{"ID":2898934,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.03176","arxiv_id":"2507.03176","title":"Deep Learning Atmospheric Models Reliably Simulate Out-of-Sample Land Heat and Cold Wave Frequencies","abstract":"Deep learning (DL)-based general circulation models (GCMs) are emerging as fast simulators, yet their ability to replicate extreme events outside their training range remains unknown. Here, we evaluate two such models -- the hybrid Neural General Circulation Model (NGCM) and purely data-driven Deep Learning Earth System Model (DL\\textit{ESy}M) -- against a conventional high-resolution land-atmosphere model (HiRAM) in simulating land heatwaves and coldwaves. All models are forced with observed sea surface temperatures and sea ice over 1900-2020, focusing on the out-of-sample early-20th-century period (1900-1960). Both DL models generalize successfully to unseen climate conditions, broadly reproducing the frequency and spatial patterns of heatwave and cold wave events during 1900-1960 with skill comparable to HiRAM. An exception is over portions of North Asia and North America, where all models perform poorly during 1940-1960. Due to excessive temperature autocorrelation, DL\\textit{ESy}M tends to overestimate heatwave and cold wave frequencies, whereas the physics-DL hybrid NGCM exhibits persistence more similar to HiRAM.","short_abstract":"Deep learning (DL)-based general circulation models (GCMs) are emerging as fast simulators, yet their ability to replicate extreme events outside their training range remains unknown. Here, we evaluate two such models -- the hybrid Neural General Circulation Model (NGCM) and purely data-driven Deep Learning Earth Syste...","url_abs":"https://arxiv.org/abs/2507.03176","url_pdf":"https://arxiv.org/pdf/2507.03176v2","authors":"[\"Zilu Meng\",\"Gregory J. Hakim\",\"Wenchang Yang\",\"Gabriel A. Vecchi\"]","published":"2025-07-03T21:09:27Z","proceeding":"physics.ao-ph","tasks":"[\"physics.ao-ph\",\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false}