Automated Picking of Seismic First-Arrivals with Neural Networks
Neural network implementations of first-arrival picking use a representative set of data and associated first-arrival pick times to create a multilayer perceptron neural network. The success of this technique depends on the statistical properties of the features input to the neural network, and the ability of the neural network to approximate a wide class of functions. Using methods from statistical pattern recognition, it is possible to determine the properties of the features input to the neural network that impact upon the reliability of the picking process. Interpreting the output of the neural network as the probability that the associated feature is the first-arrival, requires an appropriate probability model. This model is based on the multinomial distribution, since it can reflect the fact that there is only one first-arrival event on each data trace. Optimization of the neural network weights with an error function based on this probability distribution, produces a neural network that properly estimates the probability that the associated feature is a first-arrival event.
KeywordsNeural Network Instantaneous Amplitude Seismic Trace Multilayer Perceptron Neural Network Neural Network Weight
Unable to display preview. Download preview PDF.
- Bishop, C. M., 1995, Neural networks for pattern recognition: Oxford University Press.Google Scholar
- Hart, D. I., 1996, Enhancing the reliability of first-break picking using neural networks: 66`s Ann. Internat. Mtg., Soc. Expl. Geophys., Expanded Abstracts, 1662–1665.Google Scholar
- Hatherly, P. J., 1982, A computer method for determining seismic first arrival times: Geophysics, 47, 1431–1436.Google Scholar
- Hirota, K., and Iijima, T., 1978, The bounded variation quantity (B.V.Q.) and its application to feature extraction: Proceedings of the Fourth International Conference on Pattern Recognition, November 7–10, Kyoto, Japan, 457–461. (Also available through the Colorado Technical Reference Center, University of Colorado, Boulder (303) 492–8774 Engineering TK 7882.P3.)Google Scholar
- McCormack, M. D., Zaucha, D. E., and Dushek, D. W., 1993, First-break refraction event picking and seismic data trace editing using neural networks: Geophysics, 58, 67–78.Google Scholar
- Ripley, B. D., 1996, Pattern recognition and neural networks: Cambridge University Press.Google Scholar
- Salle, W. S., ed., 1999, Neural Network FAQ, part 2 of 7: Learning: periodic posting to the Usenet newsgroup comp.ai.neural-nets, URL: ftp://ftp.sas.com/pub/neural/FAQ.html Google Scholar
- Spagnolini, U., 1991, Adaptive picking of refracted first arrivals: Geophys. Prosp., 40, 587–604.Google Scholar
- Stresau, W. R., Farrell, R. C., and Ford, K. P., 1992, 3-D refraction analysis and modeling using surface-consistent decomposition on the workstation: 62n1 Ann. Internat. Mtg., Soc. Expl. Geophys., Expanded Abstracts, 1116–1119.Google Scholar
- White, H., 1992, Artificial neural networks: approximation and learning theory: Blackwell Publishers.Google Scholar