SA Deforestation Monitoring

Deforestation Map South Africa
Deforestation hotspots in South Africa (2015-2025).

The Challenge

Monitoring large-scale environmental changes like deforestation and water depletion is challenging due to the vast areas involved and the need for frequent, high-resolution data. Reliable measurement of forest cover change and water body extent is critical for nature-based carbon projects and environmental stewardship. Traditional ground surveys are insufficient for real-time policy and conservation decisions.

Datasets

The project utilizes the following datasets, all integrated via Google Earth Engine for efficient processing:

Optical & SAR

  • Sentinel-2: Multispectral data for land cover analysis.
  • Sentinel-1 SAR: Radar imagery for cloud-penetrating observations.
  • Landsat 5/8/9: Long-term dynamics and thermal infrared data.

Environmental Indices

  • Hansen GFC: Baseline forest loss and gain tracking.
  • Dynamic World: Real-time land use classifications.
  • ESA WorldCover: Annual global land cover maps.

Ancillary Data

  • HydroSHEDS: Stream networks and watershed boundaries.
  • OpenStreetMap: Critical infrastructure (dams, rivers).
  • FAO GAUL: Standardized administrative boundaries.

The Workflow

The following diagram outlines the overall project workflow, from data ingestion to final visualization:

flowchart TD subgraph Data["Data Sources"] S1["Sentinel-1 SAR (VV/VH)"] S2["Sentinel-2 SR (NDVI/NDWI)"] L5["Landsat 5 (Temperature)"] OSM["OpenStreetMap (Rivers & Dams)"] DW["Dynamic World (Trees prob.)"] HAN["Hansen GFC (baseline & loss)"] GAUL["FAO GAUL (province boundary)"] end subgraph EE["Earth Engine Processing"] A["Ingest & Preprocess
(cloud mask, SAR prep, clip)"] B["Annual Composites 2015–2024
(NDVI/NDWI, DW Trees mean)"] C["Change Detection
(NDVI/DW transitions, SAR cues)"] D["Post-process & Vectorize
(min-area filters, cleaning)"] E["Summaries & QA/QC sample points"] end subgraph Exports["Exports"] R1["COG/GeoTIFF rasters"] V1["GeoJSON/Shapefile vectors"] T1["CSV time series"] M1["EE Tile Service / titiler"] end subgraph Tools["Apps"] QG["QGIS\nvisualize/edit/validate"] AG["ArcGIS Online\nhost layers & dashboard"] end Data --> A A --> B --> C --> D --> E E --> R1 E --> V1 E --> T1 B --> M1 R1 --> QG R1 --> AG V1 --> AG T1 --> AG M1 --> AG

Methodology

  1. Tree Cover Monitoring: Computing NDVI thresholds and Random Forest classification to detect forest health and loss.
  2. Water Dynamics: Using MNDWI to track surface water changes near critical infrastructure.
  3. Carbon Stock Analysis: Training a Random Forest classifier to predict Above-Ground Biomass Density (AGBD) using multispectral indices and DEM data.
  4. Emissions MRV: Correlating surface temperatures and atmospheric methane data with deforestation patterns.

Results & Visualization

The automated pipeline generates high-resolution maps and datasets for Monitoring, Reporting, and Verification (MRV).

Water Body Changes
Water surface dynamics (MNDWI).
Water Infrastructure Map
Mapping dams and river networks.
Carbon Stock Map
Estimated Above-Ground Biomass Density.
Carbon Emissions Map
Temperature and methane-based emission tracking.

Data-Driven Conservation

Need a similar monitoring pipeline for your region or project?

Collaborate on Monitoring

Technologies Used