Materials cartography: A forward-looking perspective on materials representation and devising better maps

Steven B. Torrisi; Martin Z. Bazant; Alexander E. Cohen; Min Gee Cho; Jens S. Hummelshøj; Linda Hung; Gaurav Kamat; Arash Khajeh; Adeesh Kolluru; Xiangyun Lei; Handong Ling; Joseph H. Montoya; Tim Mueller; Aini Palizhati; Benjamin A. Paren; Brandon Phan; Jacob Pietryga; Elodie Sandraz; Daniel Schweigert; Yang Shao-Horn; Amalie Trewartha; Ruijie Zhu; Debbie Zhuang; Shijing Sun

doi:10.1063/5.0149804

Materials cartography: A forward-looking perspective on materials representation and devising better maps

Steven B. Torrisi
, Martin Z. Bazant
, Alexander E. Cohen
, Min Gee Cho
, Jens S. Hummelshøj
, Linda Hung
, Gaurav Kamat
, Arash Khajeh
, Adeesh Kolluru
, Xiangyun Lei
, Handong Ling
, Joseph H. Montoya
, Tim Mueller
, Aini Palizhati
, Benjamin A. Paren
, Brandon Phan
, Jacob Pietryga
, Elodie Sandraz
, Daniel Schweigert
, Yang Shao-Horn

Amalie Trewartha, Ruijie Zhu, Debbie Zhuang, Shijing Sun

Department of Chemical Engineering and Materials Science

Massachusetts Institute of Technology
Lawrence Berkeley National Laboratory
Stanford University
Carnegie Mellon University
University of California at Berkeley
Georgia Institute of Technology
Northwestern University

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

11 Scopus citations

Abstract

Machine learning (ML) is gaining popularity as a tool for materials scientists to accelerate computation, automate data analysis, and predict materials properties. The representation of input material features is critical to the accuracy, interpretability, and generalizability of data-driven models for scientific research. In this Perspective, we discuss a few central challenges faced by ML practitioners in developing meaningful representations, including handling the complexity of real-world industry-relevant materials, combining theory and experimental data sources, and describing scientific phenomena across timescales and length scales. We present several promising directions for future research: devising representations of varied experimental conditions and observations, the need to find ways to integrate machine learning into laboratory practices, and making multi-scale informatics toolkits to bridge the gaps between atoms, materials, and devices.

Original language	English
Article number	020901
Journal	APL Machine Learning
Volume	1
Issue number	2
DOIs	https://doi.org/10.1063/5.0149804
State	Published - 1 Jun 2023

Access to Document

10.1063/5.0149804

Cite this

Torrisi, S. B., Bazant, M. Z., Cohen, A. E., Cho, M. G., Hummelshøj, J. S., Hung, L., Kamat, G., Khajeh, A., Kolluru, A., Lei, X., Ling, H., Montoya, J. H., Mueller, T., Palizhati, A., Paren, B. A., Phan, B., Pietryga, J., Sandraz, E., Schweigert, D., ... Sun, S. (2023). Materials cartography: A forward-looking perspective on materials representation and devising better maps. APL Machine Learning, 1(2), Article 020901. https://doi.org/10.1063/5.0149804

@article{0ce45b3f14c04a069df85111c144690c,

title = "Materials cartography: A forward-looking perspective on materials representation and devising better maps",

abstract = "Machine learning (ML) is gaining popularity as a tool for materials scientists to accelerate computation, automate data analysis, and predict materials properties. The representation of input material features is critical to the accuracy, interpretability, and generalizability of data-driven models for scientific research. In this Perspective, we discuss a few central challenges faced by ML practitioners in developing meaningful representations, including handling the complexity of real-world industry-relevant materials, combining theory and experimental data sources, and describing scientific phenomena across timescales and length scales. We present several promising directions for future research: devising representations of varied experimental conditions and observations, the need to find ways to integrate machine learning into laboratory practices, and making multi-scale informatics toolkits to bridge the gaps between atoms, materials, and devices.",

author = "Torrisi, \{Steven B.\} and Bazant, \{Martin Z.\} and Cohen, \{Alexander E.\} and Cho, \{Min Gee\} and Hummelsh{\o}j, \{Jens S.\} and Linda Hung and Gaurav Kamat and Arash Khajeh and Adeesh Kolluru and Xiangyun Lei and Handong Ling and Montoya, \{Joseph H.\} and Tim Mueller and Aini Palizhati and Paren, \{Benjamin A.\} and Brandon Phan and Jacob Pietryga and Elodie Sandraz and Daniel Schweigert and Yang Shao-Horn and Amalie Trewartha and Ruijie Zhu and Debbie Zhuang and Shijing Sun",

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

year = "2023",

month = jun,

day = "1",

doi = "10.1063/5.0149804",

language = "English",

volume = "1",

number = "2",

}

Torrisi, SB, Bazant, MZ, Cohen, AE, Cho, MG, Hummelshøj, JS, Hung, L, Kamat, G, Khajeh, A, Kolluru, A, Lei, X, Ling, H, Montoya, JH, Mueller, T, Palizhati, A, Paren, BA, Phan, B, Pietryga, J, Sandraz, E, Schweigert, D, Shao-Horn, Y, Trewartha, A, Zhu, R, Zhuang, D & Sun, S 2023, 'Materials cartography: A forward-looking perspective on materials representation and devising better maps', APL Machine Learning, vol. 1, no. 2, 020901. https://doi.org/10.1063/5.0149804

TY - JOUR

T1 - Materials cartography

T2 - A forward-looking perspective on materials representation and devising better maps

AU - Torrisi, Steven B.

AU - Bazant, Martin Z.

AU - Cohen, Alexander E.

AU - Cho, Min Gee

AU - Hummelshøj, Jens S.

AU - Hung, Linda

AU - Kamat, Gaurav

AU - Khajeh, Arash

AU - Kolluru, Adeesh

AU - Lei, Xiangyun

AU - Ling, Handong

AU - Montoya, Joseph H.

AU - Mueller, Tim

AU - Palizhati, Aini

AU - Paren, Benjamin A.

AU - Phan, Brandon

AU - Pietryga, Jacob

AU - Sandraz, Elodie

AU - Schweigert, Daniel

AU - Shao-Horn, Yang

AU - Trewartha, Amalie

AU - Zhu, Ruijie

AU - Zhuang, Debbie

AU - Sun, Shijing

PY - 2023/6/1

Y1 - 2023/6/1

N2 - Machine learning (ML) is gaining popularity as a tool for materials scientists to accelerate computation, automate data analysis, and predict materials properties. The representation of input material features is critical to the accuracy, interpretability, and generalizability of data-driven models for scientific research. In this Perspective, we discuss a few central challenges faced by ML practitioners in developing meaningful representations, including handling the complexity of real-world industry-relevant materials, combining theory and experimental data sources, and describing scientific phenomena across timescales and length scales. We present several promising directions for future research: devising representations of varied experimental conditions and observations, the need to find ways to integrate machine learning into laboratory practices, and making multi-scale informatics toolkits to bridge the gaps between atoms, materials, and devices.

AB - Machine learning (ML) is gaining popularity as a tool for materials scientists to accelerate computation, automate data analysis, and predict materials properties. The representation of input material features is critical to the accuracy, interpretability, and generalizability of data-driven models for scientific research. In this Perspective, we discuss a few central challenges faced by ML practitioners in developing meaningful representations, including handling the complexity of real-world industry-relevant materials, combining theory and experimental data sources, and describing scientific phenomena across timescales and length scales. We present several promising directions for future research: devising representations of varied experimental conditions and observations, the need to find ways to integrate machine learning into laboratory practices, and making multi-scale informatics toolkits to bridge the gaps between atoms, materials, and devices.

UR - https://www.scopus.com/pages/publications/105024484543

UR - https://www.scopus.com/pages/publications/105024484543#tab=citedBy

U2 - 10.1063/5.0149804

DO - 10.1063/5.0149804

M3 - Article

AN - SCOPUS:105024484543

VL - 1

JO - APL Machine Learning

JF - APL Machine Learning

IS - 2

M1 - 020901

ER -

Materials cartography: A forward-looking perspective on materials representation and devising better maps

Abstract

Access to Document

Other files and links

Fingerprint

Cite this