% 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{Gong:908090,
      author       = {Gong, Bing and Langguth, Michael and Ji, Yan and Mozaffari,
                      Amirpasha and Stadtler, Scarlet and Mache, Karim and
                      Schultz, Martin G.},
      title        = {{T}emperature forecasting by deep learning methods},
      journal      = {Geoscientific model development},
      issn         = {1991-959X},
      address      = {Katlenburg-Lindau},
      publisher    = {Copernicus},
      reportid     = {FZJ-2022-02369},
      year         = {2022},
      abstract     = {Numerical weather prediction (NWP) models solve a system of
                      partial differential equations based on physical laws to
                      forecast the future state of the atmosphere. These models
                      are deployed operationally, but they are computationally
                      very expensive. Recently, the potential of deep neural
                      networks to generate bespoken weather forecasts has been
                      explored in a couple of scientific studies inspired by the
                      success of video frame prediction models in computer vision.
                      In this study, a simple recurrent neural network with
                      convolutional filters, called ConvLSTM, and an advanced
                      generative network, the Stochastic Adversarial Video
                      Prediction (SAVP) model, are applied to create hourly
                      forecasts of the 2 m temperature for the next 12 hours over
                      Europe. We make use of 13 years of data from the ERA5
                      reanalysis, of which 11 years are utilized for training and
                      one year each is used for validating and testing. We choose
                      the 2 m temperature, total cloud cover and the 850 hPa
                      temperature as predictors and show that both models attain
                      predictive skill by outperforming persistence forecasts.
                      SAVP is superior to ConvLSTM in terms of several evaluation
                      metrics, confirming previous results from computer vision
                      that larger, more complex networks are better suited to
                      learn complex features and to generate better predictions.
                      The 12-hour forecasts of SAVP attain a mean squared error
                      (MSE) of about 2.3 K2, an anomaly correlation coefficient
                      (ACC) larger than 0.85, a Structural Similarity Index (SSIM)
                      of around 0.72, and a gradient ratio (rG) of about 0.82. The
                      ConvLSTM yields a higher MSE (3.6 K2), a smaller ACC (0.80),
                      and SSIM (0.65), but a slightly larger rG (0.84). The
                      superior performance of SAVP in terms of MSE, ACC, and SSIM
                      can be largely attributed to the generator. A sensitivity
                      study shows that a larger weight of the GAN component in the
                      SAVP loss leads to even better preservation of spatial
                      variability at the cost of a somewhat increased MSE (2.5
                      K2). Including the 850 hPa temperature as an additional
                      predictor enhances the forecast quality and the model also
                      benefits from a larger spatial domain. By contrast, adding
                      the total cloud cover as predictor or reducing the amount of
                      training data to eight years has only small effects.
                      Although the temperature forecasts obtained in this way are
                      still less powerful than contemporary NWP models, this study
                      demonstrates that sophisticated deep neural networks may
                      achieve considerable forecast quality beyond the nowcasting
                      range in a purely data-driven way.},
      cin          = {JSC},
      ddc          = {550},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
                      (SDLs) and Research Groups (POF4-511) / MAELSTROM - MAchinE
                      Learning for Scalable meTeoROlogy and cliMate (955513) /
                      IntelliAQ - Artificial Intelligence for Air Quality (787576)
                      / Verbundprojekt DeepRain: Effiziente Lokale
                      Niederschlagsvorhersage durch Maschinelles Lernen
                      (01IS18047A) / Earth System Data Exploration (ESDE)},
      pid          = {G:(DE-HGF)POF4-5111 / G:(EU-Grant)955513 /
                      G:(EU-Grant)787576 / G:(BMBF)01IS18047A / G:(DE-Juel-1)ESDE},
      typ          = {PUB:(DE-HGF)25},
      doi          = {10.5194/gmd-2021-430},
      url          = {https://juser.fz-juelich.de/record/908090},
}