Slowness vector correction for teleseismic events with artificial neural networks

Abstract The slowness anomalies cause serious location errors. The objective of this study is to create a mapping from observed slowness values to corrected values, which will provide more accurate locations. Artificial neural networks (ANNs) are efficient tools for mapping one multidimensional space to another. ANNs have been applied to compute slowness vector corrections for teleseismic events. Separate databases were used for training, testing and validating the networks. The training data set consisted of 2218 events in the period 1988–1992. An independent test database consisted of 1091 events from the year 1993 and the first half of 1994. The observed slowness vectors were computed using a three-station array of short period stations, KEF, SUF and KAF, in central Finland. The type of neural network was multi-layer perceptron. To improve the learning capability of the networks, a set of region-dependent extra inputs, resembling bias inputs, were added to the input layer. Several nets of different sizes were tested. The smallest net with only two hidden nodes gave best results. The median of error of the validation database dropped from 523 to 138 km. The median of error after correction is smaller than achieved with the method previously used with these stations. Due to the good interpolation capability of the neural net, the corrections decreased the location error even on areas which had no previous events in the training database. The method can be applied to slowness vector correction at any type of station or array, which produces slowness and azimuth values, if the mapping from the observed slowness values to calculated values is unambiguous.

[1]  David M. Skapura,et al.  Neural networks - algorithms, applications, and programming techniques , 1991, Computation and neural systems series.

[2]  Timothy Masters,et al.  Practical neural network recipes in C , 1993 .

[3]  Guillaume Deffuant,et al.  An Algorithm for Building Regularized Piecewise Linear Discrimination Surfaces: The Perceptron Membrane , 1995, Neural Computation.

[4]  W. J. M. Epping,et al.  Data Compression of Seismic Images by Neural Networks , 1992 .

[5]  Weimin Dong,et al.  Prediction of the spatial distribution of the modified mercalli intensity using neural networks , 1994 .

[6]  E. Engdahl,et al.  Nature of travel‐time anomalies at Lasa , 1971 .

[7]  Michael D. McCormack,et al.  FIRST-BREAK REFRACTION EVENT PICKING AND SEISMIC DATA TRACE EDITING USING NEURAL NETWORKS , 1993 .

[8]  Albert Tarantola,et al.  Neural networks and inversion of seismic data , 1994 .

[9]  Thomas J. Sereno,et al.  Test and Evaluation of Neural Network Applications for Seismic Signal Discrimination , 1992 .

[10]  Zhou Cheng-Dang,et al.  Bi-directional optimal reduction of dimensionality in multi-channel seismic signal processing using neural networks , 1992 .

[11]  Farid U. Dowla,et al.  Seismic discrimination with artificial neural networks: Preliminary results with regional spectral data , 1990 .

[12]  E. Mousset.  Spikes Filtering with Neural Networks: a Two-Stage Detection System , 1992 .

[13]  V. Vemuri,et al.  A comparison of neural network performance for seismic phase identification , 1993 .

[14]  Robert J. Marks,et al.  Inversion Of Snow Parameters From Passive Microwave Remote Sensing Measurements By A Neural Network Trained With A Multiple Scattering Model , 1991, [Proceedings] IGARSS'91 Remote Sensing: Global Monitoring for Earth Management.

[15]  Roy J. Greenfield,et al.  The moho depth variations under the LASA and their effect on dT/dΔ measurements , 1969 .

[16]  Timo Tiira,et al.  Discrimination of nuclear explosions and earthquakes from teleseismic distances with a local network of short period seismic stations using artificial neural networks , 1996 .

[17]  M. Niranjan,et al.  A Dynamic Neural Network Architecture by Sequential Partitioning of the Input Space , 1994, Neural Computation.

[18]  D. Gubbins.  Source Location in Laterally Varying Media , 1981 .

[19]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[20]  Michael E. Murat,et al.  AUTOMATED FIRST ARRIVAL PICKING: A NEURAL NETWORK APPROACH1 , 1992 .

[21]  E. Husebye,et al.  On upper mantle seismic heterogeneities beneath Fennoscandia , 1982 .

[22]  Upper mantle heterogeneities beneath Central Europe , 1981 .

[23]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[24]  Patrick K. Simpson,et al.  Artificial Neural Systems: Foundations, Paradigms, Applications, and Implementations , 1990 .

[25]  S Mangrulkar,et al.  Artificial neural systems. , 1990, ISA transactions.

[26]  K. Berteussen.  The origin of slowness and azimuth anomalies at large arrays , 1976 .

[27]  W. Prothero,et al.  Observations of direct P-wave slowness and azimuth anomalies for teleseisms recorded in Long Valley caldera, California , 1993, Bulletin of the Seismological Society of America.

[28]  Jay J. Pulli,et al.  Regional seismic event classification at the NORESS array: Seismological measurements and the use of trained neural networks , 1990 .

[29]  Michio Otsuka.  Azimuth and slowness anomalies of seismic waves measured on the central California seismographic array. Part I. Observations , 1966 .