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

AI-Assisted Powdery Mildew Detection for Crops

Ecology · Healthcare

What it collects

Biometric
Anonymized data
  • Plant images submitted by users, showing leaf surfaces or other plant parts exhibiting potential fungal symptoms. No human biometric data is involved; the 'body' here is plant tissue.
Operational data
Anonymized data
  • Scientific research papers on powdery mildew used to inform or train the model. These are non-personal operational data sources that establish the scientific basis for disease classification.
Run by
Agriculture and Agri-Food Canada (AAFC)
Where
No fixed location
Kept
Not stated by the Helpful Places.
Shared with
Not stated by the Helpful Places.
Your copy
You cannot see the data it holds about you. What you can do

What it is for

EcologyHealthcare

This system uses artificial intelligence and image recognition to help farmers, gardeners, and agricultural workers identify powdery mildew — a fungal disease that reduces crop quality and yield. Users upload plant images through a web application, and the AI analyses them to flag potential disease and support management decisions. The system is currently in development at Agriculture and Agri-Food Canada and does not collect personal information.

What it collects and what happens to it

Data taken in

Biometric
Anonymized data
  • Plant images submitted by users, showing leaf surfaces or other plant parts exhibiting potential fungal symptoms. No human biometric data is involved; the 'body' here is plant tissue.
Operational data
Anonymized data
  • Scientific research papers on powdery mildew used to inform or train the model. These are non-personal operational data sources that establish the scientific basis for disease classification.

Processing

Computer Vision
  • Computer vision and image recognition algorithms analyse plant photographs to detect visual signatures of powdery mildew infection on leaf and stem surfaces.
Classification & Prediction
  • A machine learning classification model assigns a disease-present or disease-absent label to each submitted image, potentially with a confidence score, based on learned visual patterns from training data.

What it does

Sensing (Perceptive AI)
Human decides
  • The system senses plant imagery submitted by users, converting raw photos into structured disease detections for downstream analysis. A human ultimately decides on disease management actions.
Deciding (Analytical AI)
Human decides
  • A machine learning algorithm classifies submitted plant images to predict the presence or absence of powdery mildew. The result advises the user; a human decides on treatment.

Outputs

A recommendation or prediction
Anonymized data
  • The system produces a disease detection result — a prediction of whether powdery mildew is present — and supports informed decision-making for disease management. The output is advisory; no binding decision is made automatically.

Run by

Agriculture and Agri-Food Canada (AAFC)
  • The federal department responsible for deploying and developing this AI system to support disease detection in Canadian agriculture.

GC AI Register — 2526-AAFC-AAC-008

Built by

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

GC AI Register — 2526-AAFC-AAC-008

Kept for

Not stated by the Helpful Places.

Shared with

Not available to me
  • The register states that no personal information is collected by this system. As a result, there is no personal data for individuals to access about themselves.

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 Be Informed of AI UseUsers are informed that AI is in use within the web application. The register confirms that AI use is disclosed to users.
  • Right to Algorithmic TransparencyThe system's capabilities are publicly documented in the Government of Canada's AI Register, including the use of computer vision, image recognition, and machine learning to detect plant disease.

Risks and safeguards

  • Reputational harmRisk of false positives or false negatives in disease detection leading to unnecessary or missed treatments, causing economic harm to farmers.Safeguard: the system is framed as a decision-support tool requiring human confirmation; AI use is disclosed to users. The system is currently in development, allowing for accuracy refinement before wider deployment.