Estimation of individual tree biomass for three tree species using LiDAR and multispectral data in megacity Shanghai

Urban forest parks are vital ecological barriers that safeguard urban ecological security and provide essential ecosystem services. Aboveground biomass (AGB) is a key indicator for evaluating these services. This study targeted three tree species— Ligustrum lucidum , Camphora officinarum and Koelreuteria paniculata —in Haiwan National Forest Park of Shanghai, China. Based on field-measured individual tree AGB, high-density point clouds from terrestrial laser scanning (TLS), and features from UAV multispectral imagery, four machine learning models—Random Forest (RF), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Support Vector Regression (SVR)—were developed. SHapley Additive exPlanations (SHAP) analysis was conducted to identify key predictors and quantify their importance. The results show that: (1) Data fusion of TLS and multispectral imagery significantly, improves estimation accuracy compared with single data sources, with RF consistently achieving the best performance across species (test set R 2 = 0.96, 0.92, and 0.91 for L. lucidum , C. officinarum , and K. paniculata , respectively). (2) The effectiveness of data fusion varies by species: for C. officinarum and K. paniculata , fusion models outperformed TLS-only models by 2% and 5% in R 2 , respectively; for L. lucidum , fusion accuracy ( R 2 = 0.92) was comparable to TLS alone, both outperforming multispectral-only models. (3) SHAP analysis indicates that structural features from TLS—particularly the interaction between tree height and volume—dominate AGB estimation, contributing over 70% of the total feature importance, while spectral and vegetation index features (e.g., RE, NDVI, OSAVI) contribute about 20%. These findings demonstrate that integrating multi-source remote sensing data enables efficient and precise individual tree AGB estimation tailored to different species, providing a technical basis for intelligent monitoring of urban forests in megacity Shanghai.