High-temporal-spatial-resolution mapping for flood inundation using image fusion and decision tree

Abstract

The mapping of spatial inundation patterns during flood events is important for environmental management and disaster monitoring. Satellite images provide important data sources for monitoring flood disasters. However, the trade-off between spatial and temporal resolutions of current satellite sensors limits their uses in flooding studies. This study applied data fusion models, the flexible spatiotemporal method, in generating synthetic flooding images with improved temporal and spatial resolution for flood mapping. This paper performs a detailed comparison of flood maps derived from for number of post-disaster prediction based on images acquired after the flooding, selected flood events in 2016 Tumen river in China. The result shows that the Landsat-like images generated can be successfully applied in flood mapping. From simulated Tumen river flood mapping during 29 August to 3 September,2016, can know when inundation occurs, this result map flood inundation region will full in map. Meanwhile, test the maximum inundation region and severely submerged spots and flood event occur and stop date during the event. The study suggests great potential of FSDAF in flooding research. Blending multi-sources images could also support other disaster studies that require remotely sensed data with both high spatial and temporal resolution.