Accelerating Atmospheric Gravity Wave Simulations Using Machine Learning: Kelvin‐Helmholtz Instability and Mountain Wave Sources Driving Gravity Wave Breaking and Secondary Gravity Wave Generation

Dong, Wenjun; Fritts, David C.; Liu, Alan; Lund, Thomas S.; Liu, Hanli; Snively, J. B.

doi:10.1029/2023gl104668

Cited by 3 publications

(4 citation statements)

References 46 publications

(67 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning alternatives to GW parameterizations have recently gained attention in several forms. Chantry et al (2021), Espinosa et al (2022) and Hardiman et al (2023) present ML emulators of existing non-orographic GW schemes, while Dong et al (2023) and Sun et al (2023) use ML to learn GW momentum fluxes from high resolution simulations.…”

Section: Gravity Wave Parameterizationsmentioning

confidence: 99%

See 1 more Smart Citation

Uncertainty Quantification of a Machine Learning Subgrid‐Scale Parameterization for Atmospheric Gravity Waves

Mansfield,

Sheshadri

2024

J Adv Model Earth Syst

View full text Add to dashboard Cite

Subgrid‐scale processes, such as atmospheric gravity waves (GWs), play a pivotal role in shaping the Earth's climate but cannot be explicitly resolved in climate models due to limitations on resolution. Instead, subgrid‐scale parameterizations are used to capture their effects. Recently, machine learning (ML) has emerged as a promising approach to learn parameterizations. In this study, we explore uncertainties associated with a ML parameterization for atmospheric GWs. Focusing on the uncertainties in the training process (parametric uncertainty), we use an ensemble of neural networks to emulate an existing GW parameterization. We estimate both offline uncertainties in raw NN output and online uncertainties in climate model output, after the neural networks are coupled. We find that online parametric uncertainty contributes a significant source of uncertainty in climate model output that must be considered when introducing NN parameterizations. This uncertainty quantification provides valuable insights into the reliability and robustness of ML‐based GW parameterizations, thus advancing our understanding of their potential applications in climate modeling.

show abstract

Section: Gravity Wave Parameterizationsmentioning

confidence: 99%

“…(2023) present ML emulators of existing non‐orographic GW schemes, while Dong et al. (2023) and Sun et al. (2023) use ML to learn GW momentum fluxes from high resolution simulations.…”

Section: Introductionmentioning

confidence: 99%

Uncertainty Quantification of a Machine Learning Subgrid‐Scale Parameterization for Atmospheric Gravity Waves

Mansfield,

Sheshadri

2024

J Adv Model Earth Syst

View full text Add to dashboard Cite

show abstract

“…Here, we use the emulations of current physicsbased parameterization schemes as a stepping stone toward learning data-driven parameterizations from observations and high-fidelity simulations by testing ideas for addressing items 1-3 listed earlier. A number of recent studies have taken the first steps in learning data-driven GWP from observations and high-resolution simulations (Matsuoka et al, 2020;Amiramjadi et al, 2022;Dong et al, 2023), though careful and timeconsuming steps are needed in producing, analyzing, and using such data. Furthermore, three recent studies focused on emulators of simpler GWP schemes in a forecast model and idealized GCM have readily shown the usefulness of lessons learned from emulators (Chantry et al, 2021;Espinosa et al, 2022;Hardiman et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

“…A number of recent studies have taken the first steps in learning data‐driven GWP from observations and high‐resolution simulations (Matsuoka et al., 2020; Amiramjadi et al., 2022; Y. Sun et al., 2023; Dong et al., 2023), though careful and time‐consuming steps are needed in producing, analyzing, and using such data. Furthermore, three recent studies focused on emulators of simpler GWP schemes in a forecast model and idealized GCM have readily shown the usefulness of lessons learned from emulators (Chantry et al., 2021; Espinosa et al., 2022; Hardiman et al., 2023).…”

Section: Introductionmentioning

confidence: 99%

Data Imbalance, Uncertainty Quantification, and Transfer Learning in Data‐Driven Parameterizations: Lessons From the Emulation of Gravity Wave Momentum Transport in WACCM

Sun,

Pahlavan,

Chattopadhyay

et al. 2024

J Adv Model Earth Syst

View full text Add to dashboard Cite

Neural networks (NNs) are increasingly used for data‐driven subgrid‐scale parameterizations in weather and climate models. While NNs are powerful tools for learning complex non‐linear relationships from data, there are several challenges in using them for parameterizations. Three of these challenges are (a) data imbalance related to learning rare, often large‐amplitude, samples; (b) uncertainty quantification (UQ) of the predictions to provide an accuracy indicator; and (c) generalization to other climates, for example, those with different radiative forcings. Here, we examine the performance of methods for addressing these challenges using NN‐based emulators of the Whole Atmosphere Community Climate Model (WACCM) physics‐based gravity wave (GW) parameterizations as a test case. WACCM has complex, state‐of‐the‐art parameterizations for orography‐, convection‐, and front‐driven GWs. Convection‐ and orography‐driven GWs have significant data imbalance due to the absence of convection or orography in most grid points. We address data imbalance using resampling and/or weighted loss functions, enabling the successful emulation of parameterizations for all three sources. We demonstrate that three UQ methods (Bayesian NNs, variational auto‐encoders, and dropouts) provide ensemble spreads that correspond to accuracy during testing, offering criteria for identifying when an NN gives inaccurate predictions. Finally, we show that the accuracy of these NNs decreases for a warmer climate (4 × CO2). However, their performance is significantly improved by applying transfer learning, for example, re‐training only one layer using ∼1% new data from the warmer climate. The findings of this study offer insights for developing reliable and generalizable data‐driven parameterizations for various processes, including (but not limited to) GWs.

show abstract

Efficient and stable coupling of the SuperdropNet deep-learning-based cloud microphysics (v0.1.0) with the ICON climate and weather model (v2.6.5)

Arnold,

Sharma,

Weigel

et al. 2024

Geosci. Model Dev.

View full text Add to dashboard Cite

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, with ICON (Icosahedral Nonhydrostatic) model v2.6.5. SuperdropNet is trained on computationally expensive droplet-based simulations and can serve as an inexpensive proxy within weather prediction models. SuperdropNet emulates the collision–coalescence of rain and cloud droplets in a warm-rain scenario and replaces the collision–coalescence process in the two-moment cloud microphysics scheme. 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 (CFFI), pipes, and coupling of program components via Yet Another Coupler (YAC). We validate the emulator in the warm-bubble scenario and find that SuperdropNet runs stably within the experiment. By comparing experiment outcomes of the two-moment bulk scheme with SuperdropNet, we find that the results are physically consistent and discuss differences that are observed in 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.

show abstract

Accelerating Atmospheric Gravity Wave Simulations Using Machine Learning: Kelvin‐Helmholtz Instability and Mountain Wave Sources Driving Gravity Wave Breaking and Secondary Gravity Wave Generation

Cited by 3 publications

References 46 publications

Uncertainty Quantification of a Machine Learning Subgrid‐Scale Parameterization for Atmospheric Gravity Waves

Uncertainty Quantification of a Machine Learning Subgrid‐Scale Parameterization for Atmospheric Gravity Waves

Data Imbalance, Uncertainty Quantification, and Transfer Learning in Data‐Driven Parameterizations: Lessons From the Emulation of Gravity Wave Momentum Transport in WACCM

Efficient and stable coupling of the SuperdropNet deep-learning-based cloud microphysics (v0.1.0) with the ICON climate and weather model (v2.6.5)

Contact Info

Product

Resources

About