» Articles » PMID: 37943172

Gibbs-Helmholtz Graph Neural Network for the Prediction of Activity Coefficients of Polymer Solutions at Infinite Dilution

Overview
Journal J Phys Chem A
Specialty Chemistry
Date 2023 Nov 9
PMID 37943172
Authors
Affiliations
Soon will be listed here.
Abstract

Machine learning models have gained prominence for predicting pure-component properties, yet their application to mixture property prediction remains relatively limited. However, the significance of mixtures in our daily lives is undeniable, particularly in industries such as polymer processing. This study presents a modification of the Gibbs-Helmholtz graph neural network (GH-GNN) model for predicting weight-based activity coefficients at infinite dilution (Ω) in polymer solutions. We evaluate various polymer representations ranging from monomer, repeating unit, periodic unit, and oligomer and observe that, in data-scarce scenarios of polymer-solvent mixtures, polymer representation specifics have a reduced impact compared to data-rich environments. Leveraging transfer learning, we harness richer activity coefficient data from small-size systems, enhancing model accuracy and reducing prediction variability. The modified GH-GNN model achieves remarkable prediction results in mixture interpolation and solvent extrapolation tasks having an overall mean absolute error of 0.15, showcasing the potential of graph-neural-network-based models for property prediction of polymer solutions. Comparative analysis with the established models UNIFAC-ZM and Entropic-FV suggests a promising avenue for future research on the use of data-driven models for the prediction of the thermodynamic properties of polymer solutions.

References
1.
Jirasek F, Alves R, Damay J, Vandermeulen R, Bamler R, Bortz M . Machine Learning in Thermodynamics: Prediction of Activity Coefficients by Matrix Completion. J Phys Chem Lett. 2020; 11(3):981-985. DOI: 10.1021/acs.jpclett.9b03657. View

2.
Aldeghi M, Coley C . A graph representation of molecular ensembles for polymer property prediction. Chem Sci. 2022; 13(35):10486-10498. PMC: 9473492. DOI: 10.1039/d2sc02839e. View

3.
Antoniuk E, Li P, Kailkhura B, Hiszpanski A . Representing Polymers as Periodic Graphs with Learned Descriptors for Accurate Polymer Property Predictions. J Chem Inf Model. 2022; 62(22):5435-5445. DOI: 10.1021/acs.jcim.2c00875. View

4.
Park J, Shim Y, Lee F, Rammohan A, Goyal S, Shim M . Prediction and Interpretation of Polymer Properties Using the Graph Convolutional Network. ACS Polym Au. 2023; 2(4):213-222. PMC: 9954297. DOI: 10.1021/acspolymersau.1c00050. View

5.
Geyer R, Jambeck J, Law K . Production, use, and fate of all plastics ever made. Sci Adv. 2017; 3(7):e1700782. PMC: 5517107. DOI: 10.1126/sciadv.1700782. View