Crop Health Monitoring using ML & Drone/Satellite Imagery

This project applies machine learning to analyze multispectral imagery and classify crop health for precision agriculture.

🔍 Objective

• Monitor and classify crop health using NDVI/GNDVI from drone or satellite images.
• Improve decision-making for irrigation, fertilization, and crop management.

🛠️ Technologies

• Python, Scikit-learn, OpenCV, Pandas, Matplotlib
• Vegetation Indices: NDVI, GNDVI
• Classification: Random Forest

📁 Project Structure

• data/ – Raw and processed image/CSV data.
• notebooks/ – Jupyter Notebooks for EDA and modeling.
• src/ – Python scripts for preprocessing, feature extraction, and ML.
• models/ – Trained model files.
• outputs/ – Result plots and classification outputs.

✅ Results

• Achieved 95% accuracy using Random Forest on labeled crop data.

📸 Sample Outputs

(Add CCDF plots, NDVI images, or classification maps here)

📚 References

• NDVI: https://en.wikipedia.org/wiki/Normalized_difference_vegetation_index
• Dataset: (Mention if synthetic, collected, or open-source)

---

✍️ Author

Ramanjaneyulu Karipetti