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

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.