Portrait of Dounia Shaaban Kabakibo

Dounia Shaaban Kabakibo

Lab Representative
PhD
Supervisor
Michel Côté
Co-supervisor
Alex Hernández-García
Research Topics
AI for Science
Deep Learning
Molecular Modeling
Google Scholar
GitHub

Biography

I’m a PhD student in physics at Université de Montréal, co-supervised by Michel Côté and Alex Hernandez Garcia. My interests have wandered from theoretical to computational physics and, more recently, to AI—especially generative models and graph neural networks—which I see as new and exciting tools in my physicist’s toolbox. I use them to explore topics from Raman spectra to battery materials and critical phenomena. Outside of science, I’m passionate about social justice, art, and learning new things.

Since joining Mila, I fell for its vibrant, welcoming community. I got involved in many (mostly unofficial) ways—the talent show, speed science competitions, the mending workshop, and student–administration discussions—until it felt natural to make things official and propose my candidacy as a LabRep. I’m grateful to the students who said yes. As a LabRep, I hope to be able to give back by amplifying student voices and supporting social events that bring people together.

I’m often told I’m a good listener—feel free to reach out if you need an ear or have ideas for us LabReps!

Publications

A Comparative Study of Molecular Dynamics Approaches for Simulating Ionic Conductivity in Solid Lithium Electrolytes
Dounia Shaaban Kabakibo
Félix Therrien
Yoshua Bengio
Michel Côté
Hongyu Guo
Homin Shin
Alex Hernández-García
Accurate prediction of ionic conductivity is critical for the design of highperformance solid-state electrolytes in next-generation batterie… (see more)s. We benchmark molecular dynamics (MD) approaches for computing ionic conductivity in 21 lithium solid electrolytes for which experimental ionic conductivity has been previously reported in the literature. Specifically, we compare simulations driven by density functional theory (DFT) and by universal machine-learning interatomic potentials (uMLIPs), namely a MACE foundation model. Our results suggest comparable performance between DFT and MACE, with MACE requiring only a fraction of the computational cost. The framework developed here is designed to enable systematic comparisons with additional uMLIPs and fine-tuned models in future work.
2026-03-01
AI4Mat @ International Conference on Learning Representations (poster)
openreview.net
openreview.net
Large scale Raman spectrum calculations in defective 2D materials using deep learning
Olivier Malenfant-Thuot
Dounia Shaaban Kabakibo
Simon Blackburn
Bruno Rousseau
Michel Côté
We introduce a machine learning prediction workflow to study the impact of defects on the Raman response of 2D materials. By combining the u… (see more)se of machine-learned interatomic potentials, the Raman-active Γ-weighted density of states method and splitting configurations in independant patches, we are able to reach simulation sizes in the tens of thousands of atoms, with diagonalization now being the main bottleneck of the simulation. We apply the method to two systems, isotopic graphene and defective hexagonal boron nitride, and compare our predicted Raman response to experimental results, with good agreement. Our method opens up many possibilities for future studies of Raman response in solid-state physics.
2024-12-17
Journal of Physics: Condensed Matter (published)
doi.org
arxiv.org