Satellite Flood Map of Valencia Flash Flooding
Image and Signal Processing Group (ISP) – University of Valencia
The recent flash floods in Valencia, caused by a cut-off low (locally termed DANA), have provisionally left more than 230 fatalities, thousands of damaged vehicles, and severe damage to infrastructure.
In response, the Image and Signal Processing Group (isp.uv.es) of the University of Valencia has developed a detailed interactive flood extent map using multispectral satellite images (Landsat-8 and Sentinel-2), employing a flood detection model described in a recent article published in Nature Scientific Reports. This machine learning model allows for accurate segmentation of flood extent in optical satellite images and is accessible through ML4Floods.
The flood maps provide a detailed view of affected areas, highlighting the potential of Earth observation technologies for documenting and analyzing large-scale natural disasters.
Interactive Flood Map Viewer - 30th and 31th of October, 2024
The flood extent displayed on this map was derived from a machine learning flood detection model applied to satellite imagery. This detection combines results from a NASA LANDSAT-8 image taken on October 30th and an ESA Sentinel-2 image from October 31st. Some affected areas, particularly urban zones, may not have been correctly identified due to the resolution of the input data and the challenges of identifying flood damage in areas where water has already receded.
Note: This data has not been validated and it is not suitable for decision-making purposes.
Source: viewer code and flood maps in vectorial format (geojson) can be found at Simon's repository.
Accurate Flood Map of the DANA
Together with the Department of Geography, a map of the DANA floods of October 29 has been elaborated by combining satellite images, processed data and civil information from local entities and victims with exact data on flood damage in their areas.
Flood Map - October 30, 2024 (NASA/USGS Landsat-8)
Flood Map - October 31, 2024 (ESA Sentinel-2 + Super-resolution)
The ESA Sentinel-2 image from October 31st was acquired 2 days after the flood and the water had already receded in some areas. However, Sentinel-2 can provide satellite data with improved spatial resolution (10 and 20 metres) and spectral resolution (12 spectral bands). Furthermore, super-resolution models can potentially improve the effective spatial resolution of optical satellite imagery, which is of utmost importance for performing detailed analysis in such catastrophic events. Therefore, we have applied our super-resolution framework (OpenSR) to effectively upscale Sentinel-2's 10-meter and 20-meter bands to a uniform resolution of 2.5 meters across all bands.
In addition to the improved resolution of 2.5 meters, it is worthnoting that Sentinel-2 provides information at visible, infrared, and shortwave infrared bands, which are critical for the detection of flooded areas.
