A Model Ensemble Approach Enables Data-Driven Property Prediction for Chemically Deconstructable Thermosets in the Low-Data Regime-Reference-Cited by-同舟云学术

A Model Ensemble Approach Enables Data-Driven Property Prediction for Chemically Deconstructable Thermosets in the Low-Data Regime

Published:2023-09-14 Issue:9 Volume:9 Page:1810-1819
ISSN:2374-7943
Container-title:ACS Central Science
language:en
Short-container-title:ACS Cent. Sci.

Author:

AlFaraj Yasmeen S.¹^ORCID,Mohapatra Somesh²^ORCID,Shieh Peyton¹,Husted Keith E. L.¹,Ivanoff Douglass G.³⁴,Lloyd Evan M.⁴⁵,Cooper Julian C.⁴⁵^ORCID,Dai Yutong¹,Singhal Avni P.²,Moore Jeffrey S.³⁴^ORCID,Sottos Nancy R.³⁴^ORCID,Gomez-Bombarelli Rafael²^ORCID,Johnson Jeremiah A.¹^ORCID

Affiliation:

1. Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States of America

2. Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States of America

3. Department of Materials Science and Engineering, University of Illinois at Urbana─Champaign, Urbana, Illinois 61801, United States of America

4. The Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana─Champaign, Urbana, Illinois 61801, United States of America

5. Department of Chemistry, University of Illinois at Urbana─Champaign, Urbana, Illinois 61801, United States of America

Funder

Basic Energy Sciences

Publisher

American Chemical Society (ACS)

Subject

General Chemical Engineering,General Chemistry

Link

https://pubs.acs.org/doi/pdf/10.1021/acscentsci.3c00502

Reference80 articles.

1. Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties

2. Accelerating the discovery of materials for clean energy in the era of smart automation