A probabilistic ensemble model based on a conditional diffusion model (a type of generative AI) that reconciles accuracy with calibration that shows that generative AI can shift tsunami forecasting from determinism to probabilism, providing a foundation for next-generation early warning.
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. Consequently, current warnings primarily target coastal tsunami height, not onshore inundation. Although machine learning enables instant inundation predictions, they remain deterministic, lacking uncertainty quantification. Here, we develop a probabilistic ensemble model based on a conditional diffusion model (a type of generative AI) that reconciles accuracy with calibration. Validated with the 2011 Tohoku-oki earthquake data, our model faithfully tracks the postearthquake uncertainty decreasing over time while accurately predicting inundation depth and extent. Our framework shows that generative AI can shift tsunami forecasting from determinism to probabilism, providing a foundation for next-generation early warning.
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 no...
Dohyun Park, Changhoon Song, Teng-Yuan Chang et al.· 1 citation
This framework combines risk prediction, GIS risk mapping, and early warning layers by using Transformer/LSTM deep learning models to integrate six distinct data sources to address rising Glacial Lake Outburst Floods and avalanche-induced flash floods in the climate-sensitive Himalayas.
C.Sakthimurugan, D. Mahalingam, K. Santhanam et al.· Tamilmanam International Res...· 0 citations
Tropical cyclones (TCs) cause substantial disaster losses worldwide. Forecast skill for TC track and intensity has been improved by enhanced observations, high-resolution numerical models, advanced data assimilation methods, and applications of machine-learning methods. Yet these improvements have not consistently tran...
Hikari V. Yamamoto-Fukuda, Md. Rezuanul Islam, Yohei Sawada· Environmental Research Lette...· 0 citations
Accurate nowcasting of localized extreme rainfall remains particularly challenging when observations are based on sparse and irregular rain-gauge networks. This article presents a framework for 1-h-ahead severe rainfall nowcasting that integrates spatial reconstruction, spatiotemporal deep learning, and extremes-orient...
Débora S. Rodrigues, A. Caseri, S. Pesco· IEEE Geoscience and Remote S...· 0 citations
A novel application of using the integrative ERF‐tsunami approach is that features extracted in the reduced domain, particularly from manifold learning, can be mapped back to rupture zones along the fault.
E. Geist, Tom Parsons· Journal of Geophysical Resea...· 0 citations
Earthquakes represent one of the most destructive natural hazards, causing severe social and economic losses, particularly in tectonically active regions. In this context, estimating the short-term probability of earthquake occurrence is of critical importance for disaster preparedness and risk mitigation. This study f...
Melih Karagöz, Gizem Korkmaz, Ceren Özmen et al.· International Journal of New...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
