mlsanityData to 14 Oct 2026

Samudra: An AI Global Ocean Emulator for Climate

arXiv 2412.03795 ↗First posted 5 Dec 2024physics.ao-ph cs.LGcited by 27

Not on the map. Why?

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.

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

10 of 36 references.

References · 10

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2023GenCast: Diffusion-based ensemble forecasting for medium-range weathercited by 177
  3. 2023ACE: A fast, skillful learned global atmospheric model for climate predictioncited by 56
  4. 2023Advancing Parsimonious Deep Learning Weather Prediction using the HEALPix Meshcited by 28
  5. 2023AI-GOMS: Large AI-Driven Global Ocean Modeling Systemcited by 27
  6. 2024Generative Data Assimilation of Sparse Weather Station Observations at Kilometer Scalescited by 27
  7. 2024Coupled Ocean-Atmosphere Dynamics in a Machine Learning Earth System Modelcited by 21
  8. 2024Probabilistic Emulation of a Global Climate Model with Spherical DYffusioncited by 21
  9. 2024Huge Ensembles Part I: Design of Ensemble Weather Forecasts using Spherical Fourier Neural Operatorscited by 18
  10. 2024Regional Ocean Forecasting with Hierarchical Graph Neural Networkscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 11; 2026: 16.

27 papers.

Sort:

By area:

  1. 2025Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilationcited by 20
  2. 2025SamudrACE: Fast and Accurate Coupled Climate Modeling with 3D Ocean and Atmosphere Emulatorscited by 15
  3. 2025Probing forced responses and causality in data-driven climate emulators: conceptual limitations and the role of reduced-order modelscited by 6
  4. 2026FloeNet: A mass-conserving global sea ice emulator that generalizes across climatescited by 4
  5. 2025ArchesClimate: Probabilistic Decadal Ensemble Generation With Flow Matchingcited by 3
  6. 2025MedFormer: a data-driven model for forecasting the Mediterranean Seacited by 2
  7. 2025The Equilibrium Response of Atmospheric Machine-Learning Models to Uniform Sea Surface Temperature Warmingcited by 2
  8. 2025Probabilistic bias adjustment of seasonal predictions of Arctic Sea Ice Concentrationcited by 2
  9. 2025Towards fully differentiable neural ocean model with Veroscited by 2
  10. 2025Long-Range Distillation: Distilling 10,000 Years of Simulated Climate into Long Timestep AI Weather Modelscited by 2
  11. 2026Examining Fast Radiatively Driven Responses Using Machine-Learning Weather Emulatorscited by 2
  12. 2025Benchmarking atmospheric circulation variability in an AI emulator, ACE2, and a hybrid model, NeuralGCMcited by 1
15 more
  1. 2025Crowdsourcing the Frontier: Advancing Hybrid Physics-ML Climate Simulation via a 50,000 Kaggle Competitioncited by 1
  2. 2026Eddy-Resolving Global Ocean Forecasting with Multi-Scale Graph Neural Networkscited by 1
  3. 2026Towards Infinitely Long Neural Simulations: Self-Refining Neural Surrogate Models for Dynamical Systemscited by 1
  4. 2026Skillful Global Ocean Emulation and the Role of Correlation-Aware Losscited by 1
  5. 2026OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecastingcited by 1
  6. 2026Samudra 2: Scaling Ocean Emulators across Resolutionscited by 1
  7. 2026ADDA: a Modular Framework for Representing, Simulating and Assimilating Dynamics with End-to-end Differentiabilitycited by 1
  8. 2026Emulating the Forced Response of Climate Models with Generative Machine Learningcited by 0
  9. 2026Probabilistic bias adjustment of seasonal forecasts using generative machine learning: A case study of Arctic sea ice predictionscited by 0
  10. 2026Stochastic Emulation of a Fully Coupled Preindustrial E3SMv3 Simulationcited by 0
  11. 2026A Checklist to assess the energy and carbon impacts of ML/AI applications in Earth System Modelingcited by 0
  12. 2026Too Rare to Learn: Prescribed Cyclone Tracks Degrade a Bay of Bengal Ocean Emulatorcited by 0
  13. 2026Neptune: An AI model for Global Ocean Subseasonal Predictioncited by 0
  14. 2026HClimRep-Ocean: A Global Ocean Emulator on an Unstructured Meshcited by 0
  15. 2026Post-Training Quantization of Autoregressive Weather Modelscited by 0