Innovative Projects Realized

Chemical reaction mechanisms with eXplainable Machine Learning

Deep learning systems can predict properties of chemical substances but do so in a purely mathematical way. As a consequence, the user does not get any feedback on what are the essential properties a chemical must have to exhibit a certain property. This hampers getting any insight in to the relationship between molecular structure and the properties. In this project, the aim is to transform mathematical vectors that result from deep learning back to molecular properties that chemists understand and can use to their benefit to develop new molecules.

Deep Breathe Software Developer- Mobile

This project will contribute to the design and building of the systems behind our clinical-facing applications for automated point-of-care ultrasound interpretation. Working closely with our product, AI, and regulatory teams, the project focuses on building real-time respiratory imaging tools that bring immediate diagnostic answers to patients — whether at the bedside, in the back of an ambulance, or on the battlefield. Centered on Android app development, this project aims to expand the reach of our diagnostic platform, enabling access to a wider range of users and environments. The project demands innovative thinking, curiosity, and the ability to develop reliable solutions that perform under constrained computational environments, ultimately advancing the application development for how and where critical diagnostics are delivered.

Feasibility Assessment of Treatment Wetlands for Northern Riverbank Stabilization: An Exploratory Hydrodynamic Study of the Nechako River

The Nechako River in Prince George, British Columbia, suffers from eroding riverbanks and contaminated sediments left behind by past industrial activities. This project will investigate whether treatment wetlands, which are engineered ecosystems that use plants and natural processes to clean water and stabilize soil, could help address both problems at once. The student will use computer modeling software to study how water flows along the riverbanks and identify locations where treatment wetlands might work well. The project includes dedicated training on cold-climate treatment wetlands, allowing the student to gain leading-edge knowledge in an emerging field critical to Canada and other northern regions. For Canada, this research advances the development of low-cost, nature-based water infrastructure suited to northern communities, many of which face combined challenges of aging systems, legacy contamination, and limited resources for conventional engineering solutions. For UNBC, this work provides the initial site assessment needed before designing a pilot wetland system, directly supporting the university’s ongoing research on cold-climate water treatment. For Tecnológico de Monterrey, the collaboration extends their river modeling expertise into northern environments and establishes a partnership that can lead to future student exchanges and joint research projects between the two institutions.

Entrepôt inter-organisationnel de mutualisation de données

Lorsque vient le temps de concevoir des stratégies pour supporter l’innovation au Québec, le Conseil de l’innovation du Québec (CIQ) fait face à un défi important: les données relatives à la performance des différentes aides publiques sont dispersées à travers l’ensemble des organisations chargées d’administrer les aides financières ou les services.

Pour répondre à cet enjeu, le CIQ pilote une initiative de mutualisation de données, en partenariat avec plusieurs organisations partenaires.
Or, la mutualisation des données amène plusieurs grandes questions, notamment en lien avec la valeur stratégique et la gestion éthique des données.

Le projet consiste donc à concevoir et déployer une architecture infonuagique permettant de soutenir l’effort de mutualisation de données, en tenant compte des différents enjeux de gouvernance de la donnée et ce, sur la base de recommandations d’un comité d’experts.

Training for Transformation: An Initiative to Embed Climate Resilience in Engineering and Infrastructure Practices

This internship project supports the development of a global training initiative led by the Climate Risk Institute (CRI) in partnership with the World Federation of Engineering Organizations (WFEO), aimed at enhancing engineering and infrastructure climate resilience worldwide. Over a four-month period, the intern will contribute to the design and development of training materials across three key phases of the program: strategic planning, creation of a foundational asynchronous course, and the global adaptation of existing professional resilience courses. The intern will engage in research, content drafting, and instructional design, producing key deliverables such as course syllabi, draft modules, case studies, and training support materials. This work will directly support CRI and WFEO’s goal of advancing climate adaptation capacity within the engineering community. The project will also link training resources, efforts, and participants through a new, AI-enabled digital platform called CanAdapt. At the heart of CanAdapt is a growing ecosystem of practitioner networks—communities of practice that bring together professionals working on climate adaptation and resilience in areas such as infrastructure, forestry, mining, and energy. By tying these networks to CanAdapt’s course and program portal and using AI to help define learning pathways for shared interests among individual members of the networks, CanAdapt will become an adaptation accelerator. It will enhance knowledge systems, practitioner collaboration, and access to resources, all to support work and specific projects on climate and low-carbon resilience. The internship offers a unique opportunity for the intern to gain hands-on experience in international climate resilience training development while providing the partner organizations with dedicated support to accelerate content creation, course design, enhance global relevance, and strengthen the foundation for broad program implementation.

Staffworks Submission

Project Overview: Recruitment Workflow Innovation at Staffworks

About Staffworks
Staffworks is a Toronto-based staffing firm with 25 years of experience helping businesses stay agile and competitive through strategic recruitment services.

The Challenge
Recruiters face increasing administrative workloads—posting jobs across multiple platforms, managing large applicant volumes, screening candidates, coordinating interviews, and updating databases. These repetitive tasks consume significant time and limit the team’s ability to focus on high-value activities like engaging top talent and strengthening client relationships.

The Innovation Priority
Staffworks aims to redesign and streamline recruitment workflows using technology. This initiative is not about doing the same tasks faster; it’s about creating new, technology-enabled processes, testing automation tools, and implementing evidence-based improvements that transform how recruitment operates. These innovations require dedicated research, prototyping, and evaluation beyond normal business operations.

The Project
To achieve this, Staffworks is launching a Recruitment Assistant Internship focused on process analysis, automation techniques, and digital tools for routine recruiting functions. The goal is to reduce manual effort, accelerate service delivery, and improve candidate and client experiences. By minimizing administrative burden, Staffworks will enhance productivity, speed up response times, and strengthen its competitive edge—supporting long-term growth.

AI-Powered Fish Monitoring: Supporting Indigenous-led Conservation in Deadman Watershed

Secwépemc Fisheries Commission (SFC) currently relies on a semi-automated system that requires biologists and technicians to manually review video footage to confirm fish counts. This process is time-consuming, delays reporting, and limits access to real-time information. The interns will develop an automated fish-counting tool that uses computer vision and artificial intelligence (YOLOv2 object detection, ByteTracker, and custom counting logic) to detect and count salmon in the Deadman Watershed, part of the traditional territory of the Skeetchestn Indian Band. By integrating the resulting dashboard into the existing infrastructure, the system will reduce the manual validation and free up staff resources to focus on higher-value conservation work. Beyond operational efficiency and technical product development, this project also strengthens Indigenous-led monitoring efforts and builds the foundation for long-term collaborative relationships between Indigenous communities and TRU.

Étude de l’évolution de l’architecture fonctionnelle de logiciels durant la maintenance pour proposer du réusinage empêchant la dégradation de l’architecture

Ce projet de recherche a pour objectif d’analyser l’évolution de l’architecture fonctionnelle des logiciels au cours de leur maintenance, une phase souvent sujette à des modifications qui peuvent altérer la qualité et la cohérence du système. En étudiant ces transformations, le projet vise à concevoir des approches de réusinage intelligent capables de prévenir la dégradation architecturale et de maintenir la robustesse en se basant sur la théorie de langage , la performance et la clarté du code. Les résultats attendus permettront d’améliorer la durabilité, la maintenabilité et la fiabilité des logiciels, offrant ainsi aux entreprises des solutions plus stables, évolutives et économiques à long terme.

Wind turbine wake mitigation with active control in a utility sized wind farms under varying thermal stratifications of the atmosphere

Among renewable technologies, wind energy offers some of the lowest levelized costs of energy in Canada and therefore holds significant potential to contribute to the nation’s clean energy transition. However, the large-scale deployment of wind energy in wind farms presents new challenges that are not encountered with standalone turbines. When downstream turbines operate in the wake of upstream turbines, their generated power drops significantly, resulting in substantial losses of the wind farm’s efficiency and ultimately affecting its profitability and delaying the return on investment. One promising method to reduce the intra-farm wake effect is helix active wake control, which achieves power gains of up to 12% in small-scale wind turbine arrays. However, modern wind farms are orders of magnitude larger and therefore interact differently with the atmosphere. This research project assesses the potential of helix active wake control to improve the efficiency of wind farms and enhance their economic viability. Overall, the research directly contributes to Canada’s Federal Sustainable Development Strategy and addresses broad challenges in renewable energy integration, which are also top priorities for the partnering university and nation (Netherlands).

Assessing extractive development in Kaska Dena territory

The project will transfer academic research findings about extractive development on Kaska Dena territory to Kaska Dena organizations. It will involve three activities: 1) making research findings accessible to community members, policy-makers, and government organizations involved in impact assessment through reports and other tools; 2) supporting the development of a database of Kaska Dena knowledges that Kaska organizations can use in their own assessment processes; and 3) transferring raw data and data management tools to Kaska organization to support future research and assessment activities. The mobilization and integration of this material will strengthen Dena Cho’s and the Tu Lídlini Dena’s capacity to advocate for Kaska interests and implement Kaska-led IA, land use planning and IPCA systems.

Exploring the Mass-Metallicity Frontier for Gas Giant Planets Around Low Mass Stars

With now more than 6000 planets discovered outside of our Solar system, one of the next major frontier is to determine the chemical make-up of exoplanet populations, a tracer of their formation processes. Dominating the planetary system by mass, gas giants are a determining factor in the final architecture and composition of planetary systems: no planet formation theory is complete without understanding this crucial piece of the puzzle. Gas giants are formed primarily of hydrogen and metals, with a level of metal enrichment set by the formation mechanism as a function of planetary mass. We aim to measure precise masses and metallicities for the poorly-explored population of gas giants orbiting low mass stars. This will shed light on the process responsible for one of the most extreme cases of planet formation while enabling robust statistical comparison with the population of gas giants orbiting Sun-like stars, providing an important benchmark for planet formation models around a diversity of stellar hosts.

The project consists of an mutually-beneficial exchange of expertises: while the home institution provides technical knowledge in measuring precise masses of planets around low mass stars, the host institution offers scientific expertise in gas giants interior structure and planet demographics.

Technical Interns working within cross functional teams to commercialize AI-powered solutions in the Agriculture Tech industry

AltaML builds artificial intelligence (AI)-enabled solutions to business problems. We work with organisations, bringing together their data and domain expertise with our AI expertise, to develop AI solutions that are deployed in their operations. We also commercialize AI-enabled products business via industry-specific ventures, yielding scalability from our investment in the first solution. AltaML’s Venture Studio is an incubator program that works with founders and co-founders in the emerging tech industry to scale ideas, build venture products, and launch AI/ML startups across numerous industries; this includes our venture partners at Brilliant Harvest who are striving to innovate the Agriculture Technology space.

The interns listed (Marcus Eshleman) on this particular application will be working alongside the Government of Alberta team to streamline the deployment of “Smart Document Extraction Agents” using Machine Learning. The goal of a Government of Alberta Redaction Assistant would be to empower the government to handle sensitive information and access requests with greater efficiency and security.
? Focus: using the SDP application template to create an Automated PII Redaction Tool. The main reason for the project is to automate the identification and masking of Personally Identifiable Information (PII) in high-volume, unstructured public sector documents, such as those related to Freedom of Information and Protection of Privacy (FOIP) requests. This automation replaces the current manual, time-consuming, and error-prone redaction process, directly addressing the growing volume of digital data and the increasing regulatory burden under new privacy legislation.
? Value: The Value of the project is substantial in terms of financial savings, risk mitigation, and operational efficiency. The automation of redaction provides financial benefit by freeing up highly skilled FOIP analysts and records management officers from repetitive, manual tasks, allowing them to focus on complex policy interpretation and disclosure decisions. The solution brings value to citizens by ensuring the GoA is compliant with the Protection of Privacy Act (PPA), drastically reducing the risk of accidental PII disclosure (data breach risk).

The interns listed (Zongxin Liu, Reuben John) on this particular application will be working alongside the Government of Alberta team to streamline the deployment of “Research Assistants” using Machine Learning. The Government of Alberta is undergoing an organizational shift towards data-driven search capabilities to provide better service for Albertans.
? Focus: Leveraging natural language processing, large language models, RAG searches, graphs and prompt engineering to analyze and interact with government policies and documents. Deliverables will include an end to end pipeline for data ingestion, modeling and output to a chat system.
? Value: Focusing on assisting duty offices and other roles that require search, access and responses to detailed, complex policy and regulatory documents in order to respond to public requests. An AI-based assistant will provide responses to basic questions, which allows the duty offices to focus on the more complex questions that require subject matter expertise. The solution also brings value in upskilling new hires as staff retirements or transitions occur.

The intern listed (Chase Lloyd) on this particular application will be building on the work completed with one of our Venture Partners in his current internship (IT47641), Brilliant Harvest, to further develop and scale the ‘Performance of their AI Assistant,’ where they will look to further innovate and revolutionize the technology in the AgTech industry:
? Focus: The focus of this project will be the ongoing effort to enhance the application stack by expanding on its features, increased leverage of our AI Assistant. Chase will continue working on the FE apps, where he has already made a substantial contribution in his first internship with them.
? Value: With numerous and varying kinds of documentation floating around the industry, this can make it difficult for those in the industry to accurately and efficiently find the information they need. This includes operating manuals, policy documents, product specifications, and everything in between, when it comes to documentation in the Agriculture industry. By being able to train the model to be able to analyze and classify these documents, the value of this solution comes with the newfound ability of those in the industry, to be able to quickly find answers and information related to their most pressing needs. Further, optimizing how the AI Assistant interacts with the end user reduces friction and increases the value of service overall. Chase has contributed significantly to the advancement of their web app and we look forward to continuing scaling the application with his input and expertise. Chase will also provide a valuable contribution as he supports and helps onboard the new interns coming onto this project.

The intern listed (Misbah Ahmed Nauman) on this particular application will be working with one of our Venture Partners Brilliant Harvest, to further develop and scale the ‘Performance of their AI Assistant,’ where they will look to further innovate and revolutionize the technology in the AgTech industry:
? Focus: The focus of this project will be the ongoing effort to enhance the application stack by expanding on its features, hardening some of the core components of the stack and some work in furthering their test automation efforts.
? Value: With numerous and varying kinds of documentation floating around the industry, this can make it difficult for those in the industry to accurately and efficiently find the information they need. This includes operating manuals, policy documents, product specifications, and everything in between, when it comes to documentation in the Agriculture industry. By being able to train the model to be able to analyze and classify these documents, the value of this solution comes with the newfound ability of those in the industry, to be able to quickly find answers and information related to their most pressing needs. Misbah’s work will contribute to their success in several ways. 1) new features enhance the value of the app to brilliant Harvest’s customers. 2) Stack hardening improves reliability, reduces maintenance costs resulting in better customer experience. 3) Test automation reduces the cost of development and improves product quality.