Modeling Agricultural Yield Using AdaBoost Regression with Climatic and Pesticide Features

Abstract

Accurate crop yield prediction is essential for agricultural planning, food security, and sustainable farming practices. Traditional yield prediction methods often fail to capture the complex, non-linear relationships between environmental factors and agricultural management practices, such as pesticide use. Existing models frequently focus on climatic factors but overlook the impact of pesticide application on yield outcomes. Motivated by this limitation, this study proposes a crop yield prediction approach based on the AdaBoost regression algorithm, which integrates both climate variables and pesticide usage. The model is evaluated using standard regression metrics, including R-squared (R²), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE), and experimental results demonstrate that the AdaBoost model can produce accurate yield predictions by effectively capturing the interactions between climatic conditions and pesticide use. The contribution of this research lies in its ability to combine these factors within a single model, offering a more comprehensive and realistic approach to crop yield prediction. Future work could extend this framework by incorporating additional variables such as soil properties, irrigation practices, and crop variety information, as well as exploring advanced machine learning techniques to further enhance prediction accuracy. The proposed model represents a step forward in precision agriculture, supporting better decision-making and resource management for farmers and stakeholders.