Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Momahmoses/deforestation-monitoring

Domain:

environment and energygeospatial

Record type:

softwareproject
Creator:
Mom
Host:
Time-series satellite imagery analysis to track deforestation and generate ranger alerts across Cross River, Congo Basin and Niger Delta. # Deforestation & Land Use Change Monitoring Time-series satellite imagery analysis to track illegal logging, land encroachment, and deforestation across Cross River State, Congo Basin, and Niger Delta, generating automated alerts for forest rangers and policy makers. --- ## Problem Statement Nigeria loses ~350,000 hectares of forest annually, one of the world's worst deforestation rates. The Niger Delta mangroves and Cross River rainforests are critically threatened by illegal logging and agricultural encroachment. This system provides near-real-time detection and alert generation. --- ## Features | Feature | Description | |---------|-------------| | Multi-Year NDVI Analysis | Time-series 2015–2024 from Landsat-8 / Sentinel-2 | | Land-Use Classification | Random Forest, Forest / Vegetation / Agriculture / Deforested | | Automated Alert Generation | Critical / High / Moderate severity alerts for rangers | | Forest Coverage Trends | Annual loss rates by region and forest type | | Change Detection Map | Interactive map with deforestation alert markers | --- ## Tech Stack | Layer | Technology | |-------|-----------| | Remote Sensing | Landsat-8, Sentinel-2 NDVI/EVI | | Machine Learning | scikit-learn (Random Forest) | | Geospatial | GeoPandas, Folium, Rasterio | | Visualisation | Matplotlib, Seaborn, Plotly | | Data | pandas, NumPy | --- ## Project Structure ``` deforestation-monitoring/ ├── src/ │ ├── data_loader.py # Time-series satellite data ingestion and alert detection │ ├── model.py # Land-use classification, forest loss computation │ └── visualize.py # Change map, trend charts, land-use pie charts ├── data/raw/ # Landsat/Sentinel rasters, shapefiles ├── models/ # Saved Random Forest classifier ├── config.yaml # NDVI thresholds, alert levels, region config ├── main.py # Pipeline entry point └── requirements.txt ``` --- ## Quick Start ```bash git clone githu …

Visit

github.com

Similar

A Smart Deforestation Monitoring and Control System ModelOEMC project use case: Tropical deforestation monitoring and characterisation toolMomahmoses/agricultural-yield-forecastingMomahmoses/healthcare-facility-accessMomahmoses/urban-slum-detectionMomahmoses/road-accident-hotspot

A Smart Deforestation Monitoring and Control System Model

One of the greatest challenges facing effective forest management in the world is

OEMC project use case: Tropical deforestation monitoring and characterisation tool

We propose a 10-m deforestation monitoring and characterization tool to support specific tropical co

Momahmoses/agricultural-yield-forecasting

||Satellite NDVI and EVI combined with LightGBM for crop yield prediction in North-Central and North

Momahmoses/healthcare-facility-access

Travel-time analysis to identify underserved communities and guide health facility placement in Nige

Momahmoses/urban-slum-detection

Satellite image ML classification to map informal settlements and guide infrastructure planning in W

Momahmoses/road-accident-hotspot

KDE hotspot analysis and ML severity prediction to support FRSC road safety interventions across Nig