Materials cartography: A forward-looking perspective on materials representation and devising better maps-Reference-Cited by-同舟云学术

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

Published:2023-06-01 Issue:2 Volume:1 Page:
ISSN:2770-9019
Container-title:APL Machine Learning
language:en
Short-container-title:

Author:

Torrisi Steven B.¹^ORCID,Bazant Martin Z.²³^ORCID,Cohen Alexander E.³,Cho Min Gee⁴^ORCID,Hummelshøj Jens S.¹^ORCID,Hung Linda¹^ORCID,Kamat Gaurav⁵^ORCID,Khajeh Arash¹^ORCID,Kolluru Adeesh⁶^ORCID,Lei Xiangyun¹^ORCID,Ling Handong⁷^ORCID,Montoya Joseph H.¹^ORCID,Mueller Tim¹^ORCID,Palizhati Aini⁶,Paren Benjamin A.⁸^ORCID,Phan Brandon⁹^ORCID,Pietryga Jacob¹⁰^ORCID,Sandraz Elodie¹⁰^ORCID,Schweigert Daniel¹^ORCID,Shao-Horn Yang¹^ORCID,Trewartha Amalie¹^ORCID,Zhu Ruijie¹⁰^ORCID,Zhuang Debbie²^ORCID,Sun Shijing¹^ORCID

Affiliation:

1. Energy and Materials Division, Toyota Research Institute 1 , Los Altos, California 94022, USA

2. Department of Chemical Engineering, Massachusetts Institute of Technology 2 , Cambridge, Massachusetts 02142, USA

3. Department of Mathematics, Massachusetts Institute of Technology 3 , Cambridge, Massachusetts 02142, USA

4. National Center for Electron Microscopy, Molecular Foundry, Lawrence Berkeley National Laboratory 4 , Berkeley, California 94720, USA

5. Department of Chemical Engineering, Stanford University 5 , Palo Alto, California 94305, USA

6. Department of Chemical Engineering, Carnegie Mellon University 6 , Pittsburgh, Pennsylvania 15213, USA

7. Department of Materials Science and Engineering, University of California, Berkeley 7 , Berkeley, California 94720, USA

8. Research Laboratory of Electronics, Massachusetts Institute of Technology 8 , Cambridge, Massachusetts 02139, USA

9. Department of Materials Science and Engineering, Georgia Institute of Technology 9 , Atlanta, Georgia 30332, USA

10. Department of Materials Science and Engineering, Northwestern University 10 , Evanston, Illinois 94305, USA

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.

Publisher

AIP Publishing

Link

https://pubs.aip.org/aip/aml/article-pdf/doi/10.1063/5.0149804/17964152/020901_1_5.0149804.pdf

Reference111 articles.

1. Machine learning for molecular and materials science;Nature,2018

2. Knowledge-integrated machine learning for materials: Lessons from gameplaying and robotics;Nat. Rev. Mater.,2023

3. Machine learning modeling for accelerated battery materials design in the small data regime;Adv. Energy Mater.,2022

4. Materials representation and transfer learning for multi-property prediction;Appl. Phys. Rev.,2021

5. Crystal structure prediction via deep learning;J. Am. Chem. Soc.,2018

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Calibration in machine learning uncertainty quantification: Beyond consistency to target adaptivity;APL Machine Learning;2023-12-01