东北农牧交错带耕地土壤有机质遥感反演研究  

Soil Organic Matter Inversion in Agro-pastoral Ecotone of Northeast China

作　　者：王丽萍 刘焕军[2] 郑树峰 王翔 孟令华 马雨阳 官海翔 WANG Liping;LIU Huanjun;ZHENG Shufeng;WANG Xiang;MENG Linghua;MA Yuyang;GUAN Haixiang(School of Government,Heilongjiang University,Harbin 150080,China;Northeast Institute of Geography and Agroecology,Chinese Academy of Sciences,Changchun 130012,China;School of Geographical Sciences,Harbin Normal University,Harbin 150025,China;School of Public Administration and Law,Northeast Agricultural University,Harbin 150030,China)

机构地区：[1]黑龙江大学政府管理学院,哈尔滨150080 [2]中国科学院东北地理与农业生态研究所,长春130012 [3]哈尔滨师范大学地理科学学院,哈尔滨150025 [4]东北农业大学公共管理与法学院,哈尔滨150030

出　　处：《土壤》2022年第1期184-190,共7页Soils

基　　金：国家自然科学基金项目(41671438);吉林省科技发展计划项目(20170301001NY)资助。

摘　　要：农牧交错带是农耕区与草原牧区的过渡带,土壤有机质(SOM)的精确估算与变化监测对碳库估算与农业生产具有重要研究意义。以东北典型农牧交错带为研究区,Landsat 8 OLI影像和ALOS 12.5m DEM为数据源,基于波段反射率、反射率对数、亮度指数与相关地形因子,分别利用多元线性逐步回归(MLSR)模型、随机森林(RF)模型和BP神经网络(BPNN)模型,构建农牧交错带SOM多光谱反演模型。结果表明:①根据重要性排序,选择Landsat8 OLI第4波段的对数、第5波段、第6波段和亮度指数作为输入量,RF和BPNN模型的精度优于MLSR模型。②引入高程(E)与坡向变率(SOA)后,3种模型的预测精度提高,BPNN模型精度提高最多,R^(2)提高了0.22,RMSE降低了0.40 g/kg。3种模型最优反演精度由高到低为:BPNN模型(R^(2)=0.82,RMSE=1.4 g/kg)>RF模型(R^(2)=0.71,RMSE=1.9 g/kg)>MLSR模型(R^(2)=0.66,RMSE=8.8 g/kg)。研究结果可为农牧交错带SOM时空变化研究提供方法支撑。The agro-pastoral ecotone is a transitional zone between farming areas and grassland pastoral areas.Accurate estimation and monitoring of soil organic matter(SOM)has important significance for carbon pool estimation and agricultural production.Taking the typical agro-pastoral ecotone in northeast China as the study area,Landsat 8 OLI and ALOS 12.5m DEM as the data sources,the input variables included band reflectivity,reflectivity logarithm,brightness index and terrain factors.The multi-spectral inversion model of SOM in the agro-pastoral ecotone was constructed by using multiple linear stepwise regression(MLSR)model,random forest(RF)model and BP neural network(BPNN)model,respectively.The results showed that:1)According to the order of importance,the logarithm of band 4,band 5,band 6 and brightness index of Landsat 8 OLI were selected as input variables,and the accuracies of RF and BPNN models were better than that of MLSR model.2)After adding elevation(E)and slope of aspect(SOA),the prediction accuracies of the three models all improved,and the accuracy of BPNN model improved most,with R^(2) increased by 0.22 and RMSE decreased by 0.40 g/kg.The optimal inversion accuracies of the three models from high to low was:BPNN model(R^(2)=0.82,RMSE=1.4 g/kg)>RF model(R^(2)=0.71,RMSE=1.9 g/kg)>MLSR model(R^(2)=0.66,RMSE=8.8 g/kg).The research can provide methodological support for the study of SOM spatial and temporal changes in agro-pastoral ecotone.

关 键 词：农牧交错带 土壤有机质 随机森林 BP神经网络 地形因子 

分 类 号：S156.8[农业科学—土壤学]