Toward the design of ultrahigh-entropy alloys via mining six million texts

Zongrui Pei; Junqi Yin; Peter K. Liaw; Dierk Raabe

doi:10.1038/s41467-022-35766-5

Toward the design of ultrahigh-entropy alloys via mining six million texts

Zongrui Pei, Junqi Yin, Peter K. Liaw, Dierk Raabe

Analytics and AI Methods at Scale

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

30 Scopus citations

Abstract

It has long been a norm that researchers extract knowledge from literature to design materials. However, the avalanche of publications makes the norm challenging to follow. Text mining (TM) is efficient in extracting information from corpora. Still, it cannot discover materials not present in the corpora, hindering its broader applications in exploring novel materials, such as high-entropy alloys (HEAs). Here we introduce a concept of “context similarity" for selecting chemical elements for HEAs, based on TM models that analyze the abstracts of 6.4 million papers. The method captures the similarity of chemical elements in the context used by scientists. It overcomes the limitations of TM and identifies the Cantor and Senkov HEAs. We demonstrate its screening capability for six- and seven-component lightweight HEAs by finding nearly 500 promising alloys out of 2.6 million candidates. The method thus brings an approach to the development of ultrahigh-entropy alloys and multicomponent materials.

Original language	English
Article number	54
Journal	Nature Communications
Volume	14
Issue number	1
DOIs	https://doi.org/10.1038/s41467-022-35766-5
State	Published - Dec 2023

Funding

We appreciate the proofreading and valuable comments of Dr. Anubhav Jain of Lawrence Berkeley National Laboratory and John Dagdelen of the University of California Berkeley. This research used resources from New York University’s Greene supercomputer and Oak Ridge National Laboratory’s Compute and Data Environment for Science (CADES) and the Oak Ridge Leadership Computing Facility (OLCF). The latter is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725. One of us (P.K.L.) very much appreciates the support from (1) the National Science Foundation (DMR-1611180 and 1809640) with program directors, Drs. J. Yang, G. Shiflet, and D. Farkas and (2) the US Army Research Office (W911NF-13-1-0438 and W911NF-19-2-0049) with program managers, Drs. M.P. Bakas, S.N. Mathaudhu, and D.M. Stepp. We appreciate the proofreading and valuable comments of Dr. Anubhav Jain of Lawrence Berkeley National Laboratory and John Dagdelen of the University of California Berkeley. This research used resources from New York University’s Greene supercomputer and Oak Ridge National Laboratory’s Compute and Data Environment for Science (CADES) and the Oak Ridge Leadership Computing Facility (OLCF). The latter is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725. One of us (P.K.L.) very much appreciates the support from (1) the National Science Foundation (DMR-1611180 and 1809640) with program directors, Drs. J. Yang, G. Shiflet, and D. Farkas and (2) the US Army Research Office (W911NF-13-1-0438 and W911NF-19-2-0049) with program managers, Drs. M.P. Bakas, S.N. Mathaudhu, and D.M. Stepp.

Funders	Funder number
CADES
Data Environment for Science
John Dagdelen of the University of California Berkeley
Oak Ridge National Laboratory
National Science Foundation	DMR-1611180, 1809640
U.S. Department of Energy	DE-AC05-00OR22725
Army Research Office	W911NF-19-2-0049, W911NF-13-1-0438
Office of Science
Oak Ridge National Laboratory
Lawrence Berkeley National Laboratory

Access to Document

10.1038/s41467-022-35766-5

Cite this

@article{d5d18d14fc504664bb5b4800626aeeaf,

title = "Toward the design of ultrahigh-entropy alloys via mining six million texts",

abstract = "It has long been a norm that researchers extract knowledge from literature to design materials. However, the avalanche of publications makes the norm challenging to follow. Text mining (TM) is efficient in extracting information from corpora. Still, it cannot discover materials not present in the corpora, hindering its broader applications in exploring novel materials, such as high-entropy alloys (HEAs). Here we introduce a concept of “context similarity{"} for selecting chemical elements for HEAs, based on TM models that analyze the abstracts of 6.4 million papers. The method captures the similarity of chemical elements in the context used by scientists. It overcomes the limitations of TM and identifies the Cantor and Senkov HEAs. We demonstrate its screening capability for six- and seven-component lightweight HEAs by finding nearly 500 promising alloys out of 2.6 million candidates. The method thus brings an approach to the development of ultrahigh-entropy alloys and multicomponent materials.",

author = "Zongrui Pei and Junqi Yin and Liaw, {Peter K.} and Dierk Raabe",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s).",

year = "2023",

month = dec,

doi = "10.1038/s41467-022-35766-5",

language = "English",

volume = "14",

journal = "Nature Communications",

issn = "2041-1723",

publisher = "Nature Research",

number = "1",

}

TY - JOUR

T1 - Toward the design of ultrahigh-entropy alloys via mining six million texts

AU - Pei, Zongrui

AU - Yin, Junqi

AU - Liaw, Peter K.

AU - Raabe, Dierk

PY - 2023/12

Y1 - 2023/12

N2 - It has long been a norm that researchers extract knowledge from literature to design materials. However, the avalanche of publications makes the norm challenging to follow. Text mining (TM) is efficient in extracting information from corpora. Still, it cannot discover materials not present in the corpora, hindering its broader applications in exploring novel materials, such as high-entropy alloys (HEAs). Here we introduce a concept of “context similarity" for selecting chemical elements for HEAs, based on TM models that analyze the abstracts of 6.4 million papers. The method captures the similarity of chemical elements in the context used by scientists. It overcomes the limitations of TM and identifies the Cantor and Senkov HEAs. We demonstrate its screening capability for six- and seven-component lightweight HEAs by finding nearly 500 promising alloys out of 2.6 million candidates. The method thus brings an approach to the development of ultrahigh-entropy alloys and multicomponent materials.

AB - It has long been a norm that researchers extract knowledge from literature to design materials. However, the avalanche of publications makes the norm challenging to follow. Text mining (TM) is efficient in extracting information from corpora. Still, it cannot discover materials not present in the corpora, hindering its broader applications in exploring novel materials, such as high-entropy alloys (HEAs). Here we introduce a concept of “context similarity" for selecting chemical elements for HEAs, based on TM models that analyze the abstracts of 6.4 million papers. The method captures the similarity of chemical elements in the context used by scientists. It overcomes the limitations of TM and identifies the Cantor and Senkov HEAs. We demonstrate its screening capability for six- and seven-component lightweight HEAs by finding nearly 500 promising alloys out of 2.6 million candidates. The method thus brings an approach to the development of ultrahigh-entropy alloys and multicomponent materials.

UR - http://www.scopus.com/inward/record.url?scp=85145526130&partnerID=8YFLogxK

U2 - 10.1038/s41467-022-35766-5

DO - 10.1038/s41467-022-35766-5

M3 - Article

C2 - 36599862

AN - SCOPUS:85145526130

SN - 2041-1723

VL - 14

JO - Nature Communications

JF - Nature Communications

IS - 1

M1 - 54

ER -

Toward the design of ultrahigh-entropy alloys via mining six million texts

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Cite this