floodsr 0.0.5

Flood super-resolution CLI and library using ONNX Runtime.

floodsr

Super-Resolution for flood hazard rasters. Ingests lores water grid and hires DEM and infers a hires water grid using the specified model.

• Documentation: https://floodsr.readthedocs.io/en/latest/
• Contribute: https://github.com/cefect/floodsr/blob/master/CONTRIBUTING.md

Implemented models (see floodsr/models.json):

• ResUNet_16x_DEM: 16x DEM-conditioned ResUNet

Installation

see documentation for details.

basic install

pipx install floodsr

extended install

for handling rasters too large for memory, floodsr requires GDAL backends.

# advanced install for VRT workflows
conda create -n floodsr-gdal -c conda-forge python=3.12 gdal -y
conda activate floodsr-gdal
python -m pip install floodsr

Use

List available model versions:

floodsr models list

Fetch a model by version into the default cache:

floodsr models fetch ResUNet_16x_DEM 

Enhance a low-resolution flood hazard raster to high resolution (tohr), fetching the DEM from the HRDEM Mosaic data source. NOTE: this requires downloading the test data (see below) or replacing the *.tif paths with your own data paths.

floodsr tohr --in lowres032.tif --fetch-hrdem 

Enhance with a local DEM file:

floodsr tohr --in lowres032.tif --dem hires002_dem.tif  

Doctor diagnostics:

floodsr doctor

For more details, see the User Guide.

downloading test data

To download manually, browse to this release and download the assets into your current working directory.

Alternatively, bash users with curl:

curl -L -O https://github.com/cefect/floodsr/releases/download/v0.0.3/hires002_dem.tif -O https://github.com/cefect/floodsr/releases/download/v0.0.3/lowres032.tif