A hybrid SERWI ensemble model for crop yield prediction using an inverse RMSE weighting strategy

Abstract

Abstract Accurate crop yield prediction is critical for informed agricultural planning, food distribution, and policy formulation. Traditional statistical models often fail to capture the nonlinear and temporal dynamics inherent in crop yield data. This Study introduces a novel hybrid Separate Evaluation of Regression models with Weighted Integration (SERWI) ensemble model, a novel hybrid ensemble model that integrates three machine learning algorithms: Long Short-Term Memory (LSTM) networks, Support Vector Regression (SVR), and Extreme Gradient Boosting (XGBoost). These base learners combine using a dynamic inverse RMSE-based weighting strategy that adaptively assigns higher weights to models exhibiting superior validation performance. The model is trained and evaluated using a comprehensive multi-decadal dataset sourced from the Season and Crop Report 2023–24 published by the Government of Tamil Nadu, which includes historical data on cultivated area, production, and yield of principal food grains, specifically focusing on foodgrains crop. Additionally, a detailed comparative analysis is performed against several individual models and ensemble combinations, including LSTM, SVR, XGBoost, Random Forest Regressor (RFR), Gaussian Process, and hybrid pairs such as LSTM plus SVR, SVR plus XGBoost, and LSTM plus RFR. SERWI outperformed the evaluated baseline models, achieving an RMSE of 70.16, MSE of 4923.07, MAE of 47.93, and R² of 0.9918 on the test set. These results indicate strong predictive performance and potential scalability for practical agricultural yield forecasting.