Ratoon rice production has been an emerging cropping system to increase food quality and productivity worldwide. Efficient monitoring of ratoon rice aboveground biomass (AGB) over large areas is valuable for precision agriculture, as AGB is closely related to crop grain yield and quality. Unmanned aerial vehicle (UAV) remote sensing has opened an unprecedented opportunity to efficiently monitor crop AGB instead of labor-intensive ground measurements. Vegetation indices (VIs)-based approach for estimating AGB is easily affected by background materials and often suffers saturation problems at high AGB levels. Although the combined use of UAV-collected structural and spectral features can alleviate these problems to some extent, uncertainties on the AGB estimation still exist for crop with significant difference in canopy architecture and AGB composition throughout the growing season (e.g., ratoon rice). There is a hypothesis that the combination of spectral, textural and structural features can improve ratoon rice AGB estimations across different developmental stages. Therefore, the utility of UAV-based spectral, textural and structural features were quantified in estimating ratoon rice AGB at field level with contrasting agronomic treatments (i.e., nitrogen fertilizer and stubble height), in which multiple linear regression (MLR) and gaussian process regression (GPR) methods were applied and compared. Results showed that (1) each feature had its own respective limitation: specifically, spectral and textural features exhibited insufficient sensitivity to AGB variability of remaining stubbles or stem at early stage and suffered saturation problem at grain filling stage; structural features were difficult to detect the emergence of panicles from panicle initiation to heading stages; (2) the combination of three types of features can complement each other and achieved the highest accuracy using GPR method: the combination of spectral, structural and textural features achieved the best estimation accuracy for estimating ratoon rice AGB with an R2 of 0.94 and RMSE of 81.4 g m−2 across different developmental stages, which significantly improved the model performance compared to the combination of spectral and textural features (R2 = 0.56, RMSE = 170.2 g m−2) and the combination of spectral and structural features (R2 = 0.86, RMSE = 138.8 g m−2). In summary, this study provides a novel approach for efficiently estimating ratoon rice AGB at field level, which is critical for timely decision making (e.g., determine when and where to apply fertilizer or pesticide) in precision agriculture.

https://doi.org/10.1007/s11119-022-09884-5