联合ALOS-2和Landsat 8的绿洲土壤水分反演模型研究  

An Oasis Soil Moisture Inversion Model Using ALOS-2 and Landsat 8 Data

作　　者：王宇 杨丽萍 任杰 张静[1] 孔金玲 侯成磊 WANG Yu;YANG Liping;REN Jie;ZHANG Jing;KONG Jinling;HOU Chenglei(School of Geological Engineering and Geomatics,Chang'an University,Xi'an 710054,China;College of Land Resources and Surveying&Mapping Engineering,Shandong Agriculture and Engineering University,Ji'nan 250100,China)

机构地区：[1]长安大学地质工程与测绘学院,陕西西安710054 [2]山东农业工程学院国土资源与测绘工程学院,山东济南250100

出　　处：《武汉大学学报（信息科学版）》2024年第9期1630-1638,共9页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金(41371220,42071345);中央高校基本科研业务费专项资金(300102269112)。

摘　　要：机器学习和多源数据融合是土壤水分反演研究的热点方向,但对L波段合成孔径雷达(synthetic aperture radar,SAR)数据的研究较少。以额济纳绿洲为研究区,利用ALOS-2 PALSAR-2和Landsat 8影像提取雷达和光学特征参数,通过参数重要性评分进行特征筛选,采用随机森林方法建立基于雷达、光学以及雷达-光学特征参数协同的土壤水分反演模型,对比模型精度,反演绿洲土壤水分。结果表明,与C波段相比,L波段SAR数据对干旱荒漠绿洲区土壤水分含量敏感性更高;雷达特征参数中重要性较高的为表面散射和体散射分量,二面角散射和螺旋体散射分量相对偏低;光学特征参数中植被供水指数重要性最高,增强型植被指数重要性最低。雷达特征参数方案最优模型决定系数R^(2)、均方根误差(root mean square error,RMSE)分别为0.67、2.16%,光学特征参数方案模型精度普遍较低且精度相当,R^(2)、RMSE分别为0.5、2.47%;雷达-光学参数协同反演的最优模型R^(2)、RMSE分别为0.72、1.99%,相比单一数据源,R^(2)分别提升7.46%、38.4%,RMSE分别降低8.54%、22.6%。研究证明,基于多源数据融合的随机森林模型在干旱荒漠绿洲区具有较高的预测精度和良好的适用性。Objectives:Integration of machine learning and multi-source data becomes a hot topic in soil moisture inversion,where relatively few studies are performed on L-band synthetic aperture radar(SAR)imagery.Methods:ALOS-2 PALSAR-2 and Landsat 8 images of Ejina Oasis are used to extract the radar and optical characteristic parameters which are then screened according to the importance score.Random forest is adopted to establish different soil moisture inversion models based on radar,optical,and radar-optical integrated parameters.Model accuracies are evaluated and soil moisture content in Ejina Oasis is inversed.Results:Compared with C-band,L-band SAR data is more sensitive to soil moisture content in arid desert oasis.With regard to radar characteristic parameters,surface and volume scattering components have higher important scores,while dihedral and helix scattering component are less important.As for optical characteristic parameters,vegetation water supply index takes the most important place while the enhanced vegetation index is the least important one.The determination coefficient R^(2)and root mean square error(RMSE)of radar characteristic parameter scheme are 0.67 and 2.16%,respectively.The accu‐racy of optical characteristic parameter scheme model is generally low and the accuracy is equivalent,with R^(2)and RMSE about 0.5 and 2.47%,respectively.R^(2)and RMSE of the optimal radar-optical integrated parameter inversion model are 0.72 and 1.99%,respectively.Compared with either single data source,R^(2)is increased by 7.46%and 38.4%,while RMSE is decreased by 8.54%and 22.6%.Conclusions:The research proves that the random forest model based on multi-source data fusion has higher prediction accuracy and better applicability in arid desert oasis area.

关 键 词：ALOS-2 PALSAR-2 Landsat 8 土壤水分 随机森林 特征参数 

分 类 号：P237[天文地球—摄影测量与遥感]