The paper introduces Pangu‑Bayes, a probabilistic forecasting hierarchy that separates atmospheric‑state uncertainty from learned‑model uncertainty as distinct stochastic variables, allowing cross‑flow perturbations of the evolving state with Bayesian parameter samples. In tests on 90 held‑out 2023 tropical cyclones, Pangu‑Bayes reduces track, pressure, and wind errors by 54.2%, 17.2%, and 24.9% respectively, and improves rapid‑intensification detection. The study finds that atmospheric‑state variability more consistently improves track prediction, while learned‑model variability more often enhances intensity prediction, demonstrating how model‑defined uncertainty resolution can be linked to target‑dependent value and dynamical interpretation.
By Wenbo Hu, Xinlei Xiong, Shuxun Zhou, Kaifeng Bi, Lingxi Xie, Jun Zhu, Richang Hong, Qi Tian
arXiv:2608. 09683v1 Announce Type: new Abstract: Probabilistic coastal hazard assessments require accurate characterization of tropical cyclone (TC) parameters, yet datasets often contain missing records for the radius of maximum winds (Rmax), a key variable in Joint Probability Method analyses.
By Swastik Agrawal, Nishkal Hundia, Ziyue Liu, Michelle Bensi
arXiv:2603. 11229v2 Announce Type: replace-cross Abstract: Machine learning forecast systems are moving beyond point predictions to full predictive distributions for future outcomes y conditional on complex inputs x.
By Elizabeth Cucuzzella, Rafael Izbicki, Ann B. Lee
arXiv:2608. 09959v1 Announce Type: cross Abstract: AI weather models are in the process of revolutionising weather forecasting.
By Anna Allen, Wessel P. Bruinsma, Michael Maier-Gerber, Harrison Cook, Matthew Chantry, Richard E. Turner
arXiv:2609.25505v1 Announce Type: cross
Abstract: Rapid intensification (RI) remains one of the most consequential and difficult aspects of tropical cyclone (TC) forecasting. Although full-physics nu...
By Shijie Xiao, Jonathan Lin, Thomas Ehrmann, Ali Sarhadi
SurgeGen is a two‑stage generative diffusion framework that synthesizes storm surge scenarios conditioned on continuous storm parameters. The first stage produces a coarse baseline surge estimate, which then conditions a diffusion model that refines the output to capture realistic spatial patterns and variability. The method can generate diverse, realistic surge scenarios both within and beyond the training distribution.
By Shunan Zheng, John J. Hasenbein
Neural ocean emulators that use prescribed cyclone tracks as input were tested in the Bay of Bengal. Two identical U‑Net models were compared: one with four cyclone‑track channels and one without. The storm‑conditioned model performed worse than persistence on every run, while the ocean‑only model outperformed persistence, indicating that the rare cyclone input caused the model to learn a misleading response.
By Sumaiya Islam
arXiv:2606. 30920v1 Announce Type: cross Abstract: We couple Forward Flux Sampling (FFS), a non-equilibrium rare-event technique from statistical mechanics, to a neural weather emulator (SDL-WXFormer, 1{\deg} grid spacing) to estimate conditional tropical cyclogenesis rates, or how often a tropical cyclone achieves a hurricane-level central pressure, without modifying model dynamics.
By John S. Schreck, William Chapman, Charlie Becker, David John Gagne II
arXiv:2606. 04143v1 Announce Type: cross Abstract: Accurate flood forecasting is essential for mitigating disaster risks and protecting communities.
By Tewodros Syum Gebre, Jagrati Talreja, Leila Hashemi-Beni
arXiv:2603. 12828v2 Announce Type: replace-cross Abstract: This paper addresses a missing capability in infrastructure resilience: turning fast, global AI weather forecasts into asset-scale, actionable risk intelligence.
By You Wu, Zhenguo Wang, Naiyu Wang
arXiv:2607. 13101v1 Announce Type: cross Abstract: Global Station Weather Forecasting (GSWF) is pivotal for localized and extreme weather prediction over key regions.
By Songru Yang, Zili Liu, Tao Han, Ben Fei, Fenghua Ling, Lei Bai, Chang Liu, Xiangyang Ji, Zhenwei Shi, Zhengxia Zou
TC-Next is a multimodal deep learning model that forecasts tropical cyclone track and intensity for 6‑24 hour lead times by combining atmospheric forecast fields from a foundation model with GridSat infrared satellite imagery. Trained solely on GraphCast forecasts for the Western Pacific, it reduces track error by 15‑44% and intensity error by a factor of 3‑6 compared to the rule‑based tracker TempestExtremes, and maintains superior performance when applied zero‑shot to other forecast systems such as Pangu‑Weather, IFS HRES, and WeatherNext Cyclones. Ablation studies confirm that incorporating the additional satellite modality consistently improves tracking accuracy at all lead times and enhances intensity predictions, especially at longer horizons.
By Zhe Wang, Sijie Chen, Yiming Luo, Daehyun Kim, Chien-Yi Chang