HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text (PDF) References Citation Map Services Email this article to a friend Similar articles in this journal Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by DOWLA, F. U. Articles by ANDERSON, R. W. Search for Related Content GeoRef GeoRef Citation

Seismic discrimination with artificial neural networks: Preliminary results with regional spectral data

TREATY VERIFICATION PROGRAM LAWRENCE LIVERMORE NATIONAL LABORATORY, LIVERMORE, CALIFORNIA 94550

Abstract

An application of artificial neural networks (ANN) for discrimination between natural earthquakes and underground nuclear explosions has been studied using distance corrected spectral data of regional seismic phases. Pn, Pg, and Lg spectra have been analyzed from 83 western U.S. earthquakes and 87 Nevada Test Site explosions recorded at the four broadband seismic stations operated by Lawrence Livermore National Laboratory. Distance corrections are applied to the raw spectra using existing frequency-dependent Q models for the Basin and Range. The spectra are sampled logarithmically at 41 points between 0.1 and 10 Hz for each phase and checked for adequate signal-to-noise ratios (S/N > 2). The ANN was implemented on a SUN 4/110 workstation using a backpropagation-feedforward architecture. We find that, using even simple ANN architectures (82 input units, 1 hidden unit, and 2 output units), powerful discrimination systems can be designed. In order to regionalize the data characteristics, a separate neural network was assigned to each station. For this data set, the rate of correct recognition for untrained data is over 93 per cent for both earthquakes and explosions at any single station. Using a majority voting scheme with a network of four stations, the rate of correct recognition is over 97 per cent. Although the performance of the ANN is similar to that of the Fisher linear discriminant, the ANN exhibits a number of computational advantages over the conventional method. Finally, examination of the network weights suggests that, in addition to spectral shape, a criterion that the ANN utilized to discriminate between the two populations was the Lg/Pg spectral amplitude ratios.

This article has been cited by other articles:

				A. M. Esposito, F. Giudicepietro, S. Scarpetta, L. D'Auria, M. Marinaro, and M. Martini Automatic Discrimination among Landslide, Explosion-Quake, and Microtremor Seismic Signals at Stromboli Volcano Using Neural Networks Bulletin of the Seismological Society of America, August 1, 2006; 96(4A): 1230 - 1240. [Abstract] [Full Text] [PDF]

				Discrimination of Earthquakes and Underwater Explosions Using Neural Networks Bulletin of the Seismological Society of America, February 1, 2003; 93(1): 215 - 223.

				Rapid Joint Detection and Classification with Wavelet Bases via Bayes Theorem Bulletin of the Seismological Society of America, June 1, 2000; 90(3): 764 - 774.

				G. Leonard, M. Villagran, M. Joswig, Y. Bartal, N. Rabinowitz, and A. Saya Seismic source classification in Israel by signal imaging and rule-based coincidence evaluation Bulletin of the Seismological Society of America, August 1, 1999; 89(4): 960 - 969. [Abstract] [PDF]

				Y. Zhao and K. Takano An artificial neural network approach for broadband seismic phase picking Bulletin of the Seismological Society of America, June 1, 1999; 89(3): 670 - 680. [Abstract] [PDF]

				J. Wang and T.-l. Teng Identification and picking of S phase using an artificial neural network Bulletin of the Seismological Society of America, October 1, 1997; 87(5): 1140 - 1149. [Abstract] [PDF]

				W.-Y. Kim, V. Aharonian, A. L. Lerner-Lam, and P. G. Richards Discrimination of earthquakes and explosions in southern Russia using regional high-frequency three-component data from the IRIS/JSP Caucasus network Bulletin of the Seismological Society of America, June 1, 1997; 87(3): 569 - 588. [Abstract] [PDF]

				S. R. TAYLOR Analysis of high-frequency Pg/Lg ratios from NTS explosions and western U.S. earthquakes Bulletin of the Seismological Society of America, August 1, 1996; 86(4): 1042 - 1053. [Abstract] [PDF]

				M. Musil and A. Plesinger Discrimination between local microearthquakes and quarry blasts by multi-layer perceptrons and Kohonen maps Bulletin of the Seismological Society of America, August 1, 1996; 86(4): 1077 - 1090. [Abstract] [PDF]

				J. Wang and T.-L. Teng Artificial neural network-based seismic detector Bulletin of the Seismological Society of America, February 1, 1995; 85(1): 308 - 319. [Abstract] [PDF]

				R. R. LEACH Jr., F. U. DOWLA, and E. S. VERGINO Yield estimation using bandpass-filtered seismograms: Preliminary results using neural networks with mb(Pn), short-time, long-time, and coda energy measurements Bulletin of the Seismological Society of America, April 1, 1993; 83(2): 488 - 508. [Abstract] [PDF]

				S. R. TAYLOR, J. T. RAMBO, and R. P. SWIFT Near-source effects on regional seismograms: An analysis of the NTS explosions PERA and QUESO Bulletin of the Seismological Society of America, December 1, 1991; 81(6): 2371 - 2394. [Abstract] [PDF]

				P. S. DYSART and J. J. PULLI Regional seismic event classification at the NORESS array: Seismological measurements and the use of trained neural networks Bulletin of the Seismological Society of America, December 1, 1990; 80(6B): 1910 - 1933. [Abstract] [PDF]