15 Nov 2023
 | 15 Nov 2023
Status: this preprint is open for discussion.

Efficient and Stable Coupling of the SuperdropNet Deep Learning-based Cloud Microphysics (v0.1.0) to the ICON Climate and Weather Model (v2.6.5)

Caroline Arnold, Shivani Sharma, Tobias Weigel, and David Greenberg

Abstract. Machine learning (ML) algorithms can be used in Earth System models (ESMs) to emulate sub-grid-scale processes. Due to the statistical nature of ML algorithms and the high complexity of ESMs, these hybrid ML-ESMs require careful validation. Simulation stability needs to be monitored in fully coupled simulations, and the plausibility of results needs to be evaluated in suitable experiments.

We present the coupling of SuperdropNet, a machine learning model for emulating warm rain processes in cloud microphysics, into ICON~2.6.5. SuperdropNet is trained on superdroplet simulations and predicts updates of the bulk moments for cloud and rain. It replaces the accretion, autoconversion, and self-collection of rain and cloud droplets in two-moment cloud microphysics. We address the technical challenge of integrating SuperdropNet, developed in Python and PyTorch, into ICON, written in Fortran, by implementing three different coupling strategies: embedded Python via the C Foreign Function Interface, pipes, and coupling of program components via YetAnotherCoupler (YAC). We validate the emulator in the warm bubble scenario and find that SuperdropNet runs stable within the experiment. In comparing experiment outcomes from the bulk moment scheme and SuperdropNet, we find that the results are physically consistent, and discuss differences that are observed for several diagnostic variables.

In addition, we provide a quantitative and qualitative computational benchmark for three different coupling strategies—embedded Python, coupler YAC, and pipes—and find that embedded Python is a useful software tool for validating hybrid ML-ESMs.

Caroline Arnold et al.

Status: open (until 10 Jan 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Caroline Arnold et al.

Data sets

The ICON model code (version 2.6.5) including the coupling modules and the experiment results are available for download. By accessing the ICON model code, you accept the license conditions of the original code that are included in the repository. C. Arnold, S. Sharma, T. Weigel

Model code and software

SuperdropNet inference code, and modules describing the coupling between SuperdropNet inference and generic Python code, analysis scripts and Jupyter notebooks, as well as the experiment description files C. Arnold, S. Sharma, T. Weigel

Caroline Arnold et al.


Total article views: 33 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
19 13 1 33 4 2
  • HTML: 19
  • PDF: 13
  • XML: 1
  • Total: 33
  • BibTeX: 4
  • EndNote: 2
Views and downloads (calculated since 15 Nov 2023)
Cumulative views and downloads (calculated since 15 Nov 2023)

Viewed (geographical distribution)

Total article views: 33 (including HTML, PDF, and XML) Thereof 33 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 29 Nov 2023
Short summary
In weather and climate models, rain formation is simplified by parameterizations to be computationally efficient. We trained a machine learning algorithm, SuperdropNet, to emulate rain formation in warm clouds based on physically more accurate super-droplet simulations. Here, we validate SuperdropNet coupled to ICON in a warm bubble experiment. We find the coupled simulation runs stable and produces reasonable results, and present a computational benchmark for the coupling software.