Flood maps across CONUS using the U.S. National Water Model, satellite observations and convolutional neural networks
Abstract
Advances in satellite remote sensing enable accurate, rapid and cost-effective mapping of flood extent anywhere in the world. However, high resolution satellite observations are temporally sparse and are prone to have cloud gaps. Hydrologic and hydraulic models offer a continuous stream of information for flood mapping, but require trade-offs related to geospatial scale, computational efficiency, and accuracy of input data which impedes directly using them to fill gaps between clear satellite observations. Deep learning algorithms can be used to learn the information compressed within such models for flood maps without the need for intensive runtime computations or time consuming curation of local data sources.
We trained a fully convolutional encoder-decoder network to regress fractional flooded areas that can substitute direct satellite observations at a 2km grid cell resolution. Our training targets are 5740 CNN-produced flood maps from 189 events from the Dartmouth Flood Observatory archive across the CONtiguous United States (CONUS) from 2000-2021 observed by MODIS. Inputs to this network include two state variables from the U.S. National Water Model (NWM): soil moisture from the land surface component (NOAH-MP) and ponded depth from the terrain router. We also include three static inputs: a digital elevation model derived flow direction raster and flow accumulation raster, and a global surface water raster. NWM inputs include those from the NWM retrospective run (2000-2019; version 2.1) and NWM forecasts (2019-2021). Model performance is assessed in terms of matching satellite observations with RMSE. We include performance metrics on a pixel-by-pixel basis and aggregated to the zip code level. We also use Hurricane Delta and Hurricane Ida as test case studies of major flooding events in the United States, and find that our model reflects the flood extents and intensities of these two flood events.- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2022
- Bibcode:
- 2022AGUFM.H26B..06F