基于无人机多维数据集的森林地上生物量估测模型研究  

Development of Forest Aboveground Biomass Estimation Model Based on Multidimensional Dataset of UAV

作　　者：孙钊 谢运鸿 王宝莹 谭军 王轶夫[2] 孙玉军[2] SUN Zhao;XIE Yunhong;WANG Baoying;TAN Jun;WANG Yifu;SUN Yujun(Civil-Military Integration Center of China Geological Survey,Chengdu 610036,China;State Forestry and Grassland Administration Key Laboratory of Forest Resources and Environmental Management,BeijingForestryUniversity,Beijing100083,China)

机构地区：[1]中国地质调查局军民融合地质调查中心,成都610036 [2]北京林业大学森林资源和环境管理国家林业和草原局重点开放性实验室,北京100083

出　　处：《农业机械学报》2024年第6期186-195,236,共11页Transactions of the Chinese Society for Agricultural Machinery

基　　金：中国地质调查局地质调查项目(DD20243093);林业科学技术推广项目([2019]06)。

摘　　要：森林地上生物量(Aboveground biomass,AGB)是评价森林生长情况的重要指标。基于数字航空摄影(Digital aerial photography,DAP)生成的二维和三维数据,分别计算了41个点云高度变量和16个可见光植被指数,利用6种回归算法(随机森林(RF)、袋装树(BT)、支持向量回归(SVR)、Cubist、类别型特征提升(CatBoost)、极端梯度提升(XGBoost))分别构建了单一变量集和综合变量集AGB估测模型,探索了不同变量对于AGB估测模型的贡献。研究结果表明光谱数据集和点云数据集AGB预测模型精度最高分别为Cubist和XGBoost,R^(2)分别为0.5309和0.6395。组合数据集最高精度模型为XGBoost,R^(2)达到0.7601,XGBoost模型具有更高的AGB估测稳定性。研究还表明6种机器学习模型的贡献主要取决于所考虑的回归方法,所选择的特征个数和特征对模型的重要性在不同的模型中并不一致。DOM光谱特征在AGB的估测中具有更高的重要性。总体来说,二维和三维数据的结合能够有效提高森林AGB估测精度,基于无人机倾斜摄影获取的RGB影像能够实现森林AGB的快速无损估计。Forest aboveground biomass(AGB)is an important indicator for evaluating forest growth.Based on the 2D and 3D data generated by digital aerial photography(DAP),totally 41 point clouds height variables and 16 visible light vegetation indices were calculated respectively,and AGB estimation models were developed with single variable set and comprehensive variable set respectively by using six regression algorithms(random forest,RF;bagged tree,BT;support vector regression,SVR;Cubist;categorical boosting,CatBoost;extreme gradient boosting,XGBoost)to explore the contribution of different variables to the AGB estimation model.The results showed that the highest accuracy AGB prediction models for spectral and point cloud datasets were Cubist and XGBoost,with R^(2) of 0.5309 and 0.6395,respectively,and the highest accuracy model for the combined dataset was XGBoost,with R^(2) of 0.7601,and the XGBoost model had a higher stability of AGB estimation.The result also showed that the contribution of the six machine learning models mainly depended on the regression method considered,and the number of features chosen and the importance of the features to the model were not consistent across the models.DOM spectral features had a higher importance in the estimation of AGB.Overall,the combination of 2D and 3D data can effectively improve the accuracy of forest AGB estimation,and the RGB images acquired based on UAV tilt photography can realize the fast and nondestructive estimation of forest AGB.

关 键 词：森林地上生物量 估测模型 无人机密集点云 SFM 可见光植被指数 机器学习 

分 类 号：S771.8[农业科学—森林工程]