Scaling Storm-Resolving Atmospheric AI Simulation to the Entire Planet

• URL: http://arxiv.org/abs/2606.31248v1
• Date: Tue, 30 Jun 2026 07:24:33 GMT
• Title: Scaling Storm-Resolving Atmospheric AI Simulation to the Entire Planet
• Abstract summary: STRATA (Storm-resolving Tile-based autoRegressive Atmosphere Transformer Architecture) is the first autoregressive AI emulator for global storm-resolving atmospheric dynamics.<n> STRATA produces stable 24-hour global rollouts with realistic km-scale dynamics across diverse regimes.<n>It achieves 48 simulation days per megawatt-hour -- about 50 times better energy efficiency than the SCREAM physics model.
• Score: 4.77834801104581
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Kilometer-scale convection shapes precipitation extremes, tropical organization, and cloud feedbacks, but most global atmospheric models approximate these processes at 25-100 km resolution. Global storm-resolving physics models resolve convective systems explicitly, but at a cost -- roughly one MWh per simulated day on exascale supercomputers -- that limits long-duration simulation. We introduce STRATA (Storm-resolving Tile-based autoRegressive Atmosphere Transformer Architecture), the first autoregressive AI emulator for global storm-resolving atmospheric dynamics. STRATA is trained on the highest-resolution atmospheric dataset yet used for global AI emulation: 17 days of SCREAM physics-model output at 4.9-km resolution (~25 million grid cells) sampled every 10 minutes. Our central premise is that on 10-minute timescales atmospheric dynamics are predominantly local, so training on small spatial tiles trades scarce global temporal samples for abundant local spatial samples and enables global rollout via overlapping-tile blending. STRATA combines 3D patch embedding and local 3D neighborhood attention, a novel Stereographic Rotary Position Embedding (StereoRoPE) for grid-invariant encoding, and a pixel-space de-aliasing decoder that suppresses patch-scale rollout artifacts. An iso-FLOP scaling study reveals that km-scale emulation requires ~10x more FLOPs per grid point than coarse-resolution AI weather models, consistent with the higher information density of convective-scale dynamics. Trained on only 17 days of data, STRATA produces stable 24-hour global rollouts with realistic km-scale dynamics across diverse regimes, though large-scale biases develop with lead time. It achieves 48 simulation days per megawatt-hour -- about 50 times better energy efficiency than the SCREAM physics model -- and 741 simulated days per wall-clock day at 512 H100 GPUs. Code and dataset are publicly available.

Related papers

• NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation [84.88799392695893]
  We introduce OmniDreams, a foundation generative world model mid- and post-trained from the Cosmos diffusion model to autoregressively generate action-conditioned videos in real time.<n>By leveraging the rich visual priors of Cosmos and mid- and post-training on 21k hours of driving scenarios, OmniDreams synthesizes complex, unobserved phenomena.<n>Preliminary results indicate that a world-action model post-trained from OmniDreams achieves strong performance on the Physical AI Autonomous Vehicles NuRec dataset.
  arXiv  Detail & Related papers  (2026-06-02T05:11:05Z)
• DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancer [62.18680935878919]
  We introduce DiffusionHarmonizer, an online generative enhancement framework that transforms renderings into temporally consistent outputs.<n>At its core is a single-step temporally-conditioned enhancer capable of running in online simulators on a single GPU.
  arXiv  Detail & Related papers  (2026-02-27T15:35:30Z)
• Resolution Revolution: A Physics-Guided Deep Learning Framework for Spatiotemporal Temperature Reconstruction [5.6087513714958686]
  Current technology allows for hourly temperature observations at 2 km, but only every 16 days at 100 m, a gap further exacerbated by cloud cover.<n>Here, we present a physics-guided deep learning framework for temperature data reconstruction that integrates two data sources.<n>The proposed framework uses a convolutional neural network that incorporates the annual temperature cycle and includes a linear term to amplify the coarse Earth system model output into fine-scale temperature values observed from satellites.
  arXiv  Detail & Related papers  (2025-07-14T03:03:25Z)
• CAM-NET: An AI Model for Whole Atmosphere with Thermosphere and Ionosphere Extension [0.5256237513030104]
  We present CAM-NET, an AI model designed to predict neutral atmospheric variables from the Earth's surface to the ionosphere.<n>The model effectively predicts key atmospheric parameters, including zonal and meridional winds, temperature, and time rate of pressure.
  arXiv  Detail & Related papers  (2025-06-24T06:07:28Z)
• Data-efficient rapid prediction of urban airflow and temperature fields for complex building geometries [0.0]
  We propose a novel framework that leverages a multi-directional distance feature (MDDF) combined with localized training to achieve effective wind field predictions.<n>We trained on only 24 CFD simulations, our localized Fourier neural operator (Local-FNO) model generates full 3D wind velocity and temperature predictions in under one minute.<n>With mean absolute errors of 0.3 m/s for wind speed and 0.3 $circ$C for temperature on unseen urban configurations, our method demonstrates strong generalization capabilities and significant potential for practical urban applications.
  arXiv  Detail & Related papers  (2025-03-25T14:36:01Z)
• DrivingSphere: Building a High-fidelity 4D World for Closed-loop Simulation [54.02069690134526]
  We propose DrivingSphere, a realistic and closed-loop simulation framework. Its core idea is to build 4D world representation and generate real-life and controllable driving scenarios. By providing a dynamic and realistic simulation environment, DrivingSphere enables comprehensive testing and validation of autonomous driving algorithms.
  arXiv  Detail & Related papers  (2024-11-18T03:00:33Z)
• Accelerate Coastal Ocean Circulation Model with AI Surrogate [10.800252698519634]
  Oceanographers simulate ocean current circulation along the coasts to develop early warning systems that save lives and prevent loss and damage to property from coastal hazards.<n>Traditionally, such simulations are conducted using coastal ocean circulation models such as the Regional Ocean Modeling System (ROMS)<n>Recent advances in deep learning and GPU architecture have enabled the development of faster AI (neural network) surrogates.<n>This paper introduces an AI surrogate based on a 4D Swin Transformer to simulate coastal tidal wave propagation in an estuary for both hindcast and forecast (up to 12 days)
  arXiv  Detail & Related papers  (2024-10-19T02:49:30Z)
• Kilometer-Scale Convection Allowing Model Emulation using Generative Diffusion Modeling [19.340636269420692]
  Storm-scale convection-allowing models (CAMs) are an important tool for predicting the evolution of thunderstorms and mesoscale convective systems. Deep learning models have thus far not proven skilful at km-scale atmospheric simulation. We present a generative diffusion model called StormCast, which emulates the high-resolution rapid refresh (HRRR) model-NOAA's state-of-the-art 3km operational CAM.
  arXiv  Detail & Related papers  (2024-08-20T15:56:01Z)
• Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling [58.456404022536425]
  State of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis.
  arXiv  Detail & Related papers  (2023-09-24T19:57:22Z)
• ClimSim-Online: A Large Multi-scale Dataset and Framework for Hybrid ML-physics Climate Emulation [45.201929285600606]
  We present ClimSim-Online, which includes an end-to-end workflow for developing hybrid ML-physics simulators. The dataset is global and spans ten years at a high sampling frequency. We provide a cross-platform, containerized pipeline to integrate ML models into operational climate simulators.
  arXiv  Detail & Related papers  (2023-06-14T21:26:31Z)
• ClimaX: A foundation model for weather and climate [51.208269971019504]
  ClimaX is a deep learning model for weather and climate science. It can be pre-trained with a self-supervised learning objective on climate datasets. It can be fine-tuned to address a breadth of climate and weather tasks.
  arXiv  Detail & Related papers  (2023-01-24T23:19:01Z)
• 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.