ISTerre, équipe Ondes et Structures, Université Grenoble-Alpes, UMR CNRS 5375, 1381 Rue de la Piscine, 38610, Gières, France.
Electrical and Computational Engineering, Rice University, 6100 Main MS-134, Houston, TX, 77005, USA.
Nat Commun. 2020 Aug 7;11(1):3972. doi: 10.1038/s41467-020-17841-x.
The continuously growing amount of seismic data collected worldwide is outpacing our abilities for analysis, since to date, such datasets have been analyzed in a human-expert-intensive, supervised fashion. Moreover, analyses that are conducted can be strongly biased by the standard models employed by seismologists. In response to both of these challenges, we develop a new unsupervised machine learning framework for detecting and clustering seismic signals in continuous seismic records. Our approach combines a deep scattering network and a Gaussian mixture model to cluster seismic signal segments and detect novel structures. To illustrate the power of the framework, we analyze seismic data acquired during the June 2017 Nuugaatsiaq, Greenland landslide. We demonstrate the blind detection and recovery of the repeating precursory seismicity that was recorded before the main landslide rupture, which suggests that our approach could lead to more informative forecasting of the seismic activity in seismogenic areas.
全球范围内采集到的地震数据持续增长，已经超过了我们的分析能力，因为迄今为止，这些数据集都是以人工专家为主导、监督式的方式进行分析的。此外，地震学家所采用的标准模型可能会对分析结果产生严重的偏差。针对这两个挑战，我们开发了一个新的无监督机器学习框架，用于检测和聚类连续地震记录中的地震信号。我们的方法结合了深度散射网络和高斯混合模型，用于聚类地震信号段和检测新的结构。为了说明该框架的强大功能，我们分析了 2017 年 6 月在格陵兰努加茨亚克发生的滑坡事件期间采集到的地震数据。我们展示了对主滑坡破裂前记录到的重复前兆地震活动的盲目检测和恢复，这表明我们的方法可以更有效地预测地震活动多发地区的地震活动。
