Title: A Strategic Approach to Machine Learning for Material Science: How to Tackle Real-World Challenges and Avoid Pitfalls

Abstract

The exponential growth and success of Machine Learning (ML) has resulted in its application in all scientific domains including Material Science. Advancement in experimental techniques has led to an increase in the volume of material science data encouraging material scientists to investigate data-driven solutions to scientific problems. While the resources available to get started with ML are ever increasing, there is little literature on traversing through the space of decisions that need to be made for implementing a robust and trustworthy ML solution. A lack of such resources leads to researchers wading through articles and papers trying to determine the best approach for their problem and sometimes also falling prey to pitfalls in a real-world scenario. This paper aims to act as a guide for researchers who want to strategically approach a ML solution to their problem through the use of domain knowledge and systematic evaluation of the major aspects of a ML pipeline. We focus on four aspects of the ML pipeline 1. problem formulation, 2. data curation, 3. feature representation and model selection, and 4. model generalizability and real-world performance. In each case, we discuss the space of decision, provide examples from scientific literature, and illustrate how differentmore » choices can affect the outcome through a case study of predicting compressive strength of uniaxially pressed molecular solid, 2,4,6-triamino-1,3,5-trinitrobenzene (TATB) samples. Using a similar approach of critical thinking along with rigorous evaluation and diagnostics, researchers can be assured of the reliability of predictions from their ML models.« less

Authors:

Karande, Piyush  ^[1];

• Search DOE PAGES for author "Karande, Piyush"
• Search DOE PAGES for ORCID "0000-0002-0327-1936"

Gallagher, Brian  ^[2];

• Search DOE PAGES for author "Gallagher, Brian"
• Search DOE PAGES for ORCID "0000-0002-3262-6652"

Han, Thomas Yong-Jin  ^[3]

• Search DOE PAGES for author "Han, Thomas Yong-Jin"
• Search DOE PAGES for ORCID "0000-0002-3000-2782"

---

+ Show Author Affiliations

1. Computational Engineering Division, Lawrence Livermore National Laboratory, Livermore, California 94550, United States
2. Center for Applied Scientific Computing, Lawrence Livermore National Laboratory, Livermore, California 94550, United States
3. Materials Science Division, Lawrence Livermore National Laboratory, Livermore, California 94550, United States

Publication Date:

Thu Sep 01 00:00:00 EDT 2022

Research Org.:

Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

Sponsoring Org.:

USDOE National Nuclear Security Administration (NNSA); USDOE Laboratory Directed Research and Development (LDRD) Program

OSTI Identifier:

1885083

Alternate Identifier(s):

OSTI ID: 1890089

Report Number(s):

LLNL-JRNL-832494
Journal ID: ISSN 0897-4756

Grant/Contract Number:  

LDRD 19-SI-001; AC52-07NA27344; LDRD-19-SI-001

Resource Type:

Published Article

Journal Name:

Chemistry of Materials

Additional Journal Information:

Journal Name: Chemistry of Materials Journal Volume: 34 Journal Issue: 17; Journal ID: ISSN 0897-4756

Publisher:

American Chemical Society

Country of Publication:

United States

Language:

English

Subject:

42 ENGINEERING; 36 MATERIALS SCIENCE; 97 MATHEMATICS AND COMPUTING; 37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY