Simultaneous emulation and downscaling with physically-consistent deep learning-based regional ocean emulators
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909452372803584 |
|---|---|
| author | Lupin-Jimenez, Leonard Darman, Moein Hazarika, Subhashis Wu, Tianning Gray, Michael He, Ruyoing Wong, Anthony Chattopadhyay, Ashesh |
| author_facet | Lupin-Jimenez, Leonard Darman, Moein Hazarika, Subhashis Wu, Tianning Gray, Michael He, Ruyoing Wong, Anthony Chattopadhyay, Ashesh |
| contents | Building on top of the success in AI-based atmospheric emulation, we propose an AI-based ocean emulation and downscaling framework focusing on the high-resolution regional ocean over Gulf of Mexico. Regional ocean emulation presents unique challenges owing to the complex bathymetry and lateral boundary conditions as well as from fundamental biases in deep learning-based frameworks, such as instability and hallucinations. In this paper, we develop a deep learning-based framework to autoregressively integrate ocean-surface variables over the Gulf of Mexico at $8$ Km spatial resolution without unphysical drifts over decadal time scales and simulataneously downscale and bias-correct it to $4$ Km resolution using a physics-constrained generative model. The framework shows both short-term skills as well as accurate long-term statistics in terms of mean and variability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05058 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Simultaneous emulation and downscaling with physically-consistent deep learning-based regional ocean emulators Lupin-Jimenez, Leonard Darman, Moein Hazarika, Subhashis Wu, Tianning Gray, Michael He, Ruyoing Wong, Anthony Chattopadhyay, Ashesh Atmospheric and Oceanic Physics Artificial Intelligence Machine Learning Chaotic Dynamics Geophysics Building on top of the success in AI-based atmospheric emulation, we propose an AI-based ocean emulation and downscaling framework focusing on the high-resolution regional ocean over Gulf of Mexico. Regional ocean emulation presents unique challenges owing to the complex bathymetry and lateral boundary conditions as well as from fundamental biases in deep learning-based frameworks, such as instability and hallucinations. In this paper, we develop a deep learning-based framework to autoregressively integrate ocean-surface variables over the Gulf of Mexico at $8$ Km spatial resolution without unphysical drifts over decadal time scales and simulataneously downscale and bias-correct it to $4$ Km resolution using a physics-constrained generative model. The framework shows both short-term skills as well as accurate long-term statistics in terms of mean and variability. |
| title | Simultaneous emulation and downscaling with physically-consistent deep learning-based regional ocean emulators |
| topic | Atmospheric and Oceanic Physics Artificial Intelligence Machine Learning Chaotic Dynamics Geophysics |
| url | https://arxiv.org/abs/2501.05058 |