Early Peak Ground Acceleration Prediction for On-Site Earthquake Early
Warning Using LSTM Neural Network
Abstract
On-site earthquake early warning techniques, which issue alerts based on
seismic waves measured at a single station, are promising, and have
performed quite successfully during some damaging earthquakes.
Conventionally, most existing techniques extract several P-wave features
from the first few seconds of seismic waves after the trigger to predict
the intensity or destructiveness of an incoming earthquake. This type of
technique neglects the behavior of temporal varying features within P
waves. In other words, the characteristics of data sequences are not
considered. In this study, a long short-term memory (LSTM) neural
network, which was capable of learning order dependence in seismic
waves, was employed to predict the PGA of the coming earthquake. A dense
LSTM architecture was proposed and a large data set of earthquakes was
used to train the LSTM model. The general performance of the LSTM model
indicated that the predicted PGA values were quite promising but were
generally overestimated. However, the predicted PGA of the Chi-Chi
earthquake data set, whose fault rupture was complex and long, using the
proposed LSTM model was more accurate than the PGA predicted in a
previous study using a support vector regression approach. In addition,
an alternative alert criterion, which issues alerts when the predicted
PGA exceeds the threshold in successive time windows, is presented, and
the performance of the proposed LSTM model when different PGA thresholds
are considered is also discussed.