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.
arXiv:2607. 19522v1 Announce Type: new Abstract: While machine learning-based weather models hold significant promise, they struggle to predict the detailed structure of large-scale weather systems such as cyclonic storms.
arXiv:2609.38632v1 Announce Type: new Abstract: Recent probabilistic weather forecasters train stochastic predictors with the continuous ranked probability score (CRPS) to generate each ensemble memb...
arXiv:2606. 14570v1 Announce Type: cross Abstract: Emulators provide a cost-effective alternative to regional climate models (RCMs) by capturing their dynamical downscaling function.
arXiv:2608. 04327v1 Announce Type: new Abstract: Explicit onshore tsunami inundation forecasting can improve public risk awareness, but deterministically predicted inundation boundaries under highly uncertain conditions, such as near-field tsunamis generated by megathrust earthquakes, may falsely imply safety outside the boundaries.
arXiv:2605. 20494v2 Announce Type: replace Abstract: Reliable assessment of tropical cyclone risk is limited by the short and spatially uneven historical record, especially for rare, high-intensity landfalls that dominate insured loss.
The paper introduces Influpaint, a denoising diffusion probabilistic model adapted for forecasting influenza incidence. By representing influenza seasons as spatiotemporal images and training on a hybrid dataset of surveillance and simulated trajectories, the model learns a rich distribution of disease dynamics and performs forecasting as a conditional generation task. In retrospective and real‑time evaluations, Influpaint produces realistic, diverse epidemic trajectories and achieves forecast accuracy competitive with leading ensemble methods, especially when trained with 30% surveillance and 70% simulated data.
The study compares the Weather Research and Forecasting (WRF) dynamical model with an unpaired diffusion-based generative model for downscaling extreme precipitation events up to three weeks ahead. Both models outperform raw European Centre for Medium-Range Weather Forecasts forecasts when evaluated against Swiss rain gauge-radar observations, but their strengths differ by atmospheric regime: WRF excels in a multicell, non‑stationary event, while the diffusion model performs more consistently and better in a stationary supercell event.
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.
arXiv:2606. 04143v1 Announce Type: cross Abstract: Accurate flood forecasting is essential for mitigating disaster risks and protecting communities.
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.
arXiv:2507. 00719v3 Announce Type: replace-cross Abstract: Typically, numerical simulations of Earth systems are coarse, and Earth observations are sparse and gappy.
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.