Machine-Learning Methods for Earthquake Ground Motion Analysis and Simulation

This paper presents a novel method of data-based probabilistic seismic hazard analysis (PSHA) and ground motion simulation, verified using previously recorded strong-motion data and machine-learning techniques. The procedure consists of three parts: (1) selection of an orthonormal set of basis vectors called eigenquakes to represent characteristic earthquake records; (2) estimation of response spectra for the anticipated level of shaking for a scenario earthquake at a site using Gaussian process regression; and (3) optimal combination of the eigenquakes to generate time series of ground acceleration consistent with the response spectral ordinates obtained in the second part. The paper discusses the benefits of applying such machine-learning methods to strong-motion databases for PSHA and ground motion simulation, particularly in large urban areas where dense instrumentation is available or expected. The effectiveness of the proposed methodology is exhibited using four scenario examples for downtown Los Angeles. Advantages, disadvantages, and future research needs for this machine-learning approach to PSHA are discussed.

[1]  J. Ghaboussi,et al.  Evolving structural design solutions using an implicit redundant Genetic Algorithm , 2000 .

[2]  J. Baker,et al.  Spectral shape, epsilon and record selection , 2006 .

[3]  Gary C. Hart,et al.  Simulation of artificial earthquakes , 1973 .

[4]  J. Beck.  Bayesian system identification based on probability logic , 2010 .

[5]  Robert J. Geller,et al.  Shake-up time for Japanese seismology , 2011, Nature.

[6]  I. M. Idriss,et al.  Comparisons of the NGA Ground-Motion Relations , 2008 .

[7]  Jens-Uwe Klügel.  Comment on “Sigma: Issues, Insights and Challenges” by F. O. Strasser, N. A. Abrahamson, and J. J. Bommer , 2009 .

[8]  BrianS-J. Chiou,et al.  An NGA Model for the Average Horizontal Component of Peak Ground Motion and Response Spectra , 2008 .

[9]  Seok Goo Song,et al.  Physics-Based Earthquake Source Characterization and Modeling with Geostatistics , 2010 .

[10]  J. Baker,et al.  A vector‐valued ground motion intensity measure consisting of spectral acceleration and epsilon , 2005 .

[11]  G. Atkinson,et al.  Ground-Motion Prediction Equations for the Average Horizontal Component of PGA, PGV, and 5%-Damped PSA at Spectral Periods between 0.01 s and 10.0 s , 2008 .

[12]  Farzad Naeim,et al.  FUZZY PATTERN CLASSIFICATION OF STRONG GROUND MOTION RECORDS , 2005 .

[13]  Susan E. Hough,et al.  Localized damage caused by topographic amplification during the 2010 M 7.0 Haiti earthquake , 2010 .

[14]  Roger M.W. Musson.  Ground motion and probabilistic hazard , 2009 .

[15]  Arzhang Alimoradi.  Earthquake Ground Motion Simulation using Novel Machine Learning Tools , 2011 .

[16]  Julian J. Bommer,et al.  Review: Strong Ground Motions—Have We Seen the Worst? , 2009 .

[17]  Farzad Naeim,et al.  Selection and Scaling of Ground Motion Time Histories for Structural Design Using Genetic Algorithms , 2004 .

[18]  J. Beck,et al.  Updating Models and Their Uncertainties. I: Bayesian Statistical Framework , 1998 .

[19]  N. Abrahamson,et al.  Summary of the Abrahamson & Silva NGA Ground-Motion Relations , 2008 .

[20]  Sai Hung Cheung,et al.  Calculation of Posterior Probabilities for Bayesian Model Class Assessment and Averaging from Posterior Samples Based on Dynamic System Data , 2010, Comput. Aided Civ. Infrastructure Eng..

[21]  Y. K. Wen,et al.  A Record-Based Method for the Generation of Tridirectional Uniform Hazard-Response Spectra and Ground Motions Using the Hilbert-Huang Transform , 2007 .

[22]  John G. Anderson.  Source and Site Characteristics of Earthquakes That Have Caused Exceptional Ground Accelerations and Velocities , 2010 .

[23]  Zhenming Wang,et al.  Comment on “Why Do Modern Probabilistic Seismic-Hazard Analyses Often Lead to Increased Hazard Estimates?” by Julian J. Bommer and Norman A. Abrahamson , 2007 .

[24]  Mircea Grigoriu,et al.  To Scale or Not to Scale Seismic Ground-Acceleration Records , 2011 .

[25]  Alfredo H.-S. Ang,et al.  Nonstationary Stochastic Models of Earthquake Motions , 1968 .

[26]  Goodarz Ahmadi,et al.  A note on the Wiener-Hermite representation of the earthquake ground acceleration , 1980 .

[27]  Joel P. Conte,et al.  Nonstationary ARMA modeling of seismic motions , 1992 .

[28]  Robin K. McGuire,et al.  The character of high-frequency strong ground motion , 1981 .

[29]  G. Ahmadi,et al.  Simulation of earthquake records using time-varying Arma (2,1) model , 2002 .

[30]  N. Abrahamson,et al.  Selection of ground motion time series and limits on scaling , 2006 .

[31]  Thomas H. Heaton,et al.  The Slapdown Phase in High-acceleration Records of Large Earthquakes , 2009 .

[32]  W. Silva,et al.  An empirical study of earthquake source spectra for California earthquakes , 1997, Bulletin of the Seismological Society of America.

[33]  Tsuyoshi Takada,et al.  A Bayesian Framework for Prediction of Seismic Ground Motion , 2009 .

[34]  Julian J. Bommer,et al.  Selection and Scaling of Real Accelerograms for Bi-Directional Loading: A Review of Current Practice and Code Provisions , 2007 .

[35]  D. Boore.  Stochastic simulation of high-frequency ground motions based on seismological models of the radiated spectra , 1983 .

[36]  Farzad Naeim,et al.  Evolutionary modal identification utilizing coupled shear–flexural response—implication for multistory buildings. Part II : Application , 2006 .

[37]  C. Cornell.  Engineering seismic risk analysis , 1968 .

[38]  Frank Scherbaum,et al.  Information-Theoretic Selection of Ground-Motion Prediction Equations for Seismic Hazard Analysis: An Applicability Study Using Californian Data , 2009 .

[39]  Jonathan P. Stewart,et al.  Empirical Model for Basin Effects Accounts for Basin Depth and Source Location , 2005 .

[40]  Shahram Pezeshk,et al.  Improved Velocity and Displacement Time Histories in Frequency Domain Spectral-Matching Procedures , 2010 .

[41]  C. Cornell,et al.  Disaggregation of seismic hazard , 1999 .

[42]  Armen Der Kiureghian,et al.  An evolutionary model for earthquake ground motion , 1989 .

[43]  Ellen M. Rathje,et al.  A Semi-Automated Procedure for Selecting and Scaling Recorded Earthquake Motions for Dynamic Analysis , 2008 .

[44]  Jack W. Baker,et al.  Conditional Mean Spectrum: Tool for Ground-Motion Selection , 2011 .

[45]  Jens-Uwe Klügel,et al.  Comment on “Why Do Modern Probabilistic Seismic-Hazard Analyses Often Lead to Increased Hazard Estimates?” by Julian J. Bommer and Norman A. Abrahamson , 2007 .

[46]  Nicolas Luco,et al.  Does amplitude scaling of ground motion records result in biased nonlinear structural drift responses? , 2007 .

[47]  Agathoklis Giaralis,et al.  Wavelet-based response spectrum compatible synthesis of accelerograms—Eurocode application (EC8) , 2009 .

[48]  Charles M. Bishop.  Variational principal components , 1999 .

[49]  Jamshid Ghaboussi,et al.  Direct use of design criteria in genetic algorithm-based controller optimization , 2001 .

[50]  Julian J. Bommer,et al.  Reply to “Comment on ‘Why Do Modern Probabilistic Seismic-Hazard Analyses Often Lead to Increased Hazard Estimates?’ by Julian J. Bommer and Norman A. Abrahamson” by Jens-Uwe Klügel , 2007 .

[51]  Jack W. Baker,et al.  VECTOR-VALUED INTENSITY MEASURES FOR PULSE-LIKE NEAR-FAULT GROUND MOTIONS , 2008 .

[52]  Gail M. Atkinson,et al.  Ground Motions at Memphis and St. Louis from M 7.5-8.0 Earthquakes in the New Madrid Seismic Zone , 2002 .

[53]  F. Scherbaum,et al.  Model Selection in Seismic Hazard Analysis: An Information-Theoretic Perspective , 2009 .

[54]  Shahram Pezeshk,et al.  Probabilistic Performance-Based Optimal Design of Steel Moment-Resisting Frames. I: Formulation , 2007 .

[55]  K. Campbell,et al.  NGA Ground Motion Model for the Geometric Mean Horizontal Component of PGA, PGV, PGD and 5% Damped Linear Elastic Response Spectra for Periods Ranging from 0.01 to 10 s , 2008 .

[56]  Armen Der Kiureghian,et al.  A stochastic ground motion model with separable temporal and spectral nonstationarities , 2008 .

[57]  Robin K. McGuire,et al.  Probabilistic seismic hazard analysis: Early history , 2008 .

[58]  Julian J. Bommer,et al.  Why Do Modern Probabilistic Seismic-Hazard Analyses Often Lead to Increased Hazard Estimates? , 2006 .

[59]  C. Allin Cornell,et al.  Earthquakes, Records, and Nonlinear Responses , 1998 .

[60]  Julian J. Bommer,et al.  Reply to “Comment on ‘Why Do Modern Probabilistic Seismic-Hazard Analyses Often Lead to Increased Hazard Estimates?’ by Julian J. Bommer and Norman A. Abrahamson” by Zhenming Wang and Mai Zhou , 2007 .

[61]  Jamshid Ghaboussi,et al.  Genetic algorithm in structural damage detection , 2001 .