Essential Site Maintenance: Authorea-powered sites will be updated circa 15:00-17:00 Eastern on Tuesday 5 November.
There should be no interruption to normal services, but please contact us at [email protected] in case you face any issues.

loading page

Deep Learning Based Cloud Cover Parameterization for ICON
  • +3
  • Arthur Grundner,
  • Tom Beucler,
  • Fernando Iglesias-Suarez,
  • Pierre Gentine,
  • Marco A. Giorgetta,
  • Veronika Eyring
Arthur Grundner
Deutsches Zentrum für Luft- und Raumfahrt (DLR)

Corresponding Author:[email protected]

Author Profile
Tom Beucler
University of Lausanne
Author Profile
Fernando Iglesias-Suarez
Deutsches Zentrum für Luft- und Raumfahrt (DLR)
Author Profile
Pierre Gentine
Columbia University
Author Profile
Marco A. Giorgetta
Max Planck Institute for Meteorology
Author Profile
Veronika Eyring
Deutsches Zentrum für Luft- und Raumfahrt
Author Profile

Abstract

A promising approach to improve cloud parameterizations within climate models and thus climate projections is to use deep learning in combination with training data from storm-resolving model (SRM) simulations. The Icosahedral Non-Hydrostatic (ICON) modeling framework permits simulations ranging from numerical weather prediction to climate projections, making it an ideal target to develop neural network (NN) based parameterizations for sub-grid scale processes. Within the ICON framework, we train NN based cloud cover parameterizations with coarse-grained data based on realistic regional and global ICON SRM simulations. We set up three different types of NNs that differ in the degree of vertical locality they assume for diagnosing cloud cover from coarse-grained atmospheric state variables. The NNs accurately estimate sub-grid scale cloud cover from coarse-grained data that has similar geographical characteristics as their training data. Additionally, globally trained NNs can reproduce sub-grid scale cloud cover of the regional SRM simulation. Using the game-theory based interpretability library SHapley Additive exPlanations, we identify an overemphasis on specific humidity and cloud ice as the reason why our column-based NN cannot perfectly generalize from the global to the regional coarse-grained SRM data. The interpretability tool also helps visualize similarities and differences in feature importance between regionally and globally trained column-based NNs, and reveals a local relationship between their cloud cover predictions and the thermodynamic environment. Our results show the potential of deep learning to derive accurate yet interpretable cloud cover parameterizations from global SRMs, and suggest that neighborhood-based models may be a good compromise between accuracy and generalizability.