Machine learning–driven assessment of climate change impacts on Niger Delta coastal ecosystems using synthetic environmental data. The project models ecosystem health under climate stressors, supports scenario analysis, and demonstrates AI applications for coastal monitoring, research, and environmental decision-making.
Climate Change Impact on Coastal Ecosystems in the Niger Delta Using ML-Based Models
📌 Overview
This project applies machine learning to assess the impact of climate change on coastal ecosystems in the Niger Delta using realistic synthetic environmental and oceanographic data. The model predicts ecosystem health under varying climate stressors to support environmental monitoring and policy decisions.
🌍 Key Features
Synthetic climate and coastal ecosystem dataset
Random Forest–based ecosystem health prediction
Feature importance analysis of climate drivers
Future climate scenario simulation
Policy-relevant ecosystem risk insights
🧪 Dataset Description
The dataset simulates key climate and environmental variables:
Temperature (°C)
Rainfall (mm)
Sea level rise (cm)
Salinity (ppt)
Storm frequency
Soil moisture index
Target variable:
Ecosystem Health Index (0–100)
🤖 Machine Learning Model
Algorithm: Random Forest Regressor
Task: Regression (ecosystem health prediction)
Evaluation metrics: RMSE, R² Score
Feature scaling: Min-Max normalization
📊 Outputs
Feature importance visualization
Ecosystem health prediction scores
Scenario-based climate impact assessment
▶️ How to Run
pip install -r requirements.txt
python climate_change_coastal_ecosystem_ml.py
🧭 Applications
Coastal ecosystem monitoring
Climate impact assessment
Environmental planning and policy support
Research and academic demonstrations
⚠️ Disclaimer
This project uses synthetic data for research, education, and demonstration purposes. It does not represent real-world measurements.
Author:
AGBOZU EBINGIYE NELVIN
LinkedIn: *
linkedin.com
📜 License
MIT License