Metraipolis › archive › dc_8d418357bc07

Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting — arXiv:2608.18500

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18500
License (as archived)
CC0-1.0
Archived
2026-10-18T13:53:15.585Z
SHA-256 of the archived text
0dc67ab6f85b5277d92c2497ae604255ea3a7adaf0b85388870ea1b5af9f105e
Stable URL of this page
https://metraipolis.com/documento/dc_8d418357bc07

How to cite

Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting — arXiv:2608.18500 — arXiv (en), https://arxiv.org/abs/2608.18500 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8d418357bc07 (Metraipolis archive dc_8d418357bc07, sha256 0dc67ab6f85b5277d92c2497ae604255ea3a7adaf0b85388870ea1b5af9f105e)
BibTeX
@misc{dc8d418357bc07,
  title = {Tianmu-TC: Physics-constraints Generative Artificial Intelligence for Global Tropical Cyclone Forecasting — arXiv:2608.18500},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18500},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8d418357bc07; sha256 0dc67ab6f85b5277d92c2497ae604255ea3a7adaf0b85388870ea1b5af9f105e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18500. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tropical cyclones (TCs) pose severe risks from strong winds and heavy rainfall. However, forecasting their track and intensity remains challenging due to chaotic atmosphere and the rapid amplification of initial condition errors, leading to growing forecast uncertainty. While numerical weather prediction (NWP) and deep learning models have made progress, they remain computationally demanding and often fail under complex meteorological scenarios. Here, we present Tianmu-TC, a physics-constraints generative framework for global TC forecasting. Trained on Western North Pacific data, Tianmu-TC leverages physics-constraints to generate controllable outputs with reduced uncertainty thus improving forecast reliability. Experiments show Tianmu-TC outperforms deterministic and ensemble meteorological artificial intelligence models and authoritative NWP systems such as ECMWF in global ocean basins, with significantly lower computational cost. We further show Tianmu-TC performs well in challenging scenarios such as data sparsity, anomaly tracks, rapid intensification and weakening. These findings suggest physics-constraints generative AI offers a promising approach for reliable, efficient global TC forecasting.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.18500 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T13:50:58.909Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).