Satellite-Derived Bathymetry
Developing and testing methods to estimate shallow-water bathymetry from optical and lidar satellite data, and applying these methods to diverse coastal and inland environments, with a focus on the Canadian Arctic Ocean.
Research
What we study, the projects we are working on now, and a selection of our publications.
Research Themes
Our work is organized around six main research themes.
Habitat Mapping
Using remote sensing and in situ observations to map benthic and coastal habitats, including kelp, seagrass, coral, macroalgae, and other key ecosystem components.
Water Quality Monitoring
Monitoring optically active water constituents, turbidity, and related optical properties through satellite time series to track environmental status and support management.
Change Detection
Detecting and quantifying changes in bathymetry, habitat extent, and water quality over time, using multi-mission and multi-decadal satellite archives.
Self-Supervised Learning
Developing self-supervised and representation learning approaches for Earth observation, leveraging large volumes of unlabelled data to improve downstream classification and regression tasks.
Whale Detection
Designing and testing satellite-based methods for detecting the North Atlantic right whale (NARW), with a focus on operational integration into alert systems that support conservation management.
Current Projects
Ongoing projects in the lab span method development, large-scale applications, and collaborations with partners working in coastal and inland waters.
Integration of Satellite Data into a NARW Alert System
Whale detection
The objective of this project is to demonstrate a three-step methodology for detecting North Atlantic right whales (NARW) using satellite data, and to integrate this methodology into the existing governmental alert system in the Gulf of St. Lawrence.
SmartHARBOUR, monitoring the St. Lawrence aquatic environment using Earth observation
technologies in the Contrecoeur Port terminal expansion context
Environmental monitoring
This research project will test existing methods to map and monitor i) benthic habitat, ii) water depth, and iii) water quality with high-resolution optical satellite data. The study takes place on the St. Lawrence River north of Montreal, in the context of the Contrecoeur Port Terminal expansion project.
Selected Publications
A selection of recent publications from the lab related to our core research themes.
- Richardson, G., Knudby, A., Richardson, E., Millard, K., & Chen, W. (2026). Incorporating multiple bands and land cover improves cross-sensor normalization. Remote Sensing Applications: Society and Environment.
- Wu, Y., Knudby, A., Lapen, D., Craiovan, E., & Bi, S. (2026). Assessment of adjacency-effect correction for satellite-derived reflectance and water quality in agriculturally impacted rivers: a case study in Eastern Canada. GIScience & Remote Sensing.
- Knudby, A. (2025). Satellite imagery for hazard detection: better use of satellite imagery could help prevent groundings in the Canadian Arctic. International Hydrographic Review.
- Richardson, G., Knudby, A., Millard, K., & Chen, W. (2025). A tool for global and regional Landsat 7 and Landsat 8 cross-sensor harmonization. Geocarto International.
- Wu, Y., Knudby, A., Pahlevan, N., Lapen, D., & Zeng, C. (2024). Sensor-generic adjacency-effect correction for remote sensing of coastal and inland waters. Remote Sensing of Environment.
- Richardson, G., Foreman, N., Knudby, A., & Lin, Y. (2024). Global deep learning model for delineation of optically shallow and optically deep water in Sentinel-2 imagery. Remote Sensing of Environment.
- Lin, Y., & Knudby, A. J. (2023). Global automated extraction of bathymetric photons from ICESat-2 data based on a PointNet++ model. International Journal of Applied Earth Observation and Geoinformation.
- Knudby, A., & Richardson, G. (2023). Incorporation of neighborhood information improves performance of SDB models. Remote Sensing Applications: Society and Environment.