Integrating Artificial Intelligence and Multi-Source Data for Precision Deficit Irrigation in Vineyards: The ViñAI Tool Case Methodology

Efficient water management is increasingly critical in vineyard operations, particularly in the context of climate change and the rising demand for sustainable agricultural practices. Regulated deficit irrigation has emerged as a promising technique that allows significant water savings while sustaining or improving the quality of grapes. However, its effective implementation requires timely and precise information on vine water status and environmental conditions (pluviometry, humidity, radiation, etc.). This study presents the methodology of a decision-support tool that tested the application of several artificial intelligence regression models. Among the algorithms evaluated, an Extreme Gradient Boosting (XGBoost) regression model showed the best performance and was adopted as the core predictive engine of the ViñAI tool to optimize deficit irrigation in vineyards. Based on the developed methodology, the ViñAI tool integrates open-access environmental data such as weather forecasts and satellite-based estimates of evapotranspiration. Furthermore, ViñAI is designed with the potential to integrate sensor-based field data. Overall, the results demonstrate that ViñAI offers a scalable, data-driven approach to support climate-smart irrigation decisions in vineyards, particularly in sensor-sparse or resource-limited contexts, and provides a robust basis for further multi-season and multi-region validation.