Using Machine Learning to Identify Outliers in Indian Agriculture Data for Crop Yield Prediction

A substantial proportion of the Nation's rise in gross domestic product is credited to the livestock industry. Crop yields and food grain stability are affected by the country's growing population and the everchanging weather. Yield, rainfall, pesticides, fertilizers, production rate, local government guidelines, and many other factors contribute to crop selection. Improving India's economy will call for significant changes in the agriculture sector. This study estimates crop yields in Indian states for various crop varieties employing numerous kinds of algorithms based on machine learning. Out of all the algorithms that were used, the results show that some of its most efficient approaches were Random Forest, Gradient Descent, Support Vector Machine (SVM), and lengthy short-term memory training (LSTM). The results were examined using Crossvalidation techniques like R2-score, Root-Mean-Squared Error (RMSE), Mean-Squared Error (MSE), Mean Absolute Error (MAE), and outlier identification. The intention of this research is to employ crop selection approaches that help farmers to eliminate concerns about crop yield.