AI-Powered Sea-Ice Forecasting for Arctic Shipping Safety
Safety & Security · Mobility
What it collects
About a measurement
Anonymized data
- Sea-ice model output and observational data from Arctic waters, combined in a manner analogous to weather forecasting. Includes sensor and satellite-derived measurements of ice extent and conditions. No personal information is involved.
Operational data
Anonymized data
- Sea-ice model simulation outputs used as background fields for the forecasting system, in the absence of high-spatial-resolution weather forecasting data during advance tactical planning.
- Run by
- National Research Council Canada (NRC)
- Where
- No fixed location
- Kept
- Not stated by the Helpful Places.
- Shared with
- Accountable organization, 3rd parties
What it is for
Safety & Security
MobilityThis system uses artificial intelligence to produce daily seasonal forecasts of sea-ice conditions in the Canadian Arctic, helping shipping operators plan safe voyages through ice-covered waters. Forecasts are integrated into the Canadian Arctic Shipping Risk Assessment System (CASRAS) and made available to both government employees and the public. No personal information is collected or used. The Government of Canada discloses that this tool is AI-powered.
What it collects and what happens to it
Data taken in
About a measurement
Anonymized data
- Sea-ice model output and observational data from Arctic waters, combined in a manner analogous to weather forecasting. Includes sensor and satellite-derived measurements of ice extent and conditions. No personal information is involved.
Operational data
Anonymized data
- Sea-ice model simulation outputs used as background fields for the forecasting system, in the absence of high-spatial-resolution weather forecasting data during advance tactical planning.
Processing
Classification & Prediction
- SIFNET uses AI methods to generate seasonal forecasts of sea-ice presence, combining sea-ice model output with observational data through learned statistical relationships, analogous to numerical weather prediction techniques.
What it does
Deciding (Analytical AI)
Human decides
- The system predicts and scores sea-ice presence conditions across spatial grids, producing seasonal forecasts used by shipping operators and risk assessment tools. Human operators review forecasts and make final navigation and routing decisions.
Outputs
About a measurement
Anonymized data
- Daily SIFNET sea-ice presence forecast products covering the Canadian Arctic, integrated into CASRAS and made available to external stakeholders as of 2023. Outputs are aggregate environmental measurements with no personal identifiers.
A recommendation or prediction
Anonymized data
- Seasonal sea-ice forecasts serve as advisory inputs into the Canadian Arctic Shipping Risk Assessment System (CASRAS), enabling shipping operators and planners to assess route viability and risk. Final routing decisions remain with human operators.
Run by
National Research Council Canada (NRC)
- Federal department responsible for deploying and operating the sea-ice forecasting system, integrating SIFNET forecast products into the existing NRC-OCRE tool CASRAS and making updates available to external stakeholders.
Built by
University of Waterloo
- Academic co-developer of the AI-based sea-ice forecasting system, partnering with NRC to build the prototype and production SIFNET model using artificial intelligence methods.
Kept for
Not stated by the Helpful Places.
Shared with
Available to the accountable organization
- SIFNET forecast products are integrated into the NRC-OCRE CASRAS tool and available to NRC employees and other government users for operational planning.
Available to 3rd parties
- CASRAS updates, including SIFNET forecasts, have been made available to external stakeholders such as shipping operators and Arctic navigators as of 2023.
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.
- AI registerGovernment of Canada Algorithmic Impact Assessment — AI-based sea-ice presence forecasting model (2526-NRC-CNRC-022)National Research Council Canada, AI Register entry 2526-NRC-CNRC-022.
- AI registerGovernment of Canada AI Register — 2526-NRC-CNRC-022
- AI registerGovernment of Canada AI Register — 2526-NRC-CNRC-022
- AI registerGovernment of Canada AI Register — 2526-NRC-CNRC-022
- AI registerGovernment of Canada AI Register — 2526-NRC-CNRC-022
- AI registerGovernment of Canada AI Register — 2526-NRC-CNRC-022
- AI registerGovernment of Canada AI Register — 2526-NRC-CNRC-022
- AI registerGovernment of Canada AI Register — 2526-NRC-CNRC-022
- AI registerGovernment of Canada AI Register — 2526-NRC-CNRC-022
- AI registerGovernment of Canada AI Register — 2526-NRC-CNRC-022
- AI registerGovernment of Canada AI Register — 2526-NRC-CNRC-022
- AI registerGovernment of Canada AI Register — 2526-NRC-CNRC-022
- AI registerGovernment of Canada AI Register — 2526-NRC-CNRC-022
- AI registerGovernment of Canada AI Register — 2526-NRC-CNRC-022
- AI registerGovernment of Canada AI Register — 2526-NRC-CNRC-022
- AI registerGovernment of Canada AI Register — 2526-NRC-CNRC-022
- Register entryPublished by the Helpful Places. Reference e20d36ac. This disclosure was drafted with AI assistance.Schema: ai@2026-05-06-beta
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 that this tool is AI-powered and that it produces sea-ice forecasts using artificial intelligence methods. The system is listed on the public Government of Canada AI Register. For more information about how the system works, contact the National Research Council Canada.
- Right to Be Informed of AI UseUsers of CASRAS and external stakeholders are informed that sea-ice forecasts are produced by an AI system (SIFNET). The Government of Canada's AI Register publicly discloses AI use for this system.
Risks and safeguards
- Physical harmInaccurate sea-ice forecasts could lead shipping operators to underestimate ice hazards, potentially resulting in vessel damage, grounding, or loss of life in remote Arctic waters.Safeguard: SIFNET forecasts are integrated into CASRAS as advisory inputs rather than binding commands; human operators retain decision authority over routing. Forecasts are produced daily to maximize timeliness and accuracy, and the system builds on scientific co-development with the University of Waterloo to ensure state-of-the-art methods.