基于机器学习和全极化雷达数据的干旱区土壤湿度反演  

Soil moisture inversion in arid areas by using machine learning and fully polarimetric SAR imagery

作　　者：杨丽萍 侯成磊 苏志强 白宇兴 王彤 冯瑞 Yang Liping;Hou Chenglei;Su Zhiqiang;Bai Yuxing;Wang Tong;Feng Rui(School of Geological Engineering and Geomatics,Chang’an University,Xi’an 710054,China;School of Earth Science and Resources,Chang’an University,Xi’an 710054,China;College of Land Resources and Surveying&Mapping Engineering,Shandong Agriculture and Engineering University,Jinan 250100,China)

机构地区：[1]长安大学地质工程与测绘学院,西安710054 [2]长安大学地球科学与资源学院,西安710054 [3]山东农业工程学院国土资源与测绘工程学院,济南250100

出　　处：《农业工程学报》2021年第13期74-82,共9页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家自然科学基金资助项目(41371220、42071345)。

摘　　要：雷达遥感是区域土壤湿度监测最为有效的技术手段之一,为深入探讨全极化雷达特征参数和不同机器学习算法对干旱区土壤湿度反演的潜力,该研究以黑河下游的居延泽为研究区,基于全极化Radarsat-2数据,通过标准强度和相位处理提取后向散射系数(Backscattering Coefficients,BC),并通过Cloude-Pottier分解(Cloude-Pottier Decomposition,CPD)与Yamaguchi分解(Yamaguchi Decomposition,YD)提取多个极化参数作为雷达影响因子,对其进行相关性及重要性分析。采用随机森林(Random Forest,RF)、支持向量机(Support Vector Machine,SVM)和BP人工神经网络(Back Propagation Artificial Neural Network,BP-ANN)3种不同的机器学习算法,构建土壤湿度反演的多种模型,并使用10折交叉验证的方法综合评价各模型的性能,最后使用最佳模型反演研究区土壤湿度,分析其空间分布格局与影响因素。结果表明:1)平均散射角对反演精度至关重要,熵与反熵的影响次之。交叉极化相较于同极化后向散射系数有更高贡献,偶次散射与体散射的重要性明显高于表面散射和螺旋体散射。2)不同类型因子组合建模的模型,其性能表现均明显优于仅采用单种因子类型的模型。3)相较于SVM和BP-ANN模型,RF模型在干旱区土壤湿度反演中具有更好的适用性。其中,BC+CPD组合训练的RF模型性能最优,其验证集决定系数R2和均方根误差分别为0.78和6.60%,对应的标准偏差分别为0.15和1.95%,该模型可解释土壤湿度变化的89%。4)研究区土壤湿度平均值约为8.83%,整体呈现极端干旱的态势。其中,天鹅湖附近和古湖心区的土壤湿度高于其他区域,反演结果能综合反映区域土壤湿度空间分布的总体格局。Soil moisture is one of the most important variablesto affect the water cycle and energy balanceduring theevolution of regional ecosystem in arid areas.However,accurate monitoring of soil moisture is still a challenging task,due to the spatial and temporal heterogeneity.Radar remote sensing has widely been expected to be one of the most effective technologies in regional soil moisture monitoring.Fully polarimetric SAR(PolSAR)can also provide abundant polarized information for different machine learning algorithms to retrieve soil moisture in various regions.However,such research is still lacking in most arid areas,together with the specific evaluation on the performance of different machine learning algorithms.This study aims to retrieve the soil moisture in arid areas using the PolSAR parameters and various machine learning algorithms.The study area was selected as Juyanze region located in the southeast of Ejina banner of Inner Mongolia in western China.Basedon Radarsat-2 imagery,radar variables were set as the extractedbackscattering coefficients(BC)using the standard intensity and phase processing,while the multiple polarimetric parameters that derived from Cloude-Pottier decomposition(CPD)and Yamaguchi decomposition(YD).The parameter correlation and importance were also analyzed after that.Then,21 soil moisture inversion models were established using three machine learning algorithms,namely Random Forest(RF),Support Vector Machine(SVM),and Back Propagation Artificial Neural Network(BP-ANN).Model performance was further evaluated using 10-fold cross-validation.Finally,the optimal model was achieved to inverse soil moisture in the study area,where the spatial distribution pattern was analyzed.The results show that:1)The average scattering angle presented the most prominent influence on the inversion accuracy,followed by entropy and anti-entropy among all the variables.Moreover,cross-polarized backscattering coefficients made much more contribution to the model accuracy,compared with the co-polarized backscatte

关 键 词：土壤湿度 模型 算法 RF SVM BP-ANN RADARSAT-2 干旱区 

分 类 号：S152.7[农业科学—土壤学] TP79[农业科学—农业基础科学]