OceanNet: A principled neural operator-based digital twin for regional oceans

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chattopadhyay, Ashesh, Gray, Michael, Wu, Tianning, Lowe, Anna B., He, Ruoying
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910589385703424
author Chattopadhyay, Ashesh
Gray, Michael
Wu, Tianning
Lowe, Anna B.
He, Ruoying
author_facet Chattopadhyay, Ashesh
Gray, Michael
Wu, Tianning
Lowe, Anna B.
He, Ruoying
contents While data-driven approaches demonstrate great potential in atmospheric modeling and weather forecasting, ocean modeling poses distinct challenges due to complex bathymetry, land, vertical structure, and flow non-linearity. This study introduces OceanNet, a principled neural operator-based digital twin for ocean circulation. OceanNet uses a Fourier neural operator and predictor-evaluate-corrector integration scheme to mitigate autoregressive error growth and enhance stability over extended time scales. A spectral regularizer counteracts spectral bias at smaller scales. OceanNet is applied to the northwest Atlantic Ocean western boundary current (the Gulf Stream), focusing on the task of seasonal prediction for Loop Current eddies and the Gulf Stream meander. Trained using historical sea surface height (SSH) data, OceanNet demonstrates competitive forecast skill by outperforming SSH predictions by an uncoupled, state-of-the-art dynamical ocean model forecast, reducing computation by 500,000 times. These accomplishments demonstrate the potential of physics-inspired deep neural operators as cost-effective alternatives to high-resolution numerical ocean models.
format Preprint
id arxiv_https___arxiv_org_abs_2310_00813
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle OceanNet: A principled neural operator-based digital twin for regional oceans
Chattopadhyay, Ashesh
Gray, Michael
Wu, Tianning
Lowe, Anna B.
He, Ruoying
Machine Learning
Artificial Intelligence
Chaotic Dynamics
Atmospheric and Oceanic Physics
While data-driven approaches demonstrate great potential in atmospheric modeling and weather forecasting, ocean modeling poses distinct challenges due to complex bathymetry, land, vertical structure, and flow non-linearity. This study introduces OceanNet, a principled neural operator-based digital twin for ocean circulation. OceanNet uses a Fourier neural operator and predictor-evaluate-corrector integration scheme to mitigate autoregressive error growth and enhance stability over extended time scales. A spectral regularizer counteracts spectral bias at smaller scales. OceanNet is applied to the northwest Atlantic Ocean western boundary current (the Gulf Stream), focusing on the task of seasonal prediction for Loop Current eddies and the Gulf Stream meander. Trained using historical sea surface height (SSH) data, OceanNet demonstrates competitive forecast skill by outperforming SSH predictions by an uncoupled, state-of-the-art dynamical ocean model forecast, reducing computation by 500,000 times. These accomplishments demonstrate the potential of physics-inspired deep neural operators as cost-effective alternatives to high-resolution numerical ocean models.
title OceanNet: A principled neural operator-based digital twin for regional oceans
topic Machine Learning
Artificial Intelligence
Chaotic Dynamics
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2310.00813