AI-Assisted Streamflow Prediction for Hydrological Modelling

Ecology · Research & Development

What it collects

About a measurement

Anonymized data

Streamflow outputs from the WRF-Hydro hydrological model — numerical values representing simulated river flow rates at various locations and time steps. No personal information is involved.

Government of Canada Algorithmic Impact Assessment Registry — 2526-DFO-MPO-016

Operational data

Anonymized data

Observational streamflow data from monitoring stations, used as ground-truth reference data for the neural network to learn the correction mapping between model outputs and real-world measurements.

Government of Canada Algorithmic Impact Assessment Registry — 2526-DFO-MPO-016

Run by: Fisheries and Oceans Canada (DFO)
Where: No fixed location
Kept: Not stated by the Helpful Places.
Shared with: Accountable organization

What it is for

Ecology

Research & Development

This system uses neural networks to improve streamflow simulations produced by the WRF-Hydro hydrological model, correcting its outputs to better match observed river flow data. It acts as a post-processing calibration step used internally by Fisheries and Oceans Canada scientists. The system does not process personal information and is currently in development. Its outputs support environmental planning and fisheries management decisions.

What it collects and what happens to it

Data taken in

About a measurement

Anonymized data

Streamflow outputs from the WRF-Hydro hydrological model — numerical values representing simulated river flow rates at various locations and time steps. No personal information is involved.

Government of Canada Algorithmic Impact Assessment Registry — 2526-DFO-MPO-016

Operational data

Anonymized data

Observational streamflow data from monitoring stations, used as ground-truth reference data for the neural network to learn the correction mapping between model outputs and real-world measurements.

Government of Canada Algorithmic Impact Assessment Registry — 2526-DFO-MPO-016

Processing

Classification & Prediction

A neural network (machine learning model) is applied to post-process and correct the numerical streamflow predictions from the WRF-Hydro physics-based hydrological model, serving as a downstream calibration layer.

Government of Canada Algorithmic Impact Assessment Registry — 2526-DFO-MPO-016

What it does

Deciding (Analytical AI)

Human decides

The neural network post-processes and corrects numerical streamflow outputs from the WRF-Hydro model, producing improved flow predictions. Scientists review and use these corrected outputs for environmental and fisheries planning decisions.

Government of Canada Algorithmic Impact Assessment Registry — 2526-DFO-MPO-016

Outputs

About a measurement

Anonymized data

Post-processed streamflow predictions with improved alignment to observational data — corrected numerical river flow values for use by GC scientists in environmental and fisheries planning. No personal information is produced.

Government of Canada Algorithmic Impact Assessment Registry — 2526-DFO-MPO-016

Run by

Fisheries and Oceans Canada (DFO)

The federal department responsible for developing and deploying this neural network post-processing system for internal hydrological modelling. The system is used by GC employees within the department.

Government of Canada Algorithmic Impact Assessment Registry — 2526-DFO-MPO-016

Built by

Government of Canada

The system was developed internally by the Government of Canada, not by an external vendor.

Government of Canada Algorithmic Impact Assessment Registry — 2526-DFO-MPO-016

Kept for

Not stated by the Helpful Places.

Shared with

Available to the accountable organization

Outputs and model results are available to GC employees within Fisheries and Oceans Canada, used for internal hydrological modelling and research purposes.

Government of Canada Algorithmic Impact Assessment Registry — 2526-DFO-MPO-016

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 TransparencyThis system is disclosed on the Government of Canada's AI and Data Solutions registry. As it is used exclusively by GC employees and does not process personal information, public-facing individual rights such as access or correction do not directly apply. General information about the system is available through the open data registry entry.

Risks and safeguards

No risks or safeguards have been published for this system yet.