Prediction on Crop Yield on Indian based Agriculture using Machine Learning

Crop yield prediction is an important component of modern agriculture that has a significant influence on resource management, policymaking, and food security. Based on data from several sources, including soil, climate, and crop characteristics, this model applies machine learning to develop a prediction algorithm that can analyze crop production in India. Data from government websites and educational resources about traditional agricultural practices was used to train and test the model. This proposed work provides extensive preprocessing, including normalization techniques like Min-Max scaling, filling in missing values, and extracting parameters from correlation and common data. This proposed work aims to use various regression models, such as linear regression, Decision Tree, Random Forest, and XGBoost regressor, based on performance standards like R² score, Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). XGBoost performs effectively by conducting assessments because it can handle non-linear connections and prevent overfitting using boosting techniques. The model provides policymakers, agronomists, and farmers with valuable data that allows them to identify crops and locations where findings will increase agricultural yields under different climate conditions.