Predicting Yield of the Crop Using Ensemble Learning Naive Bayes with Adaboost

Abstract

Data Mining is a developing research area in the crop yield analysis. Crop prediction is the main issue in agriculture, i.e., predicting crop yields before harvest. This work presents an adaptive, accurate, and economical strategy to predict crop yields utilizing publicly accessible agricultural information. The Ensemble Learning Algorithm in this work utilizes Naïve Bayes with Adaboost to automatically determine the agricultural data even when labeled training data are scarce. It focuses on the creation of a predictive model that may be used for future prediction of crop yield and also considers the crop diseases caused by the irregularity of rainfall and temperature. The proposed methodology is implemented in the python platform and the performance results depict the effectiveness of the proposed forecasting framework.