% 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:1031656,
      author       = {Köhler, Cristiano A. and Kern, Moritz and Grün, Sonja and
                      Denker, Michael},
      title        = {{T}racking the provenance of data generation and analysis
                      in {NEST} simulations},
      reportid     = {FZJ-2024-05772},
      year         = {2024},
      abstract     = {Neural simulations using NEST are typically executed by a
                      Python script that configures the simulator kernel, builds
                      the network, and runs the simulation. The result is a series
                      of files containing the simulated network activity, which
                      can then be analyzed to provide insights into the neural
                      activity. Despite the availability of file headers to
                      identify the origin of the outputs, a user analyzing the
                      data must still interpret the findings with respect to the
                      simulation setup, network connectivity, and parameters of
                      the neuronal and synaptic models. This information is not
                      immediately available, as the exact details of the
                      simulation configuration are understandable only by
                      referring to the original script, which makes it challenging
                      to share simulation results, especially in collaborative
                      contexts. In addition, the researcher may change simulation
                      parameters over time, and tracking those changes becomes
                      increasingly difficult among collaborators with access to
                      shared files with the simulation output. Therefore, the
                      final results of a NEST simulation lack detailed provenance
                      to link each output to the detailed description of how the
                      network was instantiated and run.Here we showcase how Alpaca
                      (doi:10.5281/zenodo.10276510; $RRID:SCR_023739)$ [1] helps
                      to capture provenance in a typical NEST simulation
                      experiment and subsequent data analysis with the Elephant
                      (doi:10.5281/zenodo.1186602; $RRID:SCR_003833)$ toolbox [2].
                      Alpaca is a toolbox that captures provenance during the
                      execution of Python scripts. It uses decorators to record
                      the details of each function executed and associated data
                      objects. First, we demonstrate that Alpaca can capture
                      end-to-end provenance in a workflow that executes multiple
                      simulations with distinct parameters and performs a combined
                      analysis of all generated data. Second, we highlight how
                      data objects are annotated with simulation details using the
                      Neo library [3] to identify the data source in the
                      simulation. Third, we show how the details of the network
                      creation using the PyNEST interface are captured and related
                      to each data output and analysis result. In the end, this
                      approach contributes to representing the simulated data and
                      analysis results according to the FAIR principles [4]. The
                      results findability is improved with the detailed
                      provenance, the interoperability is supported by a
                      standardized data model, and data may be reused due to the
                      enhanced description of the data generation and analysis
                      processes. REFERENCES [1] Köhler, C.A., Ulianych, D.,
                      Grün, S., Decker, S., Denker, M., 2024. Facilitating the
                      sharing of electrophysiology data analysis results through
                      in-depth provenance capture. eNeuro 11, ENEURO.0476-23.2024,
                      10.1523/ENEURO.0476-23.2024[2] Denker, M., Yegenoglu, A.,
                      Grün, S., 2018. Collaborative HPC-enabled workflows on the
                      HBP Collaboratory using the Elephant framework.
                      Neuroinformatics 2018, P19, 10.12751/incf.ni2018.0019[3]
                      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,
                      10.3389/fninf.2014.00010[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, 10.1038/sdata.2016.18},
      month         = {Sep},
      date          = {2024-09-29},
      organization  = {Bernstein Conference 2024, Frankfurt
                       am Main (Germany), 29 Sep 2024 - 2 Oct
                       2024},
      subtyp        = {After Call},
      keywords     = {Computational Neuroscience (Other) / Data analysis, machine
                      learning and neuroinformatics (Other)},
      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) /
                      EBRAINS 2.0 - EBRAINS 2.0: A Research Infrastructure to
                      Advance Neuroscience and Brain Health (101147319) / HBP SGA2
                      - Human Brain Project Specific Grant Agreement 2 (785907) /
                      HBP SGA3 - Human Brain Project Specific Grant Agreement 3
                      (945539) / Algorithms of Adaptive Behavior and their
                      Neuronal Implementation in Health and Disease
                      (iBehave-20220812) / JL SMHB - Joint Lab Supercomputing and
                      Modeling for the Human Brain (JL SMHB-2021-2027)},
      pid          = {G:(DE-HGF)POF4-5235 / G:(DE-HGF)POF4-5231 /
                      G:(DE-Juel1)HDS-LEE-20190612 / G:(EU-Grant)101147319 /
                      G:(EU-Grant)785907 / G:(EU-Grant)945539 /
                      G:(DE-Juel-1)iBehave-20220812 / G:(DE-Juel1)JL
                      SMHB-2021-2027},
      typ          = {PUB:(DE-HGF)24},
      doi          = {10.12751/NNCN.BC2024.031},
      url          = {https://juser.fz-juelich.de/record/1031656},
}