发表机构
Swiss Seismological Service (SED), ETH Zürich, Switzerland; Univ. Grenoble Alpes, Univ. Savoie Mont Blanc, CNRS, IRD, Univ. Gustave Eiffel, ISTerre, Grenoble, France; Swiss Data Science Center (SDSC), ETH Zürich, Switzerland; Earth and Planetary Science Department, ETH Zürich, Switzerland（瑞士地震服务处（SED），苏黎世联邦理工学院; 格勒诺布尔阿尔卑斯大学，萨瓦-蒙布朗大学，法国国家科学研究中心，法国研究与可持续发展研究所，巴黎土木工程师大学，ISTerre，格勒诺布尔，法国; 瑞士数据中心（SDSC），苏黎世联邦理工学院; 地球与行星科学系，苏黎世联邦理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
HighFEM-2利用条件去噪扩散模型，基于低频波形合成高达50赫兹的宽带地面运动，实现快速、区域校准的时程生成，用于地震灾害评估。
AI 中文摘要
地震灾害和结构分析需要宽带地面运动时程，然而高频频段（高于1赫兹）是最难获得的：基于物理的模拟在这些频率下成本过高，而随机方法则失去了控制结构需求的确定性相位、方向性和长周期相干性。我们提出了HighFEM-2，一种潜在去噪扩散波形模型，通过整流流匹配在多模态扩散变换器上进行训练。它能够合成高达50赫兹的三分量加速度，以低于震源拐角频率的低频波形以及震级、震源和台站位置、V_S30为条件。低频波形提供了确定性的震源、路径和方向性，因此网络仅学习区域性的高频散射。通过对每个台站以其自身波形为条件，HighFEM-2能够为一次地震的所有台站生成共享其震源和低频路径项的记录。在195,138条意大利INSTANCE记录（矩震级1.4--6.5，距离200公里以内）上训练后，HighFEM-2生成逼真的波形：它以较小的偏差再现了观测到的峰值振幅（PGA为0.042 ± 0.088对数单位，PGV为0.057 ± 0.090），并匹配了观测到的包络、傅里叶谱以及积分速度和位移。条件波形可以来自模拟或滤波记录，并且集合的实现样本在给定输入下对高频变异性进行采样。因此，HighFEM-2为灾害和风险评估提供了快速、区域校准的宽带时程，包括记录稀缺的近断层场景。
英文摘要
Seismic hazard and structural analyses require broadband ground-motion time histories, yet the high-frequency band (above 1~Hz) is the hardest to obtain: physics-based simulations are too costly at these frequencies, and stochastic methods lose the deterministic phase, directivity, and long-period coherence that control structural demand. We present HighFEM-2, a latent denoising-diffusion waveform model trained with rectified flow matching on a multi-modal diffusion transformer. It synthesizes three-component acceleration up to 50~Hz, conditioned on a low-frequency waveform below the source corner frequency and on magnitude, hypocenter and station location, and $V_{S30}$. The low-frequency waveform supplies the deterministic source, path, and directivity, so the network learns only the regional high-frequency scattering. Conditioning each station on its own waveform lets HighFEM-2 generate records for all stations of an earthquake that share its source and low-frequency path terms. Trained on 195{,}138 Italian INSTANCE records ($M_w$ 1.4--6.5, within 200~km), HighFEM-2 produces realistic waveforms: it reproduces observed peak amplitudes with small bias ($0.042 \pm 0.088$ log units for PGA, $0.057 \pm 0.090$ for PGV) and matches observed envelopes, Fourier spectra, and integrated velocity and displacement. The conditioning waveform can come from a simulation or a filtered record, and ensembles of realizations sample the high-frequency variability given that input. HighFEM-2 thus provides fast, regionally calibrated broadband time histories for hazard and risk assessment, including near-fault scenarios where recordings are scarce.
