Active learning-assisted optimization and investigation of gas diffusion layer physical properties in anion exchange membrane water electrolyzers

Abstract

To address the challenge of synergistic optimization of the multi-physical property parameters for the gas diffusion layer—a core component of anion exchange membrane water electrolyzers (AEMWEs)—this study establishes an integrated analytical framework combining multi-physics mechanism simulation and active learning-based intelligent optimization. Based on a three-dimensional steady-state multi-physics coupling numerical model of AEMWEs, the regulatory mechanisms of permeability, electrical conductivity, and porosity in the mass transport and heat transfer processes were elucidated. On this basis, a multi-model weighted ensemble active learning surrogate model was constructed to optimize the electrochemical performance of the electrolyzer. The model achieved a root mean square error (RMSE) of 16.5539 and a mean absolute error (MAE) of 12.9643 during the training process. On the test set, the model achieved a coefficient of determination (R²) of 0.9994, an RMSE of 5.0240, and an MAE of 4.0694. The optimal parameter combination for electrochemical performance identified by the proposed framework (a permeability of 1.18 × 10⁻¹⁰ m², an electrical conductivity of 2208.86 S∙m⁻¹, and a porosity of 0.605) effectively suppresses local heat accumulation and eliminates mass transport bottlenecks. Detailed post-optimization analyses further demonstrated that the optimal parameter combination achieved a favorable balance between the optimal electrochemical response and acceptable multi-physics field distribution uniformity.

Graphical abstract

Keywords

AEMWEs / numerical simulation / active learning / gas diffusion layer

References

[1] Zhang L R , Qi F , Ren R , Gu Y L , Gao J C , Liang Y , Wang Y F , Zhu H E , Kong X Y , Zhang Q N . et al. Recent advances in green hydrogen production by electrolyzing water with anion-exchange membrane. Research, 2025, 8: 677

[2] Wang Y Q , Wen C , Tu J , Zhan Z H , Zhang B H , Liu Q , Zhang Z Y , Hu H M , Liu T Y . The multi-scenario projection of cost reduction in hydrogen production by proton exchange membrane (PEM) water electrolysis in the near future (2020–2060) of China. Fuel, 2023, 354: 129409

[3] Moradpoor I , Syri S , Santasalo-Aarnio A . Green hydrogen production for oil refining—Finnish case. Renewable and Sustainable Energy Reviews, 2023, 175: 113159

[4] Henkensmeier D , Cho W C , Jannasch P , Stojadinovic J , Li Q F , Aili D , Jensen J O . Separators and membranes for advanced alkaline water electrolysis. Chemical Reviews, 2024, 124(10): 6393–6443

[5] Boettcher S W . Introduction to green hydrogen. Chemical Reviews, 2024, 124(23): 13095–13098

[6] Wang G W , Xiao L , Zhuang L . General definition of hydrogen energy and related electrochemical technologies. Chinese Journal of Catalysis, 2024, 56: 1–8

[7] Xie H P , Zhao Z Y , Liu T , Wu Y F , Lan C , Jiang W C , Zhu L Y , Wang Y P , Yang D S , Shao Z P . A membrane-based seawater electrolyser for hydrogen generation. Nature, 2022, 612(7941): 673–678

[8] Du N Y , Roy C , Peach R , Turnbull M , Thiele S , Bock C . Anion-exchange membrane water electrolyzers. Chemical Reviews, 2022, 122(13): 11830–11895

[9] Li D G , Park E J , Zhu W L , Shi Q R , Zhou Y , Tian H Y , Lin Y H , Serov A , Zulevi B , Baca E D . et al. Highly quaternized polystyrene ionomers for high performance anion exchange membrane water electrolysers. Nature Energy, 2020, 5(5): 378–385

[10] Liu R T , Xu Z L , Li F M , Chen F Y , Yu J Y , Yan Y , Chen Y , Xia B Y . Recent advances in proton exchange membrane water electrolysis. Chemical Society Reviews, 2023, 52(16): 5652–5683

[11] López-Fernández E , Sacedón C G , Gil-Rostra J , Yubero F , González-Elipe A R , de Lucas-Consuegra A . Recent advances in alkaline exchange membrane water electrolysis and electrode manufacturing. Molecules, 2021, 26(21): 6326

[12] Zheng W T , He L L , Tang T , Ren R , Lee H , Ding G H , Wang L Q , Sun L C . Poly(dibenzothiophene-terphenyl piperidinium) for high-performance anion exchange membrane water electrolysis. Angewandte Chemie International Edition, 2024, 63(34): e202405738

[13] Liu J M , Zhang L H , Liu J Y , Xu Z H , Zhang J X , Liang L C , Du L , Song H Y , Zhu Y , Li N W . et al. Surface engineered PdNFe₃ intermetallic electrocatalyst for boosting oxygen reduction in alkaline media. Applied Catalysis B: Environmental, 2023, 334: 122807

[14] Yang N , Li H N , Lin X , Georgiadou S , Hong L , Wang Z H , He F , Qi Z F , Lin W F . Catalytic electrode comprising a gas diffusion layer and bubble-involved mass transfer in anion exchange membrane water electrolysis: a critical review and perspectives. Journal of Energy Chemistry, 2025, 105: 669–701

[15] Gunuru M , Paravada M . Mathematical modeling of an AEMWE: investigating optimum operating conditions of an alkaline-fed AEM electrolyzer. International Journal of Hydrogen Energy, 2025, 157: 150320

[16] Ma X Q , Zhao X H , Fu L , Qiang Y , Bai Q C . Recent advances in modification strategies of anion exchange membranes for AEMFCs and AEMWEs. International Journal of Hydrogen Energy, 2026, 214: 153748

[17] Mondal S , Peter S C . Unraveling anodic reaction challenges and mitigation strategies in anion exchange membrane water electrolyzer (AEMWE) systems. ACS Energy Letters, 2026, 11(1): 43–53

[18] Yang Y X , Li P , Zheng X B , Sun W P , Dou S X , Ma T Y , Pan H G . Anion-exchange membrane water electrolyzers and fuel cells. Chemical Society Reviews, 2022, 51(23): 9620–9693

[19] Mulk W U , Aziz A R A , Ismael M A , Ali Ghoto A , Ali S A , Younas M , Gallucci F . Electrochemical hydrogen production through anion exchange membrane water electrolysis (AEMWE): recent progress and associated challenges in hydrogen production. International Journal of Hydrogen Energy, 2024, 94: 1174–1211

[20] Ghorui U K , Sivaguru G , Teja U B , Aswathi M , Ramakrishna S , Ghosh S , Dalapati G K , Chakrabortty S . Anion-exchange membrane water electrolyzers for green hydrogen generation: advancement and challenges for industrial application. ACS Applied Energy Materials, 2024, 7(18): 7649–7676

[21] Huang B R , Wang X C , Li W Z , Tian W G , Luo L , Sun X M , Wang G W , Zhuang L , Xiao L . Accelerating gas escape in anion exchange membrane water electrolysis by gas diffusion layers with hierarchical grid gradients. Angewandte Chemie International Edition, 2023, 62(33): e202304230

[22] Razmjooei F , Morawietz T , Taghizadeh E , Hadjixenophontos E , Mues L , Gerle M , Wood B D , Harms C , Gago A S , Ansar S A . et al. Increasing the performance of an anion-exchange membrane electrolyzer operating in pure water with a nickel-based microporous layer. Joule, 2021, 5(7): 1776–1799

[23] Han S , Ryu J , Yoon J . Activated gas diffusion layers as electrocatalysts for sustainable anion exchange membrane water electrolysis. Advanced Functional Materials, 2026, 36(32): e20628

[24] Yang Y , Ouyang T , Tao D C , Xu B S , Li J , Huang J , Zhang L , Ye D D , Chen R , Zhu X . et al. Improving mass transfer with surface patterning of the porous transport layer for PEM water electrolysis. Cell Reports Physical Science, 2025, 6(2): 102433

[25] Tang Y L , Su S C , Niu X X , Song Z H , Li W J . A gradient porous transport layer enabling a high-performance proton-exchange membrane electrolysis cell. Renewable Energy, 2024, 237: 121707

[26] Li F J , Cai S S , Li S , Luo X B , Tu Z K . Pore-scale study of water and mass transport characteristic in anion exchange membrane fuel cells with anisotropic gas diffusion layer. Energy, 2024, 293: 130599

[27] Wu L , Hu Y X , Du X , Lu J , Li Z , Cao N , Zhang S R , Du H L . Movable SiO₂ reinforced polymethyl methacrylate dual network coating for highly stable zinc anodes. Journal of Energy Storage, 2025, 132: 117752

[28] Hu Y X , Du H L , Lu J , Zhang H , Li S , Du X . Interface synergistic stabilization of zinc anodes via polyacrylic acid doped polyvinyl alcohol ultra-thin coating. Journal of Energy Storage, 2024, 87: 111444

[29] Ozdemir S N , Pektezel O . A CFD-driven machine learning approach for predicting PEM electrolyzer performance. Fuel, 2026, 405: 136479

[30] Wang M , Chen J T , Yang G Q , Dai Q B , Zhu Z Y , Sun Y B , Du Z T , Xue Y S , Zou J X , Zhang F Y . Integrated flow field plate-porous transport layer design for hydrogen energy conversion devices. Chemical Engineering Journal, 2025, 523: 168472

[31] Huang Y S , Chen Y J . A novel technique to optimize combustor geometry for micro thermophotovoltaic system by combining numerical simulation and machine learning. International Journal of Hydrogen Energy, 2022, 47(90): 38407–38426

[32] Ozdemir S N , Pektezel O . Performance prediction of experimental PEM electrolyzer using machine learning algorithms. Fuel, 2024, 378: 132853

[33] Yilmaz C , Arslan M , Ozdemir S N , Tokgoz N . Thermal design and genetic algorithm optimization of geothermal and solar-assisted multi-energy and hydrogen production using artificial neural networks. Energy, 2025, 324: 135941

[34] Mohamed A , Ibrahem H , Yang R , Kim K . Optimization of proton exchange membrane electrolyzer cell design using machine learning. Energies, 2022, 15(18): 6657

[35] Cheng G S , Luo E C , Zhao Y , Yang Y H , Chen B B , Cai Y C , Wang X Q , Dong C Q . Analysis and prediction of green hydrogen production potential by photovoltaic-powered water electrolysis using machine learning in China. Energy, 2023, 284: 129302

[36] Tawalbeh M , Shomope I , Al-Othman A , Alshraideh H . Prediction of hydrogen production in proton exchange membrane water electrolysis via neural networks. International Journal of Thermofluids, 2024, 24: 100849

[37] Shomope I , Al-Othman A , Tawalbeh M , Alshraideh H , Almomani F . Machine learning in PEM water electrolysis: a study of hydrogen production and operating parameters. Computers & Chemical Engineering, 2025, 194: 108954

[38] Lei M F , Zhang M , Wang K . Research on bidding optimization strategy for virtual power plants with wind-solar-storage systems based on IGDT-DRO. Electrical Engineering, 2026, 108(3): 208

[39] Lv X , Cui S H , Wang Y , Lu J Y , Yu P M , Wang K . Patch time series transformer-based short-term photovoltaic power prediction enhanced by artificial fish. Energies, 2026, 19(1): 284

[40] Qian S T , Rong J F , Zheng L F , Zhao X K , He Y , Weng W B , Mu R , Wang Z H . Numerical investigation of metal foams as flow channels in anion exchange membrane water electrolyzers. Chemical Engineering Science, 2025, 314: 121782

RIGHTS & PERMISSIONS

Higher Education Press