THE IMPROVED BP NEURAL NETWORK AND ITS APPLICATION IN SEISMIC FIRST BREAKS PICKING
Luo Sheng-xian · Computing Techniques for Geophysical and Geochemical Exploration · 2006
In seismic data processing,the accurate first break time is the key parameter to solve static correction problems of complex surface.In the paper,the BP Neural Network is introduced to pick up the first break.And aiming at the shortcomings of BP neural network,such as the low speed in training,the tendency to local minimum,the limitation of amplitude,the momentum factor method and the self-adjusting learning rate are used to improve the BP algorithm.Then the feasibility and validity of the improved methods is proved by a series of simulation experiments.The application result by the method in the first break picking is satisfied.