Loading…
This layer is editable and shared with the public. To prevent unwanted editing, unshare this item or approve it for public data collection.
Finish setting up your layer
Describe your item below. Add fields on the Data tab. Configure editing on the Settings tab. Configure drawing and pop-ups through Map Viewer or Visualization tab.
Open
Creating Service

Deep learning model to detect oil spills in Sentinel-1 SAR data. A brief summary of the item is not available. Add a brief summary about the item.

‎Deep learning package by

New notebook runtime available. You can update the runtime from the settings tab of the item details page.

Item created: Nov 1, 2022 Item updated: Jan 1, 2025 Number of downloads: 4,270

Snapshot last refreshed:

1984 characters left.

Description

Oil spills are a major source of marine pollution that affect the environment, economy, and marine ecosystems. Toxic chemicals from oil spills can remain in the ocean for years and even sink down to the seabed affecting sedimentation rates. While many oil spills are accidental, some are caused deliberately by cargo ships dumping waste oil and bilge water. It is very difficult to identify, detect and remove oil from the ocean surface and routine monitoring can help prevent illegal dumping and aid with remediation efforts.

This deep learning model automates the task of detecting potential oil spills from Sentinel-1 SAR data. In addition to being inexpensive, SAR data is collected day and night in all weather conditions without getting affected by cloud cover. Use this model to identify potential oil spills that need to be reviewed or monitored, reducing time and effort required significantly.

Using the model
Follow the guide to use the model. Before using this model, ensure that the supported deep learning libraries are installed. For more details, check Deep Learning Libraries Installer for ArcGIS.

Fine-tuning the model
This model can be fine-tuned using the Train Deep Learning Model tool. Follow the guide to fine-tune this model.

Input
8-bit, 3-band Sentinel-1 C band SAR GRD VV polarization band raster.

Output
Feature layer representing oil slick.

Applicable geographies
The model is expected to work globally.

Model architecture
The model uses the MaskRCNN model architecture implemented in ArcGIS API for Python.

Accuracy metrics
The model has an average precision score of 0.69.

Training data
This model is trained on 381 Sentinel-1 scenes downloaded from the ASF portal, and the ground truth data from NESDIS Marine Pollution Products. 

Sample results
Here are a few results form the model.



An in-depth description of the item is not available.

Layers

Ground Layers

Tools

Tables

Basemap

Project Contents:

Solution Contents

Contents

Layers

Screenshots

Terms of Use

esri logoThis work is licensed under the Esri Master License Agreement.

View Summary | View Esri Terms of Use

No special restrictions or limitations on using the item's content have been provided.

Comments (13)

Sign in to add a comment.

Mwajeeh2023 Item Owner commented 7 months ago Delete Reply

the guideis not clear

spathak_deldev Item Owner commented 6 months ago Delete

We have only presented the OilSpillDetection_SAR.dlpk file in the guide. To use the model, you need to perform some preprocessing steps before using the Detect Objects Using Deep Learning tool. If you let me know where you're getting stuck, I can help clarify and resolve the issue.

Mwajeeh2023 Item Owner commented 6 months ago Delete

I'm using the OilSpillDetection_SAR.dlpk model in ArcGIS Pro for detecting oil spills from SAR imagery. However, I've noticed that the guide/documentation suggests a different approach or model for oil spill detection in SAR. Has anyone else encountered this? I'd appreciate any insights on how the DLPK model compares to the method recommended in the guide.

spathak_deldev Item Owner commented 7 months ago Delete

Could you let me know which parts are confusing or what specific information you’re looking for?

a19448_uopsl Item Owner commented 8 months ago Delete Reply

in the area and the length field in the result attrubute table cant understand. because it has decimel values. can you let me know how to calculate the area and the length in KM

spathak_deldev Item Owner commented 7 months ago Delete

Hi, you can calculate area and length in km using Calculate Geometry tool (https://pro.arcgis.com/en/pro-app/latest/tool-reference/data-management/calculate-geometry-attributes.htm), you can also refer to this page: https://support.esri.com/en-us/knowledge-base/calculate-geometry-in-arcgis-pro-000016157

cmasif3sri Item Owner commented a year ago Delete Reply

thanks demos for your kind reply. Sorry for not being specific about accuracy. Actually I'm looking for Accuracy, Precision and F1 scores for the model. Thanks again

demos_deldev Item Owner commented a year ago Delete

The python api supports Average Presicion Score metrics for evaluating performance of MaskRCNN model given that this is a segmentation based model. F1 score is a useful for models that perform classification task.

cmasif3sri Item Owner commented a year ago Delete Reply

I tried to find out accuracy and precesion for the model. Please guide where can I find this?

demos_deldev Item Owner commented a year ago Delete

In the Accuracy section, the model's accuracy metric is mentioned - it has an average precision score of 0.69.

edneprine Item Owner commented 2 years ago Delete Reply

How can I use it, Sentinel, from the portal?

Item Information

LowHigh

Item Information

LowHigh

Make your item easy to find, understand, and use by providing this information.

    Details

    Dashboard views: Desktop

    Source: (Image Collection)

    Creating data in:

    Published as:

      Other Views:

        Dependent items in the recycle bin

          Applicable: 2d

          Size: 168.724 MB

          Attachments size: 0 KB

          ID: 4dd65af881f64236ac9bbaa407e046ba

          Image Count: 0

          Image Properties

          Layer Drawing

          Using tiles from a cache

          Dynamically from data

          Share
          Owner

          esri_analytics

          Folder

          Categories

          This item has not been categorized.

          Assign Category
          Tags

          Oil Spill Detection, sentinel-1, SAR, LivingAtlasDLPK, dlpk

          Edit Tags
          Credits (Attribution)
          No acknowledgements.

          NOAA

          ArcGIS Navigator link
          URL View
          WMTS View
          Your tile layer is ready to use
          This tile layer will automatically create tiles as needed and cache them for future use. No further configuration is required. View the Settings tab to change the default options. Build tiles manually for specific scales and extents to improve display performance for the first person to view the tile layer at that scale and extent. Tiles must exist if the layer will be used offline.
          All items were exported successfully
          ${numberOfItems} item(s) were exported successfully. Some item(s) skipped or failed to export.
          See description for more information
          Cannot import
          Export packages from newer portal versions cannot be imported to older versions.
          Loading…