This study introduces the first controlled benchmark of generative models for weather data assimilation using real station observations from 11,849 NOAA MADIS stations across the U.S. It evaluates key design choices—diffusion vs. flow matching, pixel vs. latent-space formulations, and inference-time conditioning strategies—against a classical 3D-Var baseline. The benchmark finds that learned generative priors and full-gradient guidance improve RMSE over ERA5, while other design variations offer minimal benefit, especially under sparse observation conditions.
By Ruizhe Huang, Qidong Yang, Jonathan Giezendanner, Sherrie Wang
SimCast‑S2S is a generative latent‑diffusion model designed for probabilistic subseasonal‑to‑seasonal precipitation forecasting. It tackles three key challenges: it uses a diffusion pipeline to capture uncertainty, operates in a compact latent space to enable efficient large‑ensemble generation, and leverages transfer learning with low‑rank adaptation to train on limited reanalysis data after pretraining on climate simulations. The model outperforms deep‑learning baselines and competes with, or surpasses, operational systems such as the ECMWF‑S2S baseline without requiring extensive post‑processing.
By Hiep V. Dang, Antonios Mamalakis
SimCast‑S2S is a generative latent‑diffusion framework designed for probabilistic subseasonal‑to‑seasonal precipitation forecasting. It tackles three key challenges: it uses a diffusion‑based generative pipeline for uncertainty quantification, operates in a compact latent space learned by VAEs for efficient large‑ensemble generation, and employs transfer learning with LoRA to overcome limited training data. On reanalysis data, it outperforms deep‑learning baselines and competes with or surpasses state‑of‑the‑art operational systems such as ECMWF‑S2S.
By Hiep V. Dang, Antonios Mamalakis
The paper introduces STORM, a one‑stage generative AI framework that reformulates Earth system data assimilation as diffusion‑based Bayesian posterior sampling, replacing costly PDE ensemble forecasts with scalable AI inference. STORM employs a spatiotemporal transformer with a global‑attention algorithm that reduces computational complexity from quadratic to linear, enabling high‑resolution, long‑context modeling. The system scales to 74,400 GPUs on Frontier, achieving 96–99 % strong‑scaling efficiency and up to 6 ExaFLOPs sustained BF16 throughput, while supporting 32,768‑member ensembles for uncertainty quantification in just 34 seconds on 4,096 GPUs, and demonstrates improved hurricane tracking and climate reanalysis accuracy.
By Xiao Wang, Zezhong Zhang, Isaac Lyngaas, Hong-Jun Yoon, Jong-Youl Choi, Siming Liang, Janet Wang, Hristo G. Chipilski, Ashwin M. Aji, Feng Bao, Peter Jan van Leeuwen, Dan Lu, Guannan Zhang
The paper introduces prequential posteriors, a Bayesian approach that uses a predictive‑sequential loss function to update deep generative forecasting models (DGFMs) when new data arrive. By adopting a consistency notion suitable for model misspecification, the authors prove that both the loss minimizer and the posterior concentrate on parameters with optimal predictive performance. Scalable inference is achieved with parallelisable waste‑free sequential Monte Carlo samplers that employ preconditioned gradient kernels, and the method is validated on synthetic and real meteorological time‑series data.
By Shreya Sinha-Roy, Richard G. Everitt, Christian P. Robert, Ritabrata Dutta
arXiv:2610.28327v1 Announce Type: new
Abstract: We present the Observation Assimilation Transformer (OAT), a geometry-aware neural process that corrects and refines a prior numerical weather predicti...
By Christian Donner, Michele Cattaneo, Maxim Samarin, Francesco Zanetta, Ic\'iar Llor\'ens Jover, Garbiela Aznar Siguan, Michele Volpi
arXiv:2609.39626v1 Announce Type: cross
Abstract: Ensemble smoothers are the most successful and efficient techniques currently available for history matching. However, because these methods rely on...
By Marcio A. Sampaio, Paulo H. Ranazzi, Martin J. Blunt
arXiv:2610.14863v1 Announce Type: new
Abstract: Data-driven weather forecasting models are commonly trained on ERA5, yet operational deployment must use timely initial states from physics-based numer...
By Mutian Xi, Xinyu Su, Xiaohui Zhong, Hao Li
arXiv:2608. 05103v1 Announce Type: new Abstract: Data assimilation (DA) uses Bayesian inference to update the state of a numerical forecast model with observed data.
By Dibyajyoti Chakraborty, Romit Maulik
arXiv:2608. 05103v2 Announce Type: replace Abstract: Data assimilation (DA) uses Bayesian inference to update the state of a numerical forecast model with observed data.
By Dibyajyoti Chakraborty, Romit Maulik
The paper presents a method for improving atmospheric state reconstructions by conditioning a pretrained diffusion model on heterogeneous in‑situ observations. It introduces composable interfaces that transform sparse radiosonde, clustered aircraft, and dense surface‑station data into likelihood factors, allowing these diverse sources to guide posterior sampling consistently. Using 2019 data to build the interfaces and evaluating them in 2020, the combined R+A+S approach reduces RMSE by 9.24% and improves CRPS compared to using radiosondes alone, demonstrating a modular way to incorporate varied observations without retraining the model.
By Yang Xu, Dibyajyoti Chakraborty, Haiwen Guan, Sen Wang, Romit Maulik
arXiv:2605. 14285v2 Announce Type: replace-cross Abstract: Data assimilation (DA) estimates the state of an evolving dynamical system from noisy, partial observations, and is widely used in scientific simulation as well as weather and climate science.
By Yixuan Jia, Siyi Chen, Yida Pan, Xiao Li, Lianghe Shi, Chanyong Jung, Haijie Yuan, Ismail Alkhouri, Yue Cynthia Wu, Saiprasad Ravishankar, Jeffrey A Fessler, Qing Qu