You are here

Materials discovery with artificial intelligence

Speaker: 
Dr. Gareth Conduit (University Cambridge, UK)
Date: 
Wed, 13/09/2017 - 11:00am to 12:00pm
Location: 
Physics Conference Room (S11-02-07)
Host: 
Prof Feng Yuan Ping
Event Type: 
Seminars

Abstract

We have developed a computational tool that employs deep learning with neural networks to discover new materials. The tool combines databases of experimental results with Density Functional Theory calculations to get high accuracy across a broad range of compositions. This enables us to propose materials that are most likely to fulfil multivariate targets. This holistic approach to materials design has allowed us to propose four new nickel-base alloys for use in jet engines, whose properties have been experimentally verified, new Lithium-ion battery cathode materials, and titanium alloys. The neural network approach to materials modelling can also assess the integrity of materials data. We have exploited this capability to automatically validate and correct entries in a commercial metal alloy and polymer database.

About the Speaker

Dr Gareth Conduit has a track record of research in materials design. He has proposed, developed, and exploited a novel neural network to design new materials. Materials have been designed and experimentally tested with a variety of companies including nickel metal alloys, Li-ion batteries, and lubricants. More recently the method has been applied to drug discovery and commercialized through startup Intellegens. Gareth also maintains research interests in electronic structure and quantum field theory.

Theme inspired by Danetsoft