UAV-based rice aboveground biomass estimation using a random forest model with multi-organ feature selection

Background: Aboveground biomass (AGB) is important for monitoring crop growth and field management. Accurate estimation of AGB helps refine field strategies and advance precision agriculture. Remote sensing with Unmanned Aerial Vehicles (UAVs) has become an effective method for estimating key parameters of rice. Methods: This study involved four experiments conducted across varied locations and timeframes to collect field sampling data and UAV imagery. Feature extraction, including Vegetation Index (VI), textures, and canopy height, was performed. Key factors influencing biomass estimation across different rice organs were analyzed. Based on these insights, a Random Forest model was developed for AGB estimation. Results: The VIS-Leaf factor-Spike factor-Stem factor (VIS-L-Sp-St) model proposed in this study outperformed traditional methods. The training set achieved an R2 of 0.89 with a reduced RMSE of 191.30 g/m2, surpassing the traditional VIS model (R2=0.64, RMSE=363.53 g/m2). Notably, in the validation set, the VIS-L-Sp-St model showed good transferability, with an R2 of 0.85 and RMSE of 196.55 g/m2, outperforming MLR (R2=0.02, RMSE=5944.09 g/m2), PLSR (R2=0.18, RMSE=934.27 g/m2) methods, BP (R2=0.14, RMSE=581.61 g/m2) method and SVM method((R2=0.45, RMSE=600.91 g/m2). Conclusions: Sensitivity analysis showed that different rice organs respond differently to specific features. This insight improves feature selection efficiency and enhances AGB estimation accuracy. The organ-specific AGB estimation model highlights its potential to support precision agriculture and field management, contributing to advancements in agricultural research and application.