Towards Causal Deep Learning to Model Ecosystems’ Response to Environmental Change

In ecological applications, Machine Learning (ML) predictions are used to make predictions about alternative scenarios. Such alternative scenarios however can change the distribution of features that the ML model relies on for predictions. The implication is that such uses-cases implicitly expect the ML model to generalize outside of the observational distribution. Unfortunately, this is often not the case, and ML models tend to be brittle outside of their training distribution. We will work on causal techniques for more robust ML for ecological applications.

Faculty Supervisor:

Mathias Lécuyer;Joséphine Gantois

Student:

Partner:

École Nationale Supérieure de Techniques Avancées

Discipline:

Computer science

Sector:

Education

University:

The University of British Columbia

Program:

Globalink Research Award

Current openings

Find the perfect opportunity to put your academic skills and knowledge into practice!

Government

International

Load More

International

Load More