Agro-AI is a collection of machine learning models designed to provide crop and fertilizer recommendations. By leveraging supervised learning algorithms and training data, Agro-AI delivers precise and actionable insights for agricultural decision-making.
-
Crop Recommendation Models
- Algorithms Used:
- Fuzzy C-Means (FCM)
- Principal Component Regression (PCR)
- Random Forest (RF)
- Support Vector Regression (SVR)
- Algorithms Used:
-
Fertilizer Recommendation Models
- Algorithms Used:
- Linear Regression
- Neural Networks
- Random Forest (RF)
- Support Vector Regression (SVR)
- Algorithms Used:
Agro-AI takes various environmental, soil, and crop-specific input data to recommend:
- The most suitable crop to grow in a given condition.
- The best fertilizer for optimizing yield and maintaining soil health.
- Soil properties (pH, nutrients, etc.)
- Climatic data (temperature, rainfall, etc.)
- Crop-specific attributes
- Crop Recommendation: Suggested crops with suitability scores.
- Fertilizer Recommendation: Recommended fertilizers tailored to the soil and crop requirements.
-
Clone the repository:
git clone https://github.com/ViratSrivastava/Agro-AI.git cd Agro-AI -
Install the required dependencies:
pip install -r requirements.txt
-
Prepare the data: Ensure the input data is formatted correctly according to the dataset structure.
-
Run the model:
- For crop recommendations:
python crop_recommendation.py
- For fertilizer recommendations:
python fertilizer_recommendation.py
- For crop recommendations:
-
Interpret Results: The models will output the recommended crop/fertilizer and associated metrics.
- Fuzzy C-Means (FCM): A clustering algorithm used to group similar data points for crop suitability.
- Principal Component Regression (PCR): Reduces data dimensionality while maintaining prediction accuracy.
- Random Forest (RF): A robust ensemble method for both classification and regression tasks.
- Support Vector Regression (SVR): Utilizes hyperplanes for regression tasks.
- Linear Regression: Predicts fertilizer requirements based on linear relationships.
- Neural Networks: Captures complex patterns in data for fertilizer recommendations.
Contributions are welcome! Please fork the repository and submit a pull request for review.
- Fork the repository.
- Create a new branch:
git checkout -b feature-name
- Make your changes and commit them:
git commit -m "Added a new feature" - Push your changes:
git push origin feature-name
- Open a pull request.
This project is licensed under the MIT License. See the LICENSE file for details.
Author: Virat Srivastava
For questions, feel free to reach out or create an issue in the repository.