Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach
Plants · 12.12.2023 · 12 (24) · 4142
DOI: 10.3390/plants12244142 ↗Kurz gefasst
Fachartikel in der Zeitschrift Plants, online erschienen am 12.12.2023. Verfasst von Miguel Damásio und 7 weiteren Autor:innen. Beteiligte Einrichtung: INIAV I.P., Instituto Nacional de Investigação Agrária e Veterinária, Polo de Inovação de Dois Portos, Quinta da Almoinha, 2565-191 Dois Portos, Port…. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 137 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Operacional Competitividade e Internacionalização, Operacional Regional de Lisboa 2020, Operacional Competitividade e Internacionalização program.
Abstract (Originalsprache)
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).
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- INIAV I.P., Instituto Nacional de Investigação Agrária e Veterinária, Polo de Inovação de Dois Portos, Quinta da Almoinha, 2565-191 Dois Portos, Portugal.
- GI-1716 Projects and Planification, Agroforestry Engineering Department, Escuela Politécnica Superior de Ingeniería Lugo, University of Santiago de Compostela, 27002 Lugo, Spain
- SISCOG SA, Sistemas Cognitivos, Campo Grande, 378 - 3°, 1700-097 Lisboa, Portugal.
- GREEN-IT Bioresources4sustainability, ITQB NOVA, Av. da República, 2780-157 Oeiras, Portugal.
ORCID-Profile: Miguel Barbosa, Filipe Fonseca, José Silvestre
Förderung
- Operacional Competitividade e Internacionalização
- Operacional Regional de Lisboa 2020
- Operacional Competitividade e Internacionalização program
- Operacional Regional de Lisboa 2020 program
Zitieren
APA
Damásio, M., Barbosa, M., Deus, J., Fernandes, E., Leitão, A., Albino, L., Fonseca, F., & Silvestre, J. (2023). Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach. Plants, 12(24), 4142. https://doi.org/10.3390/plants12244142
Vancouver
Damásio M, Barbosa M, Deus J, Fernandes E, Leitão A, Albino L, et al. Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach. Plants. 2023;12(24):4142. doi:10.3390/plants12244142
BibTeX
@article{Damsio2023,
author = {Damásio, Miguel and Barbosa, Miguel and Deus, João and Fernandes, Eduardo and Leitão, André and Albino, Luís and Fonseca, Filipe and Silvestre, José},
title = {Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach},
journal = {Plants},
year = {2023},
volume = {12},
number = {24},
pages = {4142},
doi = {10.3390/plants12244142}
}
EUVIMED