Title: Analyzing machine learning models to accelerate generation of fundamental materials insights

Abstract

Abstract Machine learning for materials science envisions the acceleration of basic science research through automated identification of key data relationships to augment human interpretation and gain scientific understanding. A primary role of scientists is extraction of fundamental knowledge from data, and we demonstrate that this extraction can be accelerated using neural networks via analysis of the trained data model itself rather than its application as a prediction tool. Convolutional neural networks excel at modeling complex data relationships in multi-dimensional parameter spaces, such as that mapped by a combinatorial materials science experiment. Measuring a performance metric in a given materials space provides direct information about (locally) optimal materials but not the underlying materials science that gives rise to the variation in performance. By building a model that predicts performance (in this case photoelectrochemical power generation of a solar fuels photoanode) from materials parameters (in this case composition and Raman signal), subsequent analysis of gradients in the trained model reveals key data relationships that are not readily identified by human inspection or traditional statistical analyses. Human interpretation of these key relationships produces the desired fundamental understanding, demonstrating a framework in which machine learning accelerates data interpretation by leveraging the expertize of themore » human scientist. We also demonstrate the use of neural network gradient analysis to automate prediction of the directions in parameter space, such as the addition of specific alloying elements, that may increase performance by moving beyond the confines of existing data.« less

Authors:

Umehara, Mitsutaro ;

• Search DOE PAGES for author "Umehara, Mitsutaro"
• Search DOE PAGES for ORCID "0000-0001-8665-0028"

Stein, Helge S.; Guevarra, Dan; Newhouse, Paul F.; Boyd, David A.; Gregoire, John M.

• Search DOE PAGES for author "Gregoire, John M."
• Search DOE PAGES for ORCID "0000-0002-2863-5265"

Publication Date:

Fri Mar 08 00:00:00 EST 2019

Research Org.:

California Institute of Technology (CalTech), Pasadena, CA (United States). Joint Center for Artificial Photosynthesis (JCAP)

Sponsoring Org.:

USDOE Office of Science (SC), Basic Energy Sciences (BES)

OSTI Identifier:

1619633

Alternate Identifier(s):

OSTI ID: 1575062

Grant/Contract Number:  

SC0004993

Resource Type:

Published Article

Journal Name:

npj Computational Materials

Additional Journal Information:

Journal Name: npj Computational Materials Journal Volume: 5 Journal Issue: 1; Journal ID: ISSN 2057-3960

Publisher:

Nature Publishing Group

Country of Publication:

United Kingdom

Language:

English

Subject:

36 MATERIALS SCIENCE