We examined the effects of changing learning parameters on the learnin
g procedure and performance of back-propagation neural networks used t
o pick seismic arrivals. The results show that such change mainly affe
cts the speed of convergence of the learning procedures, and does not
affect the BPNN structure and its overall performance. A relationship
between the learning parameters and iteration number is obtained This
relationship may be used as a guide to check the convergence of the le
arning procedure and the BPNN performance. We also use a weight map of
BPNN structure to analyze its interior and performance. Two BPNNs use
d to pick seismic arrivals from three-component and single-component s
eismograms have similar weight patterns and operate in a similar way,
although they have different structures and trained by different train
ing dataset. (C) 1997 Elsevier Science Ltd.