# Samudra: An AI Global Ocean Emulator for Climate

arXiv: https://arxiv.org/abs/2412.03795 · HTML: https://mlsanity.com/paper/2412.03795/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 36 references that are in the map.
- First posted on arXiv 5 Dec 2024.

## Builds on (most cited first, 10 of 10)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [GenCast: Diffusion-based ensemble forecasting for medium-range weather](https://mlsanity.com/paper/2312.15796/) (2023)
- [ACE: A fast, skillful learned global atmospheric model for climate prediction](https://mlsanity.com/paper/2310.02074/) (2023)
- [Advancing Parsimonious Deep Learning Weather Prediction using the HEALPix Mesh](https://mlsanity.com/paper/2311.06253/) (2023)
- [AI-GOMS: Large AI-Driven Global Ocean Modeling System](https://mlsanity.com/paper/2308.03152/) (2023)
- [Generative Data Assimilation of Sparse Weather Station Observations at Kilometer Scales](https://mlsanity.com/paper/2406.16947/) (2024)
- [Coupled Ocean-Atmosphere Dynamics in a Machine Learning Earth System Model](https://mlsanity.com/paper/2406.08632/) (2024)
- [Probabilistic Emulation of a Global Climate Model with Spherical DYffusion](https://mlsanity.com/paper/2406.14798/) (2024)
- [Huge Ensembles Part I: Design of Ensemble Weather Forecasts using Spherical Fourier Neural Operators](https://mlsanity.com/paper/2408.03100/) (2024)
- [Regional Ocean Forecasting with Hierarchical Graph Neural Networks](https://mlsanity.com/paper/2410.11807/) (2024)

## Built on by (most cited first, 27 of 27)

- [Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation](https://mlsanity.com/paper/2504.18720/) (2025)
- [SamudrACE: Fast and Accurate Coupled Climate Modeling with 3D Ocean and Atmosphere Emulators](https://mlsanity.com/paper/2509.12490/) (2025)
- [Probing forced responses and causality in data-driven climate emulators: conceptual limitations and the role of reduced-order models](https://mlsanity.com/paper/2506.22552/) (2025)
- [FloeNet: A mass-conserving global sea ice emulator that generalizes across climates](https://mlsanity.com/paper/2603.12449/) (2026)
- [ArchesClimate: Probabilistic Decadal Ensemble Generation With Flow Matching](https://mlsanity.com/paper/2509.15942/) (2025)
- [MedFormer: a data-driven model for forecasting the Mediterranean Sea](https://mlsanity.com/paper/2509.00015/) (2025)
- [The Equilibrium Response of Atmospheric Machine-Learning Models to Uniform Sea Surface Temperature Warming](https://mlsanity.com/paper/2510.02415/) (2025)
- [Probabilistic bias adjustment of seasonal predictions of Arctic Sea Ice Concentration](https://mlsanity.com/paper/2510.09891/) (2025)
- [Towards fully differentiable neural ocean model with Veros](https://mlsanity.com/paper/2511.17427/) (2025)
- [Long-Range Distillation: Distilling 10,000 Years of Simulated Climate into Long Timestep AI Weather Models](https://mlsanity.com/paper/2512.22814/) (2025)
- [Examining Fast Radiatively Driven Responses Using Machine-Learning Weather Emulators](https://mlsanity.com/paper/2602.16090/) (2026)
- [Benchmarking atmospheric circulation variability in an AI emulator, ACE2, and a hybrid model, NeuralGCM](https://mlsanity.com/paper/2510.04466/) (2025)
- [Crowdsourcing the Frontier: Advancing Hybrid Physics-ML Climate Simulation via a 50,000 Kaggle Competition](https://mlsanity.com/paper/2511.20963/) (2025)
- [Eddy-Resolving Global Ocean Forecasting with Multi-Scale Graph Neural Networks](https://mlsanity.com/paper/2601.12775/) (2026)
- [Towards Infinitely Long Neural Simulations: Self-Refining Neural Surrogate Models for Dynamical Systems](https://mlsanity.com/paper/2603.17750/) (2026)
- [Skillful Global Ocean Emulation and the Role of Correlation-Aware Loss](https://mlsanity.com/paper/2604.18727/) (2026)
- [OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting](https://mlsanity.com/paper/2605.12639/) (2026)
- [Samudra 2: Scaling Ocean Emulators across Resolutions](https://mlsanity.com/paper/2606.02610/) (2026)
- [ADDA: a Modular Framework for Representing, Simulating and Assimilating Dynamics with End-to-end Differentiability](https://mlsanity.com/paper/2608.23297/) (2026)
- [Emulating the Forced Response of Climate Models with Generative Machine Learning](https://mlsanity.com/paper/2605.16929/) (2026)
- [Probabilistic bias adjustment of seasonal forecasts using generative machine learning: A case study of Arctic sea ice predictions](https://mlsanity.com/paper/2605.29172/) (2026)
- [Stochastic Emulation of a Fully Coupled Preindustrial E3SMv3 Simulation](https://mlsanity.com/paper/2608.10277/) (2026)
- [A Checklist to assess the energy and carbon impacts of ML/AI applications in Earth System Modeling](https://mlsanity.com/paper/2609.00847/) (2026)
- [Too Rare to Learn: Prescribed Cyclone Tracks Degrade a Bay of Bengal Ocean Emulator](https://mlsanity.com/paper/2609.04635/) (2026)
- [Neptune: An AI model for Global Ocean Subseasonal Prediction](https://mlsanity.com/paper/2609.08606/) (2026)
- [HClimRep-Ocean: A Global Ocean Emulator on an Unstructured Mesh](https://mlsanity.com/paper/2609.28601/) (2026)
- [Post-Training Quantization of Autoregressive Weather Models](https://mlsanity.com/paper/2610.02511/) (2026)

## Abstract (arXiv)

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.