Automatic classification of seismic events within a regional seismograph network

Research output: Contribution to journalArticleScientificpeer-review

Abstract

This paper presents a fully automatic method for seismic event classification within a sparse regional seismograph network. The method is based on a supervised pattern recognition technique called the Support Vector Machine (SVM). The classification relies on differences in signal energy distribution between natural and artificial seismic sources. We filtered seismic records via 20 narrow band-pass filters and divided them into four phase windows: P, P coda, S, and S coda. We then computed a short-term average (STA) value for each filter channel and phase window. The 80 discrimination parameters served as a training model for the SVM. We calculated station specific SVM models for 19 on-line seismic stations in Finland. The training data set included 918 positive (earthquake) and 3469 negative (non-earthquake) examples. An independent test period determined method and rules for integrating station-specific classification results into network results. Finally, we applied the network classification rules to independent evaluation data comprising 5435 fully automatic event determinations, 5404 of which had been manually identified as explosions or noise, and 31 as earthquakes. The SVM method correctly identified 94% of the non-earthquakes and all but one of the earthquakes.

The result implies that the SVM tool can identify and filter out blasts and spurious events from fully automatic event solutions with a high level of accuracy. The tool helps to reduce the work-load and costs of manual seismic analysis by leaving only a small fraction of automatic event determinations, the probable earthquakes, for more detailed seismological analysis. The self-learning approach presented here is flexible and easily adjustable to the requirements of a denser or wider high-frequency network.
Original languageEnglish
JournalComputers & Geosciences
Volume87
Pages (from-to)22-30
Number of pages9
ISSN0098-3004
DOIs
Publication statusPublished - Feb 2016
MoE publication typeA1 Journal article-refereed

Fields of Science

  • 114 Physical sciences
  • GEOPHYSICS
  • seismology
  • 113 Computer and information sciences
  • 1171 Geosciences

Cite this

@article{b3fae942ff0d4abc940239bc4a1fe17d,
title = "Automatic classification of seismic events within a regional seismograph network",
abstract = "This paper presents a fully automatic method for seismic event classification within a sparse regional seismograph network. The method is based on a supervised pattern recognition technique called the Support Vector Machine (SVM). The classification relies on differences in signal energy distribution between natural and artificial seismic sources. We filtered seismic records via 20 narrow band-pass filters and divided them into four phase windows: P, P coda, S, and S coda. We then computed a short-term average (STA) value for each filter channel and phase window. The 80 discrimination parameters served as a training model for the SVM. We calculated station specific SVM models for 19 on-line seismic stations in Finland. The training data set included 918 positive (earthquake) and 3469 negative (non-earthquake) examples. An independent test period determined method and rules for integrating station-specific classification results into network results. Finally, we applied the network classification rules to independent evaluation data comprising 5435 fully automatic event determinations, 5404 of which had been manually identified as explosions or noise, and 31 as earthquakes. The SVM method correctly identified 94{\%} of the non-earthquakes and all but one of the earthquakes. The result implies that the SVM tool can identify and filter out blasts and spurious events from fully automatic event solutions with a high level of accuracy. The tool helps to reduce the work-load and costs of manual seismic analysis by leaving only a small fraction of automatic event determinations, the probable earthquakes, for more detailed seismological analysis. The self-learning approach presented here is flexible and easily adjustable to the requirements of a denser or wider high-frequency network.",
keywords = "114 Physical sciences, GEOPHYSICS, seismology, 113 Computer and information sciences, 1171 Geosciences",
author = "Jari Kortstr{\"o}m and Marja Uski and Timo Tiira",
year = "2016",
month = "2",
doi = "10.1016/j.cageo.2015.11.006",
language = "English",
volume = "87",
pages = "22--30",
journal = "Computers & Geosciences",
issn = "0098-3004",
publisher = "PERGAMON",

}

Automatic classification of seismic events within a regional seismograph network. / Kortström, Jari; Uski, Marja; Tiira, Timo.

In: Computers & Geosciences, Vol. 87, 02.2016, p. 22-30.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Automatic classification of seismic events within a regional seismograph network

AU - Kortström, Jari

AU - Uski, Marja

AU - Tiira, Timo

PY - 2016/2

Y1 - 2016/2

N2 - This paper presents a fully automatic method for seismic event classification within a sparse regional seismograph network. The method is based on a supervised pattern recognition technique called the Support Vector Machine (SVM). The classification relies on differences in signal energy distribution between natural and artificial seismic sources. We filtered seismic records via 20 narrow band-pass filters and divided them into four phase windows: P, P coda, S, and S coda. We then computed a short-term average (STA) value for each filter channel and phase window. The 80 discrimination parameters served as a training model for the SVM. We calculated station specific SVM models for 19 on-line seismic stations in Finland. The training data set included 918 positive (earthquake) and 3469 negative (non-earthquake) examples. An independent test period determined method and rules for integrating station-specific classification results into network results. Finally, we applied the network classification rules to independent evaluation data comprising 5435 fully automatic event determinations, 5404 of which had been manually identified as explosions or noise, and 31 as earthquakes. The SVM method correctly identified 94% of the non-earthquakes and all but one of the earthquakes. The result implies that the SVM tool can identify and filter out blasts and spurious events from fully automatic event solutions with a high level of accuracy. The tool helps to reduce the work-load and costs of manual seismic analysis by leaving only a small fraction of automatic event determinations, the probable earthquakes, for more detailed seismological analysis. The self-learning approach presented here is flexible and easily adjustable to the requirements of a denser or wider high-frequency network.

AB - This paper presents a fully automatic method for seismic event classification within a sparse regional seismograph network. The method is based on a supervised pattern recognition technique called the Support Vector Machine (SVM). The classification relies on differences in signal energy distribution between natural and artificial seismic sources. We filtered seismic records via 20 narrow band-pass filters and divided them into four phase windows: P, P coda, S, and S coda. We then computed a short-term average (STA) value for each filter channel and phase window. The 80 discrimination parameters served as a training model for the SVM. We calculated station specific SVM models for 19 on-line seismic stations in Finland. The training data set included 918 positive (earthquake) and 3469 negative (non-earthquake) examples. An independent test period determined method and rules for integrating station-specific classification results into network results. Finally, we applied the network classification rules to independent evaluation data comprising 5435 fully automatic event determinations, 5404 of which had been manually identified as explosions or noise, and 31 as earthquakes. The SVM method correctly identified 94% of the non-earthquakes and all but one of the earthquakes. The result implies that the SVM tool can identify and filter out blasts and spurious events from fully automatic event solutions with a high level of accuracy. The tool helps to reduce the work-load and costs of manual seismic analysis by leaving only a small fraction of automatic event determinations, the probable earthquakes, for more detailed seismological analysis. The self-learning approach presented here is flexible and easily adjustable to the requirements of a denser or wider high-frequency network.

KW - 114 Physical sciences

KW - GEOPHYSICS

KW - seismology

KW - 113 Computer and information sciences

KW - 1171 Geosciences

U2 - 10.1016/j.cageo.2015.11.006

DO - 10.1016/j.cageo.2015.11.006

M3 - Article

VL - 87

SP - 22

EP - 30

JO - Computers & Geosciences

JF - Computers & Geosciences

SN - 0098-3004

ER -