Assessing plant water status accurately in both time and space is crucial for maintaining satisfactory crop yield and quality standards, especially in the face of a changing climate. Remote sensing technology offers a promising alternative to traditional in situ measurements for estimating stem water potential (Ψ_stem). In this study, we carried out field measurements of Ψ_stem in an irrigated olive orchard in southern Italy during the 2021 and 2022 seasons. Water status data were acquired at midday from 24 olive trees between June and October in both years. Reflectance data collected at the time of Ψ_stem measurements were utilized to calculate vegetation indices (VIs). Employing machine learning techniques, various prediction models were developed by considering VIs and spectral bands as predictors. Before the analyses, both datasets were randomly split into training and testing datasets. Our findings reveal that the random forest model outperformed other models, providing a more accurate prediction of olive water status (R² = 0.78). This is the first study in the literature integrating remote sensing and machine learning techniques for the prediction of olive water status in order to improve olive orchard irrigation management, offering a practical solution for estimating Ψ_stem avoiding time-consuming and resource-intensive fieldwork.

The main objective of this study was to acquire agronomic knowledge about the effects of irrigation with saline reclaimed (RW) and desalinated DESERT (DW) water and different irrigation strategies: control full irrigation (FI) and regulated deficit irrigation (RDI) on leaf nutrients, tree growth and fruit quality and yield of almond trees on pot. Our results showed that RW had the highest concentration on some valuable agronomic nutrients as N, but also on phytotoxic elements (Na and Cl⁻). Na leaf concentration on RW treatments reached toxic levels, especially under RDI, and toxicity symptoms were shown. Regarding tree growth, cumulate trunk diameter on RW-RDI was significantly lower than control treatment and shoot growth was reduced from the beginning of irrigation season in RW treatments. Maximum yield was reached on RW-FI, 18% higher than control treatment. However, RDI strategies influenced negatively on yield, being 23% less on RW and 7% less on DW although water productivity was not significantly reduced by water stress. These findings manifest that, the combination of RW and RDI, can be a promising future practice on almond irrigation, but long-term studies to establish suitable management practices must be developed.

The efficient management of irrigation water can affect crop profitability quite significantly. The application of precision irrigation based on soil monitoring can help manage water resources. In viticulture, the irrigation technique is thought to strongly influence grape ripening and the final grape composition. In this study, an irrigation decision support system was compared to a surface drip irrigation system in a commercial vineyard located in Andrea (Southern Italy) planted with Vitis vinifera cv. Montepulciano. We aimed to investigate the ability of the DSS to save water while maintaining an acceptable yield and quality of the grapes. To allow for the comparison, eco-physiological as well as yield parameters were measured during the irrigation periods in both irrigation systems over two years (2019 and 2020). The results indicate that the vines grown using the DSS treatment were less stressed compared to the plants grown using farm irrigation in both years. The yield attributes showed slight or no significant differences between the treatments. The quality results showed no significant differences between the treatments in both years. Our results indicate that with savings of 10% and 17% of the irrigation water in the first and second year, respectively, the DSS was able to maintain good yield and quality levels as compared to the farm irrigation system. These two-year results provide a promising implementation of its use in precision irrigation.