Cargando…
A Model Ensemble Approach Enables Data-Driven Property Prediction for Chemically Deconstructable Thermosets in the Low-Data Regime
[Image: see text] Thermosets present sustainability challenges that could potentially be addressed through the design of deconstructable variants with tunable properties; however, the combinatorial space of possible thermoset molecular building blocks (e.g., monomers, cross-linkers, and additives) a...
Autores principales: | , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Chemical Society
2023
|
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10540282/ https://www.ncbi.nlm.nih.gov/pubmed/37780353 http://dx.doi.org/10.1021/acscentsci.3c00502 |
_version_ | 1785113680471392256 |
---|---|
author | AlFaraj, Yasmeen S. Mohapatra, Somesh Shieh, Peyton Husted, Keith E. L. Ivanoff, Douglass G. Lloyd, Evan M. Cooper, Julian C. Dai, Yutong Singhal, Avni P. Moore, Jeffrey S. Sottos, Nancy R. Gomez-Bombarelli, Rafael Johnson, Jeremiah A. |
author_facet | AlFaraj, Yasmeen S. Mohapatra, Somesh Shieh, Peyton Husted, Keith E. L. Ivanoff, Douglass G. Lloyd, Evan M. Cooper, Julian C. Dai, Yutong Singhal, Avni P. Moore, Jeffrey S. Sottos, Nancy R. Gomez-Bombarelli, Rafael Johnson, Jeremiah A. |
author_sort | AlFaraj, Yasmeen S. |
collection | PubMed |
description | [Image: see text] Thermosets present sustainability challenges that could potentially be addressed through the design of deconstructable variants with tunable properties; however, the combinatorial space of possible thermoset molecular building blocks (e.g., monomers, cross-linkers, and additives) and manufacturing conditions is vast, and predictive knowledge for how combinations of these molecular components translate to bulk thermoset properties is lacking. Data science could overcome these problems, but computational methods are difficult to apply to multicomponent, amorphous, statistical copolymer materials for which little data exist. Here, leveraging a data set with 101 examples, we introduce a closed-loop experimental, machine learning (ML), and virtual screening strategy to enable predictions of the glass transition temperature (T(g)) of polydicyclopentadiene (pDCPD) thermosets containing cleavable bifunctional silyl ether (BSE) comonomers and/or cross-linkers with varied compositions and loadings. Molecular features and formulation variables are used as model inputs, and uncertainty is quantified through model ensembling, which together with heavy regularization helps to avoid overfitting and ultimately achieves predictions within <15 °C for thermosets with compositionally diverse BSEs. This work offers a path to predicting the properties of thermosets based on their molecular building blocks, which may accelerate the discovery of promising plastics, rubbers, and composites with improved functionality and controlled deconstructability. |
format | Online Article Text |
id | pubmed-10540282 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | American Chemical Society |
record_format | MEDLINE/PubMed |
spelling | pubmed-105402822023-09-30 A Model Ensemble Approach Enables Data-Driven Property Prediction for Chemically Deconstructable Thermosets in the Low-Data Regime AlFaraj, Yasmeen S. Mohapatra, Somesh Shieh, Peyton Husted, Keith E. L. Ivanoff, Douglass G. Lloyd, Evan M. Cooper, Julian C. Dai, Yutong Singhal, Avni P. Moore, Jeffrey S. Sottos, Nancy R. Gomez-Bombarelli, Rafael Johnson, Jeremiah A. ACS Cent Sci [Image: see text] Thermosets present sustainability challenges that could potentially be addressed through the design of deconstructable variants with tunable properties; however, the combinatorial space of possible thermoset molecular building blocks (e.g., monomers, cross-linkers, and additives) and manufacturing conditions is vast, and predictive knowledge for how combinations of these molecular components translate to bulk thermoset properties is lacking. Data science could overcome these problems, but computational methods are difficult to apply to multicomponent, amorphous, statistical copolymer materials for which little data exist. Here, leveraging a data set with 101 examples, we introduce a closed-loop experimental, machine learning (ML), and virtual screening strategy to enable predictions of the glass transition temperature (T(g)) of polydicyclopentadiene (pDCPD) thermosets containing cleavable bifunctional silyl ether (BSE) comonomers and/or cross-linkers with varied compositions and loadings. Molecular features and formulation variables are used as model inputs, and uncertainty is quantified through model ensembling, which together with heavy regularization helps to avoid overfitting and ultimately achieves predictions within <15 °C for thermosets with compositionally diverse BSEs. This work offers a path to predicting the properties of thermosets based on their molecular building blocks, which may accelerate the discovery of promising plastics, rubbers, and composites with improved functionality and controlled deconstructability. American Chemical Society 2023-09-14 /pmc/articles/PMC10540282/ /pubmed/37780353 http://dx.doi.org/10.1021/acscentsci.3c00502 Text en © 2023 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by/4.0/Permits the broadest form of re-use including for commercial purposes, provided that author attribution and integrity are maintained (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | AlFaraj, Yasmeen S. Mohapatra, Somesh Shieh, Peyton Husted, Keith E. L. Ivanoff, Douglass G. Lloyd, Evan M. Cooper, Julian C. Dai, Yutong Singhal, Avni P. Moore, Jeffrey S. Sottos, Nancy R. Gomez-Bombarelli, Rafael Johnson, Jeremiah A. A Model Ensemble Approach Enables Data-Driven Property Prediction for Chemically Deconstructable Thermosets in the Low-Data Regime |
title | A Model Ensemble Approach Enables Data-Driven Property
Prediction for Chemically Deconstructable Thermosets in the Low-Data
Regime |
title_full | A Model Ensemble Approach Enables Data-Driven Property
Prediction for Chemically Deconstructable Thermosets in the Low-Data
Regime |
title_fullStr | A Model Ensemble Approach Enables Data-Driven Property
Prediction for Chemically Deconstructable Thermosets in the Low-Data
Regime |
title_full_unstemmed | A Model Ensemble Approach Enables Data-Driven Property
Prediction for Chemically Deconstructable Thermosets in the Low-Data
Regime |
title_short | A Model Ensemble Approach Enables Data-Driven Property
Prediction for Chemically Deconstructable Thermosets in the Low-Data
Regime |
title_sort | model ensemble approach enables data-driven property
prediction for chemically deconstructable thermosets in the low-data
regime |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10540282/ https://www.ncbi.nlm.nih.gov/pubmed/37780353 http://dx.doi.org/10.1021/acscentsci.3c00502 |
work_keys_str_mv | AT alfarajyasmeens amodelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT mohapatrasomesh amodelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT shiehpeyton amodelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT hustedkeithel amodelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT ivanoffdouglassg amodelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT lloydevanm amodelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT cooperjulianc amodelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT daiyutong amodelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT singhalavnip amodelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT moorejeffreys amodelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT sottosnancyr amodelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT gomezbombarellirafael amodelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT johnsonjeremiaha amodelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT alfarajyasmeens modelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT mohapatrasomesh modelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT shiehpeyton modelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT hustedkeithel modelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT ivanoffdouglassg modelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT lloydevanm modelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT cooperjulianc modelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT daiyutong modelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT singhalavnip modelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT moorejeffreys modelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT sottosnancyr modelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT gomezbombarellirafael modelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime AT johnsonjeremiaha modelensembleapproachenablesdatadrivenpropertypredictionforchemicallydeconstructablethermosetsinthelowdataregime |