ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responses
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929595166490624 |
|---|---|
| author | Watt-Meyer, Oliver Henn, Brian McGibbon, Jeremy Clark, Spencer K. Kwa, Anna Perkins, W. Andre Wu, Elynn Harris, Lucas Bretherton, Christopher S. |
| author_facet | Watt-Meyer, Oliver Henn, Brian McGibbon, Jeremy Clark, Spencer K. Kwa, Anna Perkins, W. Andre Wu, Elynn Harris, Lucas Bretherton, Christopher S. |
| contents | Existing machine learning models of weather variability are not formulated to enable assessment of their response to varying external boundary conditions such as sea surface temperature and greenhouse gases. Here we present ACE2 (Ai2 Climate Emulator version 2) and its application to reproducing atmospheric variability over the past 80 years on timescales from days to decades. ACE2 is a 450M-parameter autoregressive machine learning emulator, operating with 6-hour temporal resolution, 1° horizontal resolution and eight vertical layers. It exactly conserves global dry air mass and moisture and can be stepped forward stably for arbitrarily many steps with a throughput of about 1500 simulated years per wall clock day. ACE2 generates emergent phenomena such as tropical cyclones, the Madden Julian Oscillation, and sudden stratospheric warmings. Furthermore, it accurately reproduces the atmospheric response to El Niño variability and global trends of temperature over the past 80 years. However, its sensitivities to separately changing sea surface temperature and carbon dioxide are not entirely realistic. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_11268 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responses Watt-Meyer, Oliver Henn, Brian McGibbon, Jeremy Clark, Spencer K. Kwa, Anna Perkins, W. Andre Wu, Elynn Harris, Lucas Bretherton, Christopher S. Atmospheric and Oceanic Physics Machine Learning Existing machine learning models of weather variability are not formulated to enable assessment of their response to varying external boundary conditions such as sea surface temperature and greenhouse gases. Here we present ACE2 (Ai2 Climate Emulator version 2) and its application to reproducing atmospheric variability over the past 80 years on timescales from days to decades. ACE2 is a 450M-parameter autoregressive machine learning emulator, operating with 6-hour temporal resolution, 1° horizontal resolution and eight vertical layers. It exactly conserves global dry air mass and moisture and can be stepped forward stably for arbitrarily many steps with a throughput of about 1500 simulated years per wall clock day. ACE2 generates emergent phenomena such as tropical cyclones, the Madden Julian Oscillation, and sudden stratospheric warmings. Furthermore, it accurately reproduces the atmospheric response to El Niño variability and global trends of temperature over the past 80 years. However, its sensitivities to separately changing sea surface temperature and carbon dioxide are not entirely realistic. |
| title | ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responses |
| topic | Atmospheric and Oceanic Physics Machine Learning |
| url | https://arxiv.org/abs/2411.11268 |