Description
Floods are natural disasters that can lead to loss of life or the destruction of infrastructure and the natural environment. A number of recent studies have reported an increase in floods globally, with some regions being affected more than others. Increases in floods have given impetus to the research of flood mapping and monitoring, which has resulted in the improvement and development of new technologies and techniques for modelling these events.
Geosmart, in collaboration with the Centre for Geographical Analysis (CGA) at Stellenbosch University, developed a flood hazard model by combining DEM derivatives and machine learning. The machine learning model was trained using 2d hydrological model outputs and a large set of terrain derivatives generated from the SUDEM5 and the DEMSA2 were used as predictor variables. The model showed results with an accuracy of 84% (i.e. the model correctly predicted a specific location’s flood hazard 84 out of 100 times). See Flood Hazard Index article for more information about our Flood Hazard Index product.
Below are some examples of flood hazard maps.
Johannesburg
Durban
Cape Town
Stellenbosch
The model has also been implemented across the whole of South Africa and can be generated anywhere in the world. The accuracy of the model is dependent on the quality of the DEM used as input. Ideally, a high-resolution DEM, such as the SUDEM5 or DEMSA2, should be employed.
Use cases
- Insurance risk assessments
- Disaster mitigation and management
- Town and regional planning
- Infrastructure development planning
- Property valuations
- Agricultural planning and development
- Environmental management
Features and benefits
- Available for anywhere in South Africa at high accuracy.
- Easy-to-understand hazard level classes (Very High, High, Medium, Low).
- Computer-to-computer dynamic hazard queries through an application programming interface (API).
- Query location-specific hazard level per coordinate (latitude and longitude) or by area (polygon).
- Additional information: Elevation, Height Above Nearest Drainage, and Slope Gradient (Slope Failure Hazard).
- Continuous accuracy improvements over time as machine learning model is trained with new data.
Product Specification
| Resolution | 5 m |
| Format | GeoTIFF (tif), Shapefile (shp), CAD (dwg or dxf) |
| Price | See pricelist below |
The flood hazard index is derived from our DEMSA2 products. Depending on the product ordered, this can be either from a digital terrain model (DTM) or a digital surface model (DSM). In other words, the flood hazard index can be derived from only the bare earth elevation, or include the heights of objects (e.g. trees, buildings) on the earth’s surface as well. See the conceptual difference between a DTM and a DSM in this image:
Pricing
| Derived from | Small area (< 400 km²) | Medium area (400 - 9 999 km²) | Large (> 10 000 km²) | Turnaround time* |
|---|---|---|---|---|
| DEMSA2 DSM (Raw) | R2 700 per AOI + R45 per km² | R30 per km² | R25 per km² | 5 workdays per 500 km² |
| DEMSA2 L2 (Quality Controlled) | R5 300 per AOI + R75 per km² | R55 per km² | R50 per km² | 20 workdays per 500 km² |
| DEMSA2 L3 (DTM) | R6 400 per AOI + R140 per km² | R110 per km² | R75 per km² | 20 workdays per 500 km² |
*Turnover time will be lower for less complex terrain types. Please enquire for a more accurate timeframe
*Areas of interest must be rectangular, with a minimum width of 1 km.
Estimate Cost and Request a Quote
Complete the form and we’ll be in touch as soon as possible.
Product Cart
| AOI Name | Product | AOI Area | Price per km² | Processing Fee | Total Price (excl VAT) | Total Price (incl VAT) |
|---|
For large orders (>5 000 km2), please contact us directly as such orders are often heavily discounted.