Unsupervised Deep Clustering of Seismic Data: Monitoring the Ross Ice Shelf, Antarctica

Unsupervised Deep Clustering of Seismic Data: Monitoring the Ross Ice Shelf, Antarctica
复制标题

无监督地震数据深度聚类:监测南极洲罗斯冰架

DOI:
10.1029/2021jb021716
复制
发表时间:
2021
期刊:
Journal of Geophysical Research: Solid Earth
影响因子:
--
通讯作者:
Bromirski, Peter D.
Bromirski, Peter D.
中科院分区:
--
文献类型:
--
作者:
Jenkins, II, William F.;Gerstoft, Peter;Bianco, Michael J.;Bromirski, Peter D.

文献摘要

参考文献

被引文献

相似文献

机器学习(ML)技术和计算能力的进步已经产生了处理、分类和分析大型地震数据集的最先进的方法。在这项研究中,我们考虑了ML的应用,用于自动识别2014-2017年间部署在南极罗斯冰架(RIS)的34个台站的宽带地震台阵观测中包含的主要脉冲地震活动类型。RIS地震数据包含许多冰川过程产生的信号和噪声,这对监测冰架的完整性和动力学很有用。深度聚类被用来有效地研究这些信号。深度聚类自动将信号分组到假设类别中,而不需要手动标记,从而允许将它们的信号特征和时空分布与潜在的源机制进行比较。该方法使用光谱图作为输入,并使用自动编码器(一种深度神经网络)将其显著特征编码为低维潜在表示。为了进行比较,将两种聚类方法应用于潜在数据:高斯混合模型(GMM)和深度嵌入聚类(DEC)。识别了8类主要的地震信号,并与温度、风速、潮汐和海冰浓度等环境数据进行了比较。在2016年厄尔尼诺现象夏季,最大的地震活动水平发生在RIS锋面,以及在整个部署过程中靠近锋面的接地区。我们展示了某些类型的地震活动与RIS锋面的季节变化以及罗斯福岛的潮汐驱动的地震活动之间的时空联系。
Advances in machine learning (ML) techniques and computational capacity have yielded state‐of‐the‐art methodologies for processing, sorting, and analyzing large seismic data sets. In this study, we consider an application of ML for automatically identifying dominant types of impulsive seismicity contained in observations from a 34‐station broadband seismic array deployed on the Ross Ice Shelf (RIS), Antarctica from 2014 to 2017. The RIS seismic data contain signals and noise generated by many glaciological processes that are useful for monitoring the integrity and dynamics of ice shelves. Deep clustering was employed to efficiently investigate these signals. Deep clustering automatically groups signals into hypothetical classes without the need for manual labeling, allowing for the comparison of their signal characteristics and spatial and temporal distribution with potential source mechanisms. The method uses spectrograms as input and encodes their salient features into a lower‐dimensional latent representation using an autoencoder, a type of deep neural network. For comparison, two clustering methods are applied to the latent data: a Gaussian mixture model (GMM) and deep embedded clustering (DEC). Eight classes of dominant seismic signals were identified and compared with environmental data such as temperature, wind speed, tides, and sea ice concentration. The greatest seismicity levels occurred at the RIS front during the 2016 El Niño summer, and near grounding zones near the front throughout the deployment. We demonstrate the spatial and temporal association of certain classes of seismicity with seasonal changes at the RIS front, and with tidally driven seismicity at Roosevelt Island.
与海洋重力波活动相关的罗斯冰架冰震
DOI: 10.1029/2019gl084123
发表时间: 2019
影响因子: 5.2
作者:
Chen, Z.;Bromirski, P. D.;Gerstoft, P.;Stephen, R. A.;Lee, W. S.;Yun, S.;Olinger, S. D.;Aster, R. C.;Wiens, D. A.;Nyblade, A. A.
通讯作者: Nyblade, A. A.
用环境地震噪声观测罗斯冰架近地表环境迫使的变化
DOI: 10.1029/2018gl079665
发表时间: 2018
影响因子: 5.2
作者:
Chaput, J.;Aster, R. C.;McGrath, D.;Baker, M.;Anthony, R. E.;Gerstoft, P.;Bromirski, P.;Nyblade, A.;Stephen, R. A.;Wiens, D. A.
通讯作者: Wiens, D. A.
DOI: 10.1017/jog.2018.66
发表时间: 2018-10-01
影响因子: 3.4
作者:
Chen, Zhao;Bromirski, Peter D.;Nyblade, Andrew A.
通讯作者: Nyblade, Andrew A.
在罗斯冰架上观测到的远震地震波场
DOI: 10.1017/jog.2020.83
发表时间: 2021
影响因子: 3.4
作者:
Baker, Michael G.;Aster, Richard C.;Wiens, Douglas A.;Nyblade, Andrew;Bromirski, Peter D.;Gerstoft, Peter;Stephen, Ralph A.
通讯作者: Stephen, Ralph A.
地震数据压缩的非线性主成分分析
DOI: --
发表时间: 2012
期刊: International Conference on Recent Advances in Information Technology
影响因子: --
作者:
T. A. Reddy;K. R. Devi;S. Gangashetty
通讯作者: S. Gangashetty