Smart Agritech

17Optimizing Crop Yield Prediction Using Machine Learning Algorithms

Rejuwan Shamim* and Trapty Agarwal

Department of Computer Science and Engineering with Data Science, Maharishi University of Information Technology, Noida, India

Abstract

This chapter attempts to improve the accuracy and efficiency of applying machine learning algorithms for predicting crop yields. This research examines the efficacy of several machine learning methods for predicting crop yields. These methods include regression models, ensemble methods, deep learning models, and support vector machines. MAE, RMSE, R², precision, and recall are just a few of the rigorous metrics used to assess the models against a properly selected dataset of important agricultural parameters. The “crop yield prediction dataset” is used to collect and prepare data, and methods like feature engineering and selection are used to improve the models’ ability to predict. The results show that ensemble methods, deep learning models, and other advanced algorithms do better than standard methods. This gives us important information about the factors that affect crop yield. The chapter talks about the problems with crop yield prediction and where it could go in the future. It also stresses how important it is that the models be easy to explain and understand. The findings of this study aid farmer aid farmers, agricultural planners, and policymakers in making better judgments and more accurate predictions of crop yields, leading to ...