Akajiaku11/Hybrid-Machine-Learning-Framework-for-Water-Quality-Assessment-and-Contamination-Clustering

Hybrid Machine Learning Framework for Water Quality Assessment and Contamination Clustering in the Niger Delta 🌊 Water Quality Assessment Using Machine Learning in the Niger Delta This repository contains the full codebase and data analysis workflow for the study: "A Hybrid Machine Learning Framework for Water Quality Assessment and Contamination Clustering in the Niger Delta" 📌 Overview This project combines Water Quality Index (WQI) analysis with supervised and unsupervised machine learning models to assess water contamination across 50 towns in Bayelsa State, Nigeria. 🔍 Key Features WQI Computation based on WHO standards ML Regression Models: Random Forest, XGBoost, and LSTM Classification Performance: Accuracy, AUC, F1-Score Clustering: KMeans used for chemical profile grouping Visualizations: Feature importance, ROC curve, spatial WQI map 📁 Files Water_Quality_ML_Analysis.py: Full standalone Python script Water_Quality_ML_Analysis.ipynb: Jupyter notebook version Water Parameters.csv: Sample dataset used in analysis /figures/: Contains model performance charts, maps, and tables (optional) README.md: Project documentation 📊 Requirements Python 3.7+ Libraries: pandas, numpy, matplotlib, seaborn, scikit-learn, xgboost, tensorflow, keras Install dependencies using: bash Copy Edit pip install -r requirements.txt 📌 Applications Smart environmental monitoring WASH (Water, Sanitation & Hygiene) policy support Real-time contamination detection in underserved regions 📜 Citation If using this work, please cite: Akajiaku and Eteh . "Hybrid ML Framework for Water Quality and Contamination Mapping in Nigeria." (Under review, Springer, 2025).