% 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{Leufen:1007047,
      author       = {Leufen, Lukas Hubert and Kleinert, Felix and Schultz,
                      Martin G.},
      title        = {{O}3{R}es{N}et: {A} {D}eep {L}earning–{B}ased {F}orecast
                      {S}ystem to {P}redict {L}ocal {G}round-{L}evel {D}aily
                      {M}aximum 8-{H}our {A}verage {O}zone in {R}ural and
                      {S}uburban {E}nvironments},
      journal      = {Artificial Intelligence for the Earth Systems},
      volume       = {2},
      number       = {3},
      issn         = {2769-7525},
      address      = {Boston},
      publisher    = {[Verlag nicht ermittelbar]},
      reportid     = {FZJ-2023-01952},
      pages        = {1 - 16},
      year         = {2023},
      abstract     = {With the impact of tropospheric ozone pollution on
                      humankind, there is a compelling need for robust air quality
                      forecasts. Here, we introduce a novel deep learning (DL)
                      forecasting system called O3ResNet that produces a four-day
                      forecast for ground-level ozone. O3ResNet is based on a
                      convolutional neural network with residual blocks. The model
                      has been trained on 22 years of ozone and nitrogen oxides
                      in-situ measurements and ERA5 reanalysis data from 2000 to
                      2021 at 328 stations in Central Europe located in rural and
                      suburban environment. Our model outperforms the
                      state-of-the-art Copernicus Atmosphere Monitoring Service
                      regional forecast model ensemble for ground-level ozone with
                      respect to the mean square error and mean absolute error of
                      the daily maximum 8-hour running average ozone, thus marking
                      a major milestone for DL-based ozone prediction. O3ResNet
                      has a very small bias without requiring additional
                      post-processing, and it generalizes well so that new
                      stations can be added with no need to re-train the neural
                      network. As the model works on hourly data, it can be easily
                      adapted to output other air quality metrics. We conclude
                      that O3ResNet is sufficiently advanced and robust to become
                      a test application for operational air quality forecasting
                      with DL.},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
                      (SDLs) and Research Groups (POF4-511) / IntelliAQ -
                      Artificial Intelligence for Air Quality (787576) / Earth
                      System Data Exploration (ESDE)},
      pid          = {G:(DE-HGF)POF4-5111 / G:(EU-Grant)787576 /
                      G:(DE-Juel-1)ESDE},
      typ          = {PUB:(DE-HGF)16},
      doi          = {10.1175/AIES-D-22-0085.1},
      url          = {https://juser.fz-juelich.de/record/1007047},
}