Very high resolution derived land cover/use classifications for the Corridor Ankeniheny-Zahamena (CAZ), Madagascar

The products capture current land use/cover for four areas of interest in Corridor Ankeniheny Zahamena (CAZ) generated based on very high resolution imagery (SPOT 6). Field-based training and validation data were used and supervised classifications created using Random Forest classifier. The study extent aims to capture the drivers of deforestation in the Corridor Ankeniheny-Zahamena (CAZ). Multiple variables were incorporated into the sampling design, including elevation, slope, bioclimate zone, length of dry season, soil type, deforestation history (by epoch and elevation), and access. Based on the above criteria, four Zones of Interest (ZOIs) were identified and modified in an iterative approach involving preliminary reconnaissance work, information on access provided by partners, and initial analyses of spatial data layers. Current land use/cover classifications were generated for each ZOI based on very high resolution imagery from SPOT 6. Field data collected by Work Package (WP) 2 and 4--which are impacts on hydrological benefits of alternative Payments for Ecosystem Services (PES) approaches and impacts on carbon storage/sequestration of alternative PES approaches--were used as training data. Supervised classifications were created using Random Forest classifier.