Glacial lake mapping provides the most feasible way for investigating the water resources and monitoring the flood outburst hazards in High Mountain Region.However,various types of glacial lakes with different propert...Glacial lake mapping provides the most feasible way for investigating the water resources and monitoring the flood outburst hazards in High Mountain Region.However,various types of glacial lakes with different properties bring a constraint to the rapid and accurate glacial lake mapping over a large scale.Existing spectral features to map glacial lakes are diverse but some are generally limited to the specific glaciated regions or lake types,some have unclear applicability,which hamper their application for the large areas.To this end,this study provides a solution for evaluating the most effective spectral features in glacial lake mapping using Landsat-8 imagery.The 23 frequently-used lake mapping spectral features,including single band reflectance features,Water Index features and image transformation features were selected,then the insignificant features were filtered out based on scoring calculated from two classical feature selection methods-random forest and decision tree algorithm.The result shows that the three most prominent spectral features(SF)with high scores are NDWI1,EWI,and NDWI3(renamed as SF8,SF19 and SF12 respectively).Accuracy assessment of glacial lake mapping results in five different test sites demonstrate that the selected features performed well and robustly in classifying different types of glacial lakes without any influence from the mountain shadows.SF8 and SF19 are superior for the detection of large amount of small glacial lakes,while some lake areas extracted by SF12 are incomplete.Moreover,SF8 achieved better accuracy than the other two features in terms of both Kappa Coefficient(0.8812)and Prediction(0.9025),which further indicates that SF8 has great potential for large scale glacial lake mapping in high mountainous area.展开更多
Lakes over the Qinghai-Tibet Plateau (TP) have large quantities and areas. As an important component of fragile plateau ecosystems,these lakes have attracted increasing attention. However,owing to the limitations of t...Lakes over the Qinghai-Tibet Plateau (TP) have large quantities and areas. As an important component of fragile plateau ecosystems,these lakes have attracted increasing attention. However,owing to the limitations of technology and methods,changes in smaller lakes on the TP have received less attention. In this study,we used Google Earth Engine (GEE) with the Analysis Ready Data (ARD) preparation framework to obtain preprocessed Sentinel-1 data covering the plateau. The D-LinkNet framework was introduced to achieve lake extraction,and the lake dataset was completed from 2016 to 2021. The lake dataset showed an area accuracy of 86.49% and Intersection over Union (IoU) of 0.72-0.99 in different regions. The findings were as follows: during the study period,the TP lakes tended to be stable after increasing,with an increase in area and number of +7.6% and +14.8%. Except for the northwest TP,the other regions show the same general trend. In particular,the Tarim Basin exhibited a lake variation pattern independent of the TP. Significantly,we found frequent lake activity in the Kunlun Mountains,Qaidam Basin,Mountain Qogir,etc. Effects of the ongoing La Niña event on the TP lakes may occur in the next few years.展开更多
基金funded by the National Key R&D Program of China(Grant No.2017YFE0100800)the International Partnership Program of the Chinese Academy of Sciences(Grant No.131551KYSB20160002/131211KYSB20170046)the National Natural Science Foundation of China(41701481)。
文摘Glacial lake mapping provides the most feasible way for investigating the water resources and monitoring the flood outburst hazards in High Mountain Region.However,various types of glacial lakes with different properties bring a constraint to the rapid and accurate glacial lake mapping over a large scale.Existing spectral features to map glacial lakes are diverse but some are generally limited to the specific glaciated regions or lake types,some have unclear applicability,which hamper their application for the large areas.To this end,this study provides a solution for evaluating the most effective spectral features in glacial lake mapping using Landsat-8 imagery.The 23 frequently-used lake mapping spectral features,including single band reflectance features,Water Index features and image transformation features were selected,then the insignificant features were filtered out based on scoring calculated from two classical feature selection methods-random forest and decision tree algorithm.The result shows that the three most prominent spectral features(SF)with high scores are NDWI1,EWI,and NDWI3(renamed as SF8,SF19 and SF12 respectively).Accuracy assessment of glacial lake mapping results in five different test sites demonstrate that the selected features performed well and robustly in classifying different types of glacial lakes without any influence from the mountain shadows.SF8 and SF19 are superior for the detection of large amount of small glacial lakes,while some lake areas extracted by SF12 are incomplete.Moreover,SF8 achieved better accuracy than the other two features in terms of both Kappa Coefficient(0.8812)and Prediction(0.9025),which further indicates that SF8 has great potential for large scale glacial lake mapping in high mountainous area.
基金supported by the National Natural Science Foundation of China [grant number 42171362].
文摘Lakes over the Qinghai-Tibet Plateau (TP) have large quantities and areas. As an important component of fragile plateau ecosystems,these lakes have attracted increasing attention. However,owing to the limitations of technology and methods,changes in smaller lakes on the TP have received less attention. In this study,we used Google Earth Engine (GEE) with the Analysis Ready Data (ARD) preparation framework to obtain preprocessed Sentinel-1 data covering the plateau. The D-LinkNet framework was introduced to achieve lake extraction,and the lake dataset was completed from 2016 to 2021. The lake dataset showed an area accuracy of 86.49% and Intersection over Union (IoU) of 0.72-0.99 in different regions. The findings were as follows: during the study period,the TP lakes tended to be stable after increasing,with an increase in area and number of +7.6% and +14.8%. Except for the northwest TP,the other regions show the same general trend. In particular,the Tarim Basin exhibited a lake variation pattern independent of the TP. Significantly,we found frequent lake activity in the Kunlun Mountains,Qaidam Basin,Mountain Qogir,etc. Effects of the ongoing La Niña event on the TP lakes may occur in the next few years.
