Extratropical Atmospheric Circulation Response to ENSO in Deep Learning Pacific Pacemaker Experiments
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909925459886080 |
|---|---|
| author | Hua, Zhanxiang Karamperidou, Christina Meng, Zilu |
| author_facet | Hua, Zhanxiang Karamperidou, Christina Meng, Zilu |
| contents | Coupled atmosphere-ocean deep learning (DL) climate emulators are a new frontier but are known to exhibit weak ENSO variability, raising questions about their ability to simulate teleconnections. Here, we present the first Pacific pacemaker (PACE) experiments using a coupled DL emulator (DLESyM) to bypass this weak variability and isolate the atmospheric response to observed ENSO forcing. We find that while the emulator realistically captures internal atmospheric variability, it produces a significantly amplified forced teleconnection response to ENSO. This amplified response leads to biases in simulating extremes, notably an overestimation of atmospheric blocking frequency and duration with the underestimation of peak intensity. Our findings underscore that coupled DL climate models require in-depth and physically-grounded validation, analogous to traditional numerical models, to build confidence in their use for physical climate analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_20899 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Extratropical Atmospheric Circulation Response to ENSO in Deep Learning Pacific Pacemaker Experiments Hua, Zhanxiang Karamperidou, Christina Meng, Zilu Atmospheric and Oceanic Physics Coupled atmosphere-ocean deep learning (DL) climate emulators are a new frontier but are known to exhibit weak ENSO variability, raising questions about their ability to simulate teleconnections. Here, we present the first Pacific pacemaker (PACE) experiments using a coupled DL emulator (DLESyM) to bypass this weak variability and isolate the atmospheric response to observed ENSO forcing. We find that while the emulator realistically captures internal atmospheric variability, it produces a significantly amplified forced teleconnection response to ENSO. This amplified response leads to biases in simulating extremes, notably an overestimation of atmospheric blocking frequency and duration with the underestimation of peak intensity. Our findings underscore that coupled DL climate models require in-depth and physically-grounded validation, analogous to traditional numerical models, to build confidence in their use for physical climate analysis. |
| title | Extratropical Atmospheric Circulation Response to ENSO in Deep Learning Pacific Pacemaker Experiments |
| topic | Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2511.20899 |