A machine learning framework for California vineyard water status monitoring using sUAS Imagery and short-term meteorological data
Irrigation Science · 2026-05 · 44 (3)
DOI: 10.1007/s00271-026-01102-8 ↗Kurz gefasst
Fachartikel in der Zeitschrift Irrigation Science, online erschienen am 14.03.2026. Verfasst von Rui Gao und 20 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NASA Water, USDA NACA, UWRL Student Grant.
Abstract (Originalsprache)
Efficient irrigation management is essential for sustainable crop production under increasing temperatures and tightening water supplies. In vineyards, water status significantly influences vine growth, yield, and fruit quality, and deficit irrigation is often used to impose controlled stress while avoiding damaging levels of water limitation. This creates a practical need for routine, field-scale monitoring of vine water status. In this study, we developed an operational machine-learning framework to estimate grapevine leaf water potential (Ψ leaf ) by integrating daytime sUAS thermal imagery with short-term local meteorological information. When all candidate predictors were included, the trained eXtreme Gradient Boosting (XGB) model achieved R 2 = 0.71, RMSE = 0.14 MPa , and bias = − 0.06 MPa on the independent test dataset. A simplified XGB model using a compact predictor set–maximum air temperature in the 24 h prior to flight, air temperature at flight time, their difference, and canopy temperature – achieved R 2 = 0.63, RMSE = 0.16 MPa , and bias = − 0.06 MPa , with performance not significantly different from the full model at α = 0.05. This reduced-feature formulation supports vineyard-scale Ψ leaf estimation and mapping while maintaining strong predictive skill and low computational burden. Our research highlights the potential for broader applicability, particularly for monitoring rapidly developing hot and dry conditions and supporting adaptive water resource management.
Förderung
- NASA Water
- USDA NACA
- UWRL Student Grant
Zitieren
APA
Gao, R., Alsina, M. M., Torres-Rua, A. F., Hipps, L., Kustas, W. P., Anderson, M., Nieto, H., McElrone, A. J., Knipper, K., Ortiz, N. B., Castro, S. J., Prueger, J. H., Alfieri, J., McKee, L. G., White, W. A., Gao, F., Coopmans, C., Gowing, I., Agam, N., …, & Dokoozlian, N. (2026). A machine learning framework for California vineyard water status monitoring using sUAS Imagery and short-term meteorological data. Irrigation Science, 44(3). https://doi.org/10.1007/s00271-026-01102-8
Vancouver
Gao R, Alsina MM, Torres-Rua AF, Hipps L, Kustas WP, Anderson M, et al. A machine learning framework for California vineyard water status monitoring using sUAS Imagery and short-term meteorological data. Irrigation Science. 2026;44(3). doi:10.1007/s00271-026-01102-8
BibTeX
@article{Gao2026,
author = {Gao, Rui and Alsina, Maria Mar and Torres-Rua, Alfonso F. and Hipps, Lawrence and Kustas, William P. and Anderson, Martha and Nieto, Héctor and McElrone, Andrew J. and Knipper, Kyle and Ortiz, Nicolas Bambach and Castro, Sebastian J. and Prueger, John H. and Alfieri, Joseph and McKee, Lynn G. and White, William A. and Gao, Feng and Coopmans, Calvin and Gowing, Ian and Agam, Nurit and Sanchez, Luis and Dokoozlian, Nick},
title = {A machine learning framework for California vineyard water status monitoring using sUAS Imagery and short-term meteorological data},
journal = {Irrigation Science},
year = {2026},
volume = {44},
number = {3},
doi = {10.1007/s00271-026-01102-8}
}
EUVIMED