Innovative Projects Realized

L2M-COASTAIR

Coastal and marine pollution is draining ecosystems and budgets across Canada and beyond, yet we still check shorelines with clipboards or wait for low-resolution satellite passes. The result: blind spots, slow responses, and costly cleanups. COASTAIR flips that script. Our AI-enabled aerial platform pairs agile drones with RGB and hyperspectral cameras to spot, classify, and measure pollution, i.e. floating plastics, oil sheens, and even harmful algal blooms, in real time. Each flight streams geo-tagged imagery to an onboard/edge model that flags anomalies, while a cloud dashboard turns detections into clear maps, trends, and alerts the inspection team immediately. Built as a simple subscription, COASTAIR gives coastal municipalities, port authorities, and environmental agencies continuous, decision-ready intelligence at a fraction of traditional costs. Schedule automated routes, track hotspots over time, and export reports for compliance. For partners, the payoff is direct: faster, safer monitoring and earlier interventions that prevent small spills from becoming headlines. Furthermore, a validated rollout plan for pilots and partnerships, including training, regulatory guidance, and shared metrics for success. In short, COASTAIR transforms the coastal monitoring of the coastal region. One can protect water, wildlife, and communities with speed and confidence.

Design and Implementation of a Generalized, Secure, and Scalable API

DiamondAI and McMaster University are working together to create a secure and scalable software interface, called an API, that connects DiamondAI’s career guidance platform with the online systems used by schools and colleges. DiamondAI helps students and newcomers understand their strengths and interests through personalized assessments powered by artificial intelligence. Right now, most schools use platforms such as Moodle, Brightspace, or Google Classroom. Because DiamondAI operates separately, students need to leave their school systems to use it, which reduces engagement and raises privacy concerns. This project will build a solution that allows schools to offer DiamondAI’s assessments directly inside their existing systems. It will support safe data sharing, single sign-on, and compliance with Canadian privacy rules. Ultimately, the project demonstrates how applied AI and software engineering can combine to strengthen Canada’s digital innovation ecosystem, bridge the gap between education and employment, and create meaningful social and economic impact. The new integration will make DiamondAI easier for schools to adopt, improve student access, and protect personal data. For DiamondAI, this project will create a strong foundation for scaling its services across Canada and help build partnerships with educational institutions, advancing both innovation and social impact.

Imagerie THz multispectrale assistée par l’IA

L’INO (Institut National d’Optique), entreprise à but non lucratif spécialisée dans le développement de solutions optiques pour l’industrie manufacturière, souhaite bâtir une base de données structurée d’images THz annotées à partir d’échantillons de plastiques représentatifs de cas industriels. Les principales activités comprennent la fabrication d’échantillons de différentes épaisseurs (par impression 3D et à partir de matériaux bruts), l’intégration d’inclusions contrôlées, la réalisation de campagnes de mesure avec plusieurs configurations (fréquences, polarisation) sur ses équipements, ainsi que le développement d’outils d’annotation et d’analyse comparant des outils maison et commerciaux. Ces travaux permettront de relier directement les signatures spectrales et texturales aux types de plastiques et aux défauts.

Les avantages économiques et sociaux attendus pour INO sont multiples : d’une part, la base de données permettra à INO de prédire rapidement, lors des consultations avec de nouveaux clients, la faisabilité et la pertinence de solutions d’imagerie THz, évitant ainsi des expérimentations onéreuses et optimisant l’allocation des ressources. D’autre part, elle constituera un socle pour le développement de futurs outils de diagnostic assisté par l’intelligence artificielle, renforçant la compétitivité d’INO et soutenant l’innovation dans l’industrie du recyclage, de l’emballage et de la fabrication avancée.

Genetic control of Reproductive Longevity in Mouse and Validation of a genetic marker panel to predict Fertility and Longevity traits in Holstein Dairy Cattle

Reproductive Longevity (RL) is a complex biological trait under the control of many genes. In Cattle, RL is a key productivity factor, especially for dairy cows. The proposed research aims to identify RL-controlling genes in mammals using: 1) a unique model system, selectively-bred mouse lines that reproduce twice as long and have twice as many litters as matched control lines and 2) cattle (bulls) with High or Low genetic merit for Longevity. The project Partner, Performance Genomics Inc. (PGI), is applying whole genome mapping and sequencing technologies (outsourced) to generate complete genomic datasets for mice and cattle. This will result in a set of DNA markers that will be validated using DNA and data from 3,000 bulls. The internship project will apply bioinformatics tools and approaches to “mine” the genomics data with the goal of selecting and ranking candidates for genes and mutations responsible for RL in mouse and/or cattle. The end result for PGI will be commercial DNA Markers tests for RL for livestock breeding, initially for Holstein cattle.

Eddy-sea ice interaction in the Arctic Beaufort Gyre in two high-resolution ocean-sea ice models

The Beaufort Gyre (BG) is the largest freshwater reservoir in the Arctic Ocean. It is climatologically anticyclonic and governed by the Beaufort High. Its dynamics have a profound impact on the general circulation, and the possible release of freshwater has significant climate implications. The equilibrium state of the BG has been proposed to be governed by the combined role of surface wind forcing, eddy fluxes, and the ice-ocean governor. In the context of global warming, the sea ice in the BG has been transitioning toward a state of thinner and younger ice, making it more dynamic and susceptible to external forcing. Eddies are crucial and active players in the transport and mixing of heat, salt, and momentum. Our proposed work will employ large datasets obtained from two state-of-the-art km-scale ocean models to investigate eddy-sea ice interaction in the BG. This work will showcase how km-scale models can help understand eddy processes and the impacts of climate change.

L2M – PORT-EM: Smart Port Energy & EV Infrastructure Management

The transition to low-carbon ocean economies requires innovative energy solutions for ports and coastal communities, where electrification of ships, ferries, and vehicles is accelerating. Building on prior research in probabilistic EV charging demand forecasting, energy consumption modeling, and emissions analysis, this project proposes a Smart Port Energy and EV Infrastructure Management Platform. The system integrates machine learning algorithms (LSTM, Random Forest, SVR etc.) to forecast highly variable port energy demand while incorporating tidal, offshore wind, and wave energy generation models. Coupled with embedded controllers for real-time load management, the platform enables demand balancing, peak reduction, and emissions minimization. Unlike existing generic energy management tools, this solution is purpose-built for the multi-source, high-variability environment of maritime ports, directly linking EV adoption with the ocean economy. The project will validate both the technical feasibility and market potential of ocean-focused smart grid solutions, advancing sustainable port operations in Atlantic Canada and beyond.

L2M – Medication Adherence Device

Older adults have difficulty keeping track of the frequency of their dosage as well as opening the medication packaging. Nonadherence to prescribed medication can lead to hospitalization which increases the burden of care both for the patients and the medication system. Our solution, Pillsette, is a smart medication adherence device that offers a reusable pill storage unit that can be operated manually or automated, and a companion app or SMS agent that alerts the patients (or their caregivers) at the time for the medication.

Email and Marketing Assistant

Nature Bee is a Canadian-based company creating microplastic-free, sustainable cleaning products. As we scale, we are looking to strengthen our digital marketing efforts—particularly our email marketing, retention strategies, and performance analytics across channels.
This internship project will focus on developing a robust, evidence-based email marketing strategy using Klaviyo, alongside reviewing paid ads performance to improve full-funnel engagement. The intern will analyze Nature Bee’s customer and subscriber data to create refined audience segments based on purchase history, email engagement, demographic details, and customer lifecycle stage.
The intern will conduct a literature and competitor analysis of lifecycle marketing best practices for purpose-driven, direct-to-consumer brands, especially those targeting eco-conscious consumers. They will design and implement new Klaviyo flows such as welcome series, abandoned cart, post-purchase education, and customer win-back campaigns. A/B testing of subject lines, timing, creative content, and CTAs will be conducted to optimize performance.
In addition to email, the intern will collaborate with the marketing team to evaluate Meta and Google Ads platform data, identifying how paid campaigns influence email signups, conversions, and long-term retention. They will help build an integrated dashboard to report on key email and ad metrics such as open/click rates, revenue per campaign, CAC, and LTV.
Deliverables include a comprehensive email marketing playbook, clearly mapped automation workflows, campaign test results, performance dashboards, and recommendations for ongoing optimization. This work will directly support Nature Bee’s growth goals by driving customer engagement and revenue while maintaining the brand’s commitment to sustainability and transparent communication.
Beyond this work, they will be supporting our marketing and operations team with other creative work, production support to gain a deeper understanding of the work we do, support with marketing channels from our creative director and communicating with sales support as well!

A Novel Torque Measurement Technique Based onPiezoelectric Sensors

In this project, a novel torque measurement technique based on piezoelectric sensors will be proposed to overcome the constraints posed by traditional methods such as strain gauges, magnetic pickups etc. Specially designed disks which are connected to the sensor will be mounted on the shaft. The proposed method will be used to compare relative twist in the shaft based on the phase difference between the disks. The angle of twist is then correlated to the torque applied. The proposed technique can be used as a low cost solution for torque measurement or rotating components. Finally, it is expected to publish the novel piezoelectric sensor based torque measurement technique in peer reviewed articles.

Advancing Climate Finance and Social Entrepreneurship

Through this project, interns will support organizations and initiatives advancing climate finance and social entrepreneurship in the Victoria and British Columbia ecosystem.

Jumeau Numérique: Profil d’échange thermique de la cuisson du sucre à la crème

NASUCO CANADA est une entreprise québécoise qui se spécialise dans la production, la transformation et la commercialisation de petits fruits, notamment des bleuets sauvages. L’entreprise souhaite optimiser son procédé de fabrication afin de soutenir sa croissance et améliorer la qualité de ses produits. Un des besoins essentiels de l’entreprise est d’optimiser le temps de cuisson du sucre à crème.
Le système de contrôle thermique automatisé (PID) actuellement en place repose exclusivement sur la mesure de la température. Cette approche, limitée à une plage restreinte de températures, ne tient pas compte de l’apport calorifique spécifique de la vapeur sous pression dans le processus de cuisson. Face à cette contrainte, plusieurs entreprises du secteur contournent le dispositif de régulation en utilisant l’interrupteur de pression de sécurité comme mécanisme de contrôle. Bien que cette pratique permette une amélioration ponctuelle de l’efficacité, elle engendre une grande variabilité du procédé et pose d’importants enjeux en matière de santé et sécurité.

Nos observations sur le terrain démontrent par ailleurs l’existence d’un profil de température particulier lors de la cuisson du sucre à la crème. En effet, les phases d‘homogénéisation des ingrédients, d‘ébullition de l‘eau et de cuisson du sucre vont chacune influencer, le taux de gras, de sucre et d‘eau dans le mélange, ce qui impact directement la chaleur spécifique du sucre à la crème. Lorsque le profil de chaleur spécifique change, la sensibilité de la pression à l‘intérieur de la double parois de la marmite passe d‘un état stable à un état instable en quelques secondes, rendant les paramètres de commande standard inadéquat dans une situation ou dans l‘autre, ce qui explique les limites d’un système de régulation basé uniquement sur la température pour assurer une gestion optimale et stable du procédé.

Debugging ML via Feature-guided Analysis: Analyzing Neural Network Robustness

Neural Networks (NN) use a set of individual units (neurons) connected together to learn a specific behavior from a dataset. For example, NN excel in classification tasks where given a dataset labelled with presence or absence of a feature in each entry, they are able to detect the feature presence on new inputs. This technology has been applied in many fields, including automotive, aerospace, medical and others.
A significant drawback of NNs is that their behavior is unknown, since it only depends on the training data and it is not understandable to humans. This significantly limits their applicability, especially in safety-critical fields. For this reason, NN interpretability is a growing field of research. Feature-Guided Analysis (FGA) is a technique that extracts rules from NNs and can help explain how the values assumed by individual neurons affect the outcome of the network.
This project aims at replicating the results of this technique on a new image-based dataset and improve upon the limitations of the existing technique. We further aim at employing this technique to analyze the robustness of the network, providing engineers with a description of which portion of the NN are more susceptible to perturbations on the inputs.