A comparative study of support vector machines and other machine learning algorithms for crop yield prediction

The growing population has raised concerns about food security due to limited agricultural resources. Technological advancements in agriculture have improved crop management. Accurately predicting crop yield is vital for ensuring food security and informing agricultural policy decisions. With the increasing availability of large datasets and advancements in machine learning (ML) algorithms, this paper explored the application of ML algorithms for crop yield prediction. This research revealed that a Support Vector Machine (SVM) model outperforms other ML algorithms like LASSO and RNN, achieving a high prediction accuracy of 90% and the lowest RMSE value of 0.15 with an MAE of 0.107. The robust SVM model can handle complex relationships between input features and crop yield. These findings have significant implications for developing accurate crop yield prediction systems, which can inform agricultural decision-making and contribute to sustainable practices.