Simulating Atmospheric Processes in Earth System Models and Quantifying Uncertainties With Deep Learning Multi‐Member and Stochastic Parameterizations
[1];
[2];
[3];
[4];
[5];
[6];
[7];
[1]
- Deutsches Zentrum für Luft‐ und Raumfahrt (DLR) Institut für Physik der Atmosphäre Oberpfaffenhofen Germany, University of Bremen Institute of Environmental Physics (IUP) Bremen Germany
- Faculty of Geosciences and Environment University of Lausanne Lausanne Switzerland, Expertise Center for Climate Extremes University of Lausanne Lausanne Switzerland
- Deutsches Zentrum für Luft‐ und Raumfahrt (DLR) Institut für Physik der Atmosphäre Oberpfaffenhofen Germany, Predictia Intelligent Data Solutions S.L. Santander Spain
- Department of Earth System Science University of California Irvine Irvine CA USA, Intel Labs Multimodal Cognitive AI Research SantaClara CA USA
- Department of Earth and Environmental Engineering Columbia University New York NY USA, Earth Institute and Data Science Institute Columbia University New York NY USA
- Department of Earth System Science University of California Irvine Irvine CA USA, NVIDIA Santa Clara CA USA
- Deutsches Zentrum für Luft‐ und Raumfahrt (DLR) Institut für Physik der Atmosphäre Oberpfaffenhofen Germany
Abstract Deep learning is a powerful tool to represent subgrid processes in climate models, but many application cases have so far used idealized settings and deterministic approaches. Here, we develop stochastic parameterizations with calibrated uncertainty quantification to learn subgrid convective and turbulent processes and surface radiative fluxes of a superparameterization embedded in an Earth System Model (ESM). We explore three methods to construct stochastic parameterizations: (a) a single Deep Neural Network (DNN) with Monte Carlo Dropout; (b) a multi‐member parameterization; and (c) a Variational Encoder Decoder with latent space perturbation. We show that the multi‐member parameterization improves the representation of convective processes, especially in the planetary boundary layer, compared to individual DNNs. The respective uncertainty quantification illustrates that methods (b) and (c) are advantageous compared to a dropout‐based DNN parameterization regarding the spread of convective processes. Hybrid simulations with our best‐performing multi‐member parameterizations remained challenging and crash within the first days. Therefore, we develop a pragmatic partial coupling strategy relying on the superparameterization for condensate emulation. Partial coupling reduces the computational efficiency of hybrid Earth‐like simulations but enables model stability over 5 months with our multi‐member parameterizations. However, our hybrid simulations exhibit biases in thermodynamic fields and differences in precipitation patterns. Despite this, the multi‐member parameterizations enable improvements in reproducing tropical extreme precipitation compared to a traditional convection parameterization. Despite these challenges, our results indicate the potential of a new generation of multi‐member machine learning parameterizations leveraging uncertainty quantification to improve the representation of stochasticity of subgrid effects.
- Sponsoring Organization:
- USDOE
- Grant/Contract Number:
- SC0022331; SC0023368
- OSTI ID:
- 2555915
- Journal Information:
- Journal of Advances in Modeling Earth Systems, Journal Name: Journal of Advances in Modeling Earth Systems Journal Issue: 4 Vol. 17; ISSN 1942-2466
- Publisher:
- American Geophysical Union (AGU)Copyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
Deep learning to represent subgrid processes in climate models
Learning Weight Uncertainty with Stochastic Gradient MCMC for Shape Classification