AI-Assisted Climate Prediction and Projection Modelling

Research & Development · Planning & Decision-making

What it collects

Operational data

Anonymized data

Output from the CRD Earth System Climate Model — gridded geophysical variables (temperature, pressure, wind, precipitation, etc.) representing simulated climate states. No personal information is involved. This is model output data used as training and inference input for the AI emulator.

Run by: Environment and Climate Change Canada (ECCC)
Where: No fixed location
Kept: Retained Not specified in the register entry
Shared with: Accountable organization
Your copy: You cannot see the data it holds about you. What you can do

What it is for

Research & Development

Planning & Decision-making

Environment and Climate Change Canada is exploring AI-powered climate emulators to expand the size of climate model ensembles, helping scientists better understand natural climate variability. The system uses a spherical Fourier neural operator (SFNO) architecture currently in deterministic form, with plans to evolve toward probabilistic outputs. It is currently in development and is used exclusively by Government of Canada employees; it does not involve any personal information.

What it collects and what happens to it

Data taken in

Operational data

Anonymized data

Output from the CRD Earth System Climate Model — gridded geophysical variables (temperature, pressure, wind, precipitation, etc.) representing simulated climate states. No personal information is involved. This is model output data used as training and inference input for the AI emulator.

Processing

Classification & Prediction

The SFNO (Spherical Fourier Neural Operator) architecture emulates Earth system model outputs, predicting climate states across time steps. Currently deterministic; planned adaptation to probabilistic form to capture uncertainty in climate projections.

What it does

Deciding (Analytical AI)

Human decides

The SFNO-based climate emulator operates in deterministic mode, producing climate state predictions and projections from model inputs. Outputs inform scientific interpretation; GC scientists decide how to act on the results. Probabilistic capability is planned but not yet deployed.

Outputs

About a measurement

Anonymized data

Emulated climate state outputs (gridded geophysical variables) forming additional ensemble members for climate predictions and projections. These outputs are used to better quantify climate internal variability. No personal information is produced.

A recommendation or prediction

Anonymized data

Ensemble-expanded climate predictions and projections provided to GC scientists as advisory scientific outputs. Researchers use these to inform their interpretation of climate variability; no binding decisions are made automatically by the system.

Run by

Environment and Climate Change Canada (ECCC)

The Canadian federal department responsible for weather forecasting, environmental monitoring, and climate science. ECCC's Canadian Centre for Climate Modelling and Analysis (CCCma) is exploring and developing this AI climate emulator system.

GC AI Register — 2526-ECCC-012

Built by

Allen Institute for AI

The ACE2 Climate Emulator, developed by the Allen Institute for AI, is the open-source model being evaluated for adaptation. ECCC is not using a commercial vendor; the system is open-source and under in-house adaptation.

GC AI Register — 2526-ECCC-012

Kept for

Retained Not specified in the register entry

The register does not specify a retention period for model outputs or input datasets. CRD Earth System Climate Model Output is scientific data; standard GC scientific data retention practices are assumed to apply.
Duration: Not specified in the register entry

Shared with

Not available to me

The system outputs are restricted to Government of Canada employees (GC scientists at CCCma). Members of the public do not have access to the system or its outputs.

Available to the accountable organization

Output data and system access are available to Environment and Climate Change Canada (specifically CCCma) GC employees who are the primary users of the system.

Stored

Stored locally

As a Government of Canada departmental system operated by ECCC/CCCma, data is expected to be stored within Canadian federal government infrastructure. The register does not specify the storage environment explicitly.
Duration: Not specified

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 underlying ACE2 Climate Emulator model is open-source, and ECCC has disclosed this system in the Government of Canada's public AI Register. GC employees and the public can consult the AI Register entry for information about this system's purpose and approach.
Right to Be Informed of AI UseThe system does not process personal information and is used only by GC scientists internally. Its existence is disclosed publicly via the Government of Canada AI Register. No individual citizen is subject to decisions made by this system.

Risks and safeguards

Reputational harmEmulator outputs used to inform climate policy could be misinterpreted or over-relied upon, potentially affecting institutional credibility if projections are inaccurate.Safeguard: The system is currently in development; outputs are advisory and reviewed by trained GC climate scientists. The open-source foundation (ACE2) allows peer scrutiny. Transition to probabilistic form will explicitly communicate uncertainty.