- This event has passed.
Seminar by Tamas Stenczel on machine-learning accelerated ab-initio molecular dynamics
7 February @ 2:15 pm - 3:15 pm
Save the date! OCAMM presents a special seminar by Tamas Stenczel on accelerating ab initio molecular dynamics with on-the-fly machine learning. This invited seminar will take place at the Department of Chemistry and Materials Science, Aalto University on 7 February 2024 @ 14:15 in lecture hall A304 (Ke2) at the main building of the School of Chemical Engineering in the Otaniemi campus, Kemistintie 1, 02150 Espoo. The seminar is open to all. Please join us in Otaniemi to learn more about how you can make molecular dynamics orders of magnitude faster while retaining ab initio accuracy!
Title
ML Acceleration for Dynamics in Ab-Initio Modelling
Abstract
Showcase of existing methods and ongoing work on accelerating various dynamical simulations in ab-initio codes with modern ML. Replacing the ab-initio energy model where possible with an on-the-fly updated ML (GAP/ACE/MACE) one, we will visit methods and frameworks making materials science & chemical ML models easy to access for all modelling needs. Next generation methods, frameworks, scientific challenges, and opportunities for using and contributing to efforts in the field will be presented, starting from recently published advances in the CASTEP code, going to a general framework currently being implemented in a range of simulation tools.
About the speaker
Tamás K. Stenczel is a researcher at the University of Cambridge, with ties in academia and in various industrial realms. Amongst heading a research and software team at a family office, conducting open academic research, and everyday life, he is a skiier and biker, always striving to see and understand more of the world.