Generative AI models enable efficient and physically consistent sea-ice simulations

• URL: http://arxiv.org/abs/2508.14984v1
• Date: Wed, 20 Aug 2025 18:12:50 GMT
• Title: Generative AI models enable efficient and physically consistent sea-ice simulations
• Authors: Tobias Sebastian Finn, Marc Bocquet, Pierre Rampal, Charlotte Durand, Flavia Porro, Alban Farchi, Alberto Carrassi,
• Abstract summary: We introduce GenSIM, the first generative AI-based pan-Arctic model.<n>It robustly reproduces statistics as observed in numerical models and observations.<n>It shows brittle-like short-term dynamics while also depicting the long-term sea-ice decline.
• Score: 0.410643402505395
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sea ice is governed by highly complex, scale-invariant, and anisotropic processes that are challenging to represent in Earth system models. While advanced numerical models have improved our understanding of the sea-ice dynamics, their computational costs often limit their application in ensemble forecasting and climate simulations. Here, we introduce GenSIM, the first generative AI-based pan-Arctic model that predicts the evolution of all relevant key properties, including concentration, thickness, and drift, in a 12-hour window with improved accuracy over deterministic predictions and high computational efficiency, while remaining physically consistent. Trained on a long simulation from a state-of-the-art sea-ice--ocean system, GenSIM robustly reproduces statistics as observed in numerical models and observations, exhibiting brittle-like short-term dynamics while also depicting the long-term sea-ice decline. Driven solely by atmospheric forcings, we attribute GenSIM's emergent extrapolation capabilities to patterns that reflect the long-term impact of the ocean: it seemingly has learned an internal ocean emulator. This ability to infer slowly evolving climate-relevant dynamics from short-term predictions underlines the large potential of generative models to generalise for unseen climates and to encode hidden physics.

Related papers

• Hierarchical Testing of a Hybrid Machine Learning-Physics Global Atmosphere Model [9.985969370583426]
  Machine learning (ML)-based models have demonstrated high skill and computational efficiency, often outperforming conventional physics-based models in weather and subseasonal predictions.<n>Here, we design three sets of experiments targeting synoptic-scale phenomena, interannual variability, and out-of-distribution uniform-warming forcings.<n>We evaluate the Neural General Circulation Model (NeuralGCM), a hybrid model integrating a dynamical core with ML-based component, against observations and physics-based Earth system models (ESMs).
  arXiv  Detail & Related papers  (2026-02-11T19:34:50Z)
• Scalable Spatio-Temporal SE(3) Diffusion for Long-Horizon Protein Dynamics [51.85385061275941]
  Molecular dynamics (MD) simulations remain the gold standard for studying protein dynamics.<n>Recent generative models have shown promise in accelerating simulations, yet they struggle with long-horizon generation.<n>We present STAR-MD, a scalable diffusion model that generates physically plausible protein trajectories over micro-scale timescales.
  arXiv  Detail & Related papers  (2026-02-02T14:13:28Z)
• Data-driven global ocean model resolving ocean-atmosphere coupling dynamics [8.075184647214861]
  This study presents KIST-Ocean, a deep learning (DL)-based global three-dimensional ocean general circulation model.<n>It integrates partial convolution, adversarial training, and transfer learning to address coastal complexity and predictive distribution drift.<n>It accurately captures realistic ocean response, such as Kelvin and Rossby wave propagation in the tropical Pacific, and vertical motions induced by cyclonic and anticyclonic wind stress.
  arXiv  Detail & Related papers  (2025-07-31T01:45:15Z)
• NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulation [41.41450298461784]
  We propose NeuralOM, a general neural operator framework for simulating complex, slow-changing dynamics.<n>We validate NeuralOM on the challenging task of global Subseasonal-to-Seasonal (S2S) ocean simulation.<n>NeuralOM achieves a 13.3% lower RMSE compared to the best-performing baseline.
  arXiv  Detail & Related papers  (2025-05-27T10:54:40Z)
• Advanced long-term earth system forecasting by learning the small-scale nature [74.19833913539053]
  We present Triton, an AI framework designed to address this fundamental challenge.<n>Inspired by increasing grids to explicitly resolve small scales in numerical models, Triton employs a hierarchical architecture processing information across multiple resolutions to mitigate spectral bias.<n>We demonstrate Triton's superior performance on challenging forecast tasks, achieving stable year-long global temperature forecasts, skillful Kuroshio eddy predictions till 120 days, and high-fidelity turbulence simulations.
  arXiv  Detail & Related papers  (2025-05-26T02:49:00Z)
• Learning to generate physical ocean states: Towards hybrid climate modeling [1.5845117761091052]
  Ocean General Circulation Models require extensive computational resources to reach equilibrium states.<n>Deep learning emulators, despite offering fast predictions, lack the physical interpretability and long-term stability necessary for climate scientists.<n>We propose to take the best from both worlds by leveraging deep generative models to produce physically consistent oceanic states.
  arXiv  Detail & Related papers  (2025-02-04T17:14:41Z)
• Harnessing AI data-driven global weather models for climate attribution: An analysis of the 2017 Oroville Dam extreme atmospheric river [0.2968738145616401]
  The analysis is framed on the extreme atmospheric river episode of February 2017 that contributed to the Oroville dam spillway incident in Northern California. Past and future simulations are generated by perturbing the initial conditions with the pre-industrial and the late-21st century temperature climate change signals. Overall, the AI models show promising results, projecting a 5-6 % increase in the integrated water vapor over the Oroville dam in the present day compared to the pre-industrial.
  arXiv  Detail & Related papers  (2024-09-17T23:34:39Z)
• Advances in Land Surface Model-based Forecasting: A comparative study of LSTM, Gradient Boosting, and Feedforward Neural Network Models as prognostic state emulators [4.852378895360775]
  We evaluate the efficiency of three surrogate models in speeding up experimental research by simulating land surface processes. Our findings indicate that while all models on average demonstrate high accuracy over the forecast period, the LSTM network excels in continental long-range predictions when carefully tuned.
  arXiv  Detail & Related papers  (2024-07-23T13:26:05Z)
• Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling [55.13352174687475]
  This paper proposes a physics-AI hybrid model (i.e., WeatherGFT) which generalizes weather forecasts to finer-grained temporal scales beyond training dataset.<n>Specifically, we employ a carefully designed PDE kernel to simulate physical evolution on a small time scale.<n>We also introduce a lead time-aware training framework to promote the generalization of the model at different lead times.
  arXiv  Detail & Related papers  (2024-05-22T16:21:02Z)
• Towards an end-to-end artificial intelligence driven global weather forecasting system [57.5191940978886]
  We present an AI-based data assimilation model, i.e., Adas, for global weather variables. We demonstrate that Adas can assimilate global observations to produce high-quality analysis, enabling the system operate stably for long term. We are the first to apply the methods to real-world scenarios, which is more challenging and has considerable practical application potential.
  arXiv  Detail & Related papers  (2023-12-18T09:05:28Z)
• An evaluation of deep learning models for predicting water depth evolution in urban floods [59.31940764426359]
  We compare different deep learning models for prediction of water depth at high spatial resolution. Deep learning models are trained to reproduce the data simulated by the CADDIES cellular-automata flood model. Our results show that the deep learning models present in general lower errors compared to the other methods.
  arXiv  Detail & Related papers  (2023-02-20T16:08:54Z)
• Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator [57.57321628587564]
  We introduce Hybrid Graph Network Simulator (HGNS) for learning reservoir simulations of 3D subsurface fluid flows. HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure. Using an industry-standard subsurface flow dataset (SPE-10) with 1.1 million cells, we demonstrate that HGNS is able to reduce the inference time up to 18 times compared to standard subsurface simulators.
  arXiv  Detail & Related papers  (2022-06-15T17:29:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.