One of the problems of optical remote sensing of crop above-ground biomass (AGB) is that vegetation indices (VIs) often saturate from the middle to late growth stages. This study focuses on combining VIs acquired by a consumer-grade multiple-spectral UAV and machine learning regression techniques to (i) determine the optimal time window for AGB estimation of winter wheat and to (ii) determine the optimal combination of multi-spectral VIs and regression algorithms. UAV-based multi-spectral data and manually measured AGB of winter wheat, under five nitrogen rates, were obtained from the jointing stage until 25 days after flowering in the growing season 2020/2021. Forty-four multi-spectral VIs were used in the linear regression (LR), partial least squares regression (PLSR), and random forest (RF) models in this study. Results of LR models showed that the heading stage was the most suitable stage for AGB prediction, with R² values varying from 0.48 to 0.93. Three PLSR models based on different datasets performed differently in estimating AGB in the training dataset (R² = 0.74~0.92, RMSE = 0.95~2.87 t/ha, MAE = 0.75~2.18 t/ha, and RPD = 2.00~3.67) and validation dataset (R² = 0.50~0.75, RMSE = 1.56~2.57 t/ha, MAE = 1.44~2.05 t/ha, RPD = 1.45~1.89). Compared with PLSR models, the performance of the RF models was more stable in the prediction of AGB in the training dataset (R² = 0.95~0.97, RMSE = 0.58~1.08 t/ha, MAE = 0.46~0.89 t/ha, and RPD = 3.95~6.35) and validation dataset (R² = 0.83~0.93, RMSE = 0.93~2.34 t/ha, MAE = 0.72~2.01 t/ha, RPD = 1.36~3.79). Monitoring AGB prior to flowering was found to be more effective than post-flowering. Moreover, this study demonstrates that it is feasible to estimate AGB for multiple growth stages of winter wheat by combining the optimal VIs and PLSR and RF models, which overcomes the saturation problem of using individual VI-based linear regression models.

Deficit irrigation is a common approach in water-scarce regions to balance productivity and water use, whereas drought stress still occurs to various extents, leading to reduced physiological performance and a decrease in yield. Therefore, seeking a rapid and reliable method to identify wheat varieties with drought resistance can help reduce yield loss under water deficit. In this study, we compared ten wheat varieties under three deficit irrigation systems (W0, no irrigation during the growing season; W1, irrigation at jointing; W2, irrigation at jointing and anthesis). UAV thermal imagery, plant physiological traits [leaf area index (LAI), SPAD, photosynthesis (Pn), transpiration (Tr), stomatal conductance (Cn)], biomass and yield were acquired at different growth stages. Wheat drought resistance performance was evaluated through using the canopy temperature extracted from UAV thermal imagery (CT-UAV), in combination with hierarchical cluster analysis (HCA). The CT-UAV of W0 and W1 treatments was significantly higher than in the W2 treatment, with the ranges of 24.8–33.3 °C, 24.3–31.6 °C, and 24.1–28.9 °C in W0, W1 and W2, respectively. We found negative correlations between CT-UAV and LAI, SPAD, Pn, Tr, Cn and biomass under the W0 (R² = 0.41–0.79) and W1 treatments (R² = 0.22–0.72), but little relevance for W2 treatment. Under the deficit irrigation treatments (W0 and W1), UAV thermal imagery was less effective before the grain-filling stage in evaluating drought resistance. This study demonstrates the potential of ensuring yield and saving irrigation water by identifying suitable wheat varieties for different water-scarce irrigation scenarios.