我国高分遥感近十年林业应用研究进展  

Ten Years of Gaofen-Series Satellite Imagery in Forestry:Applications and Trends

作　　者：王本洋 周双云 徐誉远 莫罗坚 WANG Benyang;ZHOU Shuangyun;XU Yuyuan;MO Luojian(College of Forestry&Landscape Architecture,South China Agricultural University,Guangzhou 510642,China;Forest Management Research Institute,South China Agricultural University,Guangzhou 510642,China;Guangdong Lingnanyuan Exploration and Design Co.Ltd.,Guangzhou 510663,China;Dongguan Forest Research Institute of Guangdong Province,Dongguan 523016,China)

机构地区：[1]华南农业大学林学与风景园林学院,广东广州510642 [2]华南农业大学森林经理研究室,广东广州510642 [3]广东省岭南院勘察设计有限公司,广东广州510663 [4]广东省东莞市林业科学研究所,广东东莞523106

出　　处：《湖南生态科学学报》2023年第4期110-119,共10页Journal of Hunan Ecological Science

基　　金：广东省重点领域研发计划项目(2020B020214001);东莞市社会发展科技项目(20231800936142)。

摘　　要：2013年以来,随着我国高分遥感不断发展,高分影像在森林参数提取、森林资源调查和森林灾害监测等林业细分领域得到了广泛应用。本文总结了高分遥感在上述领域的研究进展,梳理了高分影像相关的定量分析方法,重点介绍了多元线性回归、随机森林、支持向量机、BP神经网络、像元二分类法、面向对象分类法等较为常用的6种定量分析方法及其应用特点。Since 2013,the Gaofen program has been continuously developing,and high-resolution images have been widely used in the field of forestry such as forest parameter extraction,forest resource investigation,and forest resource monitoring.The paper reviewed research progress in such fields as forest parameters,forest resource investigation and forest disaster monitoring,and summarized those quantitative methods employed in above mentioned fields based on Gaofen-series imagery alone or accom-panied by other satellite imagery and field survey data.It emphasized on application characteristics of 6 most popular quantitative methods,such as MLR(Multiple Linear Regression),RF(Random Forest),SVM(Support Vector Machine),BP-ANN(Back Propagation Artificial Neural Networks),DPM(Di-midiate Pixel Modeling)and OOC(Object-Oriented Classification).

关 键 词：高分遥感 树种识别 森林生物量 林分高度 

分 类 号：S771.8[农业科学—森林工程]