{"ID":5438687,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T07:17:43.555462792Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31248","arxiv_id":"2606.31248","title":"Scaling Storm-Resolving Atmospheric AI Simulation to the Entire Planet","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.","short_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...","url_abs":"https://arxiv.org/abs/2606.31248","url_pdf":"https://arxiv.org/pdf/2606.31248v1","authors":"[\"Zeyuan Hu\",\"Akshay Subramaniam\",\"Noel Keen\",\"Tao Ge\",\"Jaideep Pathak\",\"Mohammad Shoaib Abbas\",\"Suman Ravuri\",\"Karthik Kashinath\",\"Naser Mahfouz\",\"Peter Caldwell\",\"Mike Pritchard\",\"Noah Brenowitz\"]","published":"2026-06-30T07:24:33Z","proceeding":"physics.ao-ph","tasks":"[\"physics.ao-ph\",\"cs.CE\",\"cs.LG\"]","methods":"[\"Transformer\",\"Generative Adversarial Network\"]","has_code":false}