Backpropagation neural network as earthquake early warning tool using a new modified elementary Levenberg–Marquardt Algorithm to minimise backpropagation errors

Abstract

Abstract. A new modified elementary Levenberg–Marquardt Algorithm (M-LMA) was used to minimise backpropagation errors in training a backpropagation neural network (BPNN) to predict the records related to the Chi-Chi earthquake from four seismic stations: Station-TAP003, Station-TAP005, Station-TCU084, and Station-TCU078 belonging to the Free Field Strong Earthquake Observation Network, with the learning rates of 0.3, 0.05, 0.2, and 0.28, respectively. For these four recording stations, the M-LMA has been shown to produce smaller predicted errors compared to the Levenberg–Marquardt Algorithm (LMA). A sudden predicted error could be an indicator for Early Earthquake Warning (EEW), which indicated the initiation of strong motion due to large earthquakes. A trade-Off decision-making process with BPNN (TDPB), using two alarms, adjusted the threshold of the magnitude of predicted error without a mistaken alarm. With this approach, it is unnecessary to consider the problems of characterising the wave phases and pre-processing, and does not require complex hardware; an existing seismic monitoring network-covered research area was already sufficient for these purposes.