Physics captured by data-based methods in El Niño prediction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917697685553152 |
|---|---|
| author | Lancia, G. Goede, I. J. Spitoni, C. Dijkstra, H. A. |
| author_facet | Lancia, G. Goede, I. J. Spitoni, C. Dijkstra, H. A. |
| contents | On average once every four years, the Tropical Pacific warms considerably during events called El Niño, leading to weather disruptions over many regions on Earth. Recent machine-learning approaches to El Niño prediction, in particular Convolutional Neural Networks (CNNs), have shown a surprisingly high skill at relatively long lead times. In an attempt to understand this high skill, we here use data from distorted physics simulations with an intermediate complexity El Niño model to determine what aspects of El Niño physics are represented in a specific CNN-based classification method. We find that the CNN can adequately correct for distortions in the ocean adjustment processes, but that the machine-learning method has far more trouble to deal with distortions in upwelling feedback strength. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2206_03110 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Physics captured by data-based methods in El Niño prediction Lancia, G. Goede, I. J. Spitoni, C. Dijkstra, H. A. Atmospheric and Oceanic Physics On average once every four years, the Tropical Pacific warms considerably during events called El Niño, leading to weather disruptions over many regions on Earth. Recent machine-learning approaches to El Niño prediction, in particular Convolutional Neural Networks (CNNs), have shown a surprisingly high skill at relatively long lead times. In an attempt to understand this high skill, we here use data from distorted physics simulations with an intermediate complexity El Niño model to determine what aspects of El Niño physics are represented in a specific CNN-based classification method. We find that the CNN can adequately correct for distortions in the ocean adjustment processes, but that the machine-learning method has far more trouble to deal with distortions in upwelling feedback strength. |
| title | Physics captured by data-based methods in El Niño prediction |
| topic | Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2206.03110 |