Current Trends and Perspectives on Predictive Models for Mildew Diseases in Vineyards

Area of Science:

• Agricultural science
• Plant pathology
• Data science

Background:

• Sustainable farming necessitates reduced chemical use for crop protection.
• Powdery mildew (PM) and downy mildew (DM) cause significant economic losses in viticulture.
• Accurate disease prediction is vital for timely intervention and minimizing environmental impact.

Purpose of the Study:

• To review and appraise predictive tools for PM and DM in vineyards.
• To analyze various modeling approaches, including traditional and AI-based methods.
• To identify challenges and future perspectives for disease prediction in viticulture.

Main Methods:

• Review of existing literature on predictive models for vineyard diseases.
• Analysis of mechanistic, statistical, machine learning, and deep learning approaches.
• Evaluation of the potential and constraints of different methodologies.

Main Results:

• Continuous development of strategies for disease monitoring and prediction.
• Identification of diverse methodological approaches for PM and DM prediction.
• Highlighting the need to fully leverage scientific and technological advances.

Conclusions:

• Integrated and robust predictive systems are needed for effective vineyard disease management.
• Harnessing advances in data science, sensing, and omics is key.
• Addressing challenges in predictive modeling will enhance sustainable viticulture practices.