The Application of Machine Learning Techniques for Corn Yield Prediction and Management: A Systematic Literature Review

Abstract

This systematic literature review examines the application of machine learning techniques for corn yield prediction and management. Fifty primary studies published between 2015 and 2024 were analyzed to synthesize the current state of research in this domain. The review focuses on the machine learning algorithms, input features and data sources leveraged, prediction accuracy achieved, and key challenges identified. The findings indicate that ensemble methods like Random Forest and XGBoost and deep learning approaches like Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks are the most commonly used and practical algorithms. The most critical input features are remote sensing data, weather variables, and soil properties. While machine learning models demonstrate strong predictive performance, challenges remain around data quality, interpretability, and generalizability across diverse growing conditions. This review provides a comprehensive overview to guide future research and practical machine-learning applications for corn yield forecasting.