Efficient Tree Species Classification Using Machine and Deep Learning Algorithms based on UAV-LiDAR Data in North China

Hanyu Zhang Bingjie Liu Bin Yang Jiachang Guo Zhenhua Hu ^* Mengtao Zhang Zhaohui Yang Jianshuang Zhang

• College of Forestry, Shanxi Agricultural University, Taigu, China

The unmanned aerial vehicle -based light detection and ranging (UAV-LiDAR) can quickly acquire the three-dimensional information of large areas of vegetation, and has been widely used in tree species classification. UAV-LiDAR point clouds of Populus alba, Populus simonii, Pinus sylvestris, and Pinus tabuliformis from 12 sample plots, 2622 tree in total, were obtained in North China, training and testing sets were constructed through data pre-processing, individual tree segmentation, feature extraction, Non-uniform Grid and Farther Point Sampling (NGFPS), and then four tree species were classified efficiently by two machine learning algorithms and two deep learning algorithms. Results showed that PointMLP achieved the best accuracy for identification of the tree species (overall accuracy = 96.94%), followed by RF (overall accuracy = 95.62%), SVM (overall accuracy = 94.89%) and PointNet++(overall accuracy = 85.65%). In addition, the most suitable number of point cloud sampling of single tree is between 1024 and 2048 when using the NGFPS method in the two deep learning models. Furthermore, feature value of elev_percentile_99th has an important influence on tree species classification and tree species with similar crown structures may lead to a higher misidentification rate. The study underscores the efficiency of PointMLP as a robust and streamlined solution, which offers a novel technological support for tree species classification in forestry resource management.