Skip to content
This is NOT an official site of the Government of Canada. Click here for the official AI registry.

Helpful Places

Government of Canada – DTPR AI Register

AI-Powered Oil Spill Detection in Canadian Waters

Ecology · Safety & Security · Enforcement

What it collects

About a measurement
Anonymized data
  • Synthetic aperture radar (SAR) imagery collected by the RADARSAT Constellation Mission satellites, capturing backscatter measurements of the ocean surface used to detect oil slick signatures. No personal information is involved.
Run by
Environment and Climate Change Canada (ECCC)
Where
No fixed location
Kept
Not stated by the Helpful Places.
Shared with
Not stated by the Helpful Places.

What it is for

EcologySafety & SecurityEnforcement

This system uses satellite radar imagery and machine learning to automatically detect oil pollution in Canadian waters. It is part of Canada's Integrated Satellite Tracking of Pollution (ISTOP) program, operated by the Canadian Ice Service in collaboration with Transport Canada. The system assists government employees in identifying and reporting oil spills — it does not directly affect members of the public, but its outputs influence environmental enforcement and marine safety decisions. It is currently in development and does not disclose its use of AI to those it monitors.

What it collects and what happens to it

Data taken in

About a measurement
Anonymized data
  • Synthetic aperture radar (SAR) imagery collected by the RADARSAT Constellation Mission satellites, capturing backscatter measurements of the ocean surface used to detect oil slick signatures. No personal information is involved.

Processing

Computer Vision
  • Applies image and object recognition to synthetic aperture radar (SAR) satellite imagery from the RADARSAT Constellation Mission to identify oil pollution signatures on the ocean surface.

What it does

Sensing (Perceptive AI)
Human decides
  • The system senses and interprets radar satellite imagery from the RADARSAT Constellation Mission to detect oil spills. Government employees (GC employees) review the detections and decide on follow-up reporting actions.
Deciding (Analytical AI)
Human decides
  • The AI/ML component classifies detected objects or patterns in radar imagery as likely oil spills, producing scores or labels that support human-reviewed reporting decisions.

Outputs

A recommendation or prediction
Anonymized data
  • Automated detection results flagging probable oil pollution events in Canadian waters, provided to GC employees to aid in reporting. Outputs are advisory — human staff determine whether to initiate a formal pollution report.

Run by

Environment and Climate Change Canada (ECCC)
  • The Canadian Ice Service, a division of Environment and Climate Change Canada, manages and operates the ISTOP-ML system in collaboration with Transport Canada to detect and report oil pollution in Canadian waters.

Government of Canada AI Register — ISTOP-ML

Built by

Government of Canada
  • The system was developed by the Government of Canada, with no external vendor listed. Development is conducted internally by federal government staff and resources.

Government of Canada AI Register — ISTOP-ML

Kept for

Not stated by the Helpful Places.

Shared with

Not stated by the Helpful Places.

Stored

Not stated by the Helpful Places.

How to read the colours

Can it identify you?

Anonymized data
Data about people with the link to who is broken. Stripped of identifiers, blurred, aggregated, or noised so this system can’t reasonably tie a record back to an individual.
Pseudonymous data
Each person’s data is tied to a token (hash, ID, template) that lets this system recognise the same person across events, but the token itself doesn’t reveal a name. Reidentification is possible with extra information.
Identifiable data
The data either contains a direct identifier (name, address, account name, recognisable face or voice, plate number) or carries a token this system uses to look up legal identity during processing.

Who completes the loop?

Human decides
This mode suggests; a person decides what to do next. The AI is always advisory — a human is in the loop on every decision. Example: a triage tool ranks cases for a clinician who chooses which to see first.
Human executes
This mode decides; a person carries out the result. Example: an optimizer plans the day’s trash-collection routes, and drivers run them.
Autonomous
This mode decides and acts on its own. No person reviews each decision or carries out the resulting action.

Definitions from the DTPR standard. Amber is about your data, violet about who decides. The fuller the shape and the deeper the colour, the more identifying the data or the less a person is involved.

What you can do

Ask about this system

Questions go to the Helpful Places, not the vendor.

Your rights

  • Right to Be Informed of AI UseThe AI register discloses that AI use is NOT disclosed to those monitored by this system. Vessel operators or other parties in Canadian waters subject to monitoring by ISTOP-ML are not informed of the use of AI/ML in pollution detection. There is no documented mechanism for affected parties to be notified. Individuals seeking information may contact Environment and Climate Change Canada or Transport Canada through their official public inquiry channels.

Risks and safeguards

  • Civil liberties harmThe system monitors Canadian waters without disclosing to affected parties (e.g., vessel operators) that AI surveillance is being used, raising transparency concerns regarding covert automated monitoring.Safeguard: The system targets environmental pollution detection (not individuals), does not involve personal information per the register, and outputs are reviewed by trained GC employees before enforcement action is taken. No mitigation for the lack of AI use disclosure is currently documented.