First‐break refraction event picking and seismic data trace editing using neural networks

Abstract

Interactive seismic processing systems for editing noisy seismic traces and picking first‐break refraction events have been developed using a neural network learning algorithm. We employ a backpropagation neural network (BNN) paradigm modified to improve the convergence rate of the BNN. The BNN is interactively “trained” to edit seismic data or pick first breaks by a human processor who judiciously selects and presents to the network examples of trace edits or refraction picks. The network then iteratively adjusts a set of internal weights until it can accurately duplicate the examples provided by the user. After the training session is completed, the BNN system can then process new data sets in a manner that mimics the human processor. Synthetic modeling studies indicate that the BNN uses many of the same subjective criteria that humans employ in editing and picking seismic data sets. Automated trace editing and first‐break picking based on the modified BNN paradigm achieve 90 to 98 percent agreement with manual methods for seismic data of moderate to good quality. Productivity increases over manual editing, and picking techniques range from 60 percent for two‐dimensional (2-D) data sets and up to 800 percent for three‐dimensional (3-D) data sets. Neural network‐based seismic processing can provide consistent and high quality results with substantial improvements in processing efficiency.