Autodifferentiation in atomistic simulations: interatomic potentials for battery materials, uncertainty-based active learning and rare-event sampling
Refreshments are available from 3:30pm in the Hume-Rothery Meeting Room
Deep learning, and in general differentiable programming, allow expressing many scientific problems as end-to-end learning tasks, while retaining some inductive bias derived from physics-based understanding. Common themes in scientific machine learning involve learning surrogate functions of expensive simulators, sampling complex distributions directly or time-propagation of known or unknown differential equation systems efficiently.

In this talk, we will analyse our recent work in applying deep learning surrogates and auto-differentiation in atomistic simulations of materials. In particular, we will explore active learning of machine learning potentials with differentiable uncertainty and their application to uncover the mechanism of ion diffusion in superionic inorganic conductor LGPS. Lastly, we will describe the application of differentiable simulations for learning interaction potentials from experimental data and for reaction-path finding without prior knowledge of collective variables.
Date: 25 May 2023, 16:00 (Thursday, 5th week, Trinity 2023)
Venue: Hume-Rothery Building, Parks Road OX1 3PH
Venue Details: Hybrid: Hume-Rothery Lecture Theatre and online using Panopto - SSO required: https://ox.cloud.panopto.eu/Panopto/Pages/Viewer.aspx?id=c98bbd59-80b1-4269-a7fe-b00600e1052a
Speaker: Associate Professor Rafael Gomez-Bombarelli (MIT)
Organising department: Department of Materials
Organiser: Lorraine Laird (Department of Materials)
Organiser contact email address: lorraine.laird@materials.ox.ac.uk
Host: Dr Andrey Poletayev (University of Oxford)
Part of: Materials Departmental Colloquia
Booking required?: Not required
Audience: Public
Editor: Lorraine Laird