Using Artificial Neural Networks to Predict Physical Properties of Membrane Polymers

Bestwick, Tate; Beckmann, Jessica; Camarda, Kyle V.

doi:10.1002/cite.202200102

Using Artificial Neural Networks to Predict Physical Properties of Membrane Polymers

Journal Article · Mon Nov 21 23:00:00 EST 2022 · Chemie-Ingenieur-Technik

DOI:https://doi.org/10.1002/cite.202200102· OSTI ID:2007302

Bestwick, Tate ^[1]; Beckmann, Jessica ^[2]; Camarda, Kyle V. ^[2]

University of Kansas, Lawrence, KS (United States); University of Kansas
University of Kansas, Lawrence, KS (United States)

Membrane polymers are a promising technology for use in many challenging gas separation applications. Here, the techniques of computer-aided molecular design can be used to search through the massive molecular space of heteropolymers and develop a set of likely candidate repeat units matching specific physical property targets. However, reasonably accurate property prediction algorithms are needed, but these algorithms must be very fast in order to be combined with an optimization framework. Artificial neural networks (ANNs), a branch of machine learning, are applied in this work to predict the physical properties of polymers. All of the physical properties investigated were found to be predicted by ANNs with R² scores exceeding 0.82.

View Accepted Manuscript (DOE)

Research Organization:: RAPID Manufacturing Institute, New York, NY (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE)

Grant/Contract Number:: EE0007888

OSTI ID:: 2007302

Journal Information:: Chemie-Ingenieur-Technik, Journal Name: Chemie-Ingenieur-Technik Journal Issue: 3 Vol. 95; ISSN 0009-286X

Publisher:: WileyCopyright Statement

Country of Publication:: United States

Language:: English

References (14)

Handbook of Molecular Descriptors Todeschini, Roberto; Consonni, Viviana Methods and Principles in Medicinal Chemistry https://doi.org/10.1002/9783527613106	book	January 2000
Hydrocarbon separations by glassy polymer membranes Iyer, Gaurav M.; Liu, Lu; Zhang, Chen Journal of Polymer Science, Vol. 58, Issue 18 https://doi.org/10.1002/pol.20200128	journal	July 2020
Introducing block design in graph neural networks for molecular properties prediction Li, Yuquan; Li, Pengyong; Yang, Xing Chemical Engineering Journal, Vol. 414 https://doi.org/10.1016/j.cej.2021.128817	journal	June 2021
Computer-aided molecular design of water compatible visible light photosensitizers for dental adhesive Abedin, Farhana; Roughton, Brock; Ye, Qiang Chemical Engineering Science, Vol. 159 https://doi.org/10.1016/j.ces.2016.09.033	journal	February 2017
Computer-aided molecular and processes design based on quantum chemistry: current status and future prospects Gertig, Christoph; Leonhard, Kai; Bardow, André Current Opinion in Chemical Engineering, Vol. 27 https://doi.org/10.1016/j.coche.2019.11.007	journal	March 2020
Use of three-dimensional descriptors in molecular design for biologically active compounds Mapari, Shweta; Camarda, Kyle V. Current Opinion in Chemical Engineering, Vol. 27 https://doi.org/10.1016/j.coche.2019.11.011	journal	March 2020
Use of glass transitions in carbohydrate excipient design for lyophilized protein formulations Roughton, Brock C.; Topp, E. M.; Camarda, Kyle V. Computers & Chemical Engineering, Vol. 36 https://doi.org/10.1016/j.compchemeng.2011.07.018	journal	January 2012
Deep learning and knowledge-based methods for computer-aided molecular design—toward a unified approach: State-of-the-art and future directions Alshehri, Abdulelah S.; Gani, Rafiqul; You, Fengqi Computers & Chemical Engineering, Vol. 141 https://doi.org/10.1016/j.compchemeng.2020.107005	journal	October 2020
Energy-efficient polymeric gas separation membranes for a sustainable future: A review Sanders, David F.; Smith, Zachary P.; Guo, Ruilan Polymer, Vol. 54, Issue 18 https://doi.org/10.1016/j.polymer.2013.05.075	journal	August 2013
Computer-Aided Design of a Perfluorinated Sulfonic Acid Proton Exchange Membrane Using Stochastic Optimization and Molecular Dynamic Method Guo, Wenjing; Liu, Qilei; Zhang, Lei Industrial & Engineering Chemistry Research, Vol. 60, Issue 49 https://doi.org/10.1021/acs.iecr.1c03661	journal	November 2021
Optimization in Polymer Design Using Connectivity Indices Camarda, Kyle V.; Maranas, Costas D. Industrial & Engineering Chemistry Research, Vol. 38, Issue 5 https://doi.org/10.1021/ie980682n	journal	March 1999
Progress in Applications of Polymer-Based Membranes in Gas Separation Technology Tul Muntha, Sedra; Kausar, Ayesha; Siddiq, Muhammad Polymer-Plastics Technology and Engineering, Vol. 55, Issue 12 https://doi.org/10.1080/03602559.2016.1163592	journal	April 2016
Prediction of Polymer Properties Bicerano, Jozef https://doi.org/10.1201/9780203910115	book	July 2002
Performance of Kier-Hall E-state Descriptors in Quantitative Structure Activity Relationship (QSAR) Studies of Multifunctional Molecules Butina, Darko Molecules, Vol. 9, Issue 12 https://doi.org/10.3390/91201004	journal	December 2004

Similar Records

Artificial neural networks in medicine

Technical Report · Fri Jul 01 00:00:00 EDT 1994 · OSTI ID:10162484

Neural networks: A versatile tool from artificial intelligence

Conference · Mon Dec 30 23:00:00 EST 1996 · OSTI ID:525981

Artificial neural networks as a tool for porosity and permeability prediction

Journal Article · Sat Jun 01 00:00:00 EDT 1996 · AAPG Bulletin · OSTI ID:272631

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
Artificial neural network
computer-aided molecular design
machine learning
membrane polymer
property prediction

Using Artificial Neural Networks to Predict Physical Properties of Membrane Polymers

Citation Formats

References (14)

Similar Records

Related Subjects