欢迎访问《应用生态学报》官方网站,今天是 分享到:

应用生态学报 ›› 2023, Vol. 34 ›› Issue (4): 1043-1050.doi: 10.13287/j.1001-9332.202304.026

• 研究论文 • 上一篇    下一篇

基于激光雷达与高光谱的荒漠绿洲农田防护林衰退程度评估

杨玉丽1, 肖辉杰1*, 辛智鸣2, 范光鹏3, 李俊然4, 贾肖肖1, 汪立韬1   

  1. 1北京林业大学水土保持学院, 北京 100083;
    2中国林业科学研究院沙漠林业实验中心, 内蒙古磴口 015200;
    3北京林业大学信息学院, 北京 100083;
    4香港大学地理系, 香港 999077
  • 收稿日期:2022-11-01 接受日期:2023-02-14 出版日期:2023-04-15 发布日期:2023-10-15
  • 通讯作者: *E-mail: soilandwater2006@hotmail.com
  • 作者简介:杨玉丽, 女, 1995年生, 硕士研究生。主要从事激光雷达和高光谱识别荒漠绿洲农田防护林衰退程度研究。E-mail: yangyuli@bjfu.edu.cn
  • 基金资助:
    国家重点研发计划项目(2019YFE0116500)和省级其他科研项目(2022YFHH0065)

Assessment on the declining degree of farmland shelter forest in a desert oasis based on LiDAR and hyperspectrum imagery

YANG Yuli1, XIAO Huijie1*, XIN Zhiming2, FAN Guangpeng3, LI Junran4, JIA Xiaoxiao1, WANG Litao1   

  1. 1School of Soil and Water Conservation, Beijing Forestry University, Beijing 100083, China;
    2Experimental Center of Desert Forestry, Chinese Academy of Forestry, Dengkou 015200, Inner Mongolia, China;
    3School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China;
    4Department of Geography, The University of Hong Kong, Hong Kong 999077, China
  • Received:2022-11-01 Accepted:2023-02-14 Online:2023-04-15 Published:2023-10-15

摘要: 为准确检测荒漠绿洲区农田防护林带衰退和健康状况,本研究以乌兰布和荒漠绿洲新疆杨林带和小美旱杨林带为对象,使用机载高光谱与地基式激光雷达分别采集整体林带的高光谱影像和点云数据,通过相关性分析、逐步回归分析筛选的光谱微分值、植被指数、林木结构参数为自变量,以实地调查的林木冠层枯枝指数为因变量,构建农田防护林衰退程度评估模型,并对模型进行精度检验。结果表明: 采用激光雷达方法对新疆杨和小美旱杨衰退程度的评估精度优于高光谱方法,激光雷达和高光谱相结合方法的评估精度最高。分别采用激光雷达方法、高光谱方法、两者结合方法,新疆杨最优模型均为轻量级梯度提升模型,总体分类准确度分别为0.75、0.68、0.80,Kappa系数分别为0.58、0.43、0.66;小美旱杨最优模型分别为随机森林模型、随机森林模型、多层感知机模型,总体分类准确度分别为0.76、0.62、0.81,Kappa系数分别为0.60、0.34、0.71。本研究方法可对人工林衰退状况进行精确的清查和监测。

关键词: 激光雷达, 高光谱, 随机森林模型, 衰退程度

Abstract: We examined the growth decline and health status of farmland protective forest belt (Populus alba var. pyramidalis and Populus simonii shelterbelts) in Ulanbuh Desert Oasis by using airborne hyperspectral and ground-based LiDAR to collect the hyperspectral images and point cloud data of the whole forest belt respectively. Through correlation analysis and stepwise regression analysis, we constructed the evaluation model of the decline degree of farmland protection forest with the spectral differential value, vegetation index, and forest structure parameters as independent variables and the tree canopy dead branch index of the field survey as dependent variables. We further tested the accuracy of the model. The results showed that the evaluation accuracy of the decline degree of P. alba var. pyramidalis and P. simonii by LiDAR method was better than that by hyperspectral method, and that the evaluation accuracy of the combined LiDAR and hyperspectral method was the highest. Using the LiDAR method, hyperspectral method, the combined method, the optimal model of P. alba var. pyramidalis was all light gradient boosting machine model, with the overall classification accuracy being 0.75, 0.68, 0.80, and Kappa coefficient being 0.58, 0.43, 0.66, respectively. The optimal model of P. simonii was random forest model, random forest model, and multilayer perceptron model, with the overall classification accuracy being 0.76, 0.62, 0.81, and Kappa coefficient being 0.60, 0.34, 0.71, respectively. This research method could accurately check and monitor the decline of plantations.

Key words: LiDAR, hyperspectrum, random forest model, degree of recession