The increasing global population has intensified the demand for food production, presenting significant challenges in agriculture. This study investigates the impact of historical meteorological variables on the prevalence of downy mildew in grapevines. By analyzing a comprehensive dataset including parameters such as temperature, relative humidity, rainfall metrics, sunlight exposure, wind velocity, and evaporation rates, we aim to develop predictive models to enhance grape quality. Our research focuses on: first, analyzing the relationship between key meteorological variables on downy mildew severity; second, identifying environmental factors that significantly contribute to disease development; and third, selecting the most suitable machine learning approach for predicting disease onset and severity. Through a systematic review of historical data, we assess data trends related to disease and evaluate the reliability of data sources. Our findings underscore the importance of these insights for effective disease management strategies, contributing to the sustainability of viticulture. This research enhances the understanding of environmental influences on grape diseases and offers practical applications for vineyard management.