% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Kuppa:1037215,
      author       = {Kuppa, Raman Ashoke and Hammacher, Linus and Kungl, Hans
                      and Karl, André and Jodat, Eva and Eichel, Rüdiger-A. and
                      Karyofylli, Violeta},
      title        = {{D}ata-{D}riven {S}urrogate {M}odeling {F}ramework for
                      {P}erformance {P}rediction and {S}ensitivity {A}nalysis of a
                      {P}roton {E}xchange {M}embrane {W}ater {E}lectrolyzer},
      journal      = {SSRN eLibrary},
      issn         = {1556-5068},
      address      = {[S.l.]},
      publisher    = {Social Science Electronic Publ.},
      reportid     = {FZJ-2025-00548},
      year         = {2024},
      abstract     = {Proton exchange membrane electrolytic cell (PEMEC) are
                      complex multivariate electrochemical systems that have
                      emerged as a prominent technology for generating green
                      hydrogen. To reduce costs and accelerate the commercial
                      deployment of PEMECs, it is crucial to develop accurate
                      predictive models that enable to capture the inherent
                      nonlinearities of PEM electrolyzers efficiently. Therefore,
                      in this study, we develop data-based surrogate models for
                      PEMEC with supported and unsupported catalyst layers using
                      support vector regression (SVR), extreme gradient boosting
                      (XGB), and artificial neural networks (ANN) machine learning
                      techniques. These models are developed by using the datasets
                      obtained from an analytical model and a physics-based
                      one-dimensional numerical model of PEMEC. The dataset
                      obtained from the one-dimensional model was split into
                      datasets for supported and unsupported catalyst layers,
                      based on the electronic conductivity of the anodecatalyst.
                      The performance prediction of these three models is
                      evaluated and compared with physics-based modeling results.
                      We find that both ANN and XGB models performwell in
                      predicting the cell current density. Therefore, the ANN
                      model is selected to perform parametric analysis to
                      investigate the effect of operating conditions and transport
                      properties of the anode side. Both SHAP and sensitivity
                      analysis reveal that the operating temperature is the most
                      important parameter affecting the performance of the PEMEC.
                      For supported catalyst layers, the influence of membrane
                      thickness is greater than the catalyst’s electronic
                      conductivity. However, in the case of unsupported catalysts
                      layers, the SHAP values for electronic conductivity are
                      found to be larger than membrane thickness},
      cin          = {IET-1},
      ddc          = {330},
      cid          = {I:(DE-Juel1)IET-1-20110218},
      pnm          = {1231 - Electrochemistry for Hydrogen (POF4-123) / HITEC -
                      Helmholtz Interdisciplinary Doctoral Training in Energy and
                      Climate Research (HITEC) (HITEC-20170406)},
      pid          = {G:(DE-HGF)POF4-1231 / G:(DE-Juel1)HITEC-20170406},
      typ          = {PUB:(DE-HGF)25},
      doi          = {10.2139/ssrn.4969962},
      url          = {https://juser.fz-juelich.de/record/1037215},
}