The Landsat archive includes imagery collected by multiple sensors, each with differences that can introduce errors in change-detection analyses. Galen Richardson’s research focuses on developing sensor-harmonization algorithms to enable more accurate change detection and to support the monitoring of lichen cover in the Hudson Bay Lowlands.

Mohsen works on applying Earth observation and modeling approaches to study coastal and inland waters, with an emphasis on improving the retrieval of water quality parameters using machine learning models.

Lakmal studies how pretext-task-based pre-training on unlabeled Earth Observation data can improve geospatial deep learning, boosting accuracy and label-efficiency.

Gabrielle is interested in UAV-based mapping, thermal remote sensing, and using those technologies to develop novel microclimate assessment tools.

Matus's PhD research has developed a whale detection algorithm for WorldView satellite imagery, and an innovative methods for using aerial photography for training of such algorithms.

Neve’s thesis focuses on differentiating eelgrass and submerged kelps using hyperspectral satellite imagery near Sheet Harbour, Nova Scotia. Her methods include a drop camera survey and applying machine learning models.

Kaiqi is working on extraction of bathymetry information from NASA's ICESat-2 space-based lidar, with a specific focus on automation and application in the Canadian Arctic.

Kyle’s MSc research is focused on development of whale detection algorithms and integration of those into an operational detection system for the North Atlantic right whale.

Wendian is a PhD student at Xiamen University, working in the lab for 2025-26. Wendian’s research focuses on developing high-spatial-resolution satellite-derived bathymetry algorithms to improve depth-retrieval accuracy in complex coastal environments and enable global-scale optically shallow water mapping.