AI-Powered Search and Extraction for Energy Regulatory Assessments
Inform · Research & Development
What it collects
Operational data
Anonymized data
- Environmental and Socio-economic Assessment (ESA) documents sourced from REGDOCS, the Canada Energy Regulator's public-facing regulatory document repository. These are regulatory submissions related to pipeline projects, covering biophysical, socio-economic, and regional environmental data since 2003. No personal information is involved.
- Run by
- Canada Energy Regulator (CER)
- Where
- No fixed location
- Kept
- Not stated by the Helpful Places.
- Shared with
- Download, Accountable organization
What it is for
Inform
Research & DevelopmentBERDI uses machine learning to extract structured data — tables, figures, keywords, and metadata — from Environmental and Socio-economic Assessment documents submitted to the Canada Energy Regulator since 2003. It makes this information searchable online for both government staff and the general public. The system applies safeguards to identify and exclude culturally sensitive Indigenous Knowledge before publishing extracted content. No personal information is collected or processed.
What it collects and what happens to it
Data taken in
Operational data
Anonymized data
- Environmental and Socio-economic Assessment (ESA) documents sourced from REGDOCS, the Canada Energy Regulator's public-facing regulatory document repository. These are regulatory submissions related to pipeline projects, covering biophysical, socio-economic, and regional environmental data since 2003. No personal information is involved.
Processing
Classification & Prediction
- Machine learning models classify content within PDF documents to extract structured elements (tables, figures, keywords, metadata) and to identify culturally sensitive Indigenous Knowledge for exclusion from the public dataset.
Search & Retrieval
- BERDI provides keyword search and exploratory browsing capabilities over the structured dataset extracted from ESA documents, accessible online at cer-rec.gc.ca/berdi and through the Open Science Data Portal.
What it does
Sensing (Perceptive AI)
Autonomous
- BERDI uses machine learning to read and parse PDF documents, extracting structured data including tables, figures, alignment sheets, keywords, and other metadata from Environmental and Socio-economic Assessment submissions.
Deciding (Analytical AI)
Human decides
- BERDI classifies and flags culturally sensitive Indigenous Knowledge within ESA documents, applying safeguards to identify and exclude this content from the publicly accessible dataset. Downstream curation decisions remain with CER staff.
Understanding (Semantic AI)
Human decides
- BERDI supports targeted keyword searches and exploratory browsing across the extracted ESA dataset, enabling users to find relevant documents and data points by topic or term.
Outputs
Operational data
Anonymized data
- Structured data and metadata extracted from ESA PDF documents, including data tables, figures, alignment sheets, keywords, and document metadata, published to the online BERDI platform and the Open Science Data Portal. Culturally sensitive Indigenous Knowledge is excluded before publication.
Run by
Canada Energy Regulator (CER)
- The Canada Energy Regulator is the federal department that deploys and operates BERDI to provide public access to data from Environmental and Socio-economic Assessments submitted to the regulator.
Built by
Government of Canada
- The Government of Canada developed BERDI internally; no external vendor is identified in the register entry.
Kept for
Not stated by the Helpful Places.
Shared with
Available to download
- The extracted ESA dataset is available online at cer-rec.gc.ca/berdi (English) and cer-rec.gc.ca/ciber (French) and through the Open Science Data Portal, freely accessible to both government employees and the general public.
Available to the accountable organization
- Canada Energy Regulator employees use BERDI internally as a primary user group alongside the public.
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 registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)Government of Canada, Canada Energy Regulator, AI Register entry 2526-CER-REC-003.
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- AI registerCanada AI and Data Use Registry — BERDI (2526-CER-REC-003)
- Register entryPublished by the Helpful Places. Reference 4c0d31e1. 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 Canada Energy Regulator discloses that BERDI is an AI-enabled system. Users are informed of AI use at the point of access. Further information about how the system works can be sought through the Canada Energy Regulator's public communications channels.
- Right to Be Informed of AI UseAI use is disclosed to users. The system is publicly identified as AI-enabled at cer-rec.gc.ca/berdi and through the Government of Canada's AI and Data Use Register.
Risks and safeguards
- Societal & cultural harmMachine learning extraction may fail to correctly identify all culturally sensitive Indigenous Knowledge, potentially exposing content that should remain protected.Safeguard: BERDI applies explicit safeguards to identify and exclude such knowledge from the public dataset before publication; this is a named system capability, though the specific technical method and its accuracy rate are not detailed in the register entry.