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-Automated Classification of LiDAR Aerial Survey Data

Ecology · Planning & Decision-making

What it collects

About a measurement
Anonymized data
  • Airborne LiDAR point cloud data collected across Canada — three-dimensional geometric measurements of the land surface and above-ground features captured by aircraft-mounted laser sensors. No personal information is present in this data.
About a place
Anonymized data
  • Geographic extent and spatial coordinates of the LiDAR survey areas, representing land surface locations across Canada used to contextualise point cloud classification.
Run by
Natural Resources Canada (NRCan)
Where
No fixed location
Kept
Not stated by the Helpful Places.
Shared with
Accountable organization
Your copy
You cannot see the data it holds about you. What you can do

What it is for

EcologyPlanning & Decision-making

This system automatically classifies points in airborne LiDAR point cloud data collected across Canada, identifying features such as buildings, ground surfaces, water bodies, and other landscape elements. It is used internally by Government of Canada employees at Natural Resources Canada to support geospatial data production. The public is not directly affected by this system's outputs, though the resulting geospatial datasets underpin mapping products used by many downstream users. The use of AI in this workflow is not disclosed to end users of the resulting data products.

What it collects and what happens to it

Data taken in

About a measurement
Anonymized data
  • Airborne LiDAR point cloud data collected across Canada — three-dimensional geometric measurements of the land surface and above-ground features captured by aircraft-mounted laser sensors. No personal information is present in this data.
About a place
Anonymized data
  • Geographic extent and spatial coordinates of the LiDAR survey areas, representing land surface locations across Canada used to contextualise point cloud classification.

Processing

Classification & Prediction
  • A trained machine learning model classifies each point in the LiDAR point cloud into feature categories — buildings, ground, surface water, and other features — based on geometric and contextual attributes of the points.

What it does

Sensing (Perceptive AI)
Human executes
  • The system senses and structures raw LiDAR point cloud data by classifying each point into a feature category (building, ground, water, other). GC production teams then use the classified output in downstream geospatial workflows.
Deciding (Analytical AI)
Human executes
  • The trained model predicts a classification label for each point in the LiDAR point cloud, assigning it to a category such as building, ground, surface water, or other features based on learned patterns from training data.

Outputs

About a place
Anonymized data
  • Classified LiDAR point cloud datasets and derived geospatial products in which each point is labelled with a feature category (building, ground, surface water, other), used by GC production teams to generate national-scale geospatial data products.
About a measurement
Anonymized data
  • Per-point classification labels and associated confidence or quality metrics derived from the LiDAR point cloud, representing structured numerical outputs of the classification model.

Run by

Natural Resources Canada (NRCan)
  • Natural Resources Canada (NRCan) is the federal department responsible for deploying and operating this AI system to support airborne LiDAR data classification and geospatial product production.

Government of Canada AI Register — 2526-NRCan-RNCan-008

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 — 2526-NRCan-RNCan-008

Kept for

Not stated by the Helpful Places.

Shared with

Available to the accountable organization
  • Classified LiDAR outputs and derived products are available to Natural Resources Canada production teams and Government of Canada employees who use them in geospatial workflows.
Not available to me
  • The AI classification outputs themselves are not directly available to members of the public. While downstream geospatial data products may be publicly available, the system's AI-generated classifications are not disclosed as such to end users.

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 TransparencyThe use of AI in this workflow is not currently disclosed to users of the resulting geospatial data products (the register records AI use disclosed to users as 'N'). Members of the public may submit Access to Information requests to Natural Resources Canada for information about how this system works. Contact: atip-aiprp@nrcan-rncan.gc.ca

Risks and safeguards

  • Reputational harmMisclassification of LiDAR points (e.g., incorrectly labelling buildings as ground or vice versa) could propagate errors into downstream geospatial products used in planning, infrastructure, and resource management decisions, potentially affecting public trust in national mapping data.Safeguard: The framework includes documentation and indications to improve models if required, and knowledge transfer to production teams who can review and correct outputs before they enter production datasets.