ABSTRACT Accurate identification of tree species is the foundation of forest resource surveys and an important research field in forestry remote sensing. The introduction of the PointNet++ deep learning network to point cloud processing provides a new approach for tree species identification. This network can directly compute and train unordered point clouds, greatly reducing the manual selection and extraction process of feature data. However, how to establish a high-quality single tree point cloud dataset is a key issue to be solved. In this study, a 2.5-ha temperate coniferous broad-leaved mixed forest located in Mao’er Mountain Experimental Forest Farm in Heilongjiang Province, China, was investigated. The unmanned aerial vehicle (UAV) RGB image and LiDAR synchronous observation system were used to obtain the true-colour point clouds of the forest. Combining upsampling and downsampling methods, a dataset containing coordinates, normal vectors, RGB, and intensity information was constructed from the original point cloud. Comparative experiments were designed based on resampling algorithms, number of sampling points, feature information, and time cost to find the optimal feature information and processing methods for tree species classification. The results showed that the accuracy of tree species classification by using PointNet++ was greatly improved after adding RGB and point cloud intensity information. The classification accuracy was about 5% higher than that using only coordinate data sets. In addition, the combination of PU-Net downsampling network based on point cloud completion and geometric upsampling method achieved the highest classification accuracy (OA = 0.944) when the number of single trees point cloud was 3072. The algorithm also took a relatively shorter running time. This study demonstrated that the introduction of multi-feature information and the optimization of resampling method can provide new solutions for tree species classification based on the PointNet++ deep learning network.