Our project focuses on predicting agricultural crop yields in India using machine learning techniques. With agriculture being a cornerstone of India's economy, accurate yield predictions can offer valuable insights for farmers, policymakers, and stakeholders to optimize crop planning, resource allocation, and risk management strategies.
The primary objective of this project is to leverage historical crop data and machine learning algorithms to forecast crop yields for future seasons.
We employ various machine learning algorithms for yield prediction, including:
- K-Nearest Neighbors (KNN)
- Extra Trees Regressor (ETR)
- Bagging Regressor (BR)
- AdaBoost Regressor (AR)
- XGBoost (XGB)
- Linear Regression (LR)
- Random Forest (RF)
- Gradient Boosting Regressor (GBR)
- Decision Tree Regressor (DTR)
- Convolutional Neural Network (CNN)
We assess the performance of our models using the following key metrics:
- R-squared (R2) score
- Root Mean Square Error (RMSE)
- Mean Squared Error (MSE)
- Mean Absolute Error (MAE)
- Relative Root Squared Error (RRSE)
- Relative Absolute Error (RAE)
We visualize the data using various plots such as:
- Heatmap
- Performance matrices
- Taylor diagrams
To utilize our model and predict crop yields, follow these steps:
- Data Preparation: Prepare your dataset containing historical crop data.
- Model Training: Train the machine learning models using the provided algorithms.
- Model Evaluation: Evaluate the trained models using the specified metrics.
- Prediction: Use the trained models to predict crop yields for future seasons.
- Ankit kumar
- Ayush Rathore
This project is licensed under the [License Name] License - see the LICENSE.md file for details.
We would like to acknowledge [Acknowledged Party] for their contribution to this project.
For inquiries, please contact [email protected]