Crop Yield Prediction Using Improved Random Forest

Abstract

Agriculture has an important role in India’s economic development. Crop productivity is affected by the rising population and the country’s ever-changing climate. Crop yield estimation is a challenge in the farming sector. Numerous studies have been conducted in the agricultural sector to better estimate crop yield through machine learning techniques. It is an efficient method for anticipating crop yields and determining which crops to cultivate. Random Forest has been widely utilized for this purpose. A set of parameters in the Random Forest classifier must be stay tuned. The machine learning algorithm will yield better results with correct hyper parameter adjustment. This work presents a hybrid approach to agricultural yield estimation using a Random Forest classifier and the Random Search method with a 0.99 R2 score, 0.045 MSE, and 0.022 MAE, the suggested method outperformed other existing approaches such as Decision Tree (DT), Multiple Linear Regression (MLR), Random Forest (RF), and Grid Search (GS) optimized RF. Validation methods such as R2, Mean Squared Error, and Mean Absolute Error to cross-validation have been used to confirm the authenticity of the outcomes. The purpose of this study is to apply the crop yield prediction approach into action to assist farmers in solving agricultural production concerns.