Materials science in the artificial intelligence age: High-throughput library generation, machine learning, and a pathway from correlations to the underpinning physics

Rama K. Vasudevan; Kamal Choudhary; Apurva Mehta; Ryan Smith; Gilad Kusne; Francesca Tavazza; Lukas Vlcek; Maxim Ziatdinov; Sergei V. Kalinin; Jason Hattrick-Simpers

doi:10.1557/mrc.2019.95

Materials science in the artificial intelligence age: High-throughput library generation, machine learning, and a pathway from correlations to the underpinning physics

Rama K. Vasudevan, Kamal Choudhary, Apurva Mehta, Ryan Smith, Gilad Kusne, Francesca Tavazza, Lukas Vlcek, Maxim Ziatdinov, Sergei V. Kalinin, Jason Hattrick-Simpers

Data Nanoanalytics

Research output: Contribution to journal › Review article › peer-review

128 Scopus citations

Abstract

The use of statistical/machine learning (ML) approaches to materials science is experiencing explosive growth. Here, we review recent work focusing on the generation and application of libraries from both experiment and theoretical tools. The library data enables classical correlative ML and also opens the pathway for exploration of underlying causative physical behaviors. We highlight key advances facilitated by this approach and illustrate how modeling, macroscopic experiments, and imaging can be combined to accelerate the understanding and development of new materials systems. These developments point toward a data-driven future wherein knowledge can be aggregated and synthesized, accelerating the advancement of materials science.

Original language	English
Pages (from-to)	821-838
Number of pages	18
Journal	MRS Communications
Volume	9
Issue number	3
DOIs	https://doi.org/10.1557/mrc.2019.95
State	Published - Sep 1 2019

Funding

The work was supported by the U.S. Department of Energy, Office of Science, Materials Sciences and Engineering Division (R.K.V. and S.V.K.). A portion of this research was conducted at and supported (M.Z.) by the Center for Nanophase Materials Sciences, which is a US DOE Office of Science User Facility.

Funders	Funder number
Center for Nanophase Materials Sciences
DOE Office of Science user facility
U.S. Department of Energy
Office of Science

Access to Document

10.1557/mrc.2019.95

Cite this

Vasudevan, R. K., Choudhary, K., Mehta, A., Smith, R., Kusne, G., Tavazza, F., Vlcek, L., Ziatdinov, M., Kalinin, S. V., & Hattrick-Simpers, J. (2019). Materials science in the artificial intelligence age: High-throughput library generation, machine learning, and a pathway from correlations to the underpinning physics. MRS Communications, 9(3), 821-838. https://doi.org/10.1557/mrc.2019.95

@article{7b206ff69aa441cbb5c3960e1d0a13f1,

title = "Materials science in the artificial intelligence age: High-throughput library generation, machine learning, and a pathway from correlations to the underpinning physics",

abstract = "The use of statistical/machine learning (ML) approaches to materials science is experiencing explosive growth. Here, we review recent work focusing on the generation and application of libraries from both experiment and theoretical tools. The library data enables classical correlative ML and also opens the pathway for exploration of underlying causative physical behaviors. We highlight key advances facilitated by this approach and illustrate how modeling, macroscopic experiments, and imaging can be combined to accelerate the understanding and development of new materials systems. These developments point toward a data-driven future wherein knowledge can be aggregated and synthesized, accelerating the advancement of materials science.",

author = "Vasudevan, {Rama K.} and Kamal Choudhary and Apurva Mehta and Ryan Smith and Gilad Kusne and Francesca Tavazza and Lukas Vlcek and Maxim Ziatdinov and Kalinin, {Sergei V.} and Jason Hattrick-Simpers",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2019.",

year = "2019",

month = sep,

day = "1",

doi = "10.1557/mrc.2019.95",

language = "English",

volume = "9",

pages = "821--838",

journal = "MRS Communications",

issn = "2159-6859",

publisher = "Materials Research Society",

number = "3",

}

Vasudevan, RK, Choudhary, K, Mehta, A, Smith, R, Kusne, G, Tavazza, F, Vlcek, L, Ziatdinov, M, Kalinin, SV & Hattrick-Simpers, J 2019, 'Materials science in the artificial intelligence age: High-throughput library generation, machine learning, and a pathway from correlations to the underpinning physics', MRS Communications, vol. 9, no. 3, pp. 821-838. https://doi.org/10.1557/mrc.2019.95

TY - JOUR

T1 - Materials science in the artificial intelligence age

T2 - High-throughput library generation, machine learning, and a pathway from correlations to the underpinning physics

AU - Vasudevan, Rama K.

AU - Choudhary, Kamal

AU - Mehta, Apurva

AU - Smith, Ryan

AU - Kusne, Gilad

AU - Tavazza, Francesca

AU - Vlcek, Lukas

AU - Ziatdinov, Maxim

AU - Kalinin, Sergei V.

AU - Hattrick-Simpers, Jason

PY - 2019/9/1

Y1 - 2019/9/1

N2 - The use of statistical/machine learning (ML) approaches to materials science is experiencing explosive growth. Here, we review recent work focusing on the generation and application of libraries from both experiment and theoretical tools. The library data enables classical correlative ML and also opens the pathway for exploration of underlying causative physical behaviors. We highlight key advances facilitated by this approach and illustrate how modeling, macroscopic experiments, and imaging can be combined to accelerate the understanding and development of new materials systems. These developments point toward a data-driven future wherein knowledge can be aggregated and synthesized, accelerating the advancement of materials science.

AB - The use of statistical/machine learning (ML) approaches to materials science is experiencing explosive growth. Here, we review recent work focusing on the generation and application of libraries from both experiment and theoretical tools. The library data enables classical correlative ML and also opens the pathway for exploration of underlying causative physical behaviors. We highlight key advances facilitated by this approach and illustrate how modeling, macroscopic experiments, and imaging can be combined to accelerate the understanding and development of new materials systems. These developments point toward a data-driven future wherein knowledge can be aggregated and synthesized, accelerating the advancement of materials science.

UR - http://www.scopus.com/inward/record.url?scp=85069446478&partnerID=8YFLogxK

U2 - 10.1557/mrc.2019.95

DO - 10.1557/mrc.2019.95

M3 - Review article

AN - SCOPUS:85069446478

SN - 2159-6859

VL - 9

SP - 821

EP - 838

JO - MRS Communications

JF - MRS Communications

IS - 3

ER -

Materials science in the artificial intelligence age: High-throughput library generation, machine learning, and a pathway from correlations to the underpinning physics

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Cite this