Samudra: An AI Global Ocean Emulator for Climate

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dheeshjith, Surya, Subel, Adam, Adcroft, Alistair, Busecke, Julius, Fernandez-Granda, Carlos, Gupta, Shubham, Zanna, Laure
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908387229302784
author Dheeshjith, Surya
Subel, Adam
Adcroft, Alistair
Busecke, Julius
Fernandez-Granda, Carlos
Gupta, Shubham
Zanna, Laure
author_facet Dheeshjith, Surya
Subel, Adam
Adcroft, Alistair
Busecke, Julius
Fernandez-Granda, Carlos
Gupta, Shubham
Zanna, Laure
contents AI emulators for forecasting have emerged as powerful tools that can outperform conventional numerical predictions. The next frontier is to build emulators for long climate simulations with skill across a range of spatiotemporal scales, a particularly important goal for the ocean. Our work builds a skillful global emulator of the ocean component of a state-of-the-art climate model. We emulate key ocean variables, sea surface height, horizontal velocities, temperature, and salinity, across their full depth. We use a modified ConvNeXt UNet architecture trained on multi-depth levels of ocean data. We show that the ocean emulator - Samudra - which exhibits no drift relative to the truth, can reproduce the depth structure of ocean variables and their interannual variability. Samudra is stable for centuries and 150 times faster than the original ocean model. Samudra struggles to capture the correct magnitude of the forcing trends and simultaneously remain stable, requiring further work.
format Preprint
id arxiv_https___arxiv_org_abs_2412_03795
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Samudra: An AI Global Ocean Emulator for Climate
Dheeshjith, Surya
Subel, Adam
Adcroft, Alistair
Busecke, Julius
Fernandez-Granda, Carlos
Gupta, Shubham
Zanna, Laure
Atmospheric and Oceanic Physics
Machine Learning
AI emulators for forecasting have emerged as powerful tools that can outperform conventional numerical predictions. The next frontier is to build emulators for long climate simulations with skill across a range of spatiotemporal scales, a particularly important goal for the ocean. Our work builds a skillful global emulator of the ocean component of a state-of-the-art climate model. We emulate key ocean variables, sea surface height, horizontal velocities, temperature, and salinity, across their full depth. We use a modified ConvNeXt UNet architecture trained on multi-depth levels of ocean data. We show that the ocean emulator - Samudra - which exhibits no drift relative to the truth, can reproduce the depth structure of ocean variables and their interannual variability. Samudra is stable for centuries and 150 times faster than the original ocean model. Samudra struggles to capture the correct magnitude of the forcing trends and simultaneously remain stable, requiring further work.
title Samudra: An AI Global Ocean Emulator for Climate
topic Atmospheric and Oceanic Physics
Machine Learning
url https://arxiv.org/abs/2412.03795