EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Data‐Driven Reduced Order Modeling for Warm Rain Microphysics

E. K. de Jong, N. Gunawardena, J. E. Katona, H. Beydoun, D. Ghosh, P. Caldwell

Journal of Geophysical Research: Machine Learning and Computation · 2026-06 · 3 (3)

DOI: 10.1029/2025jh001103 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Geophysical Research: Machine Learning and Computation, online erschienen am 23.06.2026. Verfasst von E. K. de Jong und 5 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Lawrence Livermore National Laboratory.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurately representing the formation of precipitation due to coalescence of cloud droplets remains a major challenge for atmospheric models. This study introduces and compares three data‐driven approaches for modeling the time evolution of droplet size distributions within a reduced‐order latent space: a polynomial‐based Sparse Identification of Nonlinear Dynamics (SINDy) framework, numerical integration of a neural‐network‐predicted time derivative, and direct prediction of state at the next timestep via neural network. All three methods are coupled and simultaneously trained with an autoencoder that discovers the latent space variables. We train with high‐fidelity data from large eddy simulations equipped with the superdroplet method, which captures the stochastic nature of the coalescence process. Our results show that while all three approaches can successfully emulate the nonlinear behavior of coalescence, the simplest, a polynomial‐based SINDy representation, generalizes most robustly to out‐of‐sample cloud regimes, achieving strong performance and physical consistency. We further quantify model uncertainty using conformal prediction intervals, thereby providing rigorous estimates of predictive confidence across the modeling pipeline. These findings highlight that simple time evolution representations, when coupled with the correct prognostic variables, are a promising approach to advancing data‐driven microphysics parameterizations toward operational atmospheric modeling.

Förderung

  • Lawrence Livermore National Laboratory

Zitieren

APA

Jong, E. K. D., Gunawardena, N., Katona, J. E., Beydoun, H., Ghosh, D., & Caldwell, P. (2026). Data‐Driven Reduced Order Modeling for Warm Rain Microphysics. Journal of Geophysical Research: Machine Learning and Computation, 3(3). https://doi.org/10.1029/2025jh001103

Vancouver

Jong EKD, Gunawardena N, Katona JE, Beydoun H, Ghosh D, Caldwell P. Data‐Driven Reduced Order Modeling for Warm Rain Microphysics. Journal of Geophysical Research: Machine Learning and Computation. 2026;3(3). doi:10.1029/2025jh001103

BibTeX
@article{Jong2026,
  author = {Jong, E. K. de and Gunawardena, N. and Katona, J. E. and Beydoun, H. and Ghosh, D. and Caldwell, P.},
  title = {Data‐Driven Reduced Order Modeling for Warm Rain Microphysics},
  journal = {Journal of Geophysical Research: Machine Learning and Computation},
  year = {2026},
  volume = {3},
  number = {3},
  doi = {10.1029/2025jh001103}
}
Kostenlos starten →