journal article·2026-11Open access

Machine-learning-based framework for quantifying and formulating oxygen bubble dynamics in PEM water electrolysis

Hiroya Tanaka, Keita Hirayama, Kohei Toyama, Kohei Wakuda, Takuto Araki, Shigenori Mitsushima

Abstract

Oxygen bubbles generated near the catalyst layer in proton exchange membrane water electrolysis (PEMWE) obstruct deionized-water supply, hinder local mass transport, and increase mass-transport overvoltage. However, quantitative characterization is challenging because the large number of bubbles makes manual analysis impractical. Here, we propose a rapid and accurate framework to quantify bubble count and volume on the porous transport layer (PTL) surface by combining high-speed imaging with machine-learning–based detection and tracking (Faster R-CNN and Deep SORT). To reduce the effort required for training data preparation, we developed a pseudo-bubble image generator to automatically create annotated datasets. Systematic experiments were performed by varying the current density (0.5–4.0 A cm −2 ) and the anode-side water-supply pressure (1–5 atm). The total detected bubble volume was well described by a scaling model based on Faraday's and Boyle's laws. Bubble count and mean bubble volume increased with current density and decreased with pressure. Power-law fits revealed that operating conditions affected the count (exponent ∼0.6) more strongly than mean bubble volume (exponent ∼0.3), suggesting that changes in bubble count contribute more significantly to the oxygen removal than those in mean volume. The proposed framework provides quantitative data for numerical modeling, facilitating structural optimization of PTLs.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Fuel Cells and Related Materials · Hybrid Renewable Energy Systems · Power Transformer Diagnostics and Insulation

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (42)

Show source-provided references
1. Bubble evolution and transport in PEM water electrolysis: mechanism, impact, and management10.1016/j.pecs.2023.101075 ↗
2. Influence of bubbles on the energy conversion efficiency of electrochemical reactors10.1016/j.joule.2020.01.005 ↗
3. Review on bubble dynamics in proton exchange membrane water electrolysis: towards optimal green hydrogen yield10.3390/mi14122234 ↗
4. Gas bubbles in electrochemical gas evolution reactions10.1021/acs.langmuir.9b00119 ↗
5. Oxygen invasion behavior of anodic porous transport layer in polymer electrolyte membrane water electrolyzer: Lattice boltzmann method simulation
6. Effects of various parameters of different porous transport layers in proton exchange membrane water electrolysis10.1016/j.electacta.2020.136641 ↗
7. Comparative analysis of fiber-based and powder-based porous transport layers in water electrolysis for green hydrogen10.1021/acssuschemeng.4c06540 ↗
8. Two-phase flow in a proton exchange membrane electrolyzer visualized in situ by simultaneous neutron radiography and optical imaging10.1016/j.ijhydene.2013.02.087 ↗
9. Observation of preferential pathways for oxygen removal through porous transport layers of polymer electrolyte water electrolyzers10.1016/j.isci.2020.101783 ↗
10. Synchrotron radiography for a proton exchange membrane (PEM) electrolyzer10.1002/fuce.201900055 ↗
11. Operando X-ray tomography and sub-second radiography for characterizing transport in polymer electrolyte membrane electrolyzer10.1016/j.electacta.2018.04.144 ↗
12. Operando flow regime diagnosis using acoustic emission in a polymer electrolyte membrane water electrolyser10.1016/j.jpowsour.2019.03.061 ↗
13. Scanning acoustic microscopy for quantifying bubble evolution in alkaline water electrolyzers10.1016/j.jpowsour.2025.238575 ↗
14. High-speed characterization of two-phase flow and bubble dynamics in titanium felt porous media for hydrogen production10.1016/j.electacta.2021.137751 ↗
15. Effects of porous transport layer wettability on performance of proton exchange membrane water electrolyzer: mass transport overvoltage and visualization of oxygen bubble dynamics with high-speed camera10.1016/j.ijhydene.2024.02.356 ↗
16. Two-phase flow behaviour and performance of polymer electrolyte membrane electrolysers: electrochemical and optical characterisation10.1016/j.ijhydene.2018.07.003 ↗
17. Insights into the rapid two-phase transport dynamics in different structured porous transport layers of water electrolyzers through high-speed visualization10.1016/j.jpowsour.2021.230641 ↗
18. Revealing anodic multi-class bubble dynamics in PEMWE systems using deep learning and post-processing detection10.1016/j.fuel.2024.131112 ↗
19. Roles of wettability and wickability on enhanced hydrogen evolution reactions10.1021/acsami.4c02428 ↗
20. Bubble feature extraction in subcooled flow boiling using AI-based object detection and tracking techniques10.1016/j.ijheatmasstransfer.2024.125188 ↗
21. A deep learning-based image processing method for bubble detection, segmentation, and shape reconstruction in high gas holdup sub-millimeter bubbly flows10.1016/j.cej.2022.137859 ↗
22. BubGAN: bubble generative adversarial networks for synthesizing realistic bubbly flow images10.1016/j.ces.2019.04.004 ↗
23. Deep learning-based automated and universal bubble detection and mask extraction in complex two-phase flows10.1038/s41598-021-88334-0 ↗
24. Void fraction detection technology of gas-liquid two-phase bubbly flow based on convolutional neural network10.1016/j.expthermflusci.2022.110804 ↗
25. BubCNN: bubble detection using faster RCNN and shape regression network10.1016/j.ces.2019.115467 ↗
26. Deep learning bubble segmentation on a shoestring10.1021/acs.iecr.3c04059 ↗
27. BYG-drop: a tool for enhanced droplet detection in liquid–liquid systems through machine learning and synthetic imaging10.3389/fceng.2024.1415453 ↗
28. Deep learning-based bubble detection with automatic training data generation: application to the PEM water electrolysis
29. Faster R-CNN-based detection and tracking of hydrogen and oxygen bubbles in alkaline water electrolysis10.5796/electrochemistry.24-00127 ↗
30. Cell performance determining parameters in high pressure water electrolysis10.1016/j.electacta.2016.06.120 ↗
31. Electrolysis of water in a system with a solid polymer electrolyte at elevated pressure10.1023/A:1016735003101 ↗
32. Numerical investigation on two-phase flow of PEM water electrolyzers under high operating pressures10.1016/j.ijhydene.2025.01.331 ↗
33. Design and characterization of compact proton exchange membrane water electrolyzer for component evaluation test10.1016/j.ijhydene.2021.08.213 ↗
34. Deep learning-enhanced characterization of bubble dynamics in proton exchange membrane water electrolyzers10.1039/D3CP05869G ↗
35. Bubble size distribution and electrode coverage at porous nickel electrodes in a novel 3-electrode flow-through cell10.1016/j.ijhydene.2022.10.165 ↗
36. Experimental investigation and analysis for the bubble size distribution during alkaline water electrolysis by using a wire electrode10.1016/j.decarb.2024.100052 ↗
37. In situ diagnostic techniques for characterisation of polymer electrolyte membrane water electrolysers – flow visualisation and electrochemical impedance spectroscopy10.1016/j.ijhydene.2014.01.026 ↗
38. In-situ investigation of bubble dynamics and two-phase flow in proton exchange membrane electrolyzer cells10.1016/j.ijhydene.2018.05.006 ↗
39. Detecting and modeling oxygen bubble evolution and detachment in proton exchange membrane water electrolyzers10.1016/j.ijhydene.2019.08.253 ↗
40. Investigating bubble impacts on PEM electrolysis performance through enhanced multiphysics modeling10.1016/j.ijhydene.2024.12.017 ↗
41. The quantities affecting the bubble coverage of gas-evolving electrodes10.1016/j.electacta.2017.03.116 ↗
42. Dynamics of single hydrogen bubbles at a platinum microelectrode10.1021/acs.langmuir.5b01825 ↗