Crop Yield Prediction Using Various Feature Selection Techniques and Classifier

Abstract

Agriculture is more reliant on soil and climatic elements like temperature, humidity, and rainfall to forecast harvests. Farmers used to have complete control over the crop they planted, the crop's development, and the date of harvest. However, due to the rapid changes in the environment, the agricultural community now finds it difficult to continue. This necessitates the need to incorporate advanced technologies in agriculture to perform automated crop monitoring and prediction. As a result, Machine Learning methodologies are now used to predict the crop growth. This study has used the machine learning algorithms to estimate agricultural productivity. To guarantee that optimal feature selection method is implemented in the proposed model. The findings show that compared to the current classification approach, an ensemble technique delivers higher prediction accuracy.