Mapping flood prone and Hazards Areas in rural landscape using landsat images and random forest classification: Case study of Nasia watershed in Ghana

Floods are hazard which poses immense threat to life and property. Identifying flood-prone areas, will enhance flood mitigation proper land use planning of affected areas. However, lack resources, the sizable extent rural settlements, evolving complexities contemporary models have hindered mapping areas in Ghana. This study used supervised Random Forest (RF) classification, Landsat 8 OLI, 7 ETM + images produce prone, Land Use Cover (LULC), maps Nasia Watershed The results indicated that about 418.82 km2 area watershed is flooded every 2–3 years (normal flooding) 689.61 7–10 (extreme flooding). LULC classification produced an overall accuracy 92.31% kappa 0.9. map within zones river include community, Flood Recession Agricultural (FRA), rainfed woodlands. When compared with a Modified Normalized Difference Water Index (MNDWI), RF had edge over MNDWI estimating from this can be by local administrators, national disaster management researchers for watershed.