中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
Downscaling Satellite Retrieved Soil Moisture Using Regression Tree-Based Machine Learning Algorithms Over Southwest France

文献类型：期刊论文

作者Liu, Yangxiaoyue1,2; Xia, Xiaolin1,2; Yao, Ling3; Jing, Wenlong1,2; Zhou, Chenghu3; Huang, Wumeng1,2; Li, Yong1,2; Yang, Ji1,2
刊名EARTH AND SPACE SCIENCE
出版日期2020-10-01
卷号7期号:10页码:25
关键词satellite based soil moisture downscale machine learning regression tree driven algorithms
DOI10.1029/2020EA001267
通讯作者Yao, Ling(yaoling@lreis.ac.cn) ; Jing, Wenlong(jingwl@lreis.ac.cn)
英文摘要Satellite retrieved soil moisture (SM) shows great potential in hydrological, meteorological, ecological, and agricultural applications, while the coarse resolution limits its utilization in regional scale. The regression tree-based machine learning algorithms reveal promising capability in SM downscaling. However, it lacks systematic study dedicated to intercomparisons of algorithms to explicitly illuminate their characteristics. In this study, comparisons are made to systematically evaluate performances of classification and regression tree (CART), random forest (RF), gradient boost decision tree (GBDT), and extreme gradient boost (XGB) in Soil Moisture Active Passive (SMAP) SM downscaling in southwest France. The results show that the four algorithms downscaled SM are capable of capturing spatial distribution features of the original SMAP SM. The downscaled regions with favorable accuracy are mostly situated in the dominant Mediterranean climate zone with moderate vegetation coverage and mild topography variation. The best results are obtained by GBDT in grassland with R value of 0.77 and ubRMSE value of 0.04 m(3)/m(3). The RF and XGB also achieve good performances. On the whole, the GBDT approach is robust and reliable, which could downscale SM with superior correlation and smaller bias than the others. Besides, it achieves higher accuracy than the original SMAP in grassland and shrubland. The feature importance index of each explainable variable fluctuates regularly among different seasons and models. This study proves the outstanding performance of GBDT in SMAP SM downscaling and is expected to act as a valuable reference for studies focusing on SM scale conversion algorithms.
WOS关键词INITIAL ASSESSMENT ; SURFACE ALBEDO ; RANDOM FOREST ; ESA CCI ; SMAP ; MODIS ; RESOLUTION ; PRODUCT ; CLASSIFICATION ; TEMPERATURE
资助项目National Postdoctoral Program for Innovative Talents,China[BX20200100] ; Open Research Fund of National Earth Observation Data Center,China[NODAOP2020002] ; National Natural Science Foundation of China[41801362] ; National Natural Science Foundation of China[41976190] ; GDAS' Project of Science and Technology Development[2020GDASYL-20200103006] ; GDAS' Project of Science and Technology Development[2020GDASYL-20200103003] ; GDAS' Project of Science and Technology Development[2020GDASYL-20200103010] ; GDAS' Project of Science and Technology Development[2018GDASCX-0905] ; GDAS' Project of Science and Technology Development[2016GDASRC-0211] ; GDAS' Project of Science and Technology Development[2017GDASCX-0601] ; GDAS' Project of Science and Technology Development[2017GDASCX-0801] ; GDAS' Project of Science and Technology Development[2018GDASCX-0403] ; GDAS' Project of Science and Technology Development[2019GDASYL-0301001] ; GDAS' Project of Science and Technology Development[2019GDASYL-0501001] ; GDAS' Project of Science and Technology Development[2019GDASYL-0502001] ; Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)[GML2019ZD0301]
WOS研究方向Astronomy & Astrophysics ; Geology
语种英语
WOS记录号WOS:000586332600024
出版者AMER GEOPHYSICAL UNION
资助机构National Postdoctoral Program for Innovative Talents,China ; Open Research Fund of National Earth Observation Data Center,China ; National Natural Science Foundation of China ; GDAS' Project of Science and Technology Development ; Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)
源URL[http://ir.igsnrr.ac.cn/handle/311030/156657]  
专题中国科学院地理科学与资源研究所
通讯作者Yao, Ling; Jing, Wenlong
作者单位1.Southern Marine Sci & Engn Guangdong Lab Guangzho, Guangzhou, Peoples R China
2.Guangzhou Inst Geog, Key Lab Guangdong Utilizat Remote Sensing & Geog, Guangdong Open Lab Geospatial Informat Technol &, Guangzhou, Peoples R China
3.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Yangxiaoyue,Xia, Xiaolin,Yao, Ling,et al. Downscaling Satellite Retrieved Soil Moisture Using Regression Tree-Based Machine Learning Algorithms Over Southwest France[J]. EARTH AND SPACE SCIENCE,2020,7(10):25.
APA Liu, Yangxiaoyue.,Xia, Xiaolin.,Yao, Ling.,Jing, Wenlong.,Zhou, Chenghu.,...&Yang, Ji.(2020).Downscaling Satellite Retrieved Soil Moisture Using Regression Tree-Based Machine Learning Algorithms Over Southwest France.EARTH AND SPACE SCIENCE,7(10),25.
MLA Liu, Yangxiaoyue,et al."Downscaling Satellite Retrieved Soil Moisture Using Regression Tree-Based Machine Learning Algorithms Over Southwest France".EARTH AND SPACE SCIENCE 7.10(2020):25.

入库方式： OAI收割

来源：地理科学与资源研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。