The High-Frequency and Rare Events Barriers to Neural Closures of Atmospheric Dynamics
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914719184453632 |
|---|---|
| author | Chekroun, Mickaël D. Liu, Honghu Srinivasan, Kaushik McWilliams, James C. |
| author_facet | Chekroun, Mickaël D. Liu, Honghu Srinivasan, Kaushik McWilliams, James C. |
| contents | Recent years have seen a surge in interest for leveraging neural networks to parameterize small-scale or fast processes in climate and turbulence models. In this short paper, we point out two fundamental issues in this endeavor. The first concerns the difficulties neural networks may experience in capturing rare events due to limitations in how data is sampled. The second arises from the inherent multiscale nature of these systems. They combine high-frequency components (like inertia-gravity waves) with slower, evolving processes (geostrophic motion). This multiscale nature creates a significant hurdle for neural network closures. To illustrate these challenges, we focus on the atmospheric 1980 Lorenz model, a simplified version of the Primitive Equations that drive climate models. This model serves as a compelling example because it captures the essence of these difficulties. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_04331 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | The High-Frequency and Rare Events Barriers to Neural Closures of Atmospheric Dynamics Chekroun, Mickaël D. Liu, Honghu Srinivasan, Kaushik McWilliams, James C. Dynamical Systems Atmospheric and Oceanic Physics Recent years have seen a surge in interest for leveraging neural networks to parameterize small-scale or fast processes in climate and turbulence models. In this short paper, we point out two fundamental issues in this endeavor. The first concerns the difficulties neural networks may experience in capturing rare events due to limitations in how data is sampled. The second arises from the inherent multiscale nature of these systems. They combine high-frequency components (like inertia-gravity waves) with slower, evolving processes (geostrophic motion). This multiscale nature creates a significant hurdle for neural network closures. To illustrate these challenges, we focus on the atmospheric 1980 Lorenz model, a simplified version of the Primitive Equations that drive climate models. This model serves as a compelling example because it captures the essence of these difficulties. |
| title | The High-Frequency and Rare Events Barriers to Neural Closures of Atmospheric Dynamics |
| topic | Dynamical Systems Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2305.04331 |