A Comparative Analysis of Ensemble Learning Techniques for Crop Yield Prediction: CYPELA

India and other emerging nations should concentrate on creating cutting-edge agricultural technology due to the exponential rise of their populations. Crop Yield Prediction (CYP) is one of the vital tasks to develop the agricultural sector; because it represents one of the most difficult challenges in precision agriculture, which requires a complete understanding of the development of the pattern with highly nonlinear factors like environmental, soil fertilizer, and crop production. In this paper, the crop yield is being estimated by employing Ensemble Learning (EL) techniques with data obtained from International Crops Research Institute for the Semi-Arid Tropics (ICRISAT) of 33 districts of Assam over a period of 28 years. This paper tries to show the performance of Ensemble Learning (EL) techniques for Crop Yield Prediction (CYP) by the concept of Bagging, Boosting and Stacking Generalization (SG). In this paper, data preprocessing has been done before classification. Finally, it is observed that Bagging techniques perform the best for CYP out of Bagging, Boosting and SG. Out of all the techniques under Bagging, Extra Trees (ET) performs the best with an accuracy of85.79% and f-l score of 84.97% for CYP of 23 categories of crop.