Supporting of Crop Yield Prediction Using Machine Learning Algorithm Techniques

This chapter delves into the application of machine learning algorithms to predict crop yields in Indian agriculture, a sector crucial to the country's economy and food security. The study begins with data collection from various sources, including the Kaggle website, focusing on key crops like rice, cotton, and maize. The data preprocessing phase involves encoding categorical variables, standardizing features, and splitting the dataset into training and testing sets. The chapter evaluates several machine learning models, including Linear Regression, Support Vector Machine (SVM), Decision Tree, and Neural Networks, using metrics like R2 score, RMSE, and MAE. The results indicate that Linear Regression and SVM models achieve the highest accuracy, with R2 scores of approximately 85% and 89.8%, respectively. The study also explores the impact of soil and rainfall data on model performance, noting that including these factors can improve prediction accuracy. The chapter concludes by discussing the potential of machine learning to optimize crop yields and the need for further research to enhance the accuracy of predictive models in agriculture.