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

Rechercher dans les titres et descriptions

Secteur

Programme

Étape

Région

Alignement stratégique

Catégorie d'IA

Sous-catégorie d'IA

Capacité d'IA

Engagement du mandat du premier ministre

Périmètre

Déclarée au SCT En pause

Réinitialiser

198 initiative(s) courante(s)

Registre des initiatives en IA
ID	Initiative en IA	Étape	Description	Secteur	Région	Catégorie d'IA	Expert en la matière
113	Improving forecasting for high-priority ports Non traduit · origine : anglais	Pilote	Research into feasibility of improving accuracy and timeliness of short-term forecasts for coastal regions by combining traditional and AI m...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Automatisation et aide à la décision	Winegardner, Amanda
114	InsightBridge: Executive CSAS Summaries Non traduit · origine : anglais	Pilote	Uses AI to convert complex, technical CSAS reports into concise, plain-language summaries tailored for executive decision-makers. Enhances...	Sciences des écosystèmes et des océans	Région de la capitale nationale	IA cognitive et générative	Winegardner, Amanda
115	PublicLens: Science in Plain Language Non traduit · origine : anglais	Pilote	Leverages AI to transform highly technical scientific and documents into accessible, plain-language summaries for the Canadian public. Foste...	Sciences des écosystèmes et des océans	Région de la capitale nationale	IA cognitive et générative	Winegardner, Amanda
116	BinderBot: A Smart Planning Binder Non traduit · origine : anglais	Pilote	Employs AI-driven extraction to identify and compile the most relevant data from technical documents for the planning binder. Streamlines t...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Automatisation et aide à la décision	Winegardner, Amanda
117	PolyDocs: Format and Translate for CSAS Non traduit · origine : anglais	Production	A modular, bilingually-optimized (EN/FR) application that automates the formatting, quality assurance, and standardization of complex Word d...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Automatisation et aide à la décision	Carr, Kevin
118	Use of artificial intelligence models to facilitate seafloor video annotations in conservation areas. Non traduit · origine : anglais	Pilote	The purpose of this initiative is to utilize AI to facilitate seafloor video annotations collected as part of the MCT and Benthic Ecology pr...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Perception et compréhension	Winegardner, Amanda
119	Computer vision to automate fish data extraction from video Non traduit · origine : anglais	Pilote	Our purpose has been to build a tool to broadly apply computer vision methods in marine research. Our work has generated several publication...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Perception et compréhension	Winegardner, Amanda
120	Characterizing areas of convergence in the Saint John Harbour Non traduit · origine : anglais	Pilote	This project is using a technique called self-organizing maps, which is an unsupervised machine learning algorithm, to identify patterns in...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Automatisation et aide à la décision	Winegardner, Amanda
121	Develop a deep-learning model to age capelin otoliths: application for stock assessment Non traduit · origine : anglais	Pilote	Investigate the utility of applying a deep-learning model developed by the DFO Gulf Region for aging fish otoliths; specifically, to determi...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Automatisation et aide à la décision	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 · origine : anglais	Pilote	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
123	Fish-Habitat Associations Non traduit · origine : anglais	Pilote	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
124	Development of an underwater videography and AI system for studying fish passage effectiveness Non traduit · origine : anglais	Pilote	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
125	Automated Paper Chart Solution Non traduit · origine : anglais	Pilote	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
126	Automated assessment of satellite imagery Non traduit · origine : anglais	Pilote	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
127	Automated assessment of Crowd Source Bathymetry Non traduit · origine : anglais	Pilote	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
128	CICADA (cumulative effects spatial data tool) Phase 2: determining stressor effects and interactions to inform decision-making Non traduit · origine : anglais	Pilote	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
130	Salmon Data Digitization Non traduit · origine : anglais	Pilote	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
132	Salmon Scale Aging Non traduit · origine : anglais	Pilote	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
133	LLM Document Extraction - Prompt Engineering to Retrieve Relevant Information Non traduit · origine : anglais	Pilote	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
134	LLM Document Chatbot Non traduit · origine : anglais	Développement	Large language model that can help users ask questions to document sets and get answers, summarize key information, and find data with citat...	Sciences des écosystèmes et des océans	Région de la capitale nationale	Interaction et engagement	Winegardner, Amanda
135	PII & Sensitivity Scores Non traduit · origine : anglais	Pilote	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
137	Method Recommendation Engine Non traduit · origine : anglais	Pilote	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
144	Factoid Finder Tool Non traduit · origine : anglais	Pilote	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
145	Automatic detection of unidentified fish sounds Non traduit · origine : anglais	Pilote	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
147	Optical Character Recognition Data transcription tool Non traduit · origine : anglais	Pilote	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

113
Improving forecasting for high-priority ports
Research into feasibility of improving accuracy and timeliness of short-term forecasts for coastal regions by combining traditional and AI modelling methods.

Pilote Sciences des écosystèmes et des océans Automatisation et aide à la décision
114
InsightBridge: Executive CSAS Summaries
Uses AI to convert complex, technical CSAS reports into concise, plain-language summaries tailored for executive decision-makers. Enhances leadership understanding and accelerates informed decision-making by providing easily digestible insights. Ensures executives can quickly grasp critical information without sifting through dense documentation.

Pilote Sciences des écosystèmes et des océans IA cognitive et générative
115
PublicLens: Science in Plain Language
Leverages AI to transform highly technical scientific and documents into accessible, plain-language summaries for the Canadian public. Fosters transparency and builds public trust by making scientific and government information easily understandable. Promotes civic engagement by breaking down barriers between experts and everyday Canadians.

Pilote Sciences des écosystèmes et des océans IA cognitive et générative
116
BinderBot: A Smart Planning Binder
Employs AI-driven extraction to identify and compile the most relevant data from technical documents for the planning binder. Streamlines the planning binder process by automatically assembling targeted, information ready for executive review. Saves valuable administrative time and ensures that binder materials are both comprehensive and user-friendly.

Pilote Sciences des écosystèmes et des océans Automatisation et aide à la décision
117
PolyDocs: Format and Translate for CSAS
A modular, bilingually-optimized (EN/FR) application that automates the formatting, quality assurance, and standardization of complex Word documents to meet Government of Canada publishing requirements. The tool orchestrates a highly configurable, low-code assembly line that handles deep document cleanup (resolving fragmented text, localizing punctuation/number conventions, and rebuilding tables of contents), applies localized terminology glossaries, and reduces file sizes for accessibility.

Production Sciences des écosystèmes et des océans Automatisation et aide à la décision
118
Use of artificial intelligence models to facilitate seafloor video annotations in conservation areas.
The purpose of this initiative is to utilize AI to facilitate seafloor video annotations collected as part of the MCT and Benthic Ecology programs in the NL Region. A large number of vidEcosystems and Oceans Science is collected annually, and manual video annotation (e.g., locating and counting observations) is extremely time-consuming. A published “object detection model” (FathomNet Megalodon Detector, YOLOv8x) trained using marine taxa by MBARI is currently being used to identify objects in our seafloor images. The model does not identify the objects (e.g., to species), but it largely accelerates the process given that locating objects is the most time-consuming part of the work.

Pilote Sciences des écosystèmes et des océans Perception et compréhension
119
Computer vision to automate fish data extraction from video
Our purpose has been to build a tool to broadly apply computer vision methods in marine research. Our work has generated several publications illustrating how we built, tested/validated, and applied computer vision methodology to collect / extract / and analyze data pertaining to marine fish in the Newfoundland and Labrador region, from video. For example, we have used it to examine the impact of seismic surveying on commercial fish in the Newfoundland and Labrador offshore. Our continuing purpose is now broadly sharing our system with commercial harvesters (fishermen), non-profit organization (AHOI), government researchers (aquaculture, MPAs, AIS), and academics (computing scientists), to collect and rapidly analyzing video data for a wide range of applications.

Pilote Sciences des écosystèmes et des océans Perception et compréhension
120
Characterizing areas of convergence in the Saint John Harbour
This project is using a technique called self-organizing maps, which is an unsupervised machine learning algorithm, to identify patterns in areas of convergence near the Saint John Harbour. The preliminary analysis suggests that these patterns are related to different environmental conditions such as river discharge and tidal phase. The work has been conducted in collaboration with scientists from the Maritimes Region and is currently on hold.

Pilote Sciences des écosystèmes et des océans Automatisation et aide à la décision
121
Develop a deep-learning model to age capelin otoliths: application for stock assessment
Investigate the utility of applying a deep-learning model developed by the DFO Gulf Region for aging fish otoliths; specifically, to determine the age of capelin in the 2J3KL stock in Newfoundland for use in stock assessments. Otolith aging is currently done visually using a microscope, this proposed method would automate that process to save time and resources, while reducing human error and bias

Pilote Sciences des écosystèmes et des océans Automatisation et aide à la décision
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.

Pilote 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.

Pilote Sciences des écosystèmes et des océans IA cognitive et générative
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.

Pilote 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).

Pilote 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.

Pilote Sciences des écosystèmes et des océans Perception et compréhension
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.

Pilote Sciences des écosystèmes et des océans Automatisation et aide à la décision
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.

Pilote Sciences des écosystèmes et des océans Automatisation et aide à la décision
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.

Pilote Sciences des écosystèmes et des océans Perception et compréhension
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.

Pilote Sciences des écosystèmes et des océans Perception et compréhension
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.

Pilote Sciences des écosystèmes et des océans Automatisation et aide à la décision
134
LLM Document Chatbot
Large language model that can help users ask questions to document sets and get answers, summarize key information, and find data with citations and sourcing.

Développement Sciences des écosystèmes et des océans Interaction et engagement
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.

Pilote Sciences des écosystèmes et des océans Automatisation et aide à la décision
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

Pilote Sciences des écosystèmes et des océans Automatisation et aide à la décision
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.

Pilote Sciences des écosystèmes et des océans IA cognitive et générative
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.

Pilote Sciences des écosystèmes et des océans Perception et compréhension
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.

Pilote Sciences des écosystèmes et des océans Perception et compréhension