Mlot et al. (2025) Integrating Artificial Intelligence and Multi-Source Data for Precision Deficit Irrigation in Vineyards: The ViñAI Tool Case Methodology

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Applied Sciences
• Year: 2025
• Date: 2025-12-17
• Authors: E. Gutierrez Mlot, Daniel Ruiz-Beamonte, M. Arroyo Cozar, J Aznar, Ignacio Latre, Eduardo García-Martínez, Alejandra María González Correal, David Zambrana-Vásquez
• DOI: 10.3390/app152413209

Research Groups

Not specified in the provided text.

Short Summary

This study develops and validates ViñAI, an AI-driven decision-support tool utilizing an Extreme Gradient Boosting (XGBoost) model, to optimize regulated deficit irrigation in vineyards by integrating open-access environmental data.

Objective

• To develop and evaluate a decision-support tool, ViñAI, utilizing artificial intelligence regression models to optimize regulated deficit irrigation in vineyards for efficient water management.

Study Configuration

• Spatial Scale: Vineyard scale (methodology for general application).
• Temporal Scale: Real-time decision support (methodology for general application).

Methodology and Data

• Models used: Artificial intelligence regression models, with Extreme Gradient Boosting (XGBoost) identified as the core predictive engine.
• Data sources: Open-access environmental data (e.g., weather forecasts, satellite-based estimates of evapotranspiration). Designed with potential for sensor-based field data integration.

Main Results

• An Extreme Gradient Boosting (XGBoost) regression model demonstrated the best performance among the artificial intelligence algorithms evaluated for predicting vine water status and environmental conditions.
• The developed ViñAI tool integrates open-access environmental data, such as weather forecasts and satellite-based evapotranspiration estimates, to provide optimized deficit irrigation recommendations.
• ViñAI offers a scalable, data-driven approach to support climate-smart irrigation decisions in vineyards, particularly beneficial in sensor-sparse or resource-limited contexts.

Contributions

• Presents a novel, data-driven decision-support tool (ViñAI) for optimizing regulated deficit irrigation in vineyards using AI.
• Offers a scalable and robust methodology for integrating open-access environmental data with AI for precision agricultural water management.
• Provides a practical solution for efficient water management in vineyards, especially valuable for regions with limited sensor infrastructure or resources.

Funding

Not specified in the provided text.

Citation

@article{Mlot2025Integrating,
  author = {Mlot, E. Gutierrez and Ruiz-Beamonte, Daniel and Cozar, M. Arroyo and Aznar, J and Latre, Ignacio and García-Martínez, Eduardo and Correal, Alejandra María González and Zambrana-Vásquez, David},
  title = {Integrating Artificial Intelligence and Multi-Source Data for Precision Deficit Irrigation in Vineyards: The ViñAI Tool Case Methodology},
  journal = {Applied Sciences},
  year = {2025},
  doi = {10.3390/app152413209},
  url = {https://doi.org/10.3390/app152413209}
}