% 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”.

@INPROCEEDINGS{Khler:1027366,
      author       = {Köhler, Cristiano and Kern, Moritz and Grün, Sonja and
                      Denker, Michael},
      title        = {{A}n approach to handle provenance-tracked analysis of
                      {NEST} simulations using {A}lpaca},
      reportid     = {FZJ-2024-03793},
      year         = {2024},
      abstract     = {NEST simulations are typically executed by a script that
                      configures and runs the simulation. Despite recent
                      improvements in NEST 3.x, where file headers specify the
                      detailed origin of the outputs, users still must interpret
                      the data with respect to the simulation setup. This
                      information is difficult to convey, especially in
                      collaborative contexts with shared simulation results.
                      Moreover, during the explorative process of scientific
                      discovery, results may change without warning when details
                      of the simulation are changed, which could lead to wrong
                      interpretations by collaborators who are unaware of such
                      changes. Therefore, we face two challenges: results are
                      stored in data objects without metadata that describe their
                      role in the simulation, and the simulation outputs are not
                      linked to a description of their provenance with respect to
                      the simulation building.Here we present concepts to tackle
                      both challenges when using the NEST Python interface. We
                      consider a typical simulation experiment and subsequent data
                      analysis using the Elephant (doi:10.5281/zenodo.1186602;
                      $RRID:SCR_003833)$ toolbox [1]. First, we show how data from
                      a NEST simulation can be represented with data objects
                      annotated with simulation details using the Neo library [2].
                      Second, we demonstrate how the software Alpaca
                      (doi:10.5281/zenodo.10276510; $RRID:SCR_023739)$ can capture
                      workflow provenance when running a simulation (see Figure)
                      [3]. The two approaches allow the semantic description of
                      the simulation experiment that contributes to the FAIR
                      principles [4] by improving the findability of results
                      through detailed provenance, supporting interoperability
                      through a standardized data model, and promoting reuse of
                      simulation data through enhanced data description.
                      References [1] Denker, M., Yegenoglu, A., Grün, S., 2018.
                      Collaborative HPC-enabled workflows on the HBP Collaboratory
                      using the Elephant framework. Neuroinformatics 2018, P19.
                      doi:10.12751/incf.ni2018.0019 [2] Garcia, S., Guarino, D.,
                      Jaillet, F., Jennings, T., Pröpper, R., Rautenberg, P.L.,
                      Rodgers, C.C., Sobolev, A., Wachtler, T., Yger, P., Davison,
                      A.P., 2014. Neo: an object model for handling
                      electrophysiology data in multiple formats. Frontiers in
                      Neuroinformatics 8, 10.
                      https://doi.org/10.3389/fninf.2014.00010 [3] Köhler, C.A.,
                      Ulianych, D., Grün, S., Decker, S., Denker, M., 2023.
                      Facilitating the sharing of electrophysiology data analysis
                      results through in-depth provenance capture.
                      https://doi.org/10.48550/arXiv.2311.09672 [4] Wilkinson,
                      M.D., Dumontier, M., Aalbersberg, Ij.J., Appleton, G.,
                      Axton, M., Baak, A., Blomberg, N. et al., 2016. The FAIR
                      Guiding Principles for scientific data management and
                      stewardship. Scientific Data 3, 160018.
                      https://doi.org/10.1038/sdata.2016.18},
      month         = {Jun},
      date          = {2024-06-17},
      organization  = {NEST Conference 2024, virtual
                       (virtual), 17 Jun 2024 - 18 Jun 2024},
      subtyp        = {After Call},
      cin          = {IAS-6 / INM-10},
      cid          = {I:(DE-Juel1)IAS-6-20130828 / I:(DE-Juel1)INM-10-20170113},
      pnm          = {5235 - Digitization of Neuroscience and User-Community
                      Building (POF4-523) / 5231 - Neuroscientific Foundations
                      (POF4-523) / HDS LEE - Helmholtz School for Data Science in
                      Life, Earth and Energy (HDS LEE) (HDS-LEE-20190612) / HBP
                      SGA2 - Human Brain Project Specific Grant Agreement 2
                      (785907) / HBP SGA3 - Human Brain Project Specific Grant
                      Agreement 3 (945539) / EBRAINS 2.0 - EBRAINS 2.0: A Research
                      Infrastructure to Advance Neuroscience and Brain Health
                      (101147319) / JL SMHB - Joint Lab Supercomputing and
                      Modeling for the Human Brain (JL SMHB-2021-2027) /
                      Algorithms of Adaptive Behavior and their Neuronal
                      Implementation in Health and Disease (iBehave-20220812)},
      pid          = {G:(DE-HGF)POF4-5235 / G:(DE-HGF)POF4-5231 /
                      G:(DE-Juel1)HDS-LEE-20190612 / G:(EU-Grant)785907 /
                      G:(EU-Grant)945539 / G:(EU-Grant)101147319 / G:(DE-Juel1)JL
                      SMHB-2021-2027 / G:(DE-Juel-1)iBehave-20220812},
      typ          = {PUB:(DE-HGF)6},
      url          = {https://juser.fz-juelich.de/record/1027366},
}