types.
ENVIRONMENT AND PLANNING B-URBAN ANALYTICS AND CITY SCIENCE
(2023)
Article
Biodiversity Conservation
Ke-tong Yang, Guo-peng Chen, Jun-ren Xian
Summary: In this study, we measured stomatal density and position of 90 widespread plants on the Loess Plateau, and analyzed the spatial patterns using replicated spatial point pattern analysis. The results showed that stomatal distribution pattern was similar in most plants, except for five species. Stomatal density and distribution were influenced by phylogeny and spatial scale, with regular distribution at small scales and random distribution at large scales. These findings provide insights into the relationships between stomatal distribution and phylogeny, which can inform the optimization of transpiration models in the future.
ECOLOGICAL INDICATORS
(2023)
Article
Computer Science, Artificial Intelligence
Lei Su, Linhan Fu
Summary: The rationality of regional land planning is evaluated and optimized through intelligent technology, combining neural networks and spatial mining to establish a model and analyze correlations between factors.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Plant Sciences
Unil Pak, Qingxi Guo, Zhili Liu, Xugao Wang, Yankun Liu, Guangze Jin
Summary: Investigating the spatial distributions and associations of tree populations provides better insights into the dynamics and processes that shape the forest community. This study focused on the spatial patterns and associations of Korean pine trees in different developmental stages, and found that mature Korean pine trees play a significant role in the spatial patterns of the Korean pine population.
Article
Mathematical & Computational Biology
Wen Cao, Jiaqi Xu, Feilin Peng, Xiaochong Tong, Xinyi Wang, Siqi Zhao, Wenhao Liu
Summary: The paper proposes a point feature label placement algorithm based on spatial data mining, which analyzes the local spatial distribution characteristics and label correlations of point features. The interference among point features is quantified by a label frequent pattern framework, and an ascending label ordering method is designed to reduce interference. Three classical metaheuristic algorithms are applied to verify the validity of this framework. Additionally, a bit-based grid spatial index is proposed to reduce cache memory and consumption time in conflict detection. Experimental results show significant improvements in label quality and efficiency.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2023)
Article
Engineering, Civil
Yun-Hao Dong, Fang-Le Peng, Yang Du, Yan-Qing Men
Summary: This study proposes an automatic method for the identification and extraction of development features of metro-led underground space (MUS) based on point of interest data. By applying the method to 28 Chinese cities, the development status of MUS in China is estimated and nationwide statistics and correlation analysis are conducted. Results show that complex MUS (CMUS) has a lower share than simple MUS, and CMUS development in China is primarily dominated by public transport and lacks a solid functional link to its surroundings. Additionally, a comparative analysis of MUS development in four primary urban agglomerations is conducted, discussing their development characteristics.
Article
Computer Science, Information Systems
Yan Zhou, Xuan Shen, Chen Wang, Yixue Liao, Junli Li
Summary: By analyzing the spatial clustering characteristics of the catering industry in Hangzhou, it was found that the distribution of the catering industry exhibits specific patterns and there are mutual attraction relationships among different types of fast food, which is of great significance for optimizing the spatial layout of the catering industry.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2022)
Article
Engineering, Geological
Xuyan Tan, Weizhong Chen, Changkun Qin, Wusheng Zhao, Wei Ye
Summary: The study presents a deep learning model, termed as transferring convolutional neural network (TCNN), to derive the stress distribution characteristics of the overall coalmine roof. The spatial correlations of structural mechanical responses at different heights above the roadway roof are learned through numerical simulation and transferred to monitoring data to derive the actual state of the roof. Experimental results show that the TCNN model captures 92.25% features of mining-induced stress distribution with a deduction error of 2.037 MPa, indicating the reliability and potential application of DL in underground construction.
GEORISK-ASSESSMENT AND MANAGEMENT OF RISK FOR ENGINEERED SYSTEMS AND GEOHAZARDS
(2023)
Article
Environmental Sciences
Hao Wang, Yunfeng Hu, Huimin Yan, Yuting Liang, Xuan Guo, Junzhi Ye
Summary: This study simulated future land use scenarios and analyzed staple grain production, sustainable stocking capacity, and habitat quality under different scenarios. A comprehensive trade-off method was used to assess their overall development quality. The results showed that the economic and ecological coordination scenario was most beneficial for regional sustainable development.
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Environmental Sciences
Xuan Guo, Junzhi Ye, Yunfeng Hu
Summary: This study used Google Earth Engine and Landsat satellite remote sensing images to classify land use/cover datasets in Vietnam over the past 21 years using the Random Forest algorithm. The spatio-temporal characteristics, dynamic changes, and driving mechanisms of land use change were analyzed using principal component analysis and multiple linear regression methods. The results provide a basis for assessing land use policies in Vietnam and a reference framework for rapid land mapping and analysis in other countries in the China-Indochina Peninsula.
Article
Green & Sustainable Science & Technology
Xuan Guo, Yunfeng Hu, Yunzhi Zhang, Lin Zhen
Summary: Soil erosion is a major cause of land degradation and desertification in northern China. This study used isotope tracing technology to measure the soil erosion modulus in the Xilingol League of Inner Mongolia and analyze the differences across different periods and regions. The results showed that the study area was in a lightly eroded state overall, but the southern parts experienced an increasing trend in soil erosion modulus due to land reclamation and grassland grazing, while the northern parts saw a slowdown in soil erosion modulus due to weakening wind and increasing precipitation.
Article
Environmental Sciences
Xiaoyu Niu, Yunfeng Hu, Lin Zhen, Yiming Wang, Huimin Yan
Summary: This study simulated the future land use/land cover scenarios in the Agro-Pastoral Zone of Northern China and analyzed the future evolution of biocapacity and landscape patterns. The results showed that cultivated land, grassland, and forest would still be the dominant land types in the research area. The study provided suggestions for formulating future ecological protection and agro-pastoral development strategies and guidance for land use/land cover simulation in other similar zones.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2022)
Article
Environmental Sciences
Yunfeng Hu, Hao Wang, Xiaoyu Niu, Wei Shao, Yichen Yang
Summary: This study compares and comprehensively evaluates four spatiotemporal fusion models for NDVI generation, and finds that the GF-SG model performs the best with the highest comprehensive trade-off score, capable of producing high-resolution NDVI images.
Article
Environmental Sciences
Hao Wang, Yunfeng Hu, Zhiming Feng
Summary: A new fusion method based on Bayesian fuzzy probability prediction was developed to improve the reliability of multisource land use/cover (LUC) datasets. A case study in the Indochina Peninsula showed that the fusion method effectively improved the accuracy of LUC data. This method can also be applied to other regions.
Article
Environmental Studies
Yiming Wang, Yunfeng Hu, Xiaoyu Niu, Huimin Yan, Lin Zhen
Summary: Land use/cover change (LUCC) research is crucial for regional ecological conservation and sustainable development. This study explores the long-time-series dynamics and driving mechanisms of LUCC in Thailand at the national scale from 2000 to 2020. The research findings reveal the changes in land use/cover, such as the expansion of impervious surfaces and the reduction of rainfed cropland and forest areas. Socioeconomic factors, including population, grain output, industrial value added, income, and urban population, have played a significant role in driving LUCC in Thailand. The research provides valuable insights for future land planning and management in Thailand.
Article
Food Science & Technology
Yexuan Liu, Lin Zhen, Yunfeng Hu
Summary: Ordos is an ecologically fragile area in China, and the local government has implemented ecological projects to optimize food production and consumption. A study was conducted using panel data from 2000 to 2020 to analyze food self-sufficiency and the dependence on imported food. The results show an increase in food production and consumption dominated by grains, but insufficient consumption of vegetables, fruits, and dairy foods. While overall self-sufficiency has been achieved, certain food types remain dependent on imports, threatening local food security.
Article
Food Science & Technology
Shuang Wang, Lin Zhen, Yunfeng Hu
Summary: This study examined the characteristics of crop planting structure and changes in crop production, focusing on the self-sufficiency rates of wheat and maize in Ningjin County, North China Plain. The results showed an increasing trend in the sown area and self-sufficiency rates of both crops, indicating a safe state of grain yield. The study also identified the limits of fertilizer use in increasing crop yield.
Article
Environmental Sciences
Feifei Peng, Wei Lu, Yunfeng Hu, Liangcun Jiang
Summary: This study proposes two methods based on composite slum spectral indices (CSSIs) to efficiently generate slum maps on a city-wide scale using medium-resolution Sentinel-2 images. The results show that the accuracies of these methods are comparable to or even higher than existing methods using high-resolution images and transfer learning. The threshold-based method performs well for larger slum areas, while the machine learning-based method improves accuracy for smaller slum pockets.
Article
Environmental Sciences
Hao Wang, Wei Shao, Yunfeng Hu, Wei Cao, Yunzhi Zhang
Summary: This study uses machine learning methods to predict grassland gross primary productivity (GPP), and the results show that the LightGBM model has the best overall performance. The key factors affecting the prediction are also explored.
Article
Environmental Studies
Xiaoyu Niu, Yunfeng Hu, Zhongying Lei, Hao Wang, Yu Zhang, Huimin Yan
Summary: This study analyzes the temporal and spatial evolution of land use/cover in Cambodia from 2000 to 2020, and explores its relationship with economic and social development as well as climate change. The findings show that cropland and forest are the most significant land cover types in Cambodia, with rainfed cropland increasing significantly and forest area shrinking. The spatial distribution of land use exhibits a differentiation pattern, with the highest dynamic degree in the northeast and the lowest in the plain area. Land use change in Cambodia is mainly influenced by economic development and human activities.
Article
Environmental Studies
Yu Zhang, Xiaoyu Niu, Yunfeng Hu, Huimin Yan, Lin Zhen
Summary: Land use/land cover change is crucial for land conservation and sustainable development in Laos. This study utilized various methods to analyze the spatiotemporal regularity and driving mechanism of LUCC in Laos from 2000 to 2020, and found that population is a key factor driving LUCC in the country.
Article
Environmental Studies
Xiaoyu Niu, Yunfeng Hu, Zhongying Lei, Huimin Yan, Junzhi Ye, Hao Wang
Summary: This study analyzed the temporal and spatial evolution of land use/land cover (LULC) in Vietnam from 2000 to 2020 using the GLC_FCS30 dataset. The results showed that cropland, forest, and shrubland were the most important LULC types in Vietnam. The LULC changes were mainly influenced by economic development and human activities.
Article
Environmental Studies
Hao Wang, Huimin Yan, Yunfeng Hu, Yue Xi, Yichen Yang
Summary: This study evaluated multiple land use/land cover datasets in the Indochina Peninsula and found differences in their consistency and accuracy. The findings provide a reference for data selection in land use studies in the region and reliability assessment of multi-source land use/land cover datasets in other areas.