Status: This program has closed.
This program has closed and is no longer accepting proposals.
In collaboration with partners across Canada, the NRC's Digital Health and Geospatial Analytics program developed innovative solutions to a range of health, safety and environmental challenges. It also supported post-secondary programs in machine learning, enabled growth of collaborator research labs and provided research support to Canadian industry through funding from the Collaborative Science Technology and Innovation program.
By supporting new approaches to chronic challenges, the program advanced Canadian research and contributed to improving the quality of life of Canadians.
Much of the research started under this program will continue under other NRC programs or at the research institutes of our partner universities.
Some of our AI models and associated software were also used by government agencies, academic institutions and industry partners.
Two university-based research initiatives that were established in part with our funding will continue to work more broadly in the program's fields of focus:
- Simon Fraser University: This project was strategically positioned for sustained innovation and leadership in leveraging AI to unlock the potential of routine clinical EEG data, ultimately aiming to improve neurological care and patient outcomes. The robust foundation laid prepared the university well for further development, larger initiatives, and continued impact in AI-driven healthcare.
- University of Victoria: The project enabled the development of a research program rooted in remote sensing, but now includes drone and ground-based imagery to provide ground truth evaluation of the algorithms that we are working on.
Program highlights
The NRC collaborated with partners under this program to develop, field test and, in some cases, use operationally AI-enabled tools to address key environmental challenges and develop innovations in the health-care sector.
Environmental challenges:
- With the University of Victoria (UVic) and Environment and Climate Change Canada: Developed tools such as UVic's Ocean pollution monitoring system that predict biotoxin plumes in sensitive shellfish production locations and spatial and temporal dynamics of the pollutants across the east and west coasts of Canada
- With the University of British Columbia: Produced a set of AI tools to predict and characterize harmful waste runoff at hard-rock mining sites
- With the Institut national de la recherche scientifique (INRS) : Implemented tools for operators to conduct more cost-effective evaluations of geo-structural risks to hydroelectric dams and other remote infrastructure
- With the University of Victoria: Built advanced AI-enabled imagery tools to enhance the effectiveness of airborne sensors for search and rescue, megafauna surveys, and more
Health-care innovations:
- With the University of Ottawa: Developed lightweight AI-enabled biomarker panels for preliminary diagnosis of 3 medical conditions in order to support patients in remote areas
- With the University of Victoria: Built an AI tool to advance the diagnosis of chronic obstructive pulmonary disease
- With the University of British Columbia: Using machine learning, delivered cybersecurity tools to support enhanced security and privacy protection across connected healthcare systems
- With Simon Fraser University: Using EEGs, created a new AI-enabled pathway to assess brain age and health and delivered new research datasets to the community
In addition, over the course of 7 years, the program provided employment opportunities and trained over 100 highly qualified personnel
Recent research publications
The program also resulted in numerous research publications. Here is a sample of the published research.
- A web-based ocean pollution monitoring system (Z. Liu et al., 2025. Marine Pollution Bulletin, vol. 212, article 117510)
- Classifying routine clinical electroencephalograms with multivariate iterative filtering and convolutional neural networks (V. Paliwal et al., 2024. IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 32, pp. 2038–48)
- Prediction of mine waste rock drainage quantity using a machine learning model with physical constraints (C. Zhang et al., 2025, February 19. UBC Faculty Research Publications)
- Estimating tree species composition from airborne laser scanning data using point-based deep learning models (B.A. Murry et al., 2024. Journal of Photogrammetry and Remote Sensing, vol. 207, pp. 282–97)
- PCLDA: An interpretable cell annotation tool for single-cell RNA-sequencing data based on simple statistical methods (K. Bai et al., 2025. Computational and Structural Biotechnology Journal, vol. 27, pp. 3264–74)