Climate change is affecting global viticulture, increasing heatwaves and drought. Precision irrigation, supported by robust water status indicators (WSIs), is inevitable in most of the Mediterranean basin. One of the most reliable WSIs is the leaf water potential (${\Psi }_{leaf}$), which is determined via an intrusive and time-consuming method. The aim of this work is to discern the most effective variables that are correlated with plants’ water status and identify the variables that better predict ${\Psi }_{leaf}$. Five grapevine varieties grown in the Alentejo region (Portugal) were selected and subjected to three irrigation treatments, starting in 2018: full irrigation (FI), deficit irrigation (DI), and no irrigation (NI). Plant monitoring was performed in 2023. Measurements included stomatal conductance ($gs$), predawn water potential ${\Psi }_{pd}$, stem water potential (${\Psi }_{stem}$), thermal imaging, and meteorological data. The WSIs, namely ${\Psi }_{pd}$ and $gs$, responded differently according to the irrigation treatment. ${\Psi }_{stem}$ measured at mid-morning (MM) and mid-day (MD) proved unable to discern between treatments. MM measurements presented the best correlations between WSIs. $gs$ showed the best correlations between the other WSIs, and consequently the best predictive capability to estimate ${\Psi }_{pd}$. Machine learning regression models were trained on meteorological, thermal, and $gs$ data to predict ${\Psi }_{pd}$, with ensemble models showing a great performance (ExtraTrees: $R^2=0.833$, $MAE=0.072$; Gradient Boosting: $R^2=0.830$; $MAE=0.073$).

A major challenge for the viticulture and oenology sector is to understand the impact of climate change on grapevine agronomic performance and wine quality. Genetic variability offers a key tool for adaptation, as some grape varieties may better withstand changing conditions while maintaining wine quality. As part of the WineClimAdapt research project (PDR2020-101-031010), a study was conducted on the adaptability of 18 white grape varieties to hot and dry conditions in Portugal. These grape varieties from Herdade do Esporão (Alentejo, Portugal) were vinified in duplicate at the INIAV winery, the result being 36 wines. The wines underwent physicochemical and sensory analyses, including gas chromatography–mass spectrometry (GC-MS) and gas chromatography–flame ionization detection (GC-FID), to assess their composition and sensory profiles. Tasters evaluated the wines using a structured scale (0–10) and rated their overall quality (0–20). Results from analysis of variance (ANOVA) revealed significant differences in the physicochemical composition and sensory profiles of the wines. Notably, some white wines displayed high acidity, which is advantageous for hot regions. The study also highlighted clear varietal differentiation across physicochemical, volatile and sensory analyses. Among the tested varieties, “Cayetana Blanca” and “Fernão Pires” achieved the highest average quality ratings, indicating promising potential for future studies and adaptation to climate change.

The intensification of olive growing has raised environmental concerns, particularly regarding nutrient loss from excessive fertiliser use. In line with the European Union’s Farm to Fork strategy, which aims to halve the soil nutrient losses by 2030, this study evaluates the effectiveness of two sensor-based approaches—proximal sensing with a FLAME spectrometer and remote sensing via UAV-mounted multispectral imaging—compared with foliar chemical analyses as the reference standard, for diagnosing the nutritional status of olive trees. The research was conducted in Elvas, Portugal, between 2022 and 2023, across three olive cultivars (‘Azeiteira’, ‘Arbequina’, and ‘Koroneiki’) subjected to different fertilisation regimes. Machine learning (ML) models showed strong correlations between sensor data and nutrient levels: the multispectral sensor performed best for phosphorus (P) (determination coefficient [$R^2$] = 0.75) and potassium (K) ($R^2$ = 0.73), while the FLAME spectrometer was more accurate for nitrogen (N) ($R^2$ = 0.64). These findings underscore the potential of sensor-based technologies for non-destructive, real-time nutrient monitoring, with each sensor offering specific strengths depending on the target nutrient. This work contributes to more sustainable and data-driven fertilisation strategies in precision agriculture.