EUVIMEDEUVIMED entdecken
Crossref

Thermodynamic Labeling Enables CO 2 Prediction in Polymers of Intrinsic Microporosity under Small Data Constraints

Johnathan W Campbell, Ashley P DeRegis, Jeffrey A Laub, David S Sholl, Konstantinos D Vogiatzis iD

Macromolecular Rapid Communications · 2025

DOI: 10.1002/marc.202500490 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Macromolecular Rapid Communications, 2025. Verfasst von Johnathan W Campbell und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemistry, University of Tennessee, Knoxville, Tennessee, USA. Hauptthemen laut MEDLINE: Carbon Dioxide, Polymers, Thermodynamics. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 110 Literaturangaben. Gefördert von: University of Tennessee-Oak Ridge Innovation Institute, Division of Chemistry.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Porous polymers, particularly polymers of intrinsic microporosity (PIMs), combine high surface areas with tunable functionalities, positioning them as promising materials for post‐combustion CO 2 capture technologies. A key physical parameter of these materials is the isosteric heat of adsorption ( Q st ), which quantifies the interaction strength between CO 2 molecules and the polymer framework. In this work, we demonstrate that data‐driven models constructed from computationally determined physicochemical descriptors can accurately predict Q st at room temperature using a modestly sized dataset of 75 PIMs. Among the multitude of machine learning models evaluated, Kernel Ridge Regression (KRR) utilizing the radial basis function (RBF) yielded notable training and testing coefficients of determination (R 2 scores) of 0.9854 and 0.9653, respectively. Additionally, an ensemble model was constructed using the KRR RBF, Lasso Regression, and XGBoost, achieving an average training R 2 score of 0.9844 and a testing score of 0.9651. By optimizing model parameters through Bayesian methods and interpreting feature importance using SHAP analysis, we identified the molecular characteristics that most strongly influence the prediction of CO 2 ‐PIMs isosteric heats of adsorption. Using a Lasso model, we screened a synthetic PIM parameter space by varying six thermochemical descriptors, revealing density as the most influential factor and identifying optimal combinations to enhance predicted isosteric heats of adsorption. These results demonstrate that accurate predictive workflows can be developed using relatively small datasets for designing polymeric adsorbents by identifying key molecular descriptors that correlate with the isosteric heat of adsorption. Overall, this adaptable methodology can be extended to future gas‐separation challenges, helping pave the way for faster discovery of advanced polymeric membranes for capturing CO 2 .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Carbon DioxidePolymersThermodynamicsPorosityAdsorptionBoosting Machine Learning AlgorithmsPrediction AlgorithmsPredictive Learning Models

Stichwörter der Autor:innen

CO2machine learningpolymer informaticspolymers of intrinsic microporositysmall data

Substanzen

Carbon DioxidePolymers

Autor:innen und Institutionen

  • Department of Chemistry, University of Tennessee, Knoxville, Tennessee, USA.
  • Oak Ridge National Laboratory, University of Tennessee-Oak Ridge Innovation Institute, Oak Ridge, Tennessee, USA.

ORCID-Profile: Konstantinos D Vogiatzis

Förderung

  • University of Tennessee-Oak Ridge Innovation Institute
  • Division of Chemistry

Zitieren

APA

Campbell, J. W., DeRegis, A. P., Laub, J. A., Sholl, D. S., & Vogiatzis, K. D. (2025). Thermodynamic Labeling Enables CO 2 Prediction in Polymers of Intrinsic Microporosity under Small Data Constraints. Macromolecular Rapid Communications. https://doi.org/10.1002/marc.202500490

Vancouver

Campbell JW, DeRegis AP, Laub JA, Sholl DS, Vogiatzis KD. Thermodynamic Labeling Enables CO 2 Prediction in Polymers of Intrinsic Microporosity under Small Data Constraints. Macromolecular Rapid Communications. 2025. doi:10.1002/marc.202500490

BibTeX
@article{Campbell2025,
  author = {Campbell, Johnathan W and DeRegis, Ashley P and Laub, Jeffrey A and Sholl, David S and Vogiatzis, Konstantinos D},
  title = {Thermodynamic Labeling Enables CO 2 Prediction in Polymers of Intrinsic Microporosity under Small Data Constraints},
  journal = {Macromolecular Rapid Communications},
  year = {2025},
  doi = {10.1002/marc.202500490}
}
Kostenlos starten →