Machine learning for satellite-based monitoring and condition assessment of critical infrastructure

This project aims to improve the monitoring and assessment of critical infrastructure using machine learning and satellite technology. By integrating machine learning techniques, we aim to improve the accuracy of detecting structural and geotechnical deterioration in public infrastructure, such as marine port wharves and airport runways. Led by experts from the NRC’s Construction Research Centre (NRC-CRC) and UBC Applied Science, the project will develop AI-trained probabilistic models to process satellite data and provide clearer insights into structural health. With the potential to monitor infrastructure across Canada in all weather conditions, satellite-based health monitoring has the potential to improve the quality and reduce service disruptions of critical infrastructure. This project will contribute to the NRC-CRC’s work towards a more data-driven and condition-based maintenance strategy for infrastructure assets by providing a new perspective on satellite-based deformation monitoring. This project will also contribute to UBC’s work on data-driven predictive analytics for infrastructure monitoring. Ultimately, the approach explored in this project promises more efficient and cost-effective asset management, ensuring safer transportation networks for communities nationwide.

Faculty Supervisor:

Zheng Liu

Student:

Partner:

Rheinisch-Westfälische Technische Hochschule Aachen

Discipline:

Engineering

Sector:

Education

University:

The University of British Columbia - Okanagan

Program: