@article{33680,
  author       = {{Khajehpasha, Ehsan Rahmatizad and Finkler, Jonas A. and Kühne, Thomas and Ghasemi, Alireza}},
  issn         = {{2469-9950}},
  journal      = {{Physical Review B}},
  number       = {{14}},
  publisher    = {{American Physical Society (APS)}},
  title        = {{{CENT2: Improved charge equilibration via neural network technique}}},
  doi          = {{10.1103/physrevb.105.144106}},
  volume       = {{105}},
  year         = {{2022}},
}

@article{29700,
  abstract     = {{We have carried out an extensive search for stable polymorphs of carbon nitride with C3N5 stoichiometry using the minima hopping method. Contrary to the widely held opinion that stacked{,} planar{,} graphite-like structures are energetically the most stable carbon nitride polymorphs for various nitrogen contents{,} we find that this does not apply for nitrogen-rich materials owing to the high abundance of N–N bonds. In fact{,} our results disclose novel morphologies with moieties not previously considered for C3N5. We demonstrate that nitrogen-rich compounds crystallize in a large variety of different structures due to particular characteristics of their energy landscapes. The newly found low-energy structures of C3N5 have band gaps within good agreement with the values measured in experimental studies.}},
  author       = {{Ghasemi, Alireza and Mirhosseini, Hossein and Kühne, Thomas}},
  journal      = {{Phys. Chem. Chem. Phys.}},
  pages        = {{6422--6432}},
  publisher    = {{The Royal Society of Chemistry}},
  title        = {{{Thermodynamically stable polymorphs of nitrogen-rich carbon nitrides: a C3N5 study}}},
  doi          = {{10.1039/D0CP06185A}},
  volume       = {{23}},
  year         = {{2021}},
}

@article{33648,
  author       = {{Ghasemi, Alireza and Kühne, Thomas}},
  issn         = {{0021-9606}},
  journal      = {{The Journal of Chemical Physics}},
  keywords     = {{Physical and Theoretical Chemistry, General Physics and Astronomy}},
  number       = {{7}},
  publisher    = {{AIP Publishing}},
  title        = {{{Artificial neural networks for the kinetic energy functional of non-interacting fermions}}},
  doi          = {{10.1063/5.0037319}},
  volume       = {{154}},
  year         = {{2021}},
}

@article{33657,
  author       = {{Mirhosseini, Hossein and Tahmasbi, Hossein and Kuchana, Sai Ram and Ghasemi, Alireza and Kühne, Thomas}},
  issn         = {{0927-0256}},
  journal      = {{Computational Materials Science}},
  keywords     = {{Computational Mathematics, General Physics and Astronomy, Mechanics of Materials, General Materials Science, General Chemistry, General Computer Science}},
  publisher    = {{Elsevier BV}},
  title        = {{{An automated approach for developing neural network interatomic potentials with FLAME}}},
  doi          = {{10.1016/j.commatsci.2021.110567}},
  volume       = {{197}},
  year         = {{2021}},
}