Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning
Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning
复制标题
DOI：
10.1038/s41467-020-17841-x
复制
发表时间：
2020-08-07
影响因子：
16.6
通讯作者：
Baraniuk, Richard
中科院分区：
文献类型：
--
作者：
Seydoux, Leonard;Balestriero, Randall;Baraniuk, Richard
全球范围内收集的地震数据量不断增长，超过了我们的分析能力，因为迄今为止，这些数据集已经以人工专家密集型的监督方式进行了分析。此外，地震学家采用的标准模型可能会使所进行的分析产生很大的偏差。为了应对这两个挑战，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散射网络和高斯混合模型来聚类地震信号段和检测新结构。为了说明框架的力量，我们分析了2017年6月格陵兰岛Nuugaatsiaq滑坡期间获得的地震数据。我们证明了盲检测和恢复的重复的地震活动，记录之前的主要滑坡破裂，这表明我们的方法可以导致更多的信息预报的地震活动在孕震区。作者在这里解决的问题，太多的地震数据是在世界范围内获得及时评估。Seydoux及其同事开发了一个机器学习框架，可以检测和聚类连续地震记录中的地震信号。
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. The authors here tackle the problem that too much seismic data is acquired worldwide to be evaluated in a timely fashion. Seydoux and colleagues develop a machine learning framework that can detect and cluster seismic signals in continuous seismic records.