Localized extreme precipitation is a major trigger of urban flash floods and landslides, yet producing nowcasts that combine fine spatial detail with probabilistic uncertainty remains challenging. Here we introduce exPreCast-ENS, a conditional residual diffusion framework that transforms the deterministic 4 km radar nowcaster exPreCast into a 1 km probabilistic ensemble while correcting systematic forecast errors. Conditioning on both the forecast and preceding radar observations lets the ensemble-mean correct the baseline rather than perturb it, while members represent unresolved fine-scale variability. Over the Korean Peninsula, skill improves with ensemble size. In two high-impact events in 2023, a 30-member ensemble recovers 38-47% of heavy-rain pixels missed by exPreCast while retaining approximately 95% of its correct detections and alarming on under 1% of the pixels it correctly left clear. The method generates a 1-h forecast in 3.4 s on a single GPU and yields consistent improvements on the French regional MeteoNet radar dataset.
Precipitation nowcasting, generating future radar fields from past observations, is critical for flood warning and disaster response. It is also a demanding benchmark for spatiotemporal generative modeling, with chaotic dynamics, heavy-tailed intensities, and rare high-intensity structures that matter most. Determinist...
Shunya Nagashima, Takumi Bannai, Makoto Misaizu et al.· 0 citations
RainCast is proposed, a high-resolution framework for hourly precipitation forecasting over China up to 72 hours ahead at 0.05° resolution that incorporates a physics-guided feature extractor and a multi-head output design that supports both deterministic forecasts with a regression head and probabilistic multi-member...
Guanlong Ma, Weiqiu Chen, Yang Zhao et al.· Proceedings of the 32nd ACM...· 0 citations
Extreme precipitation events in the Tropics are often linked to convective storms. Storm nowcasting systems for early warning have been recognized as a necessary adaptation strategy to increase public resilience in a rapidly evolving climate. Ongoing advances in deep‐learning techniques now allow better exploitation...
J. Ahmad, C. Klein, C. Taylor et al.· Quarterly Journal of the Roy...· 0 citations
Diffusion models have shown strong potential for kilometer-scale precipitation downscaling, but their performance in geographically unseen regions and event regimes remains insufficiently understood. Building on the wavelet diffusion model (WDM) framework, this study evaluates cross-region and cross-event generalizatio...
Wei-Kang Qian, Yi-Xin Wen, Chu-Gang Yi et al.· 0 citations
Results indicate that cross-attention conditioning offers advantages over simple concatenation for probabilistic precipitation downscaling, and that pre-trained foundation model representations may offer benefits in data-limited settings.
Victor Nascimento Ribeiro, Jorge Guevara, J. Moraga et al.· 0 citations
