An Analysis of Deep Learning Parameterizations for Ocean Subgrid Eddy Forcing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910693070995456 |
|---|---|
| author | Gultekin, Cem Subel, Adam Zhang, Cheng Leibovich, Matan Perezhogin, Pavel Adcroft, Alistair Fernandez-Granda, Carlos Zanna, Laure |
| author_facet | Gultekin, Cem Subel, Adam Zhang, Cheng Leibovich, Matan Perezhogin, Pavel Adcroft, Alistair Fernandez-Granda, Carlos Zanna, Laure |
| contents | Due to computational constraints, climate simulations cannot resolve a range of small-scale physical processes, which have a significant impact on the large-scale evolution of the climate system. Parameterization is an approach to capture the effect of these processes, without resolving them explicitly. In recent years, data-driven parameterizations based on convolutional neural networks have obtained promising results. In this work, we provide an in-depth analysis of these parameterizations developed using data from ocean simulations. The parametrizations account for the effect of mesoscale eddies toward improving simulations of momentum, heat, and mass exchange in the ocean. Our results provide several insights into the properties of data-driven parameterizations based on neural networks. First, their performance can be substantially improved by increasing the geographic extent of the training data. Second, they learn nonlinear structure, since they are able to outperform a linear baseline. Third, they generalize robustly across different CO2 forcings, but not necessarily across different ocean depths. Fourth, they exploit a relatively small region of their input to generate their output. Our results will guide the further development of ocean mesoscale eddy parameterizations, and multiscale modeling more generally. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_06604 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An Analysis of Deep Learning Parameterizations for Ocean Subgrid Eddy Forcing Gultekin, Cem Subel, Adam Zhang, Cheng Leibovich, Matan Perezhogin, Pavel Adcroft, Alistair Fernandez-Granda, Carlos Zanna, Laure Atmospheric and Oceanic Physics Due to computational constraints, climate simulations cannot resolve a range of small-scale physical processes, which have a significant impact on the large-scale evolution of the climate system. Parameterization is an approach to capture the effect of these processes, without resolving them explicitly. In recent years, data-driven parameterizations based on convolutional neural networks have obtained promising results. In this work, we provide an in-depth analysis of these parameterizations developed using data from ocean simulations. The parametrizations account for the effect of mesoscale eddies toward improving simulations of momentum, heat, and mass exchange in the ocean. Our results provide several insights into the properties of data-driven parameterizations based on neural networks. First, their performance can be substantially improved by increasing the geographic extent of the training data. Second, they learn nonlinear structure, since they are able to outperform a linear baseline. Third, they generalize robustly across different CO2 forcings, but not necessarily across different ocean depths. Fourth, they exploit a relatively small region of their input to generate their output. Our results will guide the further development of ocean mesoscale eddy parameterizations, and multiscale modeling more generally. |
| title | An Analysis of Deep Learning Parameterizations for Ocean Subgrid Eddy Forcing |
| topic | Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2411.06604 |