Annual Review of Materials Research
Evolving the Materials
Genome: How Machine
Learning Is Fueling the
Next Generation of
Materials Discovery
Changwon Suh,
1
Clyde Fare,
2
James A. Warren,
3
and Edward O. Pyzer-Knapp
2
1
Nexight Group, Silver Spring, Maryland 20910, USA
2
IBM Research, Daresbury WA4 4AD, United Kingdom; email: epyzerk3@uk.ibm.com
3
Material Measurement Laboratory,National Institute of Standards and Technology,
Gaithersburg, Maryland 20899, USA
Annu. Rev. Mater. Res. 2020. 50:1–25
First published as a Review in Advance on
April 21, 2020
The Annual Review of Materials Research is online at
matsci.annualreviews.org
https://doi.org/10.1146/annurev-matsci-082019-
105100
Copyright © 2020 by Annual Reviews.
All rights reserved
Keywords
materials genome, materials discovery, artifcial intelligence, machine
learning, data
Abstract
Machine learning, applied to chemical and materials data, is transforming
the feld of materials discovery and design, yet signifcant work is still re-
quired to fully take advantage of machine learning algorithms, tools, and
methods. Here, we review the accomplishments to date of the community
and assess the maturity of state-of-the-art, data-intensive research activities
that combine perspectives from materials science and chemistry. We focus
on three major themes—learning to see, learning to estimate, and learning
to search materials—to show how advanced computational learning tech-
nologies are rapidly and successfully used to solve materials and chemistry
problems. Additionally, we discuss a clear path toward a future where data-
driven approaches to materials discovery and design are standard practice.
1
Annu. Rev. Mater. Res. 2020.50:1-25. Downloaded from www.annualreviews.org
Access provided by 34.228.24.229 on 07/22/20. For personal use only.