Ouail Zakary

My research focuses on developing machine learning-driven approaches for the atomistic modeling of molecular and solid-state systems under real physicochemical conditions. By integrating quantum mechanics at the relativistic level with classical and path integral molecular dynamics, I aim to deliver highly predictive models for structural, dynamic, and spectroscopic observables.

A significant part of my work involves training equivariant graph neural networks and kernel regression models to develop MLIPs and NMR-ML models that enable realistic simulations of complex materials.