Registre des initiatives en IA

Toutes les initiatives inscrites au registre sont consultables ici, sans compte. Chaque fiche montre son avancement, ses jalons et l'historique de ses décisions. Les demandes encore en cours de triage n'y figurent pas : elles rejoignent le registre une fois examinées.

Filtrer 1

Rechercher dans les titres et descriptions

Secteur

Programme

Étape

Région

Alignement stratégique

Catégorie d'IA

Engagement du mandat du premier ministre

Périmètre

Déclarée au SCT En pause

Réinitialiser

146 initiative(s) courante(s)

Registre des initiatives en IA
ID	Initiative en IA	Statut actuel	Description	Secteur	Région	Catégorie d'IA	Expert en la matière
150	Species distribution modeling Non traduit	Pilot	Species distribution models for various coral/sponge/groundfish.	Sciences des écosystèmes et des océans	Région de la capitale nationale	Automatisation et aide à la décision	Winegardner, Amanda
149	Nearshore biotopes model Non traduit	Pilot	Tools built in python to automate image analysis and fish measurement tasks. Applications include a conveyor belt camera and underwater towe...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Perception et compréhension	Winegardner, Amanda
148	Nearshore biotopes model Non traduit	Pilot	Model to define and map nearshore biotope was developed and presented at CSAS Mar 3-4, 2025 - the paper was accepted with revisions but not...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Automatisation et aide à la décision	Winegardner, Amanda
147	Optical Character Recognition Data transcription tool Non traduit	Pilot	This completed project built a proof of concept tool to facilitate data transcription and validation from hand-written field notes. tested...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Perception et compréhension	Winegardner, Amanda
146	Comprehensive marine substrate classification applied to Canada’s Pacific shelf Non traduit	Pilot	This completed project built five regional and one coastwide substrate model for the BC coast using substrate observations and seafloor bath...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Automatisation et aide à la décision	Winegardner, Amanda
145	Automatic detection of unidentified fish sounds Non traduit	Pilot	This completed project used Random Forests and Convolutional Neural Networks (CNN) algorithms trained on manually detected fish sounds to de...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Perception et compréhension	Winegardner, Amanda
144	Factoid Finder Tool Non traduit	Pilot	This completed project used the Factoid Finder extracts text from machine-readable PDFs to create searchable content libraries. Small Langua...	Sciences des écosystèmes et des océans	Région de la capitale nationale	IA cognitive et générative	Winegardner, Amanda
143	Deep sea habitat, organism and object detection and identification. Non traduit	Pilot	Proposing a capstone project to Computer Science students from Camosun College to develop a pipeline for identifying objects and loading the...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Perception et compréhension	Winegardner, Amanda
140	Clustering to characterize extreme marine conditions for the benthic region of the Northeastern Pacific continental margin Non traduit	Pilot	We introduce a method for characterizing extremes that uses machine learning to divide the data into regions with relatively consistent envi...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Automatisation et aide à la décision	Winegardner, Amanda
139	Phytoplankton image classification model Non traduit	Pilot	Create a neural network model to classify phytoplankton images collected by in-situ phytoplankton imaging sensors. There are two discrete s...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Perception et compréhension	Winegardner, Amanda
138	CSAS Knowledge Graph Non traduit	Pilot	Using LLM to extract ontologies and relationships within published CSAS reports into a Graph RAG so that users can visualize and query relat...	Sciences des écosystèmes et des océans	Région de la capitale nationale	IA cognitive et générative	Winegardner, Amanda
137	Method Recommendation Engine Non traduit	Pilot	A large language model reviews a scientist’s objective for collecting data in the field and based on the criteria, the model will provide th...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Automatisation et aide à la décision	Winegardner, Amanda
135	PII & Sensitivity Scores Non traduit	Pilot	Determines the sensitivity of the content of a document based on a trained model and allows for the redaction of the sensitive material in t...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Automatisation et aide à la décision	Winegardner, Amanda
133	LLM Document Extraction - Prompt Engineering to Retrieve Relevant Information Non traduit	Pilot	Using LLM to extract key information from documents with multiple templates using prompt engineering approaches. These results are reviewed...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Automatisation et aide à la décision	Winegardner, Amanda
132	Salmon Scale Aging Non traduit	Pilot	A model using computer vision to look at images of salmon scale and predict the age of salmon and also explain how it arrived at its predict...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Perception et compréhension	Winegardner, Amanda
131	EN/FR Translation Model Non traduit	Pilot	A large language model that is trained on the Translations Bureau’s and DFO's language-characteristics (i.e. grammar, annotation, syntax, wo...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Interaction et engagement	Winegardner, Amanda
130	Salmon Data Digitization Non traduit	Pilot	Digitizing non-machine-readable (handwritten) documents and extracts characters into a digital format so that it is accessible, editable, an...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Perception et compréhension	Winegardner, Amanda
129	Salmon Fence Counting Non traduit	Pilot	A model using computer vision to analyze water stream fence video-footage, to simultaneously count the number of and predict the species of...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Perception et compréhension	Winegardner, Amanda
128	CICADA (cumulative effects spatial data tool) Phase 2: determining stressor effects and interactions to inform decision-making Non traduit	Pilot	Geospatial and machine learning techniques will be applied to determine the overall effect, stress(or) interactions, and relative influences...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Automatisation et aide à la décision	Winegardner, Amanda
127	Automated assessment of Crowd Source Bathymetry Non traduit	Pilot	The Community Hydrography team is working with the University of New Brunswick (UNB) on a tool-kit that will automate the assessment of larg...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Automatisation et aide à la décision	Winegardner, Amanda
126	Automated assessment of satellite imagery Non traduit	Pilot	AI routines are being developed and tested to assess large volume of satellite imagery and data to: i) Automatically Identify marine hazards...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Perception et compréhension	Winegardner, Amanda
125	Automated Paper Chart Solution Non traduit	Pilot	CHS is working closely with software provider CARIS to test and implement automated solution to generate Paper Charts from digital data sour...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Automatisation et aide à la décision	Winegardner, Amanda
124	Development of an underwater videography and AI system for studying fish passage effectiveness Non traduit	Pilot	Designed to train existing DFO tools with information on fish passage effectiveness and develop an SOP for training videography-based AI mod...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Perception et compréhension	Winegardner, Amanda
123	Fish-Habitat Associations Non traduit	Pilot	Extraction of relevant habitat association info and strengths based on vetted literature input to AI for synthesis. Goal to improve equival...	Sciences des écosystèmes et des océans	Région de la capitale nationale	IA cognitive et générative	Winegardner, Amanda
122	Development and testing of artificial intelligence and machine learning to analyze underwater photo and video data to assess marine impacts and resources Non traduit	Pilot	This completed project (2020/21) aimed to utilize machine learning and imaging technology in fisheries science. The proponent planned to use...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Perception et compréhension	Winegardner, Amanda

150
Species distribution modeling
Species distribution models for various coral/sponge/groundfish.

Pilot Sciences des écosystèmes et des océans Automatisation et aide à la décision
149
Nearshore biotopes model
Tools built in python to automate image analysis and fish measurement tasks. Applications include a conveyor belt camera and underwater towed stereo camera system.

Pilot Sciences des écosystèmes et des océans Perception et compréhension
148
Nearshore biotopes model
Model to define and map nearshore biotope was developed and presented at CSAS Mar 3-4, 2025 - the paper was accepted with revisions but not to the methods. The model use sdmTMB to predict species and then use k-means clustering method to find species assemblages. Large datasets can be used.

Pilot Sciences des écosystèmes et des océans Automatisation et aide à la décision
147
Optical Character Recognition Data transcription tool
This completed project built a proof of concept tool to facilitate data transcription and validation from hand-written field notes. tested on ~100 year old salmon observations and present-day salmon stream inspection logs to determine the cost/feasibility/effectiveness of implementing such a tool in Salmon monitoring contexts.

Pilot Sciences des écosystèmes et des océans Perception et compréhension
146
Comprehensive marine substrate classification applied to Canada’s Pacific shelf
This completed project built five regional and one coastwide substrate model for the BC coast using substrate observations and seafloor bathymetry derivatives and oceanographic predictors using Random Forests.

Pilot Sciences des écosystèmes et des océans Automatisation et aide à la décision
145
Automatic detection of unidentified fish sounds
This completed project used Random Forests and Convolutional Neural Networks (CNN) algorithms trained on manually detected fish sounds to detect fish sounds collected on a passive acoustic monitoring project. The result is an easy-to-use, open-source software called FishSoundFinder, implemented with the CNN detector.

Pilot Sciences des écosystèmes et des océans Perception et compréhension
144
Factoid Finder Tool
This completed project used the Factoid Finder extracts text from machine-readable PDFs to create searchable content libraries. Small Language Models are used to implement semantic search techniques, allowing users to search the library for relevant passages within the PDFs.

Pilot Sciences des écosystèmes et des océans IA cognitive et générative
143
Deep sea habitat, organism and object detection and identification.
Proposing a capstone project to Computer Science students from Camosun College to develop a pipeline for identifying objects and loading the results into Biigle for human review.

Pilot Sciences des écosystèmes et des océans Perception et compréhension
140
Clustering to characterize extreme marine conditions for the benthic region of the Northeastern Pacific continental margin
We introduce a method for characterizing extremes that uses machine learning to divide the data into regions with relatively consistent environmental conditions (temperature, oxygen, acidity), and define the extremes based on the historical statistics of variability of each of these fields.

Pilot Sciences des écosystèmes et des océans Automatisation et aide à la décision
139
Phytoplankton image classification model
Create a neural network model to classify phytoplankton images collected by in-situ phytoplankton imaging sensors. There are two discrete steps to this project: 1) create a library of annotated images for model training; 2) creation and refinement of the CNN model.

Pilot Sciences des écosystèmes et des océans Perception et compréhension
138
CSAS Knowledge Graph
Using LLM to extract ontologies and relationships within published CSAS reports into a Graph RAG so that users can visualize and query relationships between researches

Pilot Sciences des écosystèmes et des océans IA cognitive et générative
137
Method Recommendation Engine
A large language model reviews a scientist’s objective for collecting data in the field and based on the criteria, the model will provide the best procedure to use for their work

Pilot Sciences des écosystèmes et des océans Automatisation et aide à la décision
135
PII & Sensitivity Scores
Determines the sensitivity of the content of a document based on a trained model and allows for the redaction of the sensitive material in the document.

Pilot Sciences des écosystèmes et des océans Automatisation et aide à la décision
133
LLM Document Extraction - Prompt Engineering to Retrieve Relevant Information
Using LLM to extract key information from documents with multiple templates using prompt engineering approaches. These results are reviewed by SMEs to ensure accuracy and relevancy.

Pilot Sciences des écosystèmes et des océans Automatisation et aide à la décision
132
Salmon Scale Aging
A model using computer vision to look at images of salmon scale and predict the age of salmon and also explain how it arrived at its prediction.

Pilot Sciences des écosystèmes et des océans Perception et compréhension
131
EN/FR Translation Model
A large language model that is trained on the Translations Bureau’s and DFO's language-characteristics (i.e. grammar, annotation, syntax, words) context. The model’s enables translation to be like those by the Translation Bureau. Training on scientific documents to understand scientific terminology is currently in progress.

Pilot Sciences des écosystèmes et des océans Interaction et engagement
130
Salmon Data Digitization
Digitizing non-machine-readable (handwritten) documents and extracts characters into a digital format so that it is accessible, editable, and useable for analysis.

Pilot Sciences des écosystèmes et des océans Perception et compréhension
129
Salmon Fence Counting
A model using computer vision to analyze water stream fence video-footage, to simultaneously count the number of and predict the species of salmon.

Pilot Sciences des écosystèmes et des océans Perception et compréhension
128
CICADA (cumulative effects spatial data tool) Phase 2: determining stressor effects and interactions to inform decision-making
Geospatial and machine learning techniques will be applied to determine the overall effect, stress(or) interactions, and relative influences of different stresses(ors) on fish metrics such as species occupancy, population status or community status.

Pilot Sciences des écosystèmes et des océans Automatisation et aide à la décision
127
Automated assessment of Crowd Source Bathymetry
The Community Hydrography team is working with the University of New Brunswick (UNB) on a tool-kit that will automate the assessment of large volumes of crowd source data. AI routines will allow for automated QC, and drafting of Navigation Warnings.

Pilot Sciences des écosystèmes et des océans Automatisation et aide à la décision
126
Automated assessment of satellite imagery
AI routines are being developed and tested to assess large volume of satellite imagery and data to: i) Automatically Identify marine hazards and ii) Change detection – i.e. shorelines or riverbank changes.

Pilot Sciences des écosystèmes et des océans Perception et compréhension
125
Automated Paper Chart Solution
CHS is working closely with software provider CARIS to test and implement automated solution to generate Paper Charts from digital data sources. AI routines will improve speed and accuracy of solutions (machine learning) as software is refined to ensure product specifications are respected (as they are used for official navigation).

Pilot Sciences des écosystèmes et des océans Automatisation et aide à la décision
124
Development of an underwater videography and AI system for studying fish passage effectiveness
Designed to train existing DFO tools with information on fish passage effectiveness and develop an SOP for training videography-based AI models in support of fish passage projects.

Pilot Sciences des écosystèmes et des océans Perception et compréhension
123
Fish-Habitat Associations
Extraction of relevant habitat association info and strengths based on vetted literature input to AI for synthesis. Goal to improve equivalency models used in regulatory decisions. Possible partnership with McMaster University.

Pilot Sciences des écosystèmes et des océans IA cognitive et générative
122
Development and testing of artificial intelligence and machine learning to analyze underwater photo and video data to assess marine impacts and resources
This completed project (2020/21) aimed to utilize machine learning and imaging technology in fisheries science. The proponent planned to use Video and Image Analytics for Marine Environments (VIAME), an open-source system developed by NOAA, for two specific purposes: 1. Measure the movement of Atlantic cod across boundaries at the Gilbert Bay Marine Protected Area in Newfoundland and Labrador. 2. Assess the impact of seismic surveying on Atlantic cod as part of a project funded by the Environmental Studies Research Fund (ESRF). The automatic detection and count of fish near MPA boundaries was expected to reduce use of personnel time and effort.

Pilot Sciences des écosystèmes et des océans Perception et compréhension