Grants and Contributions

Furthermore, the current lack and/or public availability of relevant data sets hinders deployment of both current sustainability assessment methods and advanced machine leaning techniques to both develop data gap filling techniques and to identify best-fit technology solutions to known sustainability challenges.

Develop digital adoption plan

This project aims to enhance Canada's training capacity in satellite-based Earth observation to meet the growing demand for skilled professionals capable of handling large datasets and utilizing technologies like cloud computing and machine learning. Collaborating with industry and government partners across various application areas, the project will revise existing courses and develop new training materials to address emerging gaps, ensuring a mix of traditional university courses and flexible workshops accessible to professionals and students, ultimately providing long-lasting benefits to Canadians beyond the project's duration.

The project aims to develop machine learning-based methods for automatic estimation of Arctic ice concentration, classification of sea ice types, and monitoring of pack ice leads in the Arctic Ocean, focusing on regions like the Beaufort Sea and Canadian Arctic waters.

The objective of this project is to develop an AI-based algorithm that can improve atmospheric correction of satellite images over Canadian lakes. This will address current inaccuracies that hinder monitoring efforts, which are crucial for various aspects of Canadian life. The project aims to create a hyperspectral algorithm for accurate atmospheric correction by collecting in situ data and using advanced modeling techniques. AI will be leveraged to improve computational efficiency and enable more precise utilization of remote sensing data. This will ultimately advance the field of lake monitoring and benefit multiple stakeholders.

The Copernicus Expansion Missions Sea Ice Experiment (CEMSIE) project, led by a consortium of Canadian and European universities, with support from the European Space Agency (ESA), aims to enhance satellite monitoring of Arctic sea ice. This is to be achieved by simultaneously deploying multiple surface-based electromagnetic instruments in Dease Strait, near the Canadian High Arctic Research Station in Cambridge Bay, Nunavut. These instruments mimic three soon-to-be-launched ESA Copernicus Sentinel Expansion mission satellites: CRISTAL, CIMR, and ROSE-L.

CEMSIE's primary objectives include demonstrating how data integration from these three sensors can provide more comprehensive information than the sum of its parts. This integration aims to reduce uncertainties and enhance the accuracy of microwave satellite estimates of sea ice concentration, snow depth, and sea ice thickness.

This project aims to enhance understanding of Canada's surficial geology by developing an automated method using remote satellite imagery to map landforms like eskers and estimate their composition. By integrating machine learning and morphometric analysis, the project seeks to streamline natural resource projects, particularly those reliant on gravel from eskers, by providing precise remote estimates of aggregate deposits, benefiting infrastructure development initiatives.

Nitrous oxide (N2O) emissions, primarily from agricultural activities, pose a significant challenge to global warming, with Canada contributing substantially. By integrating satellite imagery and field-based measurements, this project aims to map high-risk areas for N2O emissions in western Canada, potentially reducing emissions by 40% through targeted mitigation strategies, with real-time recommendations for climate change adaptation.

This project, involving remote sensing specialists and oceanographers from universities and government departments, aims to leverage NASA's PACE mission to improve the accuracy of ocean color observations, particularly in eastern Canada, to better understand the ocean's capacity to uptake carbon and its changes over time. By enhancing phytoplankton biomass estimation and extracting additional information on phytoplankton properties, the research aligns with objectives to address climate change, foster partnerships, and enhance ocean monitoring efforts critical for ecosystem health and carbon management.

This project aims to develop open-access tools integrating LIDAR-derived forest fuel assessments with satellite data to extrapolate critical forest fuel attributes across Canada's forested areas, crucial for effective forest management and fire decision-making. By leveraging innovative modeling techniques and open data distribution, the project seeks to advance forest fuel assessment methods, potentially reaching an Application Readiness Level of 6, offering valuable resources for stakeholders and enhancing wildfire risk management.