基于星载激光雷达ICESat-2/ATLAS数据的森林郁闭度估测研究
Estimation of Forest Canopy Closure Based on Spaceborne LiDAR ICESat-2/ATLAS Data
魏治越 1李浩 2舒清态 1席磊 1宋涵玥 1邱霜 1杨泽至1
作者信息
- 1. 西南林业大学林学院,云南昆明 650233
- 2. 西南林业大学党委统战部 云南昆明 650233
- 折叠
摘要
以云南香格里拉市为研究区,基于ICESat-2/ATLAS数据,采用随机森林回归、梯度提升树回归及最近邻回归的方法分别建立遥感森林郁闭度估测模型,选择最优模型反演研究区光斑内的森林郁闭度.结果表明:采用随机森林建模估测森林郁闭度时效果最好,其R2为0.9446,RMSE为0.0560,P为90.60％.研究得到香格里拉市内74873个有效林地光斑对应的郁闭度预测值,结合光斑中心坐标得到全市内所有光斑森林郁闭度的空间分布图.研究结果可为低纬度高海拔地区森林郁闭度遥感估测提供参考.
Abstract
Taking Shangri-La City,Yunnan Province as the research area,based on ICESat-2/ATLAS data,the remote sensing forest canopy density estimation models were established by random forest regression,gradi-ent boosting tree regression and nearest neighbor regression,respectively.The optimal model was selected to in-vert the forest canopy closure within the study area spots.The results showed that random forest modeling was the best method to estimate forest canopy closure,the coefficient of determination(R2)was 0.9446,mean square error(RMSE)was 0.0560 and the prediction accuracy(P)was 90.60％.The predicted values of canopy closure corres-ponding to 74 873 effective forest spots in Shangri-La City were obtained,and the spatial distribution map of can-opy closure of all forest spots in the city was obtained by combining the spot center coordinates.The results can provide a reference for remote sensing estimation of forest canopy closure at low-high altitude areas.
关键词
激光雷达/ICESat-2/郁闭度/随机森林Key words
LiDAR/ICESat-2/canopy closure/random forest引用本文复制引用
基金项目
云南省农业联合专项重点项目(202301BD070001-002)
国家自然科学基金(31860205)
国家自然科学基金(31460194)
云南省教育厅科研项目(2021Y249)
出版年
2024
国家科技期刊平台
NSTL
万方数据