Dominant woody plant species recognition with a hierarchical model based on multimodal geospatial data for subtropical forests

作     者：Xin Chen Yujun Sun Xin Chen;Yujun Sun

作者机构：State Forestry&Grassland Administration Key Laboratory of Forest Resources&Environmental ManagementBeijing Forestry UniversityBeijing 100083People's Republic of China 

出 版 物：《Journal of Forestry Research》 (林业研究（英文版）)

年 卷 期：2024年第35卷第3期

页      面：111-130页

核心收录：

学科分类：09[农学] 0903[农学-农业资源与环境] 

基　　金：supported by the National Technology Extension Fund of Forestry,Forest Vegetation Carbon Storage Monitoring Technology Based on Watershed Algorithm (06) Fundamental Research Funds for the Central Universities (No.PTYX202107) 

主　　题：Google Earth Engine Sentinel Forest resource inventory data Dominant woody plant species Subtropics Model performance 

摘      要：Since the launch of the Google Earth Engine(GEE)cloud platform in 2010,it has been widely used,leading to a wealth of valuable ***,the potential of GEE for forest resource management has not been fully *** extract dominant woody plant species,GEE combined Sen-tinel-1(S1)and Sentinel-2(S2)data with the addition of the National Forest Resources Inventory(NFRI)and topographic data,resulting in a 10 m resolution multimodal geospatial dataset for subtropical forests in southeast *** and texture features,red-edge bands,and vegetation indices of S1 and S2 data were computed.A hierarchical model obtained information on forest distribution and area and the dominant woody plant *** results suggest that combining data sources from the S1 winter and S2 yearly ranges enhances accuracy in forest distribution and area extraction compared to using either data source ***,for dominant woody species recognition,using S1 winter and S2 data across all four seasons was *** terrain factors and removing spatial correlation from NFRI sample points further improved the recognition *** optimal forest extraction achieved an overall accuracy(OA)of 97.4%and a maplevel image classification efficacy(MICE)of 96.7%.OA and MICE were 83.6%and 80.7%for dominant species extraction,*** high accuracy and efficacy values indicate that the hierarchical recognition model based on multimodal remote sensing data performed extremely well for extracting information about dominant woody plant *** the results using the GEE application allows for an intuitive display of forest and species distribution,offering significant convenience for forest resource monitoring.