China is one the largest maize (Zea mays L.) producer worldwide. Considering water deficit as one of the most important limiting factors for crop yield stability, remote sensing technology has been successfully used to monitor water relations in the soil–plant–atmosphere system through canopy and leaf reflectance, contributing to the better management of water under precision agriculture practices and the quantification of dynamic traits. This research was aimed to evaluate the relation between maize leaf water content (LWC) and ground-based and unoccupied aerial vehicle (UAV)-based hyperspectral data using the following approaches: (I) single wavelengths, (II) broadband reflectance and vegetation indices, (III) optimum hyperspectral vegetation indices (HVIs), and (IV) partial least squares regression (PLSR). A field experiment was undertaken at the Chinese Academy of Agricultural Sciences, Beijing, China, during the 2020 cropping season following a split plot model in a randomized complete block design with three blocks. Three maize varieties were subjected to three differential irrigation schedules. Leaf-based reflectance (400–2500 nm) was measured with a FieldSpec 4 spectroradiometer, and canopy-based reflectance (400–1000 nm) was collected with a Pika-L hyperspectral camera mounted on a UAV at three assessment days. Both sensors demonstrated similar shapes in the spectral response from the leaves and canopy, with differences in reflectance intensity across near-infrared wavelengths. Ground-based hyperspectral data outperformed UAV-based data for LWC monitoring, especially when using the full spectra (Vis–NIR–SWIR). The HVI and the PLSR models were demonstrated to be more suitable for LWC monitoring, with a higher HVI accuracy. The optimal band combinations for HVI were centered between 628 and 824 nm (R² from 0.28 to 0.49) using the UAV-based sensor and were consistently located around 1431–1464 nm and 2115–2331 nm (R² from 0.59 to 0.80) using the ground-based sensor on the three assessment days. The obtained results indicate the potential for the complementary use of ground-based and UAV-based hyperspectral data for maize LWC monitoring.

Winter wheat is a major food source for the inhabitants of North China. However, its yield is affected by drought stress during the growing period. Hence, it is necessary to develop drought-resistant winter wheat varieties. For breeding researchers, yield measurement, a crucial breeding indication, is costly, labor-intensive, and time-consuming. Therefore, in order to breed a drought-resistant variety of winter wheat in a short time, field plot scale crop yield estimation is essential. Unmanned aerial vehicles (UAVs) have developed into a reliable method for gathering crop canopy information in a non-destructive and time-efficient manner in recent years. This study aimed to evaluate strategies for estimating crop yield using multispectral (MS) and hyperspectral (HS) imagery derived from a UAV in single and multiple growth stages of winter wheat. To accomplish our objective, we constructed a simple linear regression model based on the single growth stages of booting, heading, flowering, filling, and maturation and a multiple regression model that combined these five growth stages to estimate winter wheat yield using 36 vegetation indices (VIs) calculated from UAV-based MS and HS imagery, respectively. After comparing these regression models, we came to the following conclusions: (1) the flowering stage of winter wheat showed the highest correlation with crop yield for both MS and HS imagery; (2) the VIs derived from the HS imagery performed better in terms of estimation accuracy than the VIs from the MS imagery; (3) the regression model that combined the information of five growth stages presented better accuracy than the one that considered the growth stages individually. The best estimation regression model for winter wheat yield in this study was the multiple linear regression model constructed by the VI of ‘$\left({\mathrm{b}}_1-{\mathrm{b}}_2\right)/\left({\mathrm{b}}_3-{\mathrm{b}}_4\right)$’ derived from HS imagery, incorporating the five growth stages of booting, heading, flowering, filling, and maturation with r of 0.84 and RMSE of 0.69 t/ha. The corresponding central wavelengths were 782 nm, 874 nm, 762 nm, and 890 nm, respectively. Our study indicates that the multiple temporal VIs derived from UAV-based HS imagery are effective tools for breeding researchers to estimate winter wheat yield on a field plot scale.

Low-cost UAV RGB imagery combined with deep learning models has demonstrated the potential for the development of a feasible tool for field-scale yield prediction. However, collecting sufficient labeled training samples at the field scale remains a considerable challenge, significantly limiting the practical use. In this study, a split-merge framework was proposed to address the issue of limited training samples at the field scale. Based on the split-merge framework, a yield prediction method for winter wheat using the state-of-the-art Efficientnetv2_s (Efficientnetv2_s_spw) and UAV RGB imagery was presented. In order to demonstrate the effectiveness of the split-merge framework, in this study, Efficientnetv2_s_pw was built by directly feeding the plot images to Efficientnetv2_s. The results indicated that the proposed split-merge framework effectively enlarged the training samples, thus enabling improved yield prediction performance. Efficientnetv2_s_spw performed best at the grain-filling stage, with a coefficient of determination of 0.6341 and a mean absolute percentage error of 7.43%. The proposed split-merge framework improved the model ability to extract indicative image features, partially mitigating the saturation issues. Efficientnetv2_s_spw demonstrated excellent adaptability across the water treatments and was recommended at the grain-filling stage. Increasing the ground resolution of input images may further improve the estimation performance. Alternatively, improved performance may be achieved by incorporating additional data sources, such as the canopy height model (CHM). This study indicates that Efficientnetv2_s_spw is a promising tool for field-scale yield prediction of winter wheat, providing a practical solution to field-specific crop management.