Automatic Classification of Seismic P and S Wave Signals Using Multiple Parameters, Frequency Ranges and Artificial Neural Network

Tutkimustuotos: KonferenssimateriaalitKonferenssiabstraktiTutkimus

Kuvaus

Automatic classification of seismic P and S wave si
gnals is
essential in automatic seismic event detection and location
systems. The problem is tackled by utilizing multiple signals of
different types each in several frequency bands. Ar
tificial Neural
Networks (ANN) are a robust and efficient tool in c
lassification
using large amount of input parameters. P and S wave signals
have fundamentally different polarization properties. The input
parameters depending on signal polarization in this
study
included rectilinearity, principal ellipticity, glo
bal polarization
parameter, eigenresultants, quadratic resultant and
predicted
coherency. Several statistical parameters were used
also. They
included skewness, kurtosis and Jarque-Bera test. In
stead of or in
addition to several parameters their variances in time were added
to the input database. Different amplitude ratios w
ere used also.
Many of the parameters were computed separately fro
m vertical
and horizontal channels. All parameters were computed at 6
different frequency range and time window combinati
ons
resulting 210 input parameters. The parameters were
computed
from 10634 seismic traces of local events creating 2.2 new time-
series. Independent training, testing and validation datasets
picked from these time-series consisted ~1.5M input
s each.
Using a deep ANN with 4 hidden layers 98% of signal
s of
validation data were classified correctly.
Alkuperäiskielienglanti
Sivumäärä1
TilaJulkaistu - 2017
TapahtumaCTBTO: Science and Technology Conference - Vienna, Itävalta
Kesto: 26 kesäkuuta 201730 kesäkuuta 2017

Konferenssi

KonferenssiCTBTO: Science and Technology Conference
MaaItävalta
KaupunkiVienna
Ajanjakso26/06/201730/06/2017

Tieteenalat

  • 1171 Geotieteet

Lainaa tätä

Tiira, T. / Automatic Classification of Seismic P and S Wave Signals Using Multiple Parameters, Frequency Ranges and Artificial Neural Network. Abstraktin lähde: CTBTO: Science and Technology Conference, Vienna, Itävalta.1 Sivumäärä
@conference{d57b42702f584892ac4e12299068a39c,
title = "Automatic Classification of Seismic P and S Wave Signals Using Multiple Parameters, Frequency Ranges and Artificial Neural Network",
abstract = "Automatic classification of seismic P and S wave signals is essential in automatic seismic event detection and location systems. The problem is tackled by utilizing multiple signals of different types each in several frequency bands. Artificial Neural Networks (ANN) are a robust and efficient tool in classification using large amount of input parameters. P and S wave signals have fundamentally different polarization properties. The input parameters depending on signal polarization in this study included rectilinearity, principal ellipticity, global polarization parameter, eigenresultants, quadratic resultant and predicted coherency. Several statistical parameters were used also. They included skewness, kurtosis and Jarque-Bera test. Instead of or in addition to several parameters their variances in time were added to the input database. Different amplitude ratios were used also. Many of the parameters were computed separately from vertical and horizontal channels. All parameters were computed at 6 different frequency range and time window combinations resulting 210 input parameters. The parameters were computed from 10634 seismic traces of local events creating 2.2 new time-series. Independent training, testing and validation datasets picked from these time-series consisted ~1.5M inputs each. Using a deep ANN with 4 hidden layers 98{\%} of signals of validation data were classified correctly.",
keywords = "1171 Geosciences",
author = "T. Tiira",
year = "2017",
language = "English",
note = "CTBTO: Science and Technology Conference ; Conference date: 26-06-2017 Through 30-06-2017",

}

Tiira, T 2017, 'Automatic Classification of Seismic P and S Wave Signals Using Multiple Parameters, Frequency Ranges and Artificial Neural Network' CTBTO: Science and Technology Conference, Vienna, Itävalta, 26/06/2017 - 30/06/2017, .

Automatic Classification of Seismic P and S Wave Signals Using Multiple Parameters, Frequency Ranges and Artificial Neural Network. / Tiira, T.

2017. Abstraktin lähde: CTBTO: Science and Technology Conference, Vienna, Itävalta.

Tutkimustuotos: KonferenssimateriaalitKonferenssiabstraktiTutkimus

TY - CONF

T1 - Automatic Classification of Seismic P and S Wave Signals Using Multiple Parameters, Frequency Ranges and Artificial Neural Network

AU - Tiira, T.

PY - 2017

Y1 - 2017

N2 - Automatic classification of seismic P and S wave signals is essential in automatic seismic event detection and location systems. The problem is tackled by utilizing multiple signals of different types each in several frequency bands. Artificial Neural Networks (ANN) are a robust and efficient tool in classification using large amount of input parameters. P and S wave signals have fundamentally different polarization properties. The input parameters depending on signal polarization in this study included rectilinearity, principal ellipticity, global polarization parameter, eigenresultants, quadratic resultant and predicted coherency. Several statistical parameters were used also. They included skewness, kurtosis and Jarque-Bera test. Instead of or in addition to several parameters their variances in time were added to the input database. Different amplitude ratios were used also. Many of the parameters were computed separately from vertical and horizontal channels. All parameters were computed at 6 different frequency range and time window combinations resulting 210 input parameters. The parameters were computed from 10634 seismic traces of local events creating 2.2 new time-series. Independent training, testing and validation datasets picked from these time-series consisted ~1.5M inputs each. Using a deep ANN with 4 hidden layers 98% of signals of validation data were classified correctly.

AB - Automatic classification of seismic P and S wave signals is essential in automatic seismic event detection and location systems. The problem is tackled by utilizing multiple signals of different types each in several frequency bands. Artificial Neural Networks (ANN) are a robust and efficient tool in classification using large amount of input parameters. P and S wave signals have fundamentally different polarization properties. The input parameters depending on signal polarization in this study included rectilinearity, principal ellipticity, global polarization parameter, eigenresultants, quadratic resultant and predicted coherency. Several statistical parameters were used also. They included skewness, kurtosis and Jarque-Bera test. Instead of or in addition to several parameters their variances in time were added to the input database. Different amplitude ratios were used also. Many of the parameters were computed separately from vertical and horizontal channels. All parameters were computed at 6 different frequency range and time window combinations resulting 210 input parameters. The parameters were computed from 10634 seismic traces of local events creating 2.2 new time-series. Independent training, testing and validation datasets picked from these time-series consisted ~1.5M inputs each. Using a deep ANN with 4 hidden layers 98% of signals of validation data were classified correctly.

KW - 1171 Geosciences

M3 - Abstract

ER -