I’m Gabriel Sasseville, a master’s student in astrophysics co-supervised by Julie Hlavacek-Larrondo at University of Montreal and Daryl Haggard at McGill, specializing in the use of artificial intelligence to tackle complex scientific challenges. My research focuses on applying machine learning and advanced statistical models to astrophysical data, particularly in studying black holes and time series prediction. I have a strong academic foundation in both computer science and physics, with experience across computer vision, generative AI, and probabilistic modeling.

Driven by a passion for discovery and interdisciplinary research, I aim to contribute to the frontier of AI applications in science and societal challenges. In addition to my research, I enjoy collaborating on innovative projects and sharing insights through publications and public engagement.

Current Research Project

My research focuses on developing machine learning methods to interpret the complex, multi-wavelength data from Sagittarius A*, the supermassive black hole at the center of our galaxy. Specifically, I am building advanced transformer-based models to interpolate asynchronous time series data from multiple telescopes. This project aims to reveal new insights into the dynamic behavior of black holes by addressing the challenges of irregular, noisy observational data. By adapting AI methods initially developed for other fields, I am working to improve the accuracy and efficiency of time series predictions in astrophysics. This work not only deepens our understanding of black hole physics but also contributes to expanding the applications of AI in scientific research.

Research Interests

• Application-Driven Machine Learning: Focusing on application-driven AI research to tackle complex challenges in various fields.
• Time Series Forecasting: Developing and enhancing models, such as transformers, for asynchronous and irregularly sampled time series data.
• Reinforcement Learning: Exploring applications of reinforcement learning in scientific problem-solving and discovery.
• Computer Vision: Leveraging vision models for adressing social challenges/biases in models.
• Time Series Foundation Models: Improving foundation models for time series forecasting by allowing them to handle irregularly sampled data.
• Climate Change: Improving AI predictive models for climate change/environmental sciences.