Weather-Driven Mango Field Forecasting: Integrating the Prophet Model, Normalized Difference Vegetation Index, and Mealybug Dynamics for Precision Agriculture

This study focuses on developing a reliable forecasting system for mango field delimitation using weather data, the NDVI (Normalized Difference Vegetation Index), and the role of the mango mealybug (Drosicha mangiferae) in production dynamics. Hourly weather data and NDVI values were analyzed to understand their collective impact on mango cultivation. Prophet, a forecasting model designed for time series data with seasonal trends, was utilized to predict weather patterns, while NDVI changes captured vegetation health influenced by climatic conditions. Mango mealybugs, a significant pest, negatively affect mango yield through sap extraction, leading to reduced fruit quality and premature fruit drop. Climatic factors like temperature, humidity, and rainfall play a crucial role in managing mealybug infestations. Lower temperatures of 21^o C with dry conditions favor their activity, while increased rainfall and humidity limit their spread by disrupting their lifecycle and behavior. Comparisons of Prophet with traditional statistical methods like ARIMA revealed its superior accuracy in forecasting mango production and area. Stepwise regression identified significant climatic variables that influence production. By integrating real-time weather patterns, pest impacts, and NDVI trends, this research highlights an advanced, climate-responsive forecasting model. This system offers mango growers actionable insights to optimize resources, implement timely pest control strategies, and mitigate climate-related risks effectively.