A multi-source statistical supervised classification approach was undertaken to classify wetlands in the Congo basin. Passive optical remotely sensed imagery provided by the Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper Plus (ETM+) sensors, JERS-1 active radar L-band horizontal co-polarization imagery, and 3 arc second elevation data derived from the Shuttle Radar Topography Mission (SRTM) are used as inputs. These data are related to wetland/non-wetland training data through a classification tree algorithm to yield a wetland probability map of the central Congo Basin for the 1986-2000 period, with the fundamental assumption that the limits between wetland and non-wetland areas were stable for this 17 year period.
For the full description of forest alert methodology please refer to the following publication:
Bwangoy, J.-R.B., Hansen, M.C., Roy, D.P., De Grandi, G., and Justice, C.O. (2010) Wetland mapping in the Congo Basin using optical and radar remotely sensed data and derived topographical indices. Remote Sensing of Environment, 114, 73-86.