Machine learning as a contributor to physics: Understanding Mg alloys

Zongrui Pei; Junqi Yin

doi:10.1016/j.matdes.2019.107759

Machine learning as a contributor to physics: Understanding Mg alloys

Zongrui Pei, Junqi Yin

Analytics and AI Methods at Scale

Research output: Contribution to journal › Article › peer-review

28 Scopus citations

Abstract

Machine learning (ML) methods have played an increasingly important role in materials design. Take Mg alloys as an example, we show the ML methods not only supply mathematical solutions but more importantly also contribute to understand the physics in the problem. Hitherto, the role of ML methods is widely applied in high-throughput predictions, while their contribution to understand the physical mechanisms has been rarely explored. In this study, we firstly demonstrate that the Gaussian Process Classification algorithm reliably and efficiently predicts promising solutes for ductile Mg alloys, and then use these results to evaluate the correlation between two recently proposed mechanisms. Our results help clarify the controversy regarding the ductility mechanisms that can be used as the guide for materials design.

Original language	English
Article number	107759
Journal	Materials and Design
Volume	172
DOIs	https://doi.org/10.1016/j.matdes.2019.107759
State	Published - Jun 15 2019

Funding

This work was sponsored by the U.S. Department of Energy, Office of Science, Basic Energy Sciences, Materials Science and Engineering Division. This research used resources of Oak Ridge National Laboratory's Compute and Data Environment for Science (CADES) and the Oak Ridge Leadership Computing Facility, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725. This work was sponsored by the U.S. Department of Energy , Office of Science, Basic Energy Sciences, Materials Science and Engineering Division. This research used resources of Oak Ridge National Laboratory's Compute and Data Environment for Science (CADES) and the Oak Ridge Leadership Computing Facility, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725 .

Funders	Funder number
Data Environment for Science
Materials Science and Engineering Division
U.S. Department of Energy	DE-AC05-00OR22725
Office of Science
Basic Energy Sciences
Cades Foundation

Keywords

Gaussian process classification
Machine learning
Mg alloys

Access to Document

10.1016/j.matdes.2019.107759

Cite this

@article{6e96d4311a3b49e6a5f80e77800828ee,

title = "Machine learning as a contributor to physics: Understanding Mg alloys",

abstract = "Machine learning (ML) methods have played an increasingly important role in materials design. Take Mg alloys as an example, we show the ML methods not only supply mathematical solutions but more importantly also contribute to understand the physics in the problem. Hitherto, the role of ML methods is widely applied in high-throughput predictions, while their contribution to understand the physical mechanisms has been rarely explored. In this study, we firstly demonstrate that the Gaussian Process Classification algorithm reliably and efficiently predicts promising solutes for ductile Mg alloys, and then use these results to evaluate the correlation between two recently proposed mechanisms. Our results help clarify the controversy regarding the ductility mechanisms that can be used as the guide for materials design.",

keywords = "Gaussian process classification, Machine learning, Mg alloys",

author = "Zongrui Pei and Junqi Yin",

note = "Publisher Copyright: {\textcopyright} 2019 The Authors",

year = "2019",

month = jun,

day = "15",

doi = "10.1016/j.matdes.2019.107759",

language = "English",

volume = "172",

journal = "Materials and Design",

issn = "0264-1275",

publisher = "Elsevier",

}

TY - JOUR

T1 - Machine learning as a contributor to physics

T2 - Understanding Mg alloys

AU - Pei, Zongrui

AU - Yin, Junqi

PY - 2019/6/15

Y1 - 2019/6/15

N2 - Machine learning (ML) methods have played an increasingly important role in materials design. Take Mg alloys as an example, we show the ML methods not only supply mathematical solutions but more importantly also contribute to understand the physics in the problem. Hitherto, the role of ML methods is widely applied in high-throughput predictions, while their contribution to understand the physical mechanisms has been rarely explored. In this study, we firstly demonstrate that the Gaussian Process Classification algorithm reliably and efficiently predicts promising solutes for ductile Mg alloys, and then use these results to evaluate the correlation between two recently proposed mechanisms. Our results help clarify the controversy regarding the ductility mechanisms that can be used as the guide for materials design.

AB - Machine learning (ML) methods have played an increasingly important role in materials design. Take Mg alloys as an example, we show the ML methods not only supply mathematical solutions but more importantly also contribute to understand the physics in the problem. Hitherto, the role of ML methods is widely applied in high-throughput predictions, while their contribution to understand the physical mechanisms has been rarely explored. In this study, we firstly demonstrate that the Gaussian Process Classification algorithm reliably and efficiently predicts promising solutes for ductile Mg alloys, and then use these results to evaluate the correlation between two recently proposed mechanisms. Our results help clarify the controversy regarding the ductility mechanisms that can be used as the guide for materials design.

KW - Gaussian process classification

KW - Machine learning

KW - Mg alloys

UR - http://www.scopus.com/inward/record.url?scp=85063668239&partnerID=8YFLogxK

U2 - 10.1016/j.matdes.2019.107759

DO - 10.1016/j.matdes.2019.107759

M3 - Article

AN - SCOPUS:85063668239

SN - 0264-1275

VL - 172

JO - Materials and Design

JF - Materials and Design

M1 - 107759

ER -

Machine learning as a contributor to physics: Understanding Mg alloys

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this