Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach
Miguel Damásio, Miguel Barbosa, João Deus, Eduardo Fernandes, André Leitão, Luís Albino, Filipe Fonseca, José Silvestre · 2026
Read Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach by Miguel Damásio, Miguel Barbosa, João Deus, Eduardo Fernandes, André Leitão, Luís Albino, Filipe Fonseca, José Silvestre (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10747955.txt.
Description
Miguel Damásio and colleagues ask if machine learning can predict grapevine leaf water potential from easier measures. The aim is precision irrigation in Portugal's Alentejo region. Leaf water potential is one of the most reliable signs of vine water status. But it is intrusive to measure and takes a lot of time. Heatwaves and drought now grow across Mediterranean wine lands as the climate shifts.
The team tracked five grapevine varieties. Each got one of three irrigation plans: full, deficit, or none. They took measures of stomatal conductance, water potentials, thermal images, and weather. Mid-morning measures matched each other best. Stomatal conductance matched the other signs most strongly. So it had the best power to predict predawn leaf water potential. The team trained machine learning models on the weather, thermal, and plant measures. The aim is to set irrigation from measures that machines can take on their own.
Catalog record
| CREATOR | Miguel Damásio, Miguel Barbosa, João Deus, Eduardo Fernandes, André Leitão, Luís Albino, Filipe Fonseca, José Silvestre |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 56 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |