Use the model

You can use this model in the Classify Pixels Using Deep Learning tool available in the Image Analyst toolbox in ArcGIS Pro.

Recommended imagery configuration

The recommended imagery configuration is as follows:

• Resolution—The expected SAR image resolution is 10 meters.
• Dynamic range—8 bit.
• Bands—3-band Sentinel-1 C band SAR GRD VH polarization band raster.

Extract water bodies

Complete the following steps to extract water bodies from the imagery:

1. Open ArcGIS Pro, create a ArcGIS Pro project. Ensure that you have added a Sentinel-1 C band SAR GRD VH polarization band raster in ArcGIS Pro. (Note: You can download the imagery from Copernicus Open Access Hub or Sentinel Hub.)

   

2. Download the Water Body Extraction (SAR)—USA model.
3. Zoom to an area of interest.

   

4. Right-click the raster in the Contents Pane. Click Data and select Export Raster to create a 3-band raster. Set the variables on the General tab as follows:
   1. Output Raster Dataset—The name and format for the raster dataset being created.
   2. Coordinate System—Output coordinate system.
   3. Clipping Geometry—Change the parameter if required.
   4. Renderer Settings—Check Force RGB and Use Renderer.

      

5. Browse to Tools under the Analysis tab.
   
6. Click the Toolboxes tab in the Geoprocessing pane, select Image Analyst Tools and browse to Classify Pixels Using Deep Learning tool under Deep Learning.

   

7. On the Parameters tab, set the variables as follows:
   1. Input Raster—Select the 3-band Sentinel-1 GRD VH polarization imagery layer.
   2. Output Classified Raster—Set the output feature class that will contain the classification results as the binary raster representing water and nonwater classes.
   3. Model Definition (optional)—Select the pretrained or fine-tuned model .dlpk file.
   4. Model Arguments (optional)—Change the values of the arguments if required.

      

8. Set the variables under the Environments tab as follows:
   1. Processing Extent—Select Current Display Extent or any other option from the drop-down menu.
   2. Cell Size—Change if required. (Note: 10 meters is the expected SAR image resolution.)
   3. Processor Type—Select CPU/GPU as per the need. If GPU is available, it is recommended that you select GPU and set GPU ID to specify the GPU to be used.

      

9. Click Run. Once processing is complete, the output classified raster is added to the map.