Maize Crop Yield Prediction Using Machine Learning Regression Approach

Given maize’s significant role as a staple crop, it becomes imperative to carry out precise crop yield prediction to ensure food security. This research employs machine learning algorithms to analyze historical data related to maize crop yields, with the aim of developing a predictive model. The outcome of this study can serve as a valuable tool for pre-harvest planning and measuring crop production per unit of land area. The dataset utilized in this research spans from 2010 to 2021 and was sourced from Ethiopia’s Central Statistical Agency. Three machine learning regression algorithms—Logistic Regression, XGBoost, and Random Forest—were employed to design the predictive model. After data preparation and preprocessing, a total of 436,358 records were used for model development. The models were further trained with reduced features using principal component analysis (PCA). The experimental results demonstrate that the Random Forest algorithm, trained with a reduced number of features through PCA, yielded superior performance, with a lower error rate and a high R2 score of 0.98.