引用本文:
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  【EndNote】   【RefMan】   【BibTex】
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被:浏览 92次   下载 104 本文二维码信息
码上扫一扫!
分享到: 微信 更多
基于Landsat 8数据的荒漠土壤水分遥感反演
高琪1, 彭杰1, 冯春晖1, 宋奇1, 马自强2, 王玉珍1
1.塔里木大学 植物科学学院, 新疆 阿拉尔 843300;2.北京大学 地球与空间科学学院, 遥感与地理信息系统研究所, 北京 100000
摘要:
[目的] 分析荒漠土壤水分变化特征,为南疆干旱区荒漠土壤水分遥感监测提供理论依据和方法支持。[方法] 以Landsat 8数据构建干旱地区荒漠土壤水分建模指示因子,通过优选的26个光谱指数、地表温度(Ts)和地形数据(DEM)为建模因子,分别以偏最小二乘(PLSR)、支持向量机(SVM)和随机森林(RF)3种方法构建土壤水分反演模型,对模型进行验证和对比,选取最优模型反演空台里克土壤水分空间分布。[结果] ①TVDI,NR,GLI等26个优选的光谱指数中,Ts和DEM与土壤水分均达极显著相关,可作为南疆干旱区荒漠土壤水分遥感建模的指示因子;②对比3种模型,RF模型建模集和预测集的R2分别为0.93,0.91,预测集RPD为3.90,各评价指标均为最高,PLSR模型精度次之,SVM模型精度最低;③以RF模型反演研究区表层土壤水分,在不同土地利用分类中土壤水分分布特征存在明显差异,特别在盐结皮区域的差异尤为突出。[结论] 利用光谱指数、环境因子和地形数据构建的多因子、多指数综合的模型能较高精度地反演干旱区荒漠表层土壤水分,对研究该地区土地荒漠化和生态环境治理具有一定参考价值。
关键词:  Landsat 8  荒漠土壤水分  光谱指数  PLSR  SVM  RF
DOI:10.13961/j.cnki.stbctb.2021.01.018
分类号:S152.7
基金项目:国家重点研发计划项目“土壤综合观测与智能服务平台研发与应用”(2018YFE0107000)资助。
A Study on Inversion for Remote Sensing of Desert Soil Moisture Based on Landsat 8 Data
Gao Qi1, Peng Jie1, Feng Chunhui1, Song Qi1, Ma Ziqiang2, Wang Yuzhen1
1.College of Plant Science, Tarim University, Alar, Xinjiang 843300, China;2.School of Earth and Space Sciences, Peking University, Institute of Remote Sensing and Geographic Information System, Beijing 100000, China
Abstract:
[Objective] The variation characteristics of desert soil moisture were analyzed to provide a theoretical basis and methodology for remote-sensing monitoring of soil water content in the arid desert of Southern Xinjiang Uygur Autonomous Region.[Methods] The desert soil moisture modeling indicators were constructed based on Landsat 8 data. An optimal 26 spectral index, land surface temperature (Ts), and digital elevation model data (DEM) were selected as modeling factors, and the soil water inversion model was constructed using the partial least squares regression (PLSR), support vector machine (SVM), and random forest (RF) algorithms. After model validation and comparison, the spatial distribution of soil moisture in Kongtailike was retrieved using the optimal model.[Results] ① The temperature vegetation dryness index, NR, GLI, and other 26 preferred spectral indices, as well as TS and DEM, were significantly correlated with soil moisture. They could be used as indicators for remote-sensing modeling of desert soil moisture in the arid area of Southern Xinjiang. ② Among the three models, the R2 of calibration and validation based on the RF model were 0.93 and 0.91, respectively, and the RPD of validation was 3.90, which was the highest. The PLSR model accuracy was the second best, and the SVM model accuracy was the lowest. ③ The surface soil moisture in the study area was retrieved by the RF model, and the characteristics of soil moisture distribution in different ground classifications were noticeably different, especially in the salt crust region.[Conclusion] The comprehensive use of spectral index, environmental factors, and terrain factors could result in the inversion of the soil water content in arid areas with a higher accuracy, providing scientific value for the desertification and ecological environment control in this area.
Key words:  Landsat 8  desert soil moisture  spectral index  partial least squares regression (PLSR)  support vector machine (SVM)  random forest (RF)