松嫩平原典型农区玉米秸秆覆盖度遥感估算  

Remotely sensed estimation of maize residue cover in typical agricultural regions of Songnen Plain

作　　者：项小云 杜嘉[1] 赵博宇 周昊昊 宋开山[1] XIANG Xiaoyun;DU Jia;ZHAO Boyu;ZHOU Haohao;SONG Kaishan(Northeast Institute of Geography and Agroecology,Chinese Academy of Sciences,Changchun 130102,China)

机构地区：[1]中国科学院东北地理与农业生态研究所,吉林长春130102

出　　处：《土壤与作物》2021年第3期282-293,共12页Soils and Crops

基　　金：中国科学院战略性先导科技专项课题(XDA28080500);中央财政林业科技推广示范资金项目(Y8D5021001);吉林省地方标准项目(DBXM120-2021).

摘　　要：农作物秸秆覆盖是当今保护性耕作技术运用最为重要的一种方式,在减少土壤侵蚀、提高农作物水分利用效率及土壤肥力方面具有十分重要的作用。本研究以Landsat-8 OLI影像为基础,基于偏最小二乘回归方法结合耕作指数和纹理特征,对研究区玉米秸秆覆盖度(Maize Residue Cover,MRC)进行估算研究。结果表明:(1)归一化差异耕作指数、简单耕作指数与MRC相关性优于其他耕作指数,其决定系数(R^(2))均为0.86,归一化差异指数7和归一化差异指数5与短波红色外归一化差异指数及MRC相关性在0.5~0.3之间,归一化差异衰老植被指数、改良耕作指数与MRC之间相关性不明显;(2)纹理特征与MRC相关性并不显著,Band5mean与MRC相关性优于其他纹理特征,其决定系数(R^(2))为0.384,其余纹理特征与MRC相关性在0.2~0.3之间;(3)使用耕作指数和纹理特征的组合方法(R^(2)=0.907,RMSE=6.21)进行MRC的估算精度要高于仅使用耕作指数(R^(2)=0.86,RMSE=5.77)和纹理特征(R^(2)=0.153,RMSE=10.36)的方法。组合方法可以很好地提高玉米秸秆覆盖度模型的估算精度,有利于进行部分地区MRC的估算工作。其中,组合方法中纹理特征指标的选择非常关键,不同的纹理特征指标的组合会对模型精度的提高与降低产生不同的影响。Crop residue cover is one of the most important components in conservation tillage,and plays a significant role in reducing soil erosion,improving crop water use efficiency and holding soil fertility.This study used partial least squares regression(PLSR)method,tillage indices and texture features to estimate maize residue cover(MRC)in the study area based on the Landsat-8 OLI image.The normalized difference tillage index(NDTI)and simple tillage index(STI)were significantly correlated with MRC.The regression between NDTI,STI and MRC was stronger than those tillage indices.The coefficient of determination(R^(2))was 0.86.There was no significant correlation between texture features and MRC in this study.The correlation between Band5mean and MRC(R^(2)=0.384)was better than other texture features.The accuracy of MRC estimation using combination method was higher(R^(2)=0.907,RMSE=6.21)than that using tillage indices(R^(2)=0.86,RMSE=5.77)and texture features(R^(2)=0.153,RMSE=10.36)respectively.The results indicated that the combination method would be used to invert MRC.

关 键 词：玉米秸秆覆盖 耕作指数 纹理特征 偏最小二乘法 

分 类 号：K903[历史地理—人文地理学]