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 Weather Forecasting for Meteorological Services

Ecology · Planning & Decision-making

What it collects

About a measurement
Anonymized data
  • Meteorological sensor readings — atmospheric pressure, temperature, humidity, wind speed and direction, precipitation, and satellite observations — ingested as structured numerical data for use in AI weather prediction models.
Operational data
Anonymized data
  • Historical meteorological records, numerical weather prediction model outputs, and reanalysis datasets used to train and validate AI weather models such as GraphCast, ForecastNet, and AIFS.
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

EcologyPlanning & Decision-making

Environment and Climate Change Canada is exploring the use of artificial intelligence models — including GraphCast, ForecastNet, and AIFS — to improve the accuracy and efficiency of weather forecasts produced by the Meteorological Service of Canada. The system affects both government employees who rely on these forecasts in their work and the general public who use MSC weather services. A key transparency point is that AI integration is guided by a published AI Roadmap (2023) that sets out the planned path through 2030, though the models themselves are still under active exploration.

What it collects and what happens to it

Data taken in

About a measurement
Anonymized data
  • Meteorological sensor readings — atmospheric pressure, temperature, humidity, wind speed and direction, precipitation, and satellite observations — ingested as structured numerical data for use in AI weather prediction models.
Operational data
Anonymized data
  • Historical meteorological records, numerical weather prediction model outputs, and reanalysis datasets used to train and validate AI weather models such as GraphCast, ForecastNet, and AIFS.

Processing

Classification & Prediction
  • Machine learning models (including graph neural networks and transformer-based architectures such as GraphCast, ForecastNet, and AIFS) trained on historical atmospheric data to produce short- and medium-range weather forecasts by predicting future atmospheric states from current observations.

What it does

Deciding (Analytical AI)
Human decides
  • AI weather models predict, classify, and score atmospheric states from large volumes of meteorological data, producing forecasts that human meteorologists review and use to make final service decisions. The AI is advisory within MSC's forecasting processes.

Outputs

A recommendation or prediction
Anonymized data
  • Weather forecast outputs — predicted temperature, precipitation, wind, and other atmospheric variables — produced by AI models to inform MSC meteorologists and ultimately the public and government users of MSC services. These are advisory products reviewed by human forecasters before operational use.

Run by

Environment and Climate Change Canada (ECCC)
  • The Meteorological Service of Canada (MSC) and Science & Technology Branch of ECCC are responsible for deploying and operating this AI weather prediction initiative within the Canadian federal government.

Government of Canada AI Register — AI for weather prediction (2526-ECCC-013)

Built by

Not stated by the Helpful Places.

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 Algorithmic TransparencyThe MSC and ECCC have published an AI Roadmap (2023) that describes the strategy for integrating AI into forecasting processes through 2030. The Canadian AI Register entry for this system is publicly accessible at the Government of Canada Open Data portal. Members of the public may consult these documents to understand how AI is being integrated into MSC weather services.
  • Right to Be Informed of AI UseAI-generated weather forecasts and products are disclosed through MSC's public communications and the Government of Canada AI Register. The public has the right to know that AI systems may contribute to the weather forecasts and advisories they receive from Environment and Climate Change Canada.

Risks and safeguards

  • Environmental harmLarge AI weather models such as GraphCast and AIFS require significant compute resources for training and inference, contributing to energy consumption and carbon emissions.Safeguard: The AI Roadmap explicitly cites the exploration of energy-efficient AI weather models as a key objective, aiming to reduce the compute footprint relative to traditional numerical weather prediction while maintaining or improving forecast quality.