首页 | 本学科首页   官方微博 | 高级检索  
     

基于多源遥感数据融合的土壤水分反演研究
引用本文:邓超,苏南,潘晓婷,马丽丽,林薇. 基于多源遥感数据融合的土壤水分反演研究[J]. 水利信息化, 2022, 0(2): 41-45
作者姓名:邓超  苏南  潘晓婷  马丽丽  林薇
作者单位:水利部南京水利水文自动化研究所,江苏 南京 210012;扬州市生态环境局, 江苏 扬州 225000
基金项目:国家重点研发计划项目(2019YFB2102000)
摘    要:土壤含水量作为地表的重要参量之一,对地球能量循环、水循环、碳循环及生态环境都有十分重要的意义。以南京市金川河流域为研究区,融合哨兵 2 号 L2A 数据和 Landsat 8 遥感数据 2 种数据源,分别采用偏最小二乘法(PLSR)、最小二乘-支持向量机(LS-SVM)、反向传播神经网络(BPNN)和随机森林(RF)4 种建模方法,建立遥感数据与土壤含水量之间的关系,并进行模型的验证与评价。结果表明:1)土壤含水量与哨兵 2 号和 Landsat 8 各波段反射率均呈负相关关系,和海岸带监测波段(波长为 430~450 nm)和近红外波段(波长为 2 100~2 300 nm)相关性最佳;2)融合后的遥感数据相较于单一遥感数据源,预测土壤含水量的能力更佳, 最优模型 R2 达 0.996,均方根误差仅为 0.003 g/g;3)4 种建模方法中,建模效果从好到差依次为 PLSR,RF, LS-SVM,BPNN。融合哨兵 2 号 L2A 和 Landsat 8 数据,结合 PLSR 建模方法可进行土壤含水量的精准反演, 相较于现有研究反演精度大大提升,对研究该地区地表与地下水循环和生态环境治理有一定参考价值。

关 键 词:土壤含水量  多源遥感数据  融合  反演  PLSR
收稿时间:2021-10-21
修稿时间:2022-01-12

Soil moisture retrieval based on multi-source remote sensing data fusion
DENG Chao,SU Nan,PAN Xiaoting,MA Lili,LIN Wei. Soil moisture retrieval based on multi-source remote sensing data fusion[J]. Water Resources Information, 2022, 0(2): 41-45
Authors:DENG Chao  SU Nan  PAN Xiaoting  MA Lili  LIN Wei
Affiliation:Nanjing Research Institute of Hydrology and Water Conservation Automation,Ministry of Water Resources,Nanjing 210012 ,China;Bureau of Ecology and Environment of Yangzhou,Yangzhou 225000 ,China
Abstract:As one of the important parameters of the surface, it is of great significance to the earth''s energy cycle, water cycle, carbon cycle and ecological environment. In this study, Jinchuan River Basin in Nanjing was taken as the study area, and Sentinel 2 L2A data and Landsat 8 remote sensing data were used as data sources, and Partial Least Squares Regression, Least Square Support Vector Machine (LS-SVM), Back Propagation Neural Network (BPNN) and Random Forest (RF) was used to establish the relationship between remote sensing data and soil water content respectively, then the models were verified and evaluated. The results showed that: (1) There was a negative correlation between soil water content and the reflectance of Sentinel 2 and Landsat 8, and the best correlation was with coastal zone monitoring (wavelength 450-450 nm) and near infrared band (wavelength 2100-2300 nm). (2) Compared with the single remote sensing data source, the fusion remote sensing data has a better ability to predict soil water content, R2 of the optimal model is 0.996, and the RMSE is only 0.003g/g. (3) Among the four modeling methods, performance of the four model methods are PLSR>RF>LS-SVM>BPNN. The above results indicate that the fusion of Sentinel 2 L2A data and Landsat 8 data, combined with PLSR modeling method, can more accurately retrieve soil water content compared with previous studies, which provides reference data for the study of surface and groundwater circulation and ecological environment management in this area.
Keywords:Soil moisture content, multiple remote sensing data   fusion, estimation, PLSR
本文献已被 万方数据 等数据库收录!
点击此处可从《水利信息化》浏览原始摘要信息
点击此处可从《水利信息化》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号