Evaluation of Deep Neural Operator Models toward Ocean Forecasting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918222982283264 |
|---|---|
| author | Rajagopal, Ellery Babu, Anantha N. S. Ryu, Tony Haley Jr., Patrick J. Mirabito, Chris Lermusiaux, Pierre F. J. |
| author_facet | Rajagopal, Ellery Babu, Anantha N. S. Ryu, Tony Haley Jr., Patrick J. Mirabito, Chris Lermusiaux, Pierre F. J. |
| contents | Data-driven, deep-learning modeling frameworks have been recently developed for forecasting time series data. Such machine learning models may be useful in multiple domains including the atmospheric and oceanic ones, and in general, the larger fluids community. The present work investigates the possible effectiveness of such deep neural operator models for reproducing and predicting classic fluid flows and simulations of realistic ocean dynamics. We first briefly evaluate the capabilities of such deep neural operator models when trained on a simulated two-dimensional fluid flow past a cylinder. We then investigate their application to forecasting ocean surface circulation in the Middle Atlantic Bight and Massachusetts Bay, learning from high-resolution data-assimilative simulations employed for real sea experiments. We confirm that trained deep neural operator models are capable of predicting idealized periodic eddy shedding. For realistic ocean surface flows and our preliminary study, they can predict several of the features and show some skill, providing potential for future research and applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_11814 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Evaluation of Deep Neural Operator Models toward Ocean Forecasting Rajagopal, Ellery Babu, Anantha N. S. Ryu, Tony Haley Jr., Patrick J. Mirabito, Chris Lermusiaux, Pierre F. J. Machine Learning Computational Engineering, Finance, and Science Atmospheric and Oceanic Physics Geophysics 76U60, 86A05, 86-08, 86A10, 86A08, 68T01, 68T07, 68T37 J.2; I.2; I.6 Data-driven, deep-learning modeling frameworks have been recently developed for forecasting time series data. Such machine learning models may be useful in multiple domains including the atmospheric and oceanic ones, and in general, the larger fluids community. The present work investigates the possible effectiveness of such deep neural operator models for reproducing and predicting classic fluid flows and simulations of realistic ocean dynamics. We first briefly evaluate the capabilities of such deep neural operator models when trained on a simulated two-dimensional fluid flow past a cylinder. We then investigate their application to forecasting ocean surface circulation in the Middle Atlantic Bight and Massachusetts Bay, learning from high-resolution data-assimilative simulations employed for real sea experiments. We confirm that trained deep neural operator models are capable of predicting idealized periodic eddy shedding. For realistic ocean surface flows and our preliminary study, they can predict several of the features and show some skill, providing potential for future research and applications. |
| title | Evaluation of Deep Neural Operator Models toward Ocean Forecasting |
| topic | Machine Learning Computational Engineering, Finance, and Science Atmospheric and Oceanic Physics Geophysics 76U60, 86A05, 86-08, 86A10, 86A08, 68T01, 68T07, 68T37 J.2; I.2; I.6 |
| url | https://arxiv.org/abs/2308.11814 |