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 Annual Crop Mapping for Canadian Agriculture

Ecology · Planning & Decision-making · Research & Development

What it collects

About a measurement
Anonymized data
  • Multispectral and synthetic-aperture radar (SAR) readings from open-source Earth observation satellites, including imagery capturing spectral reflectance of land surfaces used to distinguish crop types.
About a place
Anonymized data
  • Geographic locations and land parcel boundaries across Canada, used as spatial reference for assigning crop-type classifications to map pixels.
Operational data
Anonymized data
  • Field survey data and crop databases providing ground-truth labels used to train and validate the machine-learning classification models.
Run by
Agriculture and Agri-Food Canada (AAFC)
Where
No fixed location
Kept
Retained indefinitely (annual map layers published since 2009 remain publicly available)
Shared with
Accountable organization, Download

What it is for

EcologyPlanning & Decision-makingResearch & Development

Every year since 2009, Agriculture and Agri-Food Canada uses machine-learning analysis of satellite imagery and field data to produce a detailed map showing what crops are growing across Canada. The map is publicly available and is used by government and researchers to track land use and environmental change over time. No personal information is collected or used. The system's use of AI is not currently disclosed to the public at the point of access.

What it collects and what happens to it

Data taken in

About a measurement
Anonymized data
  • Multispectral and synthetic-aperture radar (SAR) readings from open-source Earth observation satellites, including imagery capturing spectral reflectance of land surfaces used to distinguish crop types.
About a place
Anonymized data
  • Geographic locations and land parcel boundaries across Canada, used as spatial reference for assigning crop-type classifications to map pixels.
Operational data
Anonymized data
  • Field survey data and crop databases providing ground-truth labels used to train and validate the machine-learning classification models.

Processing

Classification & Prediction
  • Machine learning classifiers assign a crop-type label (e.g. canola, wheat, corn, pasture) to each spatial unit across Canada, drawing on satellite spectral signatures and training data from field surveys and crop databases.

What it does

Sensing (Perceptive AI)
Human decides
  • The system applies machine learning to Earth observation satellite imagery to detect and classify crop types across Canada, transforming raw pixels into structured crop-cover labels on an annual basis.
Deciding (Analytical AI)
Human decides
  • Classification and prediction models assign a crop-type label to each pixel or land parcel, producing a nationwide thematic map. Human experts review and validate outputs before publication.

Outputs

About a place
Anonymized data
  • A nationwide geospatial map layer assigning a crop-type classification to each parcel or pixel across Canada, published annually as an open dataset. The output contains no personal information.
Operational data
Anonymized data
  • Aggregated land-use metrics and time-series statistics on agricultural land cover change, used for sustainability reporting, policy development, and government programming.

Run by

Agriculture and Agri-Food Canada (AAFC)
  • Agriculture and Agri-Food Canada (AAFC) is the federal government department that deploys and operates the Annual Crop Inventory Map system, making the outputs available as open data since 2009.

Annual Crop Inventory Map — Government of Canada Algorithmic Impact Assessment Register

Built by

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

Annual Crop Inventory Map — Government of Canada Algorithmic Impact Assessment Register

Kept for

Retained indefinitely (annual map layers published since 2009 remain publicly available)
  • Annual map outputs are retained and made available as a longitudinal open dataset. The register does not specify a formal deletion schedule; layers appear to be kept indefinitely to support time-series analysis.
  • Duration: indefinitely (annual map layers published since 2009 remain publicly available)

Shared with

Available to the accountable organization
  • Agriculture and Agri-Food Canada has full access to the map outputs for internal policy, sustainability reporting, and programming purposes.
Available to download
  • The Annual Crop Inventory Map is one of AAFC's most downloaded open datasets, freely available to the public and researchers via the Open Canada data portal.

Stored

Stored on 3rd Party Cloud
  • The register does not specify the storage infrastructure. Given that the outputs are served via the Open Canada data portal, cloud or government-managed hosting is assumed. Storage jurisdiction is not disclosed.
  • Duration: indefinitely
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 register records that AI use is not currently disclosed to users at the point of access. Members of the public may consult the Government of Canada's Algorithmic Impact Assessment register entry (AI Register ID: 2526-AAFC-AAC-003) for information about how machine learning is used to produce the map.

Risks and safeguards

  • Civil liberties harmThe system does not involve personal information; however, the lack of disclosure to users that AI is in use limits informed public oversight.Safeguard: The register entry and open dataset documentation provide transparency for those who seek it. No personal or civil-liberty impact is identified in the register, as outputs are land-use maps with no individual-level data.