TY - JOUR
T1 - A Model Ensemble Approach Enables Data-Driven Property Prediction for Chemically Deconstructable Thermosets in the Low-Data Regime
AU - AlFaraj, Yasmeen S.
AU - Mohapatra, Somesh
AU - Shieh, Peyton
AU - Husted, Keith E.L.
AU - Ivanoff, Douglass G.
AU - Lloyd, Evan M.
AU - Cooper, Julian C.
AU - Dai, Yutong
AU - Singhal, Avni P.
AU - Moore, Jeffrey S.
AU - Sottos, Nancy R.
AU - Gomez-Bombarelli, Rafael
AU - Johnson, Jeremiah A.
N1 - Publisher Copyright:
© 2023 The Authors. Published by American Chemical Society
PY - 2023/9/27
Y1 - 2023/9/27
N2 - 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 (Tg) 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.
AB - 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 (Tg) 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.
UR - http://www.scopus.com/inward/record.url?scp=85174745526&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85174745526&partnerID=8YFLogxK
U2 - 10.1021/acscentsci.3c00502
DO - 10.1021/acscentsci.3c00502
M3 - Article
C2 - 37780353
AN - SCOPUS:85174745526
SN - 2374-7943
VL - 9
SP - 1810
EP - 1819
JO - ACS Central Science
JF - ACS Central Science
IS - 9
ER -