THE APPLICATION OF BACKPROPAGATION NEURAL-NETWORK TO AUTOMATIC PICKING SEISMIC ARRIVALS FROM SINGLE-COMPONENT RECORDINGS

An automatic approach is developed to pick P and S arrivals from singl e component (l-C) recordings of local earthquake data. In this approac h a back propagation neural network (BPNN) accepts a normalized segmen t (window of 40 samples) of absolute amplitudes from the l-C recording s as its input pattern, calculating two output values between 0 and 1. The outputs (0,1) or (1,0) correspond to the presence of an arrival o r background noise within a moving window. The two outputs form a time series. The P and S arrivals are then retrieved from this series by u sing a threshold and a local maximum rule. The BPNN is trained by only 10 pairs of P arrivals and background noise segments from the vertica l component (V-C) recordings. It can also successfully pick seismic ar rivals from the horizontal components (E-W and N-S). Its performance i s different for each of the three components due to strong effects of ray path and source position on the seismic waveforms. For the data fr om two stations of TDP3 seismic network, the success rates are 93%, 89 %, and 83% for P arrivals and 75%, 91%, and 87% for S arrivals from th e V-C, E-W, and N-S recordings, respectively. The accuracy of the onse t times picked from each individual l-C recording is similar. Adding a constraint on the error to be 10 ms (one sample increment), 66%, 59% and 63% of the P arrivals and 53%, 61%, and 58% of the S arrivals are picked from the V-C, E-W and N-S recordings respectively. Its performa nce is lower than a similar three-component picking approach but highe r than other 1-C picking methods.