Webinar:: Title: Foundational models for materials chemistry, Speaker: Prof. Gábor Csányi, University of Cambridge

Monthly Webinar: USACM, TTA-Nanotechnology and Lower Scale Phenomena

This is a reminder that our next monthly webinar is November 27, 2-3pm CST. The speaker will be Professor Gábor Csányi from the University of Cambridge. We are hoping the format will promote a lively interactive discussion and engage both junior and senior members of our community. Look forward to seeing you there. Talk and discussions will be archived and available on our website if accepted by the speaker.

November 27; 2pm CST

Speaker: Prof. Gábor Csányi, University of Cambridge

Title: Foundational models for materials chemistry

Join Zoom Meeting
https://us06web.zoom.us/j/84541274013?pwd=ZDhuM09BaUlVVlBuREhEV0sweGFlZz09 (Meeting ID: 845 4127 4013
Passcode: 799065)

Please forward to anyone who may be interested.

Abstract: 

A new computational task has been defined and solved over the past 15 years for extended material systems: the analytic fitting of the Born-Oppenheimer potential energy surface as a function of nuclear coordinates. The resulting potentials  ("force fields") are reactive, many-body, with evaluation costs that are currently on the order of 0.1-10 ms/atom/cpu core (or about 1-10ms on a powerful GPU), and reach accuracies of a few meV/atom when trained specifically for a given system using iterative or active learning methods. The latest and most successful architectures leverage many-body symmetric descriptions of local geometry and equivariant message passing networks.  Perhaps the most surprising recent result is the stability of models trained on very diverse training sets across the whole periodic table. Our recent discovery is that the MACE-MP-0 model that was trained on just ~150,000 real and hypothetical small inorganic crystals (90% of training set < 70 atoms), is capable of stable molecular dynamics at ambient conditions on any system tested so far - this includes crystals, liquids, surfaces, clusters, molecules, and combinations of all of these. The astounding generalisation performance of such foundation models open the possibility to creating a universally applicable interatomic potential with useful accuracy for materials (especially when fine-tuned with a little bit of domain-specific data), and democratise quantum-accurate large scale molecular simulations by lowering the barrier to entry into the field. Similarly, in the domain of organic chemistry, training just on small molecules and small clusters allows accurate simulation of condensed phase systems, and first principles prediction of quantities such as hydration free energies for the first time.