Title: A Deep Neural Network for Accurate and Robust Prediction of the Glass Transition Temperature of Polyhydroxyalkanoate Homo- and Copolymers

Abstract

The purpose of this study was to develop a data-driven machine learning model to predict the performance properties of polyhydroxyalkanoates (PHAs), a group of biosourced polyesters featuring excellent performance, to guide future design and synthesis experiments. A deep neural network (DNN) machine learning model was built for predicting the glass transition temperature, Tg, of PHA homo- and copolymers. Molecular fingerprints were used to capture the structural and atomic information of PHA monomers. The other input variables included the molecular weight, the polydispersity index, and the percentage of each monomer in the homo- and copolymers. The results indicate that the DNN model achieves high accuracy in estimation of the glass transition temperature of PHAs. In addition, the symmetry of the DNN model is ensured by incorporating symmetry data in the training process. The DNN model achieved better performance than the support vector machine (SVD), a nonlinear ML model and least absolute shrinkage and selection operator (LASSO), a sparse linear regression model. The relative importance of factors affecting the DNN model prediction were analyzed. Sensitivity of the DNN model, including strategies to deal with missing data, were also investigated. Compared with commonly used machine learning models incorporating quantitative structure–property (QSPR) relationships, itmore » does not require an explicit descriptor selection step but shows a comparable performance. The machine learning model framework can be readily extended to predict other properties.« less

Authors:

Jiang, Zhuoying  ^[1];

• Search DOE PAGES for author "Jiang, Zhuoying"
• Search DOE PAGES for ORCID "0000-0002-7157-0452"

Hu, Jiajie ^[2]; Marrone, Babetta L.  ^[3];

• Search DOE PAGES for author "Marrone, Babetta L."
• Search DOE PAGES for ORCID "0000-0001-5002-1289"

Pilania, Ghanshyam  ^[4];

• Search DOE PAGES for author "Pilania, Ghanshyam"
• Search DOE PAGES for ORCID "0000-0003-4460-1572"

Yu, Xiong  ^[5]

• Search DOE PAGES for author "Yu, Xiong"
• Search DOE PAGES for ORCID "0000-0001-6879-2567"

---

+ Show Author Affiliations

1. Case Western Reserve Univ., Cleveland, OH (United States). Dept. of Civil and Environmental Engineering
2. Case Western Reserve Univ., Cleveland, OH (United States). Depts. of Computer and Data Sciences and Electrical, Computer and Systems Engineering
3. Los Alamos National Lab. (LANL), Los Alamos, NM (United States). Bioscience Division
4. Los Alamos National Lab. (LANL), Los Alamos, NM (United States). Materials Science and Technology Division
5. (Bill) [Case Western Reserve Univ., Cleveland, OH (United States). Depts. of Computer and Data Sciences and Electrical, Computer and Systems Engineering, and Dept. of Civil and Environmental Engineering

Publication Date:

Mon Dec 14 00:00:00 EST 2020

Research Org.:

Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

Sponsoring Org.:

USDOE Office of Science (SC)

OSTI Identifier:

1815763

Alternate Identifier(s):

OSTI ID: 1861292

Report Number(s):

LA-UR-20-25907
Journal ID: ISSN 1996-1944; MATEG9; PII: ma13245701; TRN: US2213576

Grant/Contract Number:  

89233218CNA000001

Resource Type:

Accepted Manuscript

Journal Name:

Materials

Additional Journal Information:

Journal Volume: 13; Journal Issue: 24; Journal ID: ISSN 1996-1944

Publisher:

MDPI

Country of Publication:

United States

Language:

English

Subject:

97 MATHEMATICS AND COMPUTING; 36 MATERIALS SCIENCE; molecular fingerprint; deep neural network; glass transition temperature; copolymers; quantitative structure–property relationship (QSPR)