Effective detection of abnormal electricity users and analysis of the spatial distribution and influencing factors of abnormal electricity consumption in urban areas have positive effects on the quality of electricity...Effective detection of abnormal electricity users and analysis of the spatial distribution and influencing factors of abnormal electricity consumption in urban areas have positive effects on the quality of electricity consumption by customers,safe operation of power grids,and sustainable development of cities.However,current abnormal electricity consumption detection models do not consider the time dependence of time-series data and rely on a large number of training samples,and no study has analyzed the spatial distribution and influencing factors of abnormal electricity consumption in urban areas.In this study,we use the Seasonal-Trend decomposition procedure based on Loess(STL)based time series decomposition and outlier detection to detect abnormal electricity consumption in the central city of Pingxiang,and analyze the relationship between spatial variation and urban functions through Geodetector.The results show that the degree of abnormal electricity consumption in urban areas is related to geographic location and has spatial heterogeneity,and the abnormal electricity users are mainly located in areas with highly mixed residential,commercial and entertainment functions in the city.The results obtained from this study can provide a reference basis and a theoretical foundation for the detection of abnormal electricity consumption by users and the arming of electricity theft devices in the power grid.展开更多
Accurate measurement of urban sprawl is vital for urban planning and management.Urban planning-induced internal structure complexity affects the extent of urban sprawl.In addition,urban sprawl is closely linked to eco...Accurate measurement of urban sprawl is vital for urban planning and management.Urban planning-induced internal structure complexity affects the extent of urban sprawl.In addition,urban sprawl is closely linked to economic development.The study attempts to explore the impact of urban sprawl from an economic-dominated perspective.Thus a City-Ring road-County(CRC)scale framework based on top-down administrative divisions for urban sprawl measurement is proposed:1)the single-index measurement based on economic activity is applied to calculate urban sprawl;2)the spatiotemporal pattern of urban sprawl is investigated through a case study in 31 economy-dominated provincial capital cities across China from 2005 to 2015;3)the impact of economy and land on urban sprawl is explored using correlation analysis.The results indicate that the degree of urban sprawl at the city scale shows an“inverted U-shaped”curve from 2005 to 2015,which represents that the phenomenon of urban sprawl was most severe in 2010.It finds that urban sprawl was more severe in the east and central regions relative to the provincial capitals in the western region,with the situation being most severe in the northeast region.Regions that have been transformed from suburban to urban built-up areas need to be given priority attention by the local government,including population movement,land layout,and fiscal policy,to meet the criteria of the urbanization process.Through correlation analysis,we also found that urban sprawl was influenced by the industry structure and the form of built-up area.The outcome of the study suggests that the data scale is sufficiently small in granularity to provide geographic boundaries for systematic analysis of urban sprawl in multiple administrative regions.Thus,the study helps provide a reference for differential planning policy formulation by governments at diverse economic levels.展开更多
Poverty threatens human development especially for developing countries,so ending poverty has become one of the most important United Nations Sustainable Development Goals(SDGs).This study aims to explore China’s pro...Poverty threatens human development especially for developing countries,so ending poverty has become one of the most important United Nations Sustainable Development Goals(SDGs).This study aims to explore China’s progress in poverty reduction from 2016 to 2019 through time-series multi-source geospatial data and a deep learning model.The poverty reduction efficiency(PRE)is measured by the difference in the out-of-poverty rates(which measures the probability of being not poor)of 2016 and 2019.The study shows that the probability of poverty in all regions of China has shown an overall decreasing trend(PRE=0.264),which indicates that the progress in poverty reduction during this period is significant.The Hu Huanyong Line(Hu Line)shows an uneven geographical pattern of out-of-poverty rate between Southeast and Northwest China.From 2016 to 2019,the centroid of China’s out-of-poverty rate moved 105.786 km to the northeast while the standard deviation ellipse of the out-of-poverty rate moved 3 degrees away from the Hu Line,indicating that the regions with high out-of-poverty rates are more concentrated on the east side of the Hu Line from 2016 to 2019.The results imply that the government’s future poverty reduction policies should pay attention to the infrastructure construction in poor areas and appropriately increase the population density in poor areas.This study fills the gap in the research on poverty reduction under multiple scales and provides useful implications for the government’s poverty reduction policy.展开更多
Ecosystem services values(ESV)are increasingly affected by land use land cover change(LULCC)in Côte d’Ivoire.However,there is a scarcity of studies to understand the current state of the ecological environment a...Ecosystem services values(ESV)are increasingly affected by land use land cover change(LULCC)in Côte d’Ivoire.However,there is a scarcity of studies to understand the current state of the ecological environment and the factors that influence the change of ESV in Côte d’Ivoire.This study aimed to quantify LULCC and the ESV change in Côte d’Ivoire from 1990 to 2040.The method-ology used in this study is based on evaluating the change in land use and ESV from 1990 to 2020 and predicting the land cover in 2040 with a cellular au-tomata(CA)based PLUS model.Our results demonstrated that vegetation cover is predicted to decrease by 0.370%per year from 2020 to 2040.Culti-vated land is predicted to increase by 0.013%per year from 2020 to 2040.From 2020 to 2040,hotspots of ESV changes are predicted to mainly appear in the Tchologo and Hambol regions.Our results demonstrated that ecosystem management should be made to control cultivated land expansion and protect wetland,and forestland for more sustainable ecosystem services.Ecosystem management to mitigate vegetation loss is necessary to help decisions mak-ers to manage land use,facilitate land use expansion and protect the eco-system.展开更多
Semantic segmentation for remote sensing images faces challenges of unbalanced category weight,rich context causing difficulties of recognition,blurred boundaries of multi-scale objects,and so on.To address these prob...Semantic segmentation for remote sensing images faces challenges of unbalanced category weight,rich context causing difficulties of recognition,blurred boundaries of multi-scale objects,and so on.To address these problems,we propose a new model by combining HRNet with attention mechanisms and dilated convolution,denoted as:AD-HRNet for the semantic segmentation of remote sensing images.In the framework of AD-HRNet,we obtained the weight value of each category based on an improved weighted cross-entropy function by introducing the median frequency balance method to solve the issue of class weight imbalance.The Shuffle-CBAM module with channel attention and spatial attention in AD-HRNet framework was applied to extract more global context information of images through slightly increasing the amount of computation.To address the problem of blurred boundaries caused by multi-scale object segmentation and edge segmentation,we developed an MDC-DUC module in AD-HRNet framework to capture the context information of multi-scale objects and the edge information of many irregular objects.Taking Postdam,Vaihingen,and SAMA-VTOL datasets as materials,we verified the performance of AD-HRNet by comparing with eight typical semantic segmentation models.Experimental results shown that AD-HRNet increases the mIoUs to 75.59%and 71.58%based on the Postdam and Vaihingen datasets,respectively.展开更多
Wood-leaf separation from terrestrial laser scanning(TLS)is a crucial prerequisite for quantifying many biophysical properties and understanding ecological functions.In this study,we propose a novel multi-directional ...Wood-leaf separation from terrestrial laser scanning(TLS)is a crucial prerequisite for quantifying many biophysical properties and understanding ecological functions.In this study,we propose a novel multi-directional collaborative convolutional neural network(MDC-Net)that takes the original 3D coordinates and useful features from prior knowledge(prior features)as input,and outputs the semantic labels of TLS point clouds.The MDC-Net contains two key units:(1)a multi-directional neighborhood construction(MDNC)unit to obtain more representative neighbors and enable directionally aware feature encoding in the subsequent local feature extraction,to mitigate occlusion effects;(2)a collaborative feature encoding(CFE)unit is introduced to incorporate useful features from prior knowledge into the network through a collaborative cross coding to enhance the discrimination for thin structures(e.g.small branches and leaf).The MDC-Net is evaluated onfive plots from forests in Guangxi,China,with different branch architectures and leaf distributions.Experimental results showed that the MDC-Net achieved an OA of 0.973 and a mIoU of 0.821 and outperformed other related methods.We believe the MDC-Net would facilitate the usage of TLS in ecology studies for quantifying tree size and morphology and thus promote the development of relevant ecological applications.展开更多
The normalized difference vegetation index(NDVI)is the most widely used vegetation index for monitoring vegetation vigor and cover.As NDVI time series are usually derived at coarse or medium spatial resolutions,pixel ...The normalized difference vegetation index(NDVI)is the most widely used vegetation index for monitoring vegetation vigor and cover.As NDVI time series are usually derived at coarse or medium spatial resolutions,pixel size often represents a mixture of vegetated and non-vegetated surfaces.In heterogeneous urban areas,mixed pixels impede the accurate estimation of gross primary productivity(GPP).To address the mixed pixel effect on'NDVI time series and GPP estimation,we proposed a framework to extract subpixel vegetation NDVI(NDVI_(vege))from Landsat OLI images in urban areas,using endmember fractions,mixed NDVI(NDVI_(mix)),and NDVI.of non-vegetation,endmembers.Results demonstrated that the NDVI_(vege) extracted by this framework agreed well with the true NDVI_(vege) cross seasons and vegetation fractions,with R^(2) ranging from 0.74 to 0.82 and RMSE ranging from 0.03 to 0.04.The NDVI_(vege) time series was applied to evaluate vegetation GP in Wuhan,China.The total annual GPp estimated with NDVI_(vege) was 28-35%higher than the total annual GPP estimated with NDVI_(mix) implying uncertainty in the GPP estimations caused by mixed pixels.This study showed the potential of the proposed framework to resolve NDVI_(vege) for characterizing vegetation dynamics in heterogeneous areas.展开更多
基金National Natural Science Foundation of China(Nos.4180130642171466)The Scientific Research Program of the Department of Natural Resources of Hubei Province(No.ZRZY2021KJ02)。
文摘Effective detection of abnormal electricity users and analysis of the spatial distribution and influencing factors of abnormal electricity consumption in urban areas have positive effects on the quality of electricity consumption by customers,safe operation of power grids,and sustainable development of cities.However,current abnormal electricity consumption detection models do not consider the time dependence of time-series data and rely on a large number of training samples,and no study has analyzed the spatial distribution and influencing factors of abnormal electricity consumption in urban areas.In this study,we use the Seasonal-Trend decomposition procedure based on Loess(STL)based time series decomposition and outlier detection to detect abnormal electricity consumption in the central city of Pingxiang,and analyze the relationship between spatial variation and urban functions through Geodetector.The results show that the degree of abnormal electricity consumption in urban areas is related to geographic location and has spatial heterogeneity,and the abnormal electricity users are mainly located in areas with highly mixed residential,commercial and entertainment functions in the city.The results obtained from this study can provide a reference basis and a theoretical foundation for the detection of abnormal electricity consumption by users and the arming of electricity theft devices in the power grid.
基金supported by the National Natural Science Foundation of China[grant number 42271413]the Key Lab of Spatial Data Mining&Information Sharing of Ministry of Education[grant number 2022LSDMIS09]+1 种基金the National Natural Science Foundation of China[grant number 41971356]the Open Fund of Key Laboratory of Urban Land Resources Monitoring and Simulation,Ministry of Natural Resources[grant number KF-2022-07-001].
文摘Accurate measurement of urban sprawl is vital for urban planning and management.Urban planning-induced internal structure complexity affects the extent of urban sprawl.In addition,urban sprawl is closely linked to economic development.The study attempts to explore the impact of urban sprawl from an economic-dominated perspective.Thus a City-Ring road-County(CRC)scale framework based on top-down administrative divisions for urban sprawl measurement is proposed:1)the single-index measurement based on economic activity is applied to calculate urban sprawl;2)the spatiotemporal pattern of urban sprawl is investigated through a case study in 31 economy-dominated provincial capital cities across China from 2005 to 2015;3)the impact of economy and land on urban sprawl is explored using correlation analysis.The results indicate that the degree of urban sprawl at the city scale shows an“inverted U-shaped”curve from 2005 to 2015,which represents that the phenomenon of urban sprawl was most severe in 2010.It finds that urban sprawl was more severe in the east and central regions relative to the provincial capitals in the western region,with the situation being most severe in the northeast region.Regions that have been transformed from suburban to urban built-up areas need to be given priority attention by the local government,including population movement,land layout,and fiscal policy,to meet the criteria of the urbanization process.Through correlation analysis,we also found that urban sprawl was influenced by the industry structure and the form of built-up area.The outcome of the study suggests that the data scale is sufficiently small in granularity to provide geographic boundaries for systematic analysis of urban sprawl in multiple administrative regions.Thus,the study helps provide a reference for differential planning policy formulation by governments at diverse economic levels.
基金supported by the National Key Research and Development Program of China[grant number 2019YFB2102903]the National Natural Science Foundation of China[grant number 41801306]+1 种基金the“CUG Scholar”Scientific Research Funds at China University of Geosciences(Wuhan)[grant number 2022034]a grant from State Key Laboratory of Resources and Environmental Information System.
文摘Poverty threatens human development especially for developing countries,so ending poverty has become one of the most important United Nations Sustainable Development Goals(SDGs).This study aims to explore China’s progress in poverty reduction from 2016 to 2019 through time-series multi-source geospatial data and a deep learning model.The poverty reduction efficiency(PRE)is measured by the difference in the out-of-poverty rates(which measures the probability of being not poor)of 2016 and 2019.The study shows that the probability of poverty in all regions of China has shown an overall decreasing trend(PRE=0.264),which indicates that the progress in poverty reduction during this period is significant.The Hu Huanyong Line(Hu Line)shows an uneven geographical pattern of out-of-poverty rate between Southeast and Northwest China.From 2016 to 2019,the centroid of China’s out-of-poverty rate moved 105.786 km to the northeast while the standard deviation ellipse of the out-of-poverty rate moved 3 degrees away from the Hu Line,indicating that the regions with high out-of-poverty rates are more concentrated on the east side of the Hu Line from 2016 to 2019.The results imply that the government’s future poverty reduction policies should pay attention to the infrastructure construction in poor areas and appropriately increase the population density in poor areas.This study fills the gap in the research on poverty reduction under multiple scales and provides useful implications for the government’s poverty reduction policy.
文摘Ecosystem services values(ESV)are increasingly affected by land use land cover change(LULCC)in Côte d’Ivoire.However,there is a scarcity of studies to understand the current state of the ecological environment and the factors that influence the change of ESV in Côte d’Ivoire.This study aimed to quantify LULCC and the ESV change in Côte d’Ivoire from 1990 to 2040.The method-ology used in this study is based on evaluating the change in land use and ESV from 1990 to 2020 and predicting the land cover in 2040 with a cellular au-tomata(CA)based PLUS model.Our results demonstrated that vegetation cover is predicted to decrease by 0.370%per year from 2020 to 2040.Culti-vated land is predicted to increase by 0.013%per year from 2020 to 2040.From 2020 to 2040,hotspots of ESV changes are predicted to mainly appear in the Tchologo and Hambol regions.Our results demonstrated that ecosystem management should be made to control cultivated land expansion and protect wetland,and forestland for more sustainable ecosystem services.Ecosystem management to mitigate vegetation loss is necessary to help decisions mak-ers to manage land use,facilitate land use expansion and protect the eco-system.
基金supported by the National Natural Science Foundation of China(No.42271449,41901394,41971405)open research fund program of Geomatics Technology and Application Key Laboratory of Qinghai Province.
文摘Semantic segmentation for remote sensing images faces challenges of unbalanced category weight,rich context causing difficulties of recognition,blurred boundaries of multi-scale objects,and so on.To address these problems,we propose a new model by combining HRNet with attention mechanisms and dilated convolution,denoted as:AD-HRNet for the semantic segmentation of remote sensing images.In the framework of AD-HRNet,we obtained the weight value of each category based on an improved weighted cross-entropy function by introducing the median frequency balance method to solve the issue of class weight imbalance.The Shuffle-CBAM module with channel attention and spatial attention in AD-HRNet framework was applied to extract more global context information of images through slightly increasing the amount of computation.To address the problem of blurred boundaries caused by multi-scale object segmentation and edge segmentation,we developed an MDC-DUC module in AD-HRNet framework to capture the context information of multi-scale objects and the edge information of many irregular objects.Taking Postdam,Vaihingen,and SAMA-VTOL datasets as materials,we verified the performance of AD-HRNet by comparing with eight typical semantic segmentation models.Experimental results shown that AD-HRNet increases the mIoUs to 75.59%and 71.58%based on the Postdam and Vaihingen datasets,respectively.
基金supported by the National Natural Science Foundation of China[grant number 42101456]funded by Key Laboratory of Spatial-temporal Big Data Analysis and Application of Natural Resources in Megacities,MNR(No.KFKT-2022-04)+1 种基金Open Research Fund of State Key Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing of Wuhan University(21S01)Research Fund of post-doctoral innovation in Hubei Province under Grant No.1232168.
文摘Wood-leaf separation from terrestrial laser scanning(TLS)is a crucial prerequisite for quantifying many biophysical properties and understanding ecological functions.In this study,we propose a novel multi-directional collaborative convolutional neural network(MDC-Net)that takes the original 3D coordinates and useful features from prior knowledge(prior features)as input,and outputs the semantic labels of TLS point clouds.The MDC-Net contains two key units:(1)a multi-directional neighborhood construction(MDNC)unit to obtain more representative neighbors and enable directionally aware feature encoding in the subsequent local feature extraction,to mitigate occlusion effects;(2)a collaborative feature encoding(CFE)unit is introduced to incorporate useful features from prior knowledge into the network through a collaborative cross coding to enhance the discrimination for thin structures(e.g.small branches and leaf).The MDC-Net is evaluated onfive plots from forests in Guangxi,China,with different branch architectures and leaf distributions.Experimental results showed that the MDC-Net achieved an OA of 0.973 and a mIoU of 0.821 and outperformed other related methods.We believe the MDC-Net would facilitate the usage of TLS in ecology studies for quantifying tree size and morphology and thus promote the development of relevant ecological applications.
基金supported by the National Key Research and Development Program of China(No..2022YFB3903405)National Natural Science Foundation of China(General Program:42171466 and 42171350)the Fundamental Research Funds for the Central Universities(2662021JC002).
文摘The normalized difference vegetation index(NDVI)is the most widely used vegetation index for monitoring vegetation vigor and cover.As NDVI time series are usually derived at coarse or medium spatial resolutions,pixel size often represents a mixture of vegetated and non-vegetated surfaces.In heterogeneous urban areas,mixed pixels impede the accurate estimation of gross primary productivity(GPP).To address the mixed pixel effect on'NDVI time series and GPP estimation,we proposed a framework to extract subpixel vegetation NDVI(NDVI_(vege))from Landsat OLI images in urban areas,using endmember fractions,mixed NDVI(NDVI_(mix)),and NDVI.of non-vegetation,endmembers.Results demonstrated that the NDVI_(vege) extracted by this framework agreed well with the true NDVI_(vege) cross seasons and vegetation fractions,with R^(2) ranging from 0.74 to 0.82 and RMSE ranging from 0.03 to 0.04.The NDVI_(vege) time series was applied to evaluate vegetation GP in Wuhan,China.The total annual GPp estimated with NDVI_(vege) was 28-35%higher than the total annual GPP estimated with NDVI_(mix) implying uncertainty in the GPP estimations caused by mixed pixels.This study showed the potential of the proposed framework to resolve NDVI_(vege) for characterizing vegetation dynamics in heterogeneous areas.
