Classification of the Amazon rain forest using JERS-1 SAR data

Imaging radar offers potential for regular monitoring of changes in this region. In particular, the JERS-1 satellite carries an L-band HH SAR system which, via an on-board type recorder, can collect data from almost anywhere on the globe, at any time of year. The authors show how JERS-1 radar images can be used to accurately classify different forest types (i.e. flood plain vs. upland forest) and river courses in the Amazon basin. JERS-1 data has also shown significant differences between data obtained during the dry season and the wet season, indicating a strong potential for monitoring seasonal change. The algorithms used to classify JERS-1 data is a standard maximum-likelihood classifier, using the radar image local mean and standard deviation of texture as input. Rivers are detected using an edge detection and edge-following algorithm. This work was performed by the Jet Propulsion Laboratory, California Institute of Technology, under contract from NASA.<>