发表机构
Fujitsu Research, Fujitsu Limited; Earthquake Research Institute, The University of Tokyo; International Research Institute of Disaster Science, Tohoku University（富士通研究所，富士通株式会社; 东京大学地震研究所; 东北大学国际灾害科学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究开发基于条件扩散模型的概率集成模型，利用2011年东北地方太平洋近海地震数据验证，实现实时概率海啸预报，将海啸预报从确定性转向概率性，为下一代预警奠定基础。
AI 中文摘要
明确的陆上海啸淹没预报可提升公众风险意识，但在近场巨震海啸等高度不确定条件下，确定性预测的淹没边界可能错误暗示边界外安全。因此当前预警主要针对沿海海啸高度而非陆上淹没。尽管机器学习可实现即时淹没预测，但仍为确定性的，缺乏不确定性量化。本文开发了基于条件扩散模型（一种生成式AI）的概率集成模型，兼顾准确性与校准度。通过2011年东北地方太平洋近海地震数据验证，该模型能准确追踪震后随时间降低的不确定性，同时精准预测淹没深度与范围。本框架表明生成式AI可将海啸预报从确定性转向概率性，为下一代预警奠定基础。
英文摘要
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.
Comments24 pages, 14 figures, 1 table
