Development of Deep Learning Simulation and Density Functional Theory Framework for Electrocatalyst Layers for PEM Electrolyzers

Jaydev Zaveri, Shankar Raman Dhanushkodi (), Michael W. Fowler, Brant A. Peppley, Dawid Taler, Tomasz Sobota and Jan Taler ()
Additional contact information
Jaydev Zaveri: Dhanushkodi Research Group, Department of Chemical Engineering, Vellore Institute of Technology, Katpadi, Vellore 632014, Tamil Nadu, India
Shankar Raman Dhanushkodi: Dhanushkodi Research Group, Department of Chemical Engineering, Vellore Institute of Technology, Katpadi, Vellore 632014, Tamil Nadu, India
Michael W. Fowler: Department of Chemical Engineering, University of Waterloo, Waterloo, ON N2L3G1, Canada
Brant A. Peppley: Department of Chemical Engineering, Queens University, Kingston, ON K7L 3L6, Canada
Dawid Taler: Department of Thermal Processes, Faculty of Environmental Engineering and Energy, Cracow University of Technology, 31-864 Cracow, Poland
Tomasz Sobota: Department of Thermal Processes, Faculty of Environmental Engineering and Energy, Cracow University of Technology, 31-864 Cracow, Poland
Jan Taler: Department of Energy, Cracow University of Technology, 31-864 Cracow, Poland

Energies, 2025, vol. 18, issue 5, 1-28

Abstract: The electrocatalyst layers (ECLs) in polymer electrolyte membrane (PEM) electrolyzers are fundamentally comprised of IrOx catalysts, support material, and an ionomer. Their stability is critically dependent on structure and composition, necessitating a thorough understanding of ionization potential and work function. We employ Density Functional Theory (DFT) to determine the ionization states of ECLs and to optimize their electronic properties. Furthermore, advanced deep learning simulations (DLSs) significantly enhance the kinetic and transport behaviors of these layers. This work integrates DFT and DLS to elucidate the characteristics of ECLs within PEM electrolyzer cells. We strategically utilize DFT to refine catalyst molecules and assess their electronic properties, while DLS is employed to predict the potential energy of support molecules in the catalyst layers. We establish a clear relationship between the energy and geometry of IrOx molecules. The DFT-DLS framework robustly calculates potential energy and reaction coordinates, effectively bridging theoretical computations with the dynamic behavior of molecules in catalyst layers. We validate our model by comparing it with the experimental polarization curve of the IrOx-based anode catalyst layer in a functioning electrolyzer. The observed Tafel slope and exchange current density unequivocally confirm that the oxygen evolution reaction (OER) occurs through a well-defined electrochemical pathway, with oxygen generation proceeding according to the charge transfer mechanism predicted by the DFT-DLS framework.

Keywords: computational chemistry; deep learning simulations; artificial neural network; density functional theory; electrocatalyst (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/5/1022/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/5/1022/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:5:p:1022-:d:1595448

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().