School of Computing, Faculty of Computing, Engineering and the Built Environment, Ulster University, Newtownabbey, United Kingdom.
PLoS One. 2019 Apr 29;14(4):e0212098. doi: 10.1371/journal.pone.0212098. eCollection 2019.
In this work we introduce a system pipeline for the analysis of earth's electromagnetic field that is used to analyse precursors to earthquakes. Data gathered by the Swarm satellites are used to present the utility of our system. Our objective is to provide a streamlined method to analyze electromagnetic data over a region and investigate the relationship of precursory signals to seismic events. The process follows three distinct stages: data extraction, data pre-processing and anomaly detection. The first stage consists of the region selection and data extraction. The second stage consists of four different pre-processing methods that address the data sparsity problem and the cause of artificial anomalies. The last stage is the Anomaly Detection (AD) of the Swarm satellite data, over the investigated region. The different methods that are implemented are known to perform well in the field of AD. Following the presentation of our system, a case study is described where the seismic event of 6.2 Mw is in Ludian, China and occurred on 3rd August 2014. The event is used to present the usefulness of our approach and pinpoint some critical problems regarding satellite data that were identified.
在这项工作中，我们引入了一个用于分析地球电磁场的系统流程，该流程用于分析地震前的前兆。我们使用 Swarm 卫星收集的数据来展示我们系统的实用性。我们的目标是提供一种简化的方法来分析一个区域的电磁数据，并研究前兆信号与地震事件的关系。该过程分为三个不同的阶段：数据提取、数据预处理和异常检测。第一阶段包括区域选择和数据提取。第二阶段包括四种不同的预处理方法，这些方法解决了数据稀疏和人为异常的原因。最后一个阶段是对研究区域的 Swarm 卫星数据进行异常检测（AD）。所实施的不同方法在 AD 领域表现良好。在介绍我们的系统之后，描述了一个案例研究，其中地震事件是 2014 年 8 月 3 日发生在中国鲁甸的 6.2 级地震。该事件用于展示我们方法的有用性，并指出了一些在卫星数据中发现的关键问题。
