Nelvinebi/Mangrove-Degradation-and-Health-Assessment-in-the-Niger-Delta-Using-NDVI-NDWI-and-ML

This project evaluates mangrove ecosystem health in the Niger Delta using NDVI and NDWI indices with machine learning on synthetic data, demonstrating scalable methods for detecting degradation, supporting environmental monitoring, conservation planning, and geospatial decision-making. Mangrove Degradation and Health Assessment in the Niger Delta Using NDVI, NDWI, and Machine Learning 📌 Project Overview This project assesses mangrove ecosystem health in the Niger Delta using synthetic remote sensing indices—NDVI and NDWI—combined with machine learning techniques. It demonstrates how satellite-derived vegetation and water indicators can be used to identify degraded versus healthy mangrove zones for environmental monitoring and decision-making. 🎯 Objectives Simulate NDVI and NDWI data representing mangrove environments Classify mangrove health status (healthy vs degraded) using ML Provide GIS-ready outputs for spatial analysis and visualization 🧪 Data Type: Synthetic dataset Features: NDVI, NDWI, pixel coordinates Label: Mangrove health status Format: Excel (.xlsx), suitable for ML and GIS workflows 🧠 Methodology Generate synthetic NDVI and NDWI values Label mangrove health conditions Train a machine learning classifier Evaluate classification performance Prepare outputs for GIS integration 🛠️ Technologies Used Python NumPy, Pandas Scikit-learn Remote Sensing Indices (NDVI, NDWI) 📂 Project Structure ├── data/ │ └── mangrove_ndvi_ndwi_health_dataset.xlsx ├── scripts/ │ └── mangrove_health_ml.py ├── README.md 🌍 Applications Mangrove conservation planning Coastal ecosystem monitoring Environmental impact assessment Academic and research demonstrations 👤 Author Agbozu Ebingiye Nelvin Email: nelvinebingiye@gmail.com GitHub: *github.com LinkedIn: *linkedin.com 📄 License This project is intended for academic, research, and educational use.