Crop yield prediction with environmental and chemical variables using optimized ensemble predictive model in machine learning

Abstract Enhanced crop yield prediction is necessary for agronomists to make dynamic premonsoon decisions. The input variables precipitation, temperature, evaporation, wind speed, and chemical use influence crop yield estimations. In this study, we analyzed the correlation between crop yield and input features, and scaled up the prediction power of the crop yield model using optimized ensemble learning for machine learning. The proposed model is expected to deal with the limitations of existing models by minimizing effort and data requirements. It achieved better performance than the other approaches with a MSE (Mean Squared Error) of 42963, MAE (Mean Absolute Error) of 87, and R 2 (Coefficient of Determination) of 0.96. The findings of this study have important suggestions for agricultural management and policy-making. The proposed model offers possible applications for enhancing crop yield prediction across various perspectives, thereby assisting more informed decision-making in agriculture.