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-Powered Land and Infrastructure Feature Extraction from Satellite Imagery

Ecology · Planning & Decision-making · Research & Development

What it collects

About a place
Anonymized data
  • Multi-modal satellite and aerial imagery covering Canada's land surface, used as the primary runtime input for feature extraction. The training dataset also includes NRCan-owned digitized vector information.

Government of Canada AI Register — CCMEO GeoAI Factory and GeoAI Data Series

Run by
Natural Resources Canada (NRCan)
Where
No fixed location
Kept
Not stated by the Helpful Places.
Shared with
Accountable organization

What it is for

EcologyPlanning & Decision-makingResearch & Development

This system uses artificial intelligence to automatically extract geographic features — buildings, roads, waterways, and forested areas — from satellite and aerial imagery across Canada over time. It is operated by Natural Resources Canada and primarily serves federal government employees who need up-to-date geospatial data about Canada's land, water, and infrastructure. The AI's use is disclosed to users, and outputs are used to improve authoritative mapping of Canada.

What it collects and what happens to it

Data taken in

About a place
Anonymized data
  • Multi-modal satellite and aerial imagery covering Canada's land surface, used as the primary runtime input for feature extraction. The training dataset also includes NRCan-owned digitized vector information.

Government of Canada AI Register — CCMEO GeoAI Factory and GeoAI Data Series

Processing

Computer Vision
  • The system uses computer vision techniques applied to multi-modal satellite and aerial imagery to automatically detect and delineate buildings, roads, hydrographic features, and forested areas.
Classification & Prediction
  • Classifies image pixels and regions into geographic feature categories (building, road, water body, forest) based on patterns learned from labeled training data.

What it does

Sensing (Perceptive AI)
Autonomous
  • The system interprets multi-modal satellite and aerial imagery to detect and extract structured geospatial features such as buildings, roads, waterways, and forested areas without manual review of each image.
Deciding (Analytical AI)
Human decides
  • The system classifies and scores image regions to identify land cover and infrastructure feature types, producing structured outputs that GC employees use to inform mapping decisions.

Outputs

About a place
Anonymized data
  • Extracted geospatial vector data representing buildings, roads, hydrographic features, and forested areas across Canada, delivered as the GeoAI Data Series for use in authoritative mapping products.

Government of Canada AI Register — CCMEO GeoAI Factory and GeoAI Data Series

Run by

Natural Resources Canada (NRCan)
  • Natural Resources Canada's Canada Centre for Mapping and Earth Observation (CCMEO) deploys and operates this AI system to produce authoritative geospatial data about Canada's land, water, and infrastructure.

Government of Canada AI Register — CCMEO GeoAI Factory and GeoAI Data Series

Built by

Government of Canada
  • The system was developed internally by the Government of Canada, with no external vendor identified in the register entry.

Government of Canada AI Register — CCMEO GeoAI Factory and GeoAI Data Series

Kept for

Not stated by the Helpful Places.

Shared with

Available to the accountable organization
  • Outputs are available to Government of Canada employees, primarily those at Natural Resources Canada who use the geospatial data for mapping and earth observation purposes.

Stored

Stored locally
  • As a Government of Canada system operated by Natural Resources Canada, data is expected to be stored within Canadian federal government infrastructure, consistent with Government of Canada data residency requirements.
  • Duration: Not specified in register
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 TransparencyThe Government of Canada discloses the use of AI in this system on its public AI register. Users are informed that AI is used to extract geospatial features from satellite and aerial imagery. Further information is available through Natural Resources Canada.
  • Right to Be Informed of AI UseThe Government of Canada confirms that AI use is disclosed to users of this system. The system appears in the public Government of Canada AI register, enabling Canadians to be informed about its existence and operation.

Risks and safeguards

  • Reputational harmAutomated extraction of geographic features could mis-classify or omit features, leading to inaccurate authoritative maps that misrepresent ownership, land use, or infrastructure. The system is used by GC employees who can review and correct outputs before they become authoritative, and the GeoAI Data Series is versioned over time to allow for correction.