.svg)
.svg)
.svg)
.svg)
.svg)
.svg)
.png)
Minisymposium Presentation
Accelerating Materials Modelling with Machine Learning: Challenges and Opportunities
Presenter
Phil is a Research Software Engineer and lecturer in the School of Physics, Engineering & Technology at the University of York. He grew up in the 1980s, where he learned physics at school and computer programming on his 8-bit Sinclair ZX Spectrum. He now combines both interests, developing high-performance software to model and predict new materials using quantum mechanics. Phil chairs the UK Car-Parrinello High-End Computing Consortium, and is the Knowledge Exchange Coordinator for the Particles At eXascale (PAX-HPC) project, part of the UK's ExCALIBUR exascale readiness programme.
Description
First-principles materials modelling software can accurately predict many materials properties, but requires the numerical solution of complex, non-linear partial differential equations. Solving these equations is computationally intensive, and first-principles simulations consume a significant fraction of HPC usage (e.g. ~40% of the UK ARCHER2 Tier-1 facility). In recent years, machine learning (ML) methods have been applied to some of these property simulations, to reduce the number of numerical evaluations. The vast materials parameter space means that devising a "universal" ML model is challenging. One promising alternative is to couple the ML and direct numerical simulations more tightly, training and using the ML "on-the-fly". We will discuss these challenges and opportunities, along with results from embedding Gaussian Process-based ML models in the popular CASTEP first-principles modelling software, to reproduce and predict atomic forces substantially faster and with controllable uncertainty.