红树林作为独特的海陆过渡湿地,具有极高的生态系统服务价值.红树林的保护、管理和恢复与多项联合国可持续发展目标(Sustainable Development Goals,SDGs)密切相关.然而,迄今还没有面向SDGs的中国红树林时空变化分析.本研究利用Landsat...红树林作为独特的海陆过渡湿地,具有极高的生态系统服务价值.红树林的保护、管理和恢复与多项联合国可持续发展目标(Sustainable Development Goals,SDGs)密切相关.然而,迄今还没有面向SDGs的中国红树林时空变化分析.本研究利用Landsat系列卫星数据和面向对象分析方法解译1973~2020年中国红树林生长区的土地覆被,得出近50年红树林及其与周边土地覆被类型的时空变化和相互转化.结合红树林的保护和恢复等政策,探讨SDGs在中国红树林方面的实施进展.结果表明:由于农田和养殖池扩张等因素,1973~2000年中国红树林面积减少30199ha(1 ha=1×10^(4)m^(2))(约占1973年的62%);2000~2020年,由于中国政府的大力保护和造林,全国新增红树林9408 ha,红树林总面积基本恢复到1980年的水平;1973~2020年,中国滨海一直生长有红树林的陆表面积为8657 ha,仅占1973年红树林总面积的18%.从SDGs元年(2015年)到目标完成年(2020年),中国沿海新增25%的红树林;截至2020年9月,中国红树林保护区面积占生长区的16%,77%的红树林得到良好的保护,国家级经济特区中实施基于生态系统管理措施的比例达80%.近年来,中国政府颁布了一系列的法律、法规和行动计划以达到停止毁林、恢复红树林的目的,中国红树林的保护和恢复已基本达到了相关SDGs的规定.本工作的研究方法、数据集和结论可为监测和评估中国乃至全球落实可持续发展议程提供方法借鉴和数据基础.展开更多
Internal migration is highly valued due to its increasingly acknowledged potential for social and economic development. However, despite its significant contribution to the development of towns and cities, it has led ...Internal migration is highly valued due to its increasingly acknowledged potential for social and economic development. However, despite its significant contribution to the development of towns and cities, it has led to the deterioration of many ecosystems globally. Lake Bosomtwe, a natural Lake in Ghana and one of the six major meteoritic lakes in the world is affected by land cover changes caused by the rising effects of migration, population expansion, and urbanization, owing to the development of tourist facilities on the lakeshore. This study investigated land cover change trajectories using a post-classification comparison approach and identified the factors influencing alteration in the Lake Bosomtwe Basin. Using Landsat imagery, an integrated approach of remote sensing, geographical information systems (GIS), and statistical analysis was successfully employed to analyze the land cover change of the basin. The findings show that over the 17 years, the basin’s forest cover decreased significantly by 16.02%, indicating that population expansion significantly affects changes in land cover. Ultimately, this study will raise the awareness of stakeholders, decision-makers, policy-makers, government, and non-governmental agencies to evaluate land use development patterns, optimize land use structures, and provide a reference for the formulation of sustainable development policies to promote the sustainable development of the ecological environment.展开更多
Suspended particulate matter(SPM)in lakes exerts strong impact on light propagation,aquatic ecosystem productivity,which co-varies with nutrients,heavy metal and micro-pollutant in waters.In lakes,SPM exerts strong ab...Suspended particulate matter(SPM)in lakes exerts strong impact on light propagation,aquatic ecosystem productivity,which co-varies with nutrients,heavy metal and micro-pollutant in waters.In lakes,SPM exerts strong absorption and backscattering,ultimately affects water leaving signals that can be detected by satellite sensors.Simple regression models based on specific band or hand ratios have been widely used for SPM estimate in the past with moderate accuracy.There are still rooms for model accuracy improvements,and machine learning models may solve the non-linear relationships between spectral variable and SPM in waters.We assembled more than 16,400 in situ measured SPM in lakes from six continents(excluding the Antarctica continent),of which 9640 samples were matched with Landsat overpasses within±7 days.Seven machine learning algorithms and two simple regression methods(linear and partial least squares models)were used to estimate SPM in lakes and the performance were compared.To overcome the problem of imbalance datasets in regression,a Synthetic Minority Over-Sampling technique for regression with Gaussian Noise(SMOGN)was adopted in this study.Through comparison,we found that gradient boosting decision tree(GBDT),random forest(RF),and extreme gradient boosting(XGBoost)models demonstrated good spatiotemporal transferability with SMOGN processed dataset,and has potential to map SPM at different year with good quality of Landsat land surface reflectance images.In all the tested modeling approaches,the GBDT model has accurate calibration(n=6428,R^(2)=0.95,MAPE=29.8%)from SPM collected in 2235 lakes across the world,and the validation(n=3214,R^(2)=0.84,MAPE=38.8%)also exhibited stable performance.Further,the good performances were also exhibited by RF model with calibration(R^(2)=0.93)and validation(R^(2)=0.86,MAPE=24.2%)datasets.We applied GBDT and RF models to map SPM of typical lakes,and satisfactory result was obtained.In addition,the GBDT model was evaluated by historical SPM measurements coincident with d展开更多
Land use/land cover (LULC) changes have become a central issue in current global change and sustainability research. Saudi Arabia has undergone significant change in land use and land cover since the government embark...Land use/land cover (LULC) changes have become a central issue in current global change and sustainability research. Saudi Arabia has undergone significant change in land use and land cover since the government embarked on a course of intense national development 30 years ago, as a result of huge national oil revenues. This study evaluates LULC change in Makkah and Al-Taif, Saudi Arabia from 1986 to 2013 using Landsat images. Maximum likelihood and object-oriented classification were used to develop LULC maps. The change detection was executed using post-classification comparison and GIS. The results indicated that urban areas have increased over the period by approximately 174% in Makkah and 113% in Al-Taif. Analysis of vegetation cover over the study area showed a variable distribution from year to year due to changing average precipitation in this environment. Object-based classification provided slightly greater accuracy than maximum likelihood classification. Information provided by satellite remote sensing can play an important role in quantifying and understanding the relationship between population growth and LULC changes, which can assist future planning and potential environmental impacts of expanding urban areas.展开更多
Cloud detection in remote sensing images is a crucial task in various applications,such as meteorological disaster prediction and earth resource exploration,which require accurate cloud identi¯cation.This work pr...Cloud detection in remote sensing images is a crucial task in various applications,such as meteorological disaster prediction and earth resource exploration,which require accurate cloud identi¯cation.This work proposes a cloud detection model based on the Cloud Detection neural Network(CDNet),incorporating a fusion mechanism of channel and spatial attention.Depthwise separable convolution is adopted to achieve a lightweight network model and enhance the e±ciency of network training and detection.In addition,the Convolutional Block Attention Module(CBAM)is integrated into the network to train the cloud detection model with attention features in channel and spatial dimensions.Experiments were conducted on Landsat 8 imagery to validate the proposed improved CDNet.Averaged over all testing images,the overall accuracy(OA),mean Pixel Accuracy(mPA),Kappa coe±cient and Mean Intersection over Union(MIoU)of improved CDNet were 96.38%,81.18%,96.05%,and 84.69%,respectively.Those results were better than the original CDNet and DeeplabV3+.Experiment results show that the improved CDNet is e®ective and robust for cloud detection in remote sensing images.展开更多
The Lake Chad located in the west-central Africa in the Sahel region at the edge of the Sahara experienced severe drought during 1970s and 1980s and overexploitation (unintegrated and unsustainable use), which is a re...The Lake Chad located in the west-central Africa in the Sahel region at the edge of the Sahara experienced severe drought during 1970s and 1980s and overexploitation (unintegrated and unsustainable use), which is a result of variant land uses and water management practices during the last 50 years. This resulted in a decline of the water level in the Lake and surrounding rivers. The present study analyzed satellite images of Lake Chad from Landsat-MSS, Landsat-OLI to investigate the change of the open water surface area during the years of 1973, 1987, 2001, 2013, and 2017. Supervised classifications were performed for the land cover analysis. The open water area in 1973 was covering 16,157.34 km<sup>2</sup> approximately, and that was 64.6% of the total lake area in the 1960s. As an ultimate result of the extreme drought that the study area witnessed through 1970s-1980s, the open water area has decreased to 1831.44 km<sup>2</sup>, <i>i.e.</i> around 11.33%, compared to that in 1973. The dilemma that the study area is suffering from is believed to be a catastrophic complication of the aforementioned drought crisis, which arose as an ultimate result the climate change, global warming, and the unintegrated and unsustainable use of water challenges the study area is still encountering.展开更多
Due to the atmosphere effect,the qualities of images decrease conspicuously,practically in the visible bands,in the processing of earth observation by the satellite-borne sensors.Thus,removing the atmosphere effects h...Due to the atmosphere effect,the qualities of images decrease conspicuously,practically in the visible bands,in the processing of earth observation by the satellite-borne sensors.Thus,removing the atmosphere effects has become a key step to improve the qualities of images and to retrieve the actual reflectivity of surface features.An atmospheric correction approach,called ACVSS(Atmospheric Correction based Vector Space of Spectrum),is proposed here based on the vector space of the features' spectrum.The reflectance image of each band is retrieved first according to the radiative transfer equation,then the spectrum's vector space is constructed using the infrared bands,and finally the residual errors of the reflectance images in the visible bands are corrected based on the pixel position in the spectrum's vector space.The proposed methodology is verified through atmospheric correction on Landsat-7 ETM+ imagery.The experimental results show that our method is more accurate and the corrected image is more distinct,compared with those offered by current popular atmospheric correction software.展开更多
文摘Internal migration is highly valued due to its increasingly acknowledged potential for social and economic development. However, despite its significant contribution to the development of towns and cities, it has led to the deterioration of many ecosystems globally. Lake Bosomtwe, a natural Lake in Ghana and one of the six major meteoritic lakes in the world is affected by land cover changes caused by the rising effects of migration, population expansion, and urbanization, owing to the development of tourist facilities on the lakeshore. This study investigated land cover change trajectories using a post-classification comparison approach and identified the factors influencing alteration in the Lake Bosomtwe Basin. Using Landsat imagery, an integrated approach of remote sensing, geographical information systems (GIS), and statistical analysis was successfully employed to analyze the land cover change of the basin. The findings show that over the 17 years, the basin’s forest cover decreased significantly by 16.02%, indicating that population expansion significantly affects changes in land cover. Ultimately, this study will raise the awareness of stakeholders, decision-makers, policy-makers, government, and non-governmental agencies to evaluate land use development patterns, optimize land use structures, and provide a reference for the formulation of sustainable development policies to promote the sustainable development of the ecological environment.
基金The research was jointly supported by the National Key Research and Development Project of China(2021YFB3901101)the National Natural Science Foundation of China(42171374,42071336,42001311,42101366)+3 种基金the Natural Science Foundation of Jilin Province,China(20220203024SF)Youth Innovation Promotion Association of Chinese Academy of Sciences,China(2020234)Young Scientist Group Project of Northeast Institute of Geography and Agroecology,China(2023QNXZ01)Chinese Academy of Sciences and Postdoctoral Fellowship of Jilin Province of China to Yingxin Shang.
文摘Suspended particulate matter(SPM)in lakes exerts strong impact on light propagation,aquatic ecosystem productivity,which co-varies with nutrients,heavy metal and micro-pollutant in waters.In lakes,SPM exerts strong absorption and backscattering,ultimately affects water leaving signals that can be detected by satellite sensors.Simple regression models based on specific band or hand ratios have been widely used for SPM estimate in the past with moderate accuracy.There are still rooms for model accuracy improvements,and machine learning models may solve the non-linear relationships between spectral variable and SPM in waters.We assembled more than 16,400 in situ measured SPM in lakes from six continents(excluding the Antarctica continent),of which 9640 samples were matched with Landsat overpasses within±7 days.Seven machine learning algorithms and two simple regression methods(linear and partial least squares models)were used to estimate SPM in lakes and the performance were compared.To overcome the problem of imbalance datasets in regression,a Synthetic Minority Over-Sampling technique for regression with Gaussian Noise(SMOGN)was adopted in this study.Through comparison,we found that gradient boosting decision tree(GBDT),random forest(RF),and extreme gradient boosting(XGBoost)models demonstrated good spatiotemporal transferability with SMOGN processed dataset,and has potential to map SPM at different year with good quality of Landsat land surface reflectance images.In all the tested modeling approaches,the GBDT model has accurate calibration(n=6428,R^(2)=0.95,MAPE=29.8%)from SPM collected in 2235 lakes across the world,and the validation(n=3214,R^(2)=0.84,MAPE=38.8%)also exhibited stable performance.Further,the good performances were also exhibited by RF model with calibration(R^(2)=0.93)and validation(R^(2)=0.86,MAPE=24.2%)datasets.We applied GBDT and RF models to map SPM of typical lakes,and satisfactory result was obtained.In addition,the GBDT model was evaluated by historical SPM measurements coincident with d
文摘Land use/land cover (LULC) changes have become a central issue in current global change and sustainability research. Saudi Arabia has undergone significant change in land use and land cover since the government embarked on a course of intense national development 30 years ago, as a result of huge national oil revenues. This study evaluates LULC change in Makkah and Al-Taif, Saudi Arabia from 1986 to 2013 using Landsat images. Maximum likelihood and object-oriented classification were used to develop LULC maps. The change detection was executed using post-classification comparison and GIS. The results indicated that urban areas have increased over the period by approximately 174% in Makkah and 113% in Al-Taif. Analysis of vegetation cover over the study area showed a variable distribution from year to year due to changing average precipitation in this environment. Object-based classification provided slightly greater accuracy than maximum likelihood classification. Information provided by satellite remote sensing can play an important role in quantifying and understanding the relationship between population growth and LULC changes, which can assist future planning and potential environmental impacts of expanding urban areas.
基金supported by the National Natural Science Foundation of China (61973164,62373192).
文摘Cloud detection in remote sensing images is a crucial task in various applications,such as meteorological disaster prediction and earth resource exploration,which require accurate cloud identi¯cation.This work proposes a cloud detection model based on the Cloud Detection neural Network(CDNet),incorporating a fusion mechanism of channel and spatial attention.Depthwise separable convolution is adopted to achieve a lightweight network model and enhance the e±ciency of network training and detection.In addition,the Convolutional Block Attention Module(CBAM)is integrated into the network to train the cloud detection model with attention features in channel and spatial dimensions.Experiments were conducted on Landsat 8 imagery to validate the proposed improved CDNet.Averaged over all testing images,the overall accuracy(OA),mean Pixel Accuracy(mPA),Kappa coe±cient and Mean Intersection over Union(MIoU)of improved CDNet were 96.38%,81.18%,96.05%,and 84.69%,respectively.Those results were better than the original CDNet and DeeplabV3+.Experiment results show that the improved CDNet is e®ective and robust for cloud detection in remote sensing images.
文摘The Lake Chad located in the west-central Africa in the Sahel region at the edge of the Sahara experienced severe drought during 1970s and 1980s and overexploitation (unintegrated and unsustainable use), which is a result of variant land uses and water management practices during the last 50 years. This resulted in a decline of the water level in the Lake and surrounding rivers. The present study analyzed satellite images of Lake Chad from Landsat-MSS, Landsat-OLI to investigate the change of the open water surface area during the years of 1973, 1987, 2001, 2013, and 2017. Supervised classifications were performed for the land cover analysis. The open water area in 1973 was covering 16,157.34 km<sup>2</sup> approximately, and that was 64.6% of the total lake area in the 1960s. As an ultimate result of the extreme drought that the study area witnessed through 1970s-1980s, the open water area has decreased to 1831.44 km<sup>2</sup>, <i>i.e.</i> around 11.33%, compared to that in 1973. The dilemma that the study area is suffering from is believed to be a catastrophic complication of the aforementioned drought crisis, which arose as an ultimate result the climate change, global warming, and the unintegrated and unsustainable use of water challenges the study area is still encountering.
基金supported by National High-tech R&D Program (Grant Nos.2011AA120300,2011AA120302)Foster-ing Program of Science and Technology Innovative Platform,Northeast Normal University (Grant No.106111065202)
文摘Due to the atmosphere effect,the qualities of images decrease conspicuously,practically in the visible bands,in the processing of earth observation by the satellite-borne sensors.Thus,removing the atmosphere effects has become a key step to improve the qualities of images and to retrieve the actual reflectivity of surface features.An atmospheric correction approach,called ACVSS(Atmospheric Correction based Vector Space of Spectrum),is proposed here based on the vector space of the features' spectrum.The reflectance image of each band is retrieved first according to the radiative transfer equation,then the spectrum's vector space is constructed using the infrared bands,and finally the residual errors of the reflectance images in the visible bands are corrected based on the pixel position in the spectrum's vector space.The proposed methodology is verified through atmospheric correction on Landsat-7 ETM+ imagery.The experimental results show that our method is more accurate and the corrected image is more distinct,compared with those offered by current popular atmospheric correction software.
