% 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{Kaffashzadeh:875342,
      author       = {Kaffashzadeh, Najmeh and Chang, Kai-Lan and Schröder,
                      Sabine and Schultz, Martin G.},
      title        = {{A} {S}tatistical {M}odel for {A}utomated {Q}uality
                      {A}ssessment of the {TOAR}-{II}},
      reportid     = {FZJ-2020-01965},
      year         = {2020},
      abstract     = {The Tropospheric Ozone Assessment Report, phase 2,
                      (TOAR-II) database is a collection of global ground-level
                      ozone in-situ measurements from various locations. It also
                      holds data of selected ozone precursors and meteorological
                      variables. TOAR-II assembles air quality data from many
                      different sources and thus requires a common data quality
                      assessment (QA) to ensure the data meet the quality required
                      for globally consistent analyses. The large volume of this
                      database (more than 100,000 data series) enforces the use of
                      automated, data-driven QA procedures. Accordingly, we have
                      developed a statistical model for automated QA. This model
                      consists of several statistical tests that are classified
                      into several sub-groups. In this model, a QA-score (an
                      indicator ranging from 0 to 1) was assigned to each
                      individual data point to estimates the $value\‘s$
                      plausibility. The foundation of this concept is statistical
                      hypothesis testing and the probability theory. This model
                      was implemented in a Python package and is called
                      AutoQA4Env. One application of AutoQA4Env is the data
                      ingestion workflow of TOAR-II. The tool generates a data
                      quality report which is then sent back to the data provider
                      for inspection. Since AutoQA4Env is easily configurable, it
                      allows the users to set quality thresholds and thus filter
                      data according to their use case. While we primarily develop
                      AutoQA4Env for air quality data, the same concept and model
                      might be applicable to other databases and the software
                      framework is flexible enough to allow for other use cases.},
      month         = {May},
      date          = {2020-05-04},
      organization  = {EGU2020: Sharing Geoscience Online,
                       Vienna (Austria), 4 May 2020 - 8 May
                       2020},
      subtyp        = {Other},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {512 - Data-Intensive Science and Federated Computing
                      (POF3-512) / IntelliAQ - Artificial Intelligence for Air
                      Quality (787576) / Earth System Data Exploration (ESDE)},
      pid          = {G:(DE-HGF)POF3-512 / G:(EU-Grant)787576 /
                      G:(DE-Juel-1)ESDE},
      typ          = {PUB:(DE-HGF)6},
      doi          = {10.5194/egusphere-egu2020-13357},
      url          = {https://juser.fz-juelich.de/record/875342},
}