Data space reduction, quality assessment and searching of seismograms: autoencoder networks for waveform data
Data space reduction, quality assessment and searching of seismograms: autoencoder networks for waveform data
复制标题
DOI：
10.1111/j.1365-246x.2012.05429.x
复制
发表时间：
2012-05-01
影响因子：
2.8
通讯作者：
Trampert, Jeannot
中科院分区：
文献类型：
--
作者：
Valentine, Andrew P.;Trampert, Jeannot
是什么让地震图看起来像地震图？地震数据集通常包含共享某些视觉特征和特征的波形，事实上，地震学家在手动执行质量控制时通常会利用这一点。了解和利用这些特征为更深入地了解地震波形提供了前景，并开辟了许多潜在的数据处理和处理新技术。此外，波形之间共享某些特征的事实表明，可以将数据从时域转换出来，并使用更少的参数来表示相同的信息。如果是这样，这将是朝着使完全非线性层析成像反演在计算上易于处理的方向迈出的重要一步。Hinton 和 Salakhutdinov 表明，一类特定的神经网络，称为“自动编码器网络”，可用于查找复杂二进制数据集的低维编码。在这里，我们将他们的工作适应连续情况，以允许使用地震波形的自动编码器，并提供一个演示，其中我们将 512 点波形压缩为 32 元素编码。我们还证明，从数据到编码空间的映射及其逆映射都表现良好，符合许多应用程序的要求。最后，我们概述了该技术的一些潜在应用，我们希望这些应用能够在所有地震学学科及其他领域产生实际意义。
What makes a seismogram look like a seismogram? Seismic data sets generally contain waveforms sharing some set of visual characteristics and featuresindeed, seismologists routinely exploit this when performing quality control by hand. Understanding and harnessing these characteristics offers the prospect of a deeper understanding of seismic waveforms, and opens up many potential new techniques for processing and working with data. In addition, the fact that certain features are shared between waveforms suggests that it may be possible to transform the data away from the time domain, and represent the same information using fewer parameters. If so, this would be a significant step towards making fully non-linear tomographic inversions computationally tractable.Hinton & Salakhutdinov showed that a particular class of neural network, termed 'autoencoder networks', may be used to find lower-dimensional encodings of complex binary data sets. Here, we adapt their work to the continuous case to allow the use of autoencoders for seismic waveforms, and offer a demonstration in which we compress 512-point waveforms to 32-element encodings. We also demonstrate that the mapping from data to encoding space, and its inverse, are well behaved, as required for many applications. Finally, we sketch a number of potential applications of the technique, which we hope will be of practical interest across all seismological disciplines, and beyond.