Materials Fingerprinting Classification

Adam Spannaus; Kody J.H. Law; Piotr Luszczek; Farzana Nasrin; Cassie Putman Micucci; Peter K. Liaw; Louis J. Santodonato; David J. Keffer; Vasileios Maroulas

doi:10.1016/j.cpc.2021.108019

Materials Fingerprinting Classification

Adam Spannaus, Kody J.H. Law, Piotr Luszczek, Farzana Nasrin, Cassie Putman Micucci, Peter K. Liaw, Louis J. Santodonato, David J. Keffer, Vasileios Maroulas

Biostatistics and Biomedical Informatics

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

7 Scopus citations

Abstract

Significant progress in many classes of materials could be made with the availability of experimentally-derived large datasets composed of atomic identities and three-dimensional coordinates. Methods for visualizing the local atomic structure, such as atom probe tomography (APT), which routinely generate datasets comprised of millions of atoms, are an important step in realizing this goal. However, state-of-the-art APT instruments generate noisy and sparse datasets that provide information about elemental type, but obscure atomic structures, thus limiting their subsequent value for materials discovery. The application of a materials fingerprinting process, a machine learning algorithm coupled with topological data analysis, provides an avenue by which here-to-fore unprecedented structural information can be extracted from an APT dataset. As a proof of concept, the material fingerprint is applied to high-entropy alloy APT datasets containing body-centered cubic (BCC) and face-centered cubic (FCC) crystal structures. A local atomic configuration centered on an arbitrary atom is assigned a topological descriptor, with which it can be characterized as a BCC or FCC lattice with near perfect accuracy, despite the inherent noise in the dataset. This successful identification of a fingerprint is a crucial first step in the development of algorithms which can extract more nuanced information, such as chemical ordering, from existing datasets of complex materials. Program summary: Program Title: Materials Fingerprinting CPC Library link to program files: https://doi.org/10.17632/2fhch3x85m.1 Developer's repository link: https://github.com/maroulaslab/Materials-Fingerprinting Licensing provisions: GPLv3 Programming language: Python Supplementary material: A user manual and examples are provided with the source code in the GitHub repository. Nature of problem: Atom probe tomography provides sub-nanometer resolution of a material, but due to noise and sparsity introduced by the process, the crystal structure of a material cannot presently be determined from the resulting data. Solution method: Our Materials Fingerprinting library presents a topologically informed machine learning methodology to classify the lattice structure of a material from atomic probe tomography data. We create persistence diagrams from small neighborhoods centered at each atom in the resulting APT data and use the summary statistics of a novel metric on the space of persistence diagrams as features for a classification algorithm.

Original language	English
Article number	108019
Journal	Computer Physics Communications
Volume	266
DOIs	https://doi.org/10.1016/j.cpc.2021.108019
State	Published - Sep 2021

Funding

This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan ( http://energy.gov/downloads/doe-public-access-plan ). The authors are grateful to two anonymous referees for helpful comments and suggestions that substantially improved the manuscript. The APT experiments were conducted at the Oak Ridge National Laboratory's Center for Nanophase Materials Sciences (CNMS), which is a U.S. DOE Office of Science User Facility. The authors would like to thank Jonathan Poplawsky for insightful discussions about the APT method. V.M. is grateful for support from Army Research Office Grant # W911NF-17-1-0313 and the National Science Foundation DMS-1821241 . D.K. and V.M. are grateful for support from grant University of Tennessee – Knoxville , Seed: Keffer 19 . A.S., C.M., and F.N., acknowledge the Mathematics Department of the University of Tennessee, where A.S. and C.M. conducted this research as part of their Ph.D studies and F.N. was a Post-Doctoral research associate. This research used resources of the Compute and Data Environment for Science (CADES) at the Oak Ridge National Laboratory, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725 . The authors are grateful to two anonymous referees for helpful comments and suggestions that substantially improved the manuscript. The APT experiments were conducted at the Oak Ridge National Laboratory's Center for Nanophase Materials Sciences (CNMS), which is a U.S. DOE Office of Science User Facility. The authors would like to thank Jonathan Poplawsky for insightful discussions about the APT method. V.M. is grateful for support from Army Research Office Grant # W911NF-17-1-0313 and the National Science Foundation DMS-1821241. D.K. and V.M. are grateful for support from grant University of Tennessee – Knoxville, Seed: Keffer 19. A.S. C.M. and F.N. acknowledge the Mathematics Department of the University of Tennessee, where A.S. and C.M. conducted this research as part of their Ph.D studies and F.N. was a Post-Doctoral research associate. This research used resources of the Compute and Data Environment for Science (CADES) at the Oak Ridge National Laboratory, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725. This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan).

Funders	Funder number
CADES
DOE Public Access Plan
Data Environment for Science
United States Government
National Science Foundation	DMS-1821241
U.S. Department of Energy	DE-AC05-00OR22725
Directorate for Mathematical and Physical Sciences	1821241
Army Research Office	W911NF-17-1-0313
Office of Science
University of Tennessee

Keywords

Atom probe tomography
High entropy alloy
Machine learning
Materials discovery
Topological data analysis

Access to Document

10.1016/j.cpc.2021.108019

Cite this

@article{7d3ed2b5df5543e59b0ea0fc06d4090e,

title = "Materials Fingerprinting Classification",

abstract = "Significant progress in many classes of materials could be made with the availability of experimentally-derived large datasets composed of atomic identities and three-dimensional coordinates. Methods for visualizing the local atomic structure, such as atom probe tomography (APT), which routinely generate datasets comprised of millions of atoms, are an important step in realizing this goal. However, state-of-the-art APT instruments generate noisy and sparse datasets that provide information about elemental type, but obscure atomic structures, thus limiting their subsequent value for materials discovery. The application of a materials fingerprinting process, a machine learning algorithm coupled with topological data analysis, provides an avenue by which here-to-fore unprecedented structural information can be extracted from an APT dataset. As a proof of concept, the material fingerprint is applied to high-entropy alloy APT datasets containing body-centered cubic (BCC) and face-centered cubic (FCC) crystal structures. A local atomic configuration centered on an arbitrary atom is assigned a topological descriptor, with which it can be characterized as a BCC or FCC lattice with near perfect accuracy, despite the inherent noise in the dataset. This successful identification of a fingerprint is a crucial first step in the development of algorithms which can extract more nuanced information, such as chemical ordering, from existing datasets of complex materials. Program summary: Program Title: Materials Fingerprinting CPC Library link to program files: https://doi.org/10.17632/2fhch3x85m.1 Developer's repository link: https://github.com/maroulaslab/Materials-Fingerprinting Licensing provisions: GPLv3 Programming language: Python Supplementary material: A user manual and examples are provided with the source code in the GitHub repository. Nature of problem: Atom probe tomography provides sub-nanometer resolution of a material, but due to noise and sparsity introduced by the process, the crystal structure of a material cannot presently be determined from the resulting data. Solution method: Our Materials Fingerprinting library presents a topologically informed machine learning methodology to classify the lattice structure of a material from atomic probe tomography data. We create persistence diagrams from small neighborhoods centered at each atom in the resulting APT data and use the summary statistics of a novel metric on the space of persistence diagrams as features for a classification algorithm.",

keywords = "Atom probe tomography, High entropy alloy, Machine learning, Materials discovery, Topological data analysis",

author = "Adam Spannaus and Law, {Kody J.H.} and Piotr Luszczek and Farzana Nasrin and Micucci, {Cassie Putman} and Liaw, {Peter K.} and Santodonato, {Louis J.} and Keffer, {David J.} and Vasileios Maroulas",

note = "Publisher Copyright: {\textcopyright} 2021 Elsevier B.V.",

year = "2021",

month = sep,

doi = "10.1016/j.cpc.2021.108019",

language = "English",

volume = "266",

journal = "Computer Physics Communications",

issn = "0010-4655",

publisher = "Elsevier",

}

TY - JOUR

T1 - Materials Fingerprinting Classification

AU - Spannaus, Adam

AU - Law, Kody J.H.

AU - Luszczek, Piotr

AU - Nasrin, Farzana

AU - Micucci, Cassie Putman

AU - Liaw, Peter K.

AU - Santodonato, Louis J.

AU - Keffer, David J.

AU - Maroulas, Vasileios

PY - 2021/9

Y1 - 2021/9

N2 - Significant progress in many classes of materials could be made with the availability of experimentally-derived large datasets composed of atomic identities and three-dimensional coordinates. Methods for visualizing the local atomic structure, such as atom probe tomography (APT), which routinely generate datasets comprised of millions of atoms, are an important step in realizing this goal. However, state-of-the-art APT instruments generate noisy and sparse datasets that provide information about elemental type, but obscure atomic structures, thus limiting their subsequent value for materials discovery. The application of a materials fingerprinting process, a machine learning algorithm coupled with topological data analysis, provides an avenue by which here-to-fore unprecedented structural information can be extracted from an APT dataset. As a proof of concept, the material fingerprint is applied to high-entropy alloy APT datasets containing body-centered cubic (BCC) and face-centered cubic (FCC) crystal structures. A local atomic configuration centered on an arbitrary atom is assigned a topological descriptor, with which it can be characterized as a BCC or FCC lattice with near perfect accuracy, despite the inherent noise in the dataset. This successful identification of a fingerprint is a crucial first step in the development of algorithms which can extract more nuanced information, such as chemical ordering, from existing datasets of complex materials. Program summary: Program Title: Materials Fingerprinting CPC Library link to program files: https://doi.org/10.17632/2fhch3x85m.1 Developer's repository link: https://github.com/maroulaslab/Materials-Fingerprinting Licensing provisions: GPLv3 Programming language: Python Supplementary material: A user manual and examples are provided with the source code in the GitHub repository. Nature of problem: Atom probe tomography provides sub-nanometer resolution of a material, but due to noise and sparsity introduced by the process, the crystal structure of a material cannot presently be determined from the resulting data. Solution method: Our Materials Fingerprinting library presents a topologically informed machine learning methodology to classify the lattice structure of a material from atomic probe tomography data. We create persistence diagrams from small neighborhoods centered at each atom in the resulting APT data and use the summary statistics of a novel metric on the space of persistence diagrams as features for a classification algorithm.

AB - Significant progress in many classes of materials could be made with the availability of experimentally-derived large datasets composed of atomic identities and three-dimensional coordinates. Methods for visualizing the local atomic structure, such as atom probe tomography (APT), which routinely generate datasets comprised of millions of atoms, are an important step in realizing this goal. However, state-of-the-art APT instruments generate noisy and sparse datasets that provide information about elemental type, but obscure atomic structures, thus limiting their subsequent value for materials discovery. The application of a materials fingerprinting process, a machine learning algorithm coupled with topological data analysis, provides an avenue by which here-to-fore unprecedented structural information can be extracted from an APT dataset. As a proof of concept, the material fingerprint is applied to high-entropy alloy APT datasets containing body-centered cubic (BCC) and face-centered cubic (FCC) crystal structures. A local atomic configuration centered on an arbitrary atom is assigned a topological descriptor, with which it can be characterized as a BCC or FCC lattice with near perfect accuracy, despite the inherent noise in the dataset. This successful identification of a fingerprint is a crucial first step in the development of algorithms which can extract more nuanced information, such as chemical ordering, from existing datasets of complex materials. Program summary: Program Title: Materials Fingerprinting CPC Library link to program files: https://doi.org/10.17632/2fhch3x85m.1 Developer's repository link: https://github.com/maroulaslab/Materials-Fingerprinting Licensing provisions: GPLv3 Programming language: Python Supplementary material: A user manual and examples are provided with the source code in the GitHub repository. Nature of problem: Atom probe tomography provides sub-nanometer resolution of a material, but due to noise and sparsity introduced by the process, the crystal structure of a material cannot presently be determined from the resulting data. Solution method: Our Materials Fingerprinting library presents a topologically informed machine learning methodology to classify the lattice structure of a material from atomic probe tomography data. We create persistence diagrams from small neighborhoods centered at each atom in the resulting APT data and use the summary statistics of a novel metric on the space of persistence diagrams as features for a classification algorithm.

KW - Atom probe tomography

KW - High entropy alloy

KW - Machine learning

KW - Materials discovery

KW - Topological data analysis

UR - http://www.scopus.com/inward/record.url?scp=85106224747&partnerID=8YFLogxK

U2 - 10.1016/j.cpc.2021.108019

DO - 10.1016/j.cpc.2021.108019

M3 - Article

AN - SCOPUS:85106224747

SN - 0010-4655

VL - 266

JO - Computer Physics Communications

JF - Computer Physics Communications

M1 - 108019

ER -

Materials Fingerprinting Classification

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this