文献类型：期刊文献

英文题名：Mapping multiple tree species classes using a hierarchical procedure with optimized node variables and thresholds based on high spatial resolution satellite data

作者：Chen, Yaoliang[1,2] Zhao, Shuai[1,2] Xie, Zhuli[3,4] Lu, Dengsheng[1,2] Chen, Erxue[5]

第一作者：Chen, Yaoliang

通信作者：Lu, DS[1];Lu, DS[2]

机构：[1]Fujian Normal Univ, State Key Lab Subtrop Mt Ecol, Minist Sci & Technol & Fujian Prov, Fuzhou, Peoples R China;[2]Fujian Normal Univ, Sch Geog Sci, Fuzhou, Peoples R China;[3]Zhejiang A&F Univ, State Key Lab Subtrop Silviculture, Hangzhou, Peoples R China;[4]Zhejiang A&F Univ, Sch Environm & Resource Sci, Hangzhou, Peoples R China;[5]Chinese Acad Forestry, Inst Forest Resources Informat Tech, Beijing, Peoples R China

年份：2020

卷号：57

期号：4

起止页码：526-542

外文期刊名：GISCIENCE & REMOTE SENSING

收录：;Scopus(收录号：2-s2.0-85082446709);WOS:【SCI-EXPANDED(收录号:WOS:000530949100007)】；

基金：This study was supported by the National Key R&D Program of China project ?Research of Key Technologies for Monitoring Forest Plantation Resources? under grant 2017YFD0600900 and the National Natural Science Foundation of China under grant 41901124. The authors would like to thank the anonymous reviewers for their valuable comments as well as Longwei Li, Xiandie Jiang, Xiaozhi Yu, Wei Lu, Yukun Gao, and Zhenlong Cheng for their support during the field survey and in sample data processing.

语种：英文

外文关键词：Tree species classification; hierarchical classification procedure; variable optimization; threshold optimization; high spatial resolution

摘要：Tree species distribution mapping using remotely sensed data has long been an important research area. However, previous studies have rarely established a comprehensive and efficient classification procedure to obtain an accurate result. This study proposes a hierarchical classification procedure with optimized node variables and thresholds to classify tree species based on high spatial resolution satellite imagery. A classification tree structure consisting of parent and leaf nodes was designed based on user experience and visual interpretation. Spectral, textural, and topographic variables were extracted based on pre-segmented images. The random forest algorithm was used to select variables by ranking the impact of all variables. An iterating approach was used to optimize variables and thresholds in each loop by comprehensively considering the test accuracy and selected variables. The threshold range for each selected variable was determined by a statistical method considering the mean and standard deviation for two subnode types at each parent node. Classification of tree species was implemented using the optimized variables and thresholds. The results show that (1) the proposed procedure can accurately map the tree species distribution, with an overall accuracy of over 86% for both training and test stages; (2) critical variables for each class can be identified using this proposed procedure, and optimal variables of most tree plantation nodes are spectra related; (3) the overall forest classification accuracy using the proposed method is more accurate than that using the random forest (RF) and classification and regression tree (CART). The proposed approach provides results with 3.21% and 7.56% higher overall land cover classification accuracy and 4.68% and 10.28% higher overall forest classification accuracy than RF and CART, respectively.