Simulating Atmospheric Processes in Earth System Models and Quantifying Uncertainties with Deep Learning Multi-Member and Stochastic Parameterizations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909498425212928 |
|---|---|
| author | Behrens, Gunnar Beucler, Tom Iglesias-Suarez, Fernando Yu, Sungduk Gentine, Pierre Pritchard, Michael Schwabe, Mierk Eyring, Veronika |
| author_facet | Behrens, Gunnar Beucler, Tom Iglesias-Suarez, Fernando Yu, Sungduk Gentine, Pierre Pritchard, Michael Schwabe, Mierk Eyring, Veronika |
| contents | 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 (SP) embedded in an Earth System Model (ESM). We explore three methods to construct stochastic parameterizations: 1) a single Deep Neural Network (DNN) with Monte Carlo Dropout; 2) a multi-member parameterization; and 3) a Variational Encoder Decoder with latent space perturbation. We show that the multi-member (MM) parameterization improves the representation of convective processes, especially in the planetary boundary layer, compared to individual DNNs. The respective uncertainty quantification illustrates that methods 2) and 3) are advantageous compared to a dropout-based DNN parameterization regarding the spread of convective processes. Hybrid simulations with our best-performing MM parameterizations remained challenging and crash within the first days. Therefore, we develop a pragmatic partial coupling strategy relying on the SP for condensate emulation. Partial coupling reduces the computational efficiency of hybrid Earth-like simulations but enables model stability over 5 months with our MM parameterizations. However, our hybrid simulations exhibit biases in thermodynamic fields and differences in precipitation patterns. Despite this, the MM 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 MM machine learning parameterizations leveraging uncertainty quantification to improve the representation of stochasticity of subgrid effects. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_03079 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Simulating Atmospheric Processes in Earth System Models and Quantifying Uncertainties with Deep Learning Multi-Member and Stochastic Parameterizations Behrens, Gunnar Beucler, Tom Iglesias-Suarez, Fernando Yu, Sungduk Gentine, Pierre Pritchard, Michael Schwabe, Mierk Eyring, Veronika Atmospheric and Oceanic Physics 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 (SP) embedded in an Earth System Model (ESM). We explore three methods to construct stochastic parameterizations: 1) a single Deep Neural Network (DNN) with Monte Carlo Dropout; 2) a multi-member parameterization; and 3) a Variational Encoder Decoder with latent space perturbation. We show that the multi-member (MM) parameterization improves the representation of convective processes, especially in the planetary boundary layer, compared to individual DNNs. The respective uncertainty quantification illustrates that methods 2) and 3) are advantageous compared to a dropout-based DNN parameterization regarding the spread of convective processes. Hybrid simulations with our best-performing MM parameterizations remained challenging and crash within the first days. Therefore, we develop a pragmatic partial coupling strategy relying on the SP for condensate emulation. Partial coupling reduces the computational efficiency of hybrid Earth-like simulations but enables model stability over 5 months with our MM parameterizations. However, our hybrid simulations exhibit biases in thermodynamic fields and differences in precipitation patterns. Despite this, the MM 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 MM machine learning parameterizations leveraging uncertainty quantification to improve the representation of stochasticity of subgrid effects. |
| title | Simulating Atmospheric Processes in Earth System Models and Quantifying Uncertainties with Deep Learning Multi-Member and Stochastic Parameterizations |
| topic | Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2402.03079 |