Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach.

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 (Ψleaf), 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 Ψleaf. 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 Ψpd, stem water potential (Ψstem), thermal imaging, and meteorological data. The WSIs, namely Ψpd and gs, responded differently according to the irrigation treatment. Ψstem 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 Ψpd. Machine learning regression models were trained on meteorological, thermal, and gs data to predict Ψpd, with ensemble models showing a great performance (ExtraTrees: R2=0.833, MAE=0.072; Gradient Boosting: R2=0.830; MAE=0.073).

First Approach to the Aroma Characterization of Monovarietal Red Wines Produced from Varieties Better Adapted to Abiotic Stresses.

Adaptation strategies in the wine sector consist of the use of cultural techniques to limit damages caused by climate change, using, among other resources, varieties better adapted to the scenarios of abiotic stress exacerbation, namely water and thermal stress, as well as those more tolerant to heatwaves. With the intention to determine the aromatic characterization of ten monovarietal wines produced from cultivars with high productive performance in a global warming scenario ('Petit Verdot', 'Marselan', 'Merlot', 'Touriga Franca', 'Syrah', 'Vinhão', 'Bobal', 'Preto Martinho', 'Trincadeira', and 'Alicante Bouschet'), grown in Esporão vineyard (Alentejo, Portugal) and submitted to deficit irrigation (Ks ± 0.5), their aromatic character has been analyzed. Each grape variety was vinified at a small scale, in duplicate, and the wines were evaluated by a sensory panel, which rated several sensory attributes (visual, olfactory, and gustatory). Sensory analysis revealed a discrete appreciation for the monovarietal wines tasted, showing a differentiation at the olfactory level that was not too marked, although present, between the samples. The free volatile compounds were analysed using gas chromatography-olfactometry (GC-O), identified using a gas chromatography-mass spectrometry (GC-MS) technique and semi-quantified using the gas chromatography-flame ionization detector (GC-FID) technique. Based on the interpolation of the results of the various statistical analyses carried out, 49 probable odor active compounds (pOACs) were identified and based on the odor activity values (OAVs), 24 of them were recognized as odor active compounds (OACs) originated mainly during the fermentation processes. An aromatic characterization of the varieties has been proposed.