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

Back to your search

AI-Assisted Quality Control for Ocean Sensor Data

Ecology · Research & Development

What it collects

About a measurement
Anonymized data
  • Historical and new Conductivity, Temperature, and Depth (CTD) profile sensor scans collected by DFO Pacific Region. Each row represents a physical oceanographic measurement at a given depth; no personal information is involved.
Run by
Fisheries and Oceans Canada (DFO)
Where
No fixed location
Kept
Not stated by the Helpful Places.
Shared with
Accountable organization

What it is for

EcologyResearch & Development

This tool uses artificial intelligence to automatically flag oceanographic sensor readings (Conductivity, Temperature, and Depth) for deletion or preservation during quality control. It is designed to assist Government of Canada oceanographers at Fisheries and Oceans Canada by reducing the time spent on repetitive manual review. The system does not process personal information. It is currently in development and AI use is disclosed to its users.

What it collects and what happens to it

Data taken in

About a measurement
Anonymized data
  • Historical and new Conductivity, Temperature, and Depth (CTD) profile sensor scans collected by DFO Pacific Region. Each row represents a physical oceanographic measurement at a given depth; no personal information is involved.

Processing

Classification & Prediction
  • Binary classification of tabular CTD sensor scan rows using Gaussian Mixture Models (for clustering similar data) followed by Multi-Layer Perceptrons (for classifying individual rows within each cluster). The output is a flag indicating deletion or preservation for each row.

What it does

Deciding (Analytical AI)
Human decides
  • The system performs binary classification of CTD sensor scan rows, flagging each for deletion or preservation. Oceanographers review the AI's flags and make final decisions, retaining human expertise in the loop.

Outputs

A recommendation or prediction
Anonymized data
  • A binary flag for each CTD sensor scan row recommending deletion or preservation. Oceanographers review these recommendations and make final quality control decisions; the AI output is advisory, not binding.

Run by

Fisheries and Oceans Canada (DFO)
  • The federal department responsible for developing and deploying this AI-assisted quality control tool for oceanographic CTD data collected in the Pacific Region.

Government of Canada AI Register — entry 2526-DFO-MPO-014

Built by

Government of Canada
  • The Government of Canada developed this AI tool internally. The register lists the developer as the Government of Canada, with no external vendor identified.

Government of Canada AI Register — entry 2526-DFO-MPO-014

Kept for

Not stated by the Helpful Places.

Shared with

Available to the accountable organization
  • Output flags and quality control recommendations are available to Fisheries and Oceans Canada oceanographers and staff who use the tool. Primary users are identified as Government of Canada employees.

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 Algorithmic TransparencyAI use is disclosed to the tool's users (Government of Canada employees). The register entry is publicly accessible, describing the system's purpose, capabilities, and data sources. As this system does not affect members of the public, transparency is directed at its internal GC employee users.
  • Right to a Human ReviewOceanographers retain final decision-making authority over quality control outcomes. The AI flags data for deletion or preservation, but human experts review and confirm these recommendations, ensuring human oversight of all consequential data quality decisions.

Risks and safeguards

No risks or safeguards have been published for this system yet.