Simulation of broad-band ground motions with consistent long-period and short-period components using the Wasserstein interpolation of acceleration envelopes
Simulation of broad-band ground motions with consistent long-period and short-period components using the Wasserstein interpolation of acceleration envelopes
复制标题
DOI：
10.1093/gji/ggab225
复制
发表时间：
2021-06
影响因子：
2.8
通讯作者：
Tomohisa Okazaki;Hirotaka Hachiya;A. Iwaki;T. Maeda;H. Fujiwara;N. Ueda
中科院分区：
文献类型：
--
作者：
Tomohisa Okazaki;Hirotaka Hachiya;A. Iwaki;T. Maeda;H. Fujiwara;N. Ueda
实际用于模拟宽带地面运动的混合方法通常是将不同方法在不同周期范围内的不同假设下合成的长周期和短周期波形组合在一起，这有时会导致时程和频率特性不相容。本研究探索了一种利用过去的观测记录产生一致的宽带波形的方法，假设可以从基于物理的模拟中获得长周期波形。具体来说，使用机器学习方法将加速度包络和傅立叶振幅谱从长周期转换为短周期，并将它们组合起来产生宽带波形。为了从有限的数据中有效地获得高维包络的关系，我们(1)将问题表述为概率分布的转换，从而可以引入一个称为Wasserstein距离的度量；(2)将长周期和短周期包络对嵌入到一个共同的潜在空间中，以提高整个波形的一致性。对过去地震的实验应用表明，与现有方法和神经网络方法相比，该方法具有更好的性能。特别是，该方法在时域内再现了全局属性，这证实了嵌入方法的有效性以及Wasserstein距离作为包络不同度度量的优势。该方法是一种新颖的机器学习方法，可以在波形的时域和频域特性中保持一致性。
Practical hybrid approaches for the simulation of broad-band ground motions often combine long-period and short-period waveforms synthesized by independent methods under different assumptions for different period ranges, which at times can lead to incompatible time histories and frequency properties. This study explores an approach that generates consistent broad-band waveforms using past observation records, under the assumption that long-period waveforms can be obtained from physics-based simulations. Specifically, acceleration envelopes and Fourier amplitude spectra are transformed from long-period to short-period using machine learning methods, and they are combined to produce a broad-band waveform. To effectively obtain the relationship of high-dimensional envelopes from limited amount of data, we (1) formulate the problem as the conversion of probability distributions, which enables the introduction of a metric known as the Wasserstein distance, and (2) embed pairs of long-period and short-period envelopes into a common latent space to improve the consistency of the entire waveform. An experimental application to a past earthquake demonstrates that the proposed method exhibits superior performance compared to existing methods as well as neural network approaches. In particular, the proposed method reproduces global properties in the time domain, which confirms the effectiveness of the embedding approach as well as the advantage of the Wasserstein distance as a measure of dissimilarity of the envelopes. This method serves as a novel machine learning approach that maintains consistency both in the time-domain and frequency-domain properties of waveforms.