Skip To Content

Use the model

You can use this model in the Detect Objects 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—Three-band Sentinel-1 C band SAR GRD VV polarization band raster.

Extract oil spills

Complete the following steps to extract oil spills from the imagery:

  1. Open ArcGIS Pro and create an ArcGIS Pro project.
  2. Browse to Tools on the Analysis tab.
    Note:

    You can download the imagery from Copernicus Open Access Hub, Sentinel Hub, or ASF portal.

    Tools
  3. Click the Toolboxes tab in the Geoprocessing pane, select Image Analyst Tools, and browse to the Despeckle tool under Synthetic Aperture Radar.
    Despeckle
  4. Select manifest.safe file in the Input Radar Data parameter using file explorer icon.
    Despeckle Parameters tab
    Adding the manifest file
  5. Select VV band in Polarization Bands parameter. Click Run.

    The output layer is added to the map.

  6. Click the Toolboxes tab in the Geoprocessing pane, select Image Analyst Tools, and browse to the Log10 tool under Math.
    Log10
  7. Add the output from the Despeckle function as an input file into the Input raster or constant value option and click Run.
    Log10 Parameters tab

    The output layer is added to the map.

  8. In the Raster Functions window, search for and select Clip to remove land area.
    Clip Tool
  9. Add the output from the Log10 function as an input file into the Raster option and click Run.
    Clip Properties

    The output layer is added to the map.

  10. In the Raster Functions window, search for and select Composite Bands.
    Composite Bands
  11. For Rasters, add the output from Clip three times as the input file to create a three-band image, and click Create new layer.
    Composite Bands Properties Parameter tab

    The output layer is added to the map.

  12. Zoom to an area of interest.
    Area of interest
  13. Click the Toolboxes tab in the Geoprocessing pane, select Image Analyst Tools, and browse to Detect Objects Using Deep Learning under Deep Learning.
    Detect Objects Using Deep Learning
  14. On the Parameters tab, set the variables as follows:
    1. Input Raster—Select Composite Bands.
    2. Output Detected Objects—Select the feature layer representing oil spills.
    3. Model Definition (optional)—Select the pretrained or fine-tuned model .dlpk file.
    4. Arguments (optional)—Change the values of the arguments if required.
      Parameters tab
  15. Set the variables on 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:

      The expected SAR image resolution is 10 meters.

    3. Processor Type—Select CPU or GPU as needed. It is recommended that you select GPU, if available, and set GPU ID to the GPU to be used.
      Environments tab
  16. Click Run.
    Output layer added

    The output layer is added to the map.

  17. Convert multiple overlapping polygons into a single polygon in cases where multiple polygons must be generated over a single oil spill. Use the Pairwise Dissolve tool to convert them.
    Multiple overlapping output polygons
  18. Click the Toolboxes tab in the Geoprocessing pane, expand Analysis Tools, and browse to the Pairwise Dissolve tool.
    Pairwise Dissolve tool
  19. Set the variables on the Parameters tab as follows:
    1. Input Features—Select the detected oil spill feature layer.
    2. Output Feature Class—Set the output feature class that contains the dissolved oil spills.
      Pairwise Dissolve Parameters tab
    3. Click Run.

      The output layer is added to the map.

      Dissolved Oil Spills