Projets novateurs réalisés

Outil d’aide à la décision pour réduire les émissions de gaz des installations de production d’œufs du Québec

Pour répondre aux nouvelles exigences des consommateurs, l’industrie ovocole vise à modifier la façon de produire en transitant des systèmes de cages traditionnelles vers des systèmes de logement alternatifs, tels que les cages enrichies et les volières. Ce changement, bien qu’avantageux pour le bien-être animal, complique la gestion de la qualité de l’air en raison des facteurs interdépendants influençant les émissions tels la ventilation, les variables environnementales, ainsi que la gestion de la litière et du fumier. Cette complexité nécessite des stratégies robustes pour atteindre la neutralité carbone tout en maintenant la santé animale et humaine.
Ce projet vise à développer un prototype d’outil d’aide à la décision pour les installations de production d’œufs du Québec afin de réduire les gaz à effet de serre (GES), l’ammoniac (NH3), les particules fines (PM) et les bioaérosols. Dans un premier temps, les outils existants tels que Comet-farm, ALFAM2 et DATAMAN seront étudiés tout en sachant bien que ces outils ne soient pas axés sur l’industrie des œufs. Les étudier aidera à comprendre comment ils estiment les GES et le NH3 en fonction des caractéristiques spécifiques du système de production.

Collaborer pour une gestion circulaire et durable des eaux usées

Divers types organisations doivent de plus en plus travailler ensemble pour résoudre des problèmes mondiaux et
locaux. Cependant, des divergences d’opinions et de secteur d’activité peuvent rendre cette collaboration difficile.
Ce projet de recherche, en partenariat avec La Serre+, a pour objectif de comprendre, par une analyse historique
de la démarche, comment différents groupes peuvent travailler efficacement ensemble pour gérer les eaux usées
en utilisant les principes de l’économie circulaire, c’est-à-dire réemployer les rejets de manière bénéfique.
Faire un bilan de l’initiative de La Serre+, en tirer des leçons et documenter son évolution permettra de développer
des cadres de travail flexible qui pourront être utilisés pour guider d’autres projets de collaboration, non seulement
au Québec, mais aussi ailleurs. En résumé, ce projet pourrait avancer des recommandations à partir des leçons
tirées, en proposant une feuille de route de projet pluripotent multidisciplinaire et porté par plus de 10 partenaires.

Light and Darkness in Counter-Reformation Painting of Repentance

In the late sixteenth century, a distinctive Italian painting style emerged, characterized by the contrast of light and darkness, known as chiaroscuro. While this artistic development is often seen as a stylistic or optical advancement, My PhD dissertation argues that the light-dark interplay in Italian Counter-Reformation paintings, especially those showing a repentant figure, has deep theological and intellectual roots. Grounded in the writings on repentance, these paintings were meant to engage viewers and encourage their own repentance. The study will explore how the spirituality that emerged during the Counter-Reformation influenced the use of light and darkness, focusing on painters who incorporated these ideas and examining evidence of audience responses. This thesis will argue that without this theological context, our understanding of the era’s painting style and light manipulation would be incomplete.

PCBA AI Testing

Price Electronics, a leader in the design and manufacturing of commercial-grade HVAC products, also operates as an Electronics Manufacturing Services (EMS) provider, producing electronic components for a variety of industries. A critical aspect of their production process is the testing and verification of Printed Circuit Board Assemblies (PCBAs), which currently relies heavily on manual inspection. This manual process is not only time-consuming but also prone to human error, which can compromise the quality of the final product.

To address these challenges, Price Electronics seeks to implement an AI-driven solution that automates the PCBA testing process. By leveraging machine learning and advanced imaging techniques, the company aims to enhance the accuracy and efficiency of its testing procedures. This project will introduce a cost-effective, automated system that uses cameras to capture images of PCBAs and verify their quality based on pre-defined criteria. The system will be trained to detect defects and ensure that all components, such as LEDs, function correctly.

This initiative is crucial for Price Electronics to maintain its high standards of quality while scaling its production capabilities. The automated system will not only reduce labor costs but also ensure that every product meets stringent quality requirements, thereby minimizing returns and enhancing customer satisfaction.

Development of Advanced Machine Learning and Artificial Intelligence Models in an Open Cloud-Based Platform to Accelerate Drug Discovery (AIRCHECK)

The Artificial Intelligence Ready CHEmiCal Knowledgebase (AIRCHECK) is an open platform developed to share and analyze large-scale, freely accessible chemical activity data. AIRCHECK is specifically designed to integrate high-throughput chemical screens data generated from DNA-encoded libraries (DEL) and Affinity Selection Mass-Spectrometry (ASMS). AIRCHECK aims to become a global platform that advances Machine Learning (ML) and artificial intelligence (AI) in drug discovery through open collaboration across academia and industry. The goal is to create a dynamic, inclusive, and collaborative community that accelerates innovation in chemical biology through the availability of analysis-ready datasets and open-source AI models that are transparent, reproducible, and reusable. To support researchers worldwide, AIRCHECK aims to offer resources (data and computation) and host workshops, webinars, and competitions to become a cornerstone for collaborative drug discovery and a way to open science in chemical biology.
The Structural Genomics Consortium (SGC) supports the project by contributing its expertise in data curation, standardization, and fostering open science collaborations between academia and industry. SGC plays a key role in ensuring the quality and accessibility of the datasets integrated into AIRCHECK.
This proposal seeks to enhance AIRCHECK by improving data management strategies, standardizing DEL and ASMS datasets, and developing machine learning models with benchmark datasets. We will focus on building novel algorithms for large-scale chemical screening and a Machine Learning Operations (MLOps) framework to streamline data ingestion, model development, testing, and deployment, enabling collaborators to focus on advancing ML/AI techniques without the complexities of managing the research lifecycle.

Novel next-generation large diameter fiber reinforced polymer piping

This project addresses the significant demand for composite piping capable of withstanding elevated temperatures and/or pressure in water service and oil and gas transportation. In collaboration with Flexpipe at Mattr Infrastructure Technologies, we aim to develop rapid testing methods for designing and manufacturing large-diameter spoolable fiber-reinforced composite piping. Our focus is on exploring alternative procedures that are safe, efficient, cost-effective, and ensure high quality. This initiative is vital for our industrial partner and for Canada because: (1) There is an increasing need to enhance the cost-effectiveness and efficiency of fabrication and testing methods in key sectors such as oil and gas. (2) There is currently a lack of comprehensive understanding regarding the long-term performance of commercially available multilayer composite pipe in specific applications, such as linepipe for oil, gas, and water. (3) There are opportunities to transfer knowledge to other Canadian organizations facing similar technological challenges, specifically the use of durable fiber-reinforced composite materials in harsh environments.

Implementing and Testing of Additively Manufactured High-Temperature Ceramics in Hydrogen Production Reactors

THIS IS A GENERIC TEXT PUT IN PLACE AS THERE WAS NO PROJECT OVERVIEW

Partenariat intersectoriel pour une transition écoresponsable en logistique des soins et des services de santé

Ce projet marque la première phase d’un programme visant à réduire l’impact environnemental des établissements de santé. Ces derniers sont d’importants contributeurs aux émissions de gaz à effet de serre, un domaine encore peu exploré par la recherche académique mais crucial pour la transition écologique et la responsabilité sociétale.
Il se concentre sur l’analyse approfondie des flux logistiques des médicaments et produits de santé, ainsi que la gestion des déchets médicaux, afin de mettre en lumière la pertinence et la nécessité de développer des solutions innovantes et écoresponsables. Les objectifs spécifiques incluent l’identification des prérequis pour une chaîne logistique éco-responsable, la définition des pratiques exemplaires en gestion des flux et la proposition de stratégies adaptées aux spécificités des établissements de santé.
Les stagiaires doctoraux s’immergeront tôt dans la recherche appliquée et théorique, renforçant leurs capacités par le développement de nouvelles avenues de recherche et de compétences en méthodologie et modélisation mathématique.

Building efficiencies and expanding the reach of training curriculum for cell & gene therapies biomanufacturing

The Canadian Advanced Therapies Training Institute (CATTI), is filling the shortage of qualified, job-ready talent by developing and scaling e-learning and on-site GMP training programs for cell and gene therapies (CGT) production to rapidly upskill the biomanufacturing workforce in Canada and internationally. Using industry-focused best practices for competency based demonstration of acquired skills in operating under aseptic conditions, CATTI is ensures the CGT manufacturing talent is worksite ready. Currently, CATTI develops and deploys training at its host site at the University of Guelph: a dedicated CL2 training laboratory with adjacent 50 person classroom (over 2050 sq ft.). Here, curriculum is developed, tested, refined and deployed and is packaged for mobile training at other sites around the country. To accomplish CATTI’s goals, interns are needed to build the training cell banks that correspond to a wide variety of platform technologies for therapeutic production. Additionally, in the age of industry 4.0 and digitization, CATTI is automating laboratory management and inventory practices to reduce entry errors and gain efficiency in laboratory based operations. This submission for 4 internship projects spanning over 2 years will ensure continuity between CATTI’s current Mitacs BSI Intern and additional interns that will benefit form the dynamic team environment. Objective 1 will focus on the generation of training cell banks for several cell lines, each taking up to 7 months to generate; Objective 2 centres on the implementation of digital solutions for lab operations and training and will take place over a 6 month span. Intern 1 has already completed a round of eligible Mitacs BSI Intership; Intern 2 will be newly onboarded; Interns 3 and 4 (to be named) will be onboarded in January and April 2025, respectively. Each Intern will work very closely with the CATTI team and projects will be closely managed.

Identifying climate change resilient habitat using an integrative machine learning and coupled microclimate-biophysical modelling framework

Loss of biodiversity is occurring at unprecedented rates with an estimated 1 million species facing global extinction. Canada has the second largest area of intact natural landscapes and, therefore, a responsibility and opportunity to be a global leader in biodiversity conservation. Yet, Canada is facing a biodiversity crisis that particularly targets reptiles, one of the most endangered groups of vertebrates in the world and the most endangered in Canada. Continued reptile declines are the result of multiple stressors, including land use and climate change, which continue to accelerate. Ultimately, failure to address the biodiversity crisis will be costly as declines in ecosystem biodiversity negatively impact food production, human health, and water quality, posing direct and indirect socio-economic consequences. Our project will leverage an open-sourced habitat mapping database currently under development in collaboration with project partners to identify (1) reproductive and (2) overwintering habitats that will be resilient to climate change, thus providing critical refugia to species at risk. Specifically, our project will (O1) develop a regional-scale microclimate model based on land cover by leveraging a habitat mapping database and by up-scaling a site-specific soil depth model; (O2) develop a regional-scale biophysical model to identify climate-resilient upland habitat that provides critical habitat for reptile reproduction (i.e., nesting); and (O3) develop a regional-scale wetlands model to prioritize protection of critical reptile overwintering habitat. Biophysical models represent the cutting edge in modelling connections between physical and biological/ecological dynamics, and their use is integral to understanding habitat conditions under present and future climate conditions. The outcomes and tools generated in this research will facilitate effective habitat management, enhanced land use planning, collaborative stewardship among partners, and enable evidence-based decision making.

AI Enabled Very Small Aperture Terminal Modem

A Very Small Aperture Terminal (VSAT) is a satellite communication technology that enables two-way data transmission between a ground station and a satellite. It is used for data, voice, and video communications, particularly in remote or underserved areas lacking adequate terrestrial infrastructure, ensuring reliable and secure communication for both personal and commercial needs.
Optimizing the satellite link in hubless full mesh VSAT technology is critical for achieving bandwidth efficiency, reducing latency, enhancing reliability, supporting scalability, and maintaining high Quality of Service. However, the resource constraints of hubless full mesh modems, due to the absence of a central network manager, pose significant challenges. Existing rule-based approaches limit the potential for smarter link management.
Artificial Intelligence (AI) has the potential to enhance the development of new modems supporting this technology. AI can optimize the features such as bandwidth and power allocation, adaptive coding and modulation, enable predictive maintenance, manage traffic and QoS. These advancements can result in more efficient, reliable, and cost-effective satellite communication networks.
This project will conduct a comprehensive study on suitable AI models for integration into embedded systems. The project will involve identifying appropriate AI models, optimizing these models for embedded systems, and developing the accelerator architecture for them.

Federated Query Processing for AI-Copilots

THIS IS A GENERIC TEXT PUT IN PLACE AS THERE WAS NO PROJECT OVERVIEW.