% 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{Eslamibidgoli:897486,
      author       = {Eslamibidgoli, Mohammad Javad and Tipp, Fabian and Jitsev,
                      Jenia and Jankovic, Jasna and Eikerling, Michael H. and
                      Malek, Kourosh},
      title        = {{C}onvolutional neural networks for high throughput
                      screening of catalyst layer inks for polymer electrolyte
                      fuel cells},
      journal      = {RSC Advances},
      volume       = {11},
      number       = {51},
      issn         = {2046-2069},
      address      = {London},
      publisher    = {RSC Publishing},
      reportid     = {FZJ-2021-03819},
      pages        = {32126 - 32134},
      year         = {2021},
      abstract     = {The performance of polymer electrolyte fuel cells
                      decisively depends on the structure and processes in
                      membrane electrode assemblies and their components,
                      particularly the catalyst layers. The structural building
                      blocks of catalyst layers are formed during the processing
                      and application of catalyst inks. Accelerating the
                      structural characterization at the ink stage is thus crucial
                      to expedite further advances in catalyst layer design and
                      fabrication. In this context, deep learning algorithms based
                      on deep convolutional neural networks (ConvNets) can
                      automate the processing of the complex and multi-scale
                      structural features of ink imaging data. This article
                      presents the first application of ConvNets for the high
                      throughput screening of transmission electron microscopy
                      images at the ink stage. Results indicate the importance of
                      model pre-training and data augmentation that works on
                      multiple scales in training robust and accurate
                      classification pipelines.},
      cin          = {IEK-13 / JSC},
      ddc          = {540},
      cid          = {I:(DE-Juel1)IEK-13-20190226 / I:(DE-Juel1)JSC-20090406},
      pnm          = {1231 - Electrochemistry for Hydrogen (POF4-123) / 5112 -
                      Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and
                      Research Groups (POF4-511)},
      pid          = {G:(DE-HGF)POF4-1231 / G:(DE-HGF)POF4-5112},
      typ          = {PUB:(DE-HGF)16},
      UT           = {WOS:000716076100001},
      doi          = {10.1039/D1RA05324H},
      url          = {https://juser.fz-juelich.de/record/897486},
}