Samudra: An AI Global Ocean Emulator for Climate

Abstract

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.

References in corpus (14)

• Neural General Circulation Models for Weather and Climate
• GenCast: Diffusion-based ensemble forecasting for medium-range weather
• Parameterizing Vertical Mixing Coefficients in the Ocean Surface Boundary Layer using Neural Networks
• ACE: A fast, skillful learned global atmospheric model for climate prediction
• AI-GOMS: Large AI-Driven Global Ocean Modeling System
• Coupled Ocean-Atmosphere Dynamics in a Machine Learning Earth System Model
• Transfer Learning for Emulating Ocean Climate Variability across $C{O}_2$ forcing
• ACE2-SOM: Coupling an ML atmospheric emulator to a slab ocean and learning the sensitivity of climate to changed CO${}_2$
• Building Ocean Climate Emulators
• Generative Data Assimilation of Sparse Weather Station Observations at Kilometer Scales
• Probabilistic Emulation of a Global Climate Model with Spherical DYffusion
• Data-driven Global Ocean Modeling for Seasonal to Decadal Prediction
• Regional Ocean Forecasting with Hierarchical Graph Neural Networks
• Prediction Beyond the Medium Range with an Atmosphere-Ocean Model that Combines Physics-based Modeling and Machine Learning

Cited by in corpus (2)

• Benchmarking atmospheric circulation variability in an AI emulator, ACE2, and a hybrid model, NeuralGCM
• FloeNet: A mass-conserving global sea ice emulator that generalizes across climates