Detection of Tree Species in Beijing Plain Afforestation Project Using Satellite Sensors and Machine Learning Algorithms

Abstract

Mapping tree species distributions in urban areas is significant for managing afforestation plans and pest infestations but can be challenging over large areas. This research compared the classification accuracy of three data sources and three machine learning algorithm combinations. It evaluated the cost benefit of various combinations by mapping the species distribution of the Beijing Plain Afforestation Project with a three-level hierarchical approach. First, vegetation and non-vegetation were mapped. Then, tree crowns were extracted from the vegetation mask. Finally, Decision Tree (DT), Support Vector Machines (SVM), and Random Forest (RF) were applied to the three data sources: Pléiades-1B, WorldView-2, and Sentinel-2. The tree species classification was based on the original bands and spectral and texture indices. Sentinel-2 performed well at the stand level, with an overall accuracy of 89.29%. WorldView-2 was significantly better than Pléiades-1 at the single-tree identification level. The combination of WorldView-2 and SVM achieved the best classification result, with an overall accuracy of 90.91%. This research concludes that the low-resolution Sentinel-2 sensor can accurately map tree areas while performing satisfactorily in classifying pure forests. For mixed forests, on the other hand, WorldView-2 and Pléiades-1, which have higher resolutions, are needed for single-tree scale classification. Compared to Pléiades-1, WorldView-2 produced higher classification accuracy. In addition, this study combines algorithm comparison to provide further reference and guidance for plantation forest classification.