AI - Powered crop yield forecasting

Accurate crop yield forecasting plays a pivotal role in agriculture, helping optimize resource allocation, policy formulation, and planning. This project presents an AI-powered crop yield forecasting system utilizing machine learning algorithms such as Random Forest, XGBoost, , RNN (Recurrent Neural Networks), and ANN (Artificial Neural Networks). The ensemble model, Stacking Classifier Regressor, is employed to enhance prediction accuracy by combining the outputs of multiple base learners. To ensure transparency and improve the interpretability of the predictions, SHAP (SHapley Additive exPlanations) is integrated into the system. The backend is developed using Python with the Flask framework, and the frontend is designed with HTML, CSS, and JavaScript. The system is capable of predicting crop yields for various states based on features such as climate data, crop type, and historical yield information. The project aims to provide a user-friendly platform where users can input relevant data and receive accurate predictions, along with explanations of the model's decision-making process. The framework can be adapted to forecast yields for different crops and regions, making it highly versatile.

Keywords:

Crop yield, Machine learning, Random Forest, XGBoost, Stacking Classifier, RNN, ANN, SHAP, Flask, Data prediction, Feature importance.