A tool for Swarm satellite data analysis and anomaly detection

Vyron Christodoulou, Y Bi, FG Wilkie

Research output: Contribution to journalArticle

Abstract

In this work we introduce a system pipeline for the analysis of earth’s electromagnetic field. 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 relation of precursory signals caused by 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 a number of different pre-processing methods that address the data sparsity problem and the cause of artificial anomalies. The end stage is the Anomaly Detection of the SWARM satellite data, over the investigated region. Four different methods are implemented that are known to perform well in the field of AD. Following the presentation of our system, a case study is shown. The seismic event under scrutiny is in China, Wenping that occurred on 03/08/2014 and is used to present the usefulness of our approach and pinpoint some critical problems regarding satellite data that were identified.
LanguageEnglish
Pages1
Number of pages17
JournalPLoS ONE
Publication statusAccepted/In press - 25 Mar 2019

Fingerprint

swarms
remote sensing
satellite data
data analysis
Satellites
anomaly
processing technology
Electromagnetic Fields
Electromagnetic Phenomena
Processing
case studies
Electromagnetic fields
China
Pipelines
Earth (planet)
methodology
electromagnetic field
detection
method

Keywords

  • Anomaly Detection
  • big data analytics
  • Electromagnetic Data
  • SWARM satellites

Cite this

@article{35b9827476024ea1bb03b9062dbe41ab,
title = "A tool for Swarm satellite data analysis and anomaly detection",
abstract = "In this work we introduce a system pipeline for the analysis of earth’s electromagnetic field. 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 relation of precursory signals caused by 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 a number of different pre-processing methods that address the data sparsity problem and the cause of artificial anomalies. The end stage is the Anomaly Detection of the SWARM satellite data, over the investigated region. Four different methods are implemented that are known to perform well in the field of AD. Following the presentation of our system, a case study is shown. The seismic event under scrutiny is in China, Wenping that occurred on 03/08/2014 and is used to present the usefulness of our approach and pinpoint some critical problems regarding satellite data that were identified.",
keywords = "Anomaly Detection, big data analytics, Electromagnetic Data, SWARM satellites",
author = "Vyron Christodoulou and Y Bi and FG Wilkie",
year = "2019",
month = "3",
day = "25",
language = "English",
pages = "1",
journal = "PLoS ONE",
issn = "1932-6203",

}

A tool for Swarm satellite data analysis and anomaly detection. / Christodoulou, Vyron; Bi, Y; Wilkie, FG.

In: PLoS ONE, 25.03.2019, p. 1.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A tool for Swarm satellite data analysis and anomaly detection

AU - Christodoulou, Vyron

AU - Bi, Y

AU - Wilkie, FG

PY - 2019/3/25

Y1 - 2019/3/25

N2 - In this work we introduce a system pipeline for the analysis of earth’s electromagnetic field. 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 relation of precursory signals caused by 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 a number of different pre-processing methods that address the data sparsity problem and the cause of artificial anomalies. The end stage is the Anomaly Detection of the SWARM satellite data, over the investigated region. Four different methods are implemented that are known to perform well in the field of AD. Following the presentation of our system, a case study is shown. The seismic event under scrutiny is in China, Wenping that occurred on 03/08/2014 and is used to present the usefulness of our approach and pinpoint some critical problems regarding satellite data that were identified.

AB - In this work we introduce a system pipeline for the analysis of earth’s electromagnetic field. 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 relation of precursory signals caused by 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 a number of different pre-processing methods that address the data sparsity problem and the cause of artificial anomalies. The end stage is the Anomaly Detection of the SWARM satellite data, over the investigated region. Four different methods are implemented that are known to perform well in the field of AD. Following the presentation of our system, a case study is shown. The seismic event under scrutiny is in China, Wenping that occurred on 03/08/2014 and is used to present the usefulness of our approach and pinpoint some critical problems regarding satellite data that were identified.

KW - Anomaly Detection

KW - big data analytics

KW - Electromagnetic Data

KW - SWARM satellites

M3 - Article

SP - 1

JO - PLoS ONE

T2 - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

ER -