Uncertainty Quantification of a Machine Learning Subgrid‐Scale Parameterization for Atmospheric Gravity Waves
Open Access
- 17 July 2024
- journal article
- research article
- Published by American Geophysical Union (AGU) in Journal of Advances in Modeling Earth Systems
- Vol. 16 (7)
Abstract
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.Keywords
All Related Versions
Funding Information
- National Science Foundation (OAC‐2004492)
This publication has 45 references indexed in Scilit:
- Stochastic parameterization of column physics using generative adversarial networksEnvironmental Data Science, 2022
- Physics-informed learning of aerosol microphysicsEnvironmental Data Science, 2022
- A review of uncertainty quantification in deep learning: Techniques, applications and challengesInformation Fusion, 2021
- An evaluation of tropical waves and wave forcing of the QBO in the QBOi modelsQuarterly Journal of the Royal Meteorological Society, 2020
- Evaluation of the Quasi‐Biennial Oscillation in global climate models for the SPARC QBO‐initiativeQuarterly Journal of the Royal Meteorological Society, 2020
- On recent interannual variability of the Arctic winter mesosphere: Implications for tracer descentGeophysical Research Letters, 2007
- Complex hybrid models combining deterministic and machine learning components for numerical climate modeling and weather predictionNeural Networks, 2006
- Gravity wave dynamics and effects in the middle atmosphereReviews of Geophysics, 2003
- The quasi‐biennial oscillationReviews of Geophysics, 2001
- Use of a neural‐network‐based long‐wave radiative‐transfer scheme in the ECMWF atmospheric modelQuarterly Journal of the Royal Meteorological Society, 2000