This work presents quantitative detection of water stress and estimation of the water stress level: none, light, moderate, and severe on potato crops. We use hyperspectral imagery and state of the art machine learning algorithms: random decision forest, multilayer perceptron, convolutional neural networks, support vector machines, extreme gradient boost, and AdaBoost. The detection and estimation of water stress in potato crops is carried out on two different phenological stages of the plants: tubers differentiation and maximum tuberization. The machine learning algorithms are trained with a small subset of each hyperspectral image corresponding to the plant canopy. The results are improved using majority voting to classify all the canopy pixels in the hyperspectral images. The results indicate that both detection of water stress and estimation of the level of water stress can be obtained with good accuracy, improved further by majority voting. The importance of each band of the hyperspectral images in the classification of the images is assessed by random forest and extreme gradient boost, which are the machine learning algorithms that perform best overall on both phenological stages and detection and estimation of water stress in potato crops.

Water stress is among the most critical factors limiting plant performance. Proteomics serves as a powerful tool for assessing changes in protein expression and identifying mechanisms underlying drought stress tolerance in plants. This study aims to identify proteins associated with water stress severity in potato (Solanum tuberosum L.) and to characterize their differential expression as potential defense mechanisms against stress. Potato plants at the tuber differentiation stage were subjected to mild, moderate, and severe water stress by withholding irrigation. Gas exchange measurements and proteomic analyses were conducted at each stress level. For protein extraction and proteome profiling using two-dimensional polyacrylamide gel electrophoresis (2D-PAGE), leaf samples were collected from plants under different stress conditions and from well-watered controls. A total of 74 protein spots were detected, and proteins associated with water stress were selected based on correlation analysis between their relative abundance and leaf water potential. Seven proteins were identified via mass spectrometry. Increasing water stress severity was associated with a decline in gas exchange and an increase in water use efficiency. Notably, an increase in the relative abundance of Rubisco activase, Photosystem I subunit IV B reaction center, and the manganese-stabilizing protein of Photosystem II under water stress suggests a potential protective strategy for maintaining photosynthetic function. Conversely, three isoforms of cytochrome oxidase (COX) subunit I exhibited decreased expression, which may be linked to a heat dissipation mechanism aimed at mitigating reactive oxygen species (ROS) formation during water stress. The identification of these proteins provides a baseline to further understand water stress in potatoes.