Research project title

Machine Learning and Downscaling to Advance Ecological Applications

Education level

Post-doctoral fellowship

Director/co-director

Director: Julie Carreau

Co-director(s): Laura Pollock, Assistant Professor in Quantitative Ecology at McGill University

End of display

September 30, 2025

Areas of expertise

Environment

Evolution and ecology

Artificial intelligence

Applied mathematics

Primary sphere of excellence in research

Modeling and Artificial Intelligence

Secondary sphere(s) of excellence in research

Environment, Economy, and Society

Unit(s) and department(s)

Department of Mathematical and Industrial Engineering

IVADO

Conditions

• PhD, either completed or about to be completed (field of PhD is flexible).
• Strong background in machine learning.
• Experience in applications of machine learning to either downscaling or ecology.
• Preference will be given to candidates with expertise in machine learning and knowledge of ecology or conservation.

Detailed description

IVADO is an artificial intelligence research, training and knowledge mobilization consortium that generates, stimulates and supports initiatives in the field of artificial intelligence (AI) by bringing together the community of researchers, organizations and institutions. IVADO’s Regroupement 7 focuses on innovation in artificial intelligence and machine learning for major climate and biodiversity issues.

We seek a postdoctoral researcher for an interdisciplinary project applying state-of-the-art machine learning approaches to the spatial scaling of biodiversity.

The spatial and temporal resolution of our ecological datasets (including hyperspectral, drone and satellite imagery, and climate models) is rapidly increasing and outpacing our ability to use this data to answer key ecological questions, such as how biodiversity scales with area and how trophic structure scales with terrestrial biomass. Effective use of these new data combined with more traditional biological surveys is critical to address these questions so that we can better understand ecosystem function and potential biodiversity loss.

Specifically, the project requires knowledge of downscaling/superresolution techniques using machine learning models. The researcher is expected to lead and manage a project that applies machine learning and downscaling algorithms to ecological applications and will work with a team of half ecologists and half machine learning researchers. Our case study is a comparison study between temperate and tropical forests using existing tools (e.g., species distribution modeling) and ecological as well as climate scaling to make cross-scale predictions on forest composition and terrestrial biomass. The researcher will have the opportunity to innovate in machine learning techniques and/or ecological applications.

Financing possibility

Funding is provided by IVADO.

The candidate will be affiliated with Polytechnique Montréal or McGill University and will work at Mila. The candidate will have the opportunity to collaborate with the other two co-directors of the R7 environment cluster: David Rolnick (McGill University, Mila) and Étienne Laliberté (Université de Montréal, Mila).

We are committed to fostering equality, diversity, and inclusion within our team. We strongly encourage applications from members of all underrepresented groups, including visible minorities, women, Indigenous Peoples, people with disabilities, and individuals of all gender identities.

How to apply: Please send your application file to Dana F. Simon (Dana.simon@ivado.ca) consisting of:

• CV
• Cover letter
• PhD transcripts (official or unofficial if ongoing term not yet completed)
• A letter of recommendation is required. Please ensure the referee’s email address is accurate and that they are available.