Neural networks to predict earthquakes in Chile

A new earthquake prediction system is presented in this work. This method, based on the application of artificial neural networks, has been used to predict earthquakes in Chile, one of the countries with larger seismic activity. The input values are related to the b-value, the Bath's law, and the Omori-Utsu's law, parameters that are strongly correlated with seismicity, as shown in solid previous works. Two kind of prediction are provided in this study: The probability that an earthquake of magnitude larger than a threshold value happens, and the probability that an earthquake of a limited magnitude interval might occur, both during the next five days in the areas analyzed. For the four Chile's seismic regions examined, with epicenters placed on meshes with dimensions varying from 0.5^ox0.5^o to 1^ox1^o, a prototype of neuronal network is presented. The prototypes predict an earthquake every time the probability of an earthquake of magnitude larger than a threshold is sufficiently high. The threshold values have been adjusted with the aim of obtaining as few false positives as possible. The accuracy of the method has been assessed in retrospective experiments by means of statistical tests and compared with well-known machine learning classifiers. The high success rate achieved supports the suitability of applying soft computing in this field and poses new challenges to be addressed.

[1]  Mark D. Petersen,et al.  Time-independent and Time-dependent Seismic Hazard Assessment for the State of California: Uniform California Earthquake Rupture Forecast Model 1.0 , 2007 .

[2]  Karl Rihaczek,et al.  1. WHAT IS DATA MINING? , 2019, Data Mining for the Social Sciences.

[3]  J. Douglas Zechar,et al.  Earthquake Forecasting and Earthquake Prediction: Different Approaches for Obtaining the Best Model , 2011 .

[4]  Cezar-Ioan Trifu,et al.  A method for multidimensional analysis of earthquake frequency-magnitude distribution with an application to the Vrancea region of Romania , 1996 .

[5]  Alicia Troncoso Lora,et al.  Computational Intelligence Techniques for Predicting Earthquakes , 2011, HAIS.

[6]  G. Ranalli.  A Statistical Study of Aftershock Sequences , 1969 .

[7]  B. Bolt,et al.  The standard error of the magnitude-frequency b value , 1982 .

[8]  M. Wyss,et al.  Earthquake statistics at Parkfield: 1. Stationarity of b values , 2004 .

[9]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[10]  S. J. Gibowicz,et al.  Frequency-magnitude, depth, and time relations for earthquakes in an island arc: North Island, New Zealand , 1974 .

[11]  Edward H. Field,et al.  Overview of the Working Group for the Development of Regional Earthquake Likelihood Models (RELM) , 2005 .

[12]  Danijel Schorlemmer,et al.  First Results of the Regional Earthquake Likelihood Models Experiment , 2010 .

[13]  Roger M.W. Musson,et al.  Seismic hazard maps for the U.K. , 1996 .

[14]  R. Madahizadeh,et al.  PREDICTION OF AFTERSHOCKS DISTRIBUTION USING ARTIFICIAL NEURAL NETWORKS AND ITS APPLICATION ON THE MAY 12, 2008 SICHUAN EARTHQUAKE , 2009 .

[15]  Jorge Reyes,et al.  A Chilean seismic regionalization through a Kohonen neural network , 2010, Neural Computing and Applications.

[16]  M. Wyss,et al.  Variations in earthquake-size distribution across different stress regimes , 2005, Nature.

[17]  Matthew C. Gerstenberger,et al.  Short-term Aftershock Probabilities: Case Studies in California , 2007 .

[18]  Y. Kagan.  Seismic moment distribution revisited: I. Statistical results , 2002 .

[19]  J. Kirschvink.  Earthquake Prediction by Animals: Evolution and Sensory Perception , 2000 .

[20]  P. Nuannin.  Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology 183 The Potential of b-value Variations as Earthquake Precursors for Small and Large Events , 2006 .

[21]  F. Omori.  4. Seismographical Observations at the Central Meteorological Observatory, 1885-1897(Macro-seismic Measurement in Tokyo. III) , .

[22]  Carl Kisslinger,et al.  Estimating tectonic stress rate and state with Landers aftershocks , 1997 .

[23]  Sebastian Hainzl,et al.  Dependence of the Omori‐Utsu law parameters on main shock magnitude: Observations and modeling , 2007 .

[24]  Danijel Schorlemmer,et al.  Earth science: Microseismicity data forecast rupture area , 2005, Nature.

[25]  A. Gelman,et al.  Of Beauty, Sex and Power , 2009 .

[26]  Yan Y. Kagan,et al.  Statistical distributions of earthquake numbers: consequence of branching process , 2009, 0909.2372.

[27]  Zhen Liu,et al.  Seismic Hazard Inferred from Tectonics: California , 2005 .

[28]  J. Douglas Zechar,et al.  Testing alarm‐based earthquake predictions , 2008 .

[29]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[30]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[31]  Mustafa Erdik,et al.  Istanbul Earthquake Rapid Response and the Early Warning System , 2003 .

[32]  T. Utsu.  A statistical study on the occurrence of aftershocks. , 1961 .

[33]  Jorge Reyes,et al.  An integrated neural network model for PM10 forecasting , 2006 .

[34]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[35]  P. Reasenberg,et al.  Earthquake Hazard After a Mainshock in California , 1989, Science.

[36]  John McCloskey,et al.  Limited overlap between the seismic gap and coseismic slip of the great 2010 Chile earthquake , 2011 .

[37]  Stefan Wiemer,et al.  Mapping the B‐value anomaly at 100 km depth in the Alaska and New Zealand Subduction Zones , 1996 .

[38]  Andrew Gelman,et al.  Of beauty, sex, and power: Statistical challenges in estimating small eects , 2008 .

[39]  M. Holschneider,et al.  Temporal limits of the power law aftershock decay rate , 2002 .

[40]  Ming Li.  Fractal Time Series—A Tutorial Review , 2010 .

[41]  B. Gutenberg,et al.  Frequency of Earthquakes in California , 1944, Nature.

[42]  Keiiti Aki,et al.  3-D inhomogeneities in the upper mantle , 1981 .

[43]  Kristy F. Tiampo,et al.  Seismicity-based earthquake forecasting techniques: Ten years of progress , 2012 .

[44]  David A. Rhoades.  Application of the EEPAS Model to Forecasting Earthquakes of Moderate Magnitude in Southern California , 2007 .

[45]  A. Zollo,et al.  Space and Time Behavior of Seismic Activity at Mt. Vesuvius Volcano, Southern Italy , 2002 .

[46]  Markus Båth,et al.  Lateral inhomogeneities of the upper mantle , 1965 .

[47]  Gerassimos A. Papadopoulos,et al.  OPERATIONAL EARTHQUAKE FORECASTING. State of Knowledge and Guidelines for Utilization , 2011 .

[48]  W. K. Cloud,et al.  United States earthquakes, 1960 , 1984 .

[49]  A. Zollo,et al.  Space and Time Behavior of Seismic Activity at Mt. Vesuvius Volcano , 2002 .

[50]  Hojjat Adeli,et al.  Recurrent Neural Network for Approximate Earthquake Time and Location Prediction Using Multiple Seismicity Indicators , 2009, Comput. Aided Civ. Infrastructure Eng..

[51]  Steven N. Ward,et al.  Methods for Evaluating Earthquake Potential and Likelihood in and around California , 2007 .

[52]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[53]  ASHIF PANAKKAT,et al.  Neural Network Models for Earthquake Magnitude Prediction Using Multiple seismicity Indicators , 2007, Int. J. Neural Syst..

[54]  Rodolfo Console,et al.  Physical and stochastic models of earthquake clustering , 2006 .

[55]  Kristy F. Tiampo,et al.  A RELM earthquake forecast based on pattern informatics , 2005 .

[56]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[57]  Anshel J. Schiff.  The Loma Prieta, California, earthquake of October 17, 1989 : lifelines , 1998 .

[58]  P. Sammonds,et al.  Role of pore fluids in the generation of seismic precursors to shear fracture , 1992, Nature.

[59]  B. Mandelbrot,et al.  Fractals: Form, Chance and Dimension , 1978 .

[60]  Cinna Lomnitz,et al.  Major Earthquakes of Chile: A Historical Survey, 1535-1960 , 2004 .

[61]  T. Utsu.  A method for determining the value of b in a formula log n=a-bM showing the magnitude frequency relation for earthquakes , 1965 .

[62]  S. Sri Lakshmi,et al.  Model dissection from earthquake time series: A comparative analysis using modern non-linear forecasting and artificial neural network approaches , 2009, Comput. Geosci..

[63]  Y. Ogata,et al.  The Centenary of the Omori Formula for a Decay Law of Aftershock Activity , 1995 .

[64]  Alicia Troncoso Lora,et al.  Pattern recognition to forecast seismic time series , 2010, Expert Syst. Appl..

[65]  T. Utsu.  Representation and Analysis of the Earthquake Size Distribution: A Historical Review and Some New Approaches , 1999 .

[66]  Felipe Dimer de Oliveira.  Power of earthquake cluster detection tests , 2012 .

[67]  O. Kulhánek,et al.  Spatial and temporal b value anomalies preceding the devastating off coast of NW Sumatra earthquake of December 26, 2004 , 2005 .

[68]  Danijel Schorlemmer,et al.  ALM: An Asperity-based Likelihood Model for California , 2007 .

[69]  Edwin Cartlidge,et al.  Italy. Quake experts to be tried for manslaughter. , 2011, Science.

[70]  Yan Y. Kagan,et al.  A Testable Five-Year Forecast of Moderate and Large Earthquakes in Southern California Based on Smoothed Seismicity , 2007 .

[71]  Y. Kagan,et al.  High-resolution Time-independent Grid-based Forecast for M ≥ 5 Earthquakes in California , 2007 .

[72]  Kiehwa Lee,et al.  Historical Seismicity of Korea , 2006 .

[73]  C. Richter.  An instrumental earthquake magnitude scale , 1935 .

[74]  Matthew C. Gerstenberger,et al.  Properties of the Aftershock Sequence of the 1999 Mw 7.1 Hector Mine Earthquake: Implications for Aftershock Hazard , 2002 .

[75]  Y. Kagan,et al.  Implications of Geodetic Strain Rate for Future Earthquakes, with a Five-Year Forecast of M5 Earthquakes in Southern California , 2007 .

[76]  Jenny A. Baglivo,et al.  Non-Poissonian Earthquake Clustering and the Hidden Markov Model as Bases for Earthquake Forecasting in California , 2007 .

[77]  K. Aki.  17. Maximum Likelihood Estimate of b in the Formula logN=a-bM and its Confidence Limits , 1965 .

[78]  Yan Y. Kagan,et al.  VAN earthquake predictions‒An attempt at statistical evaluation , 1996 .

[79]  C. R. Allen,et al.  Responsibilities in earthquake prediction: To the Seismological Society of America, delivered in Edmonton, Alberta, May 12, 1976 , 1976 .

[80]  Y. Kagan,et al.  Long‐term probabilistic forecasting of earthquakes , 1994 .

[81]  Hojjat Adeli,et al.  A probabilistic neural network for earthquake magnitude prediction , 2009, Neural Networks.

[82]  Akira Hasegawa,et al.  Characteristic small‐earthquake sequence off Sanriku, northeastern Honshu, Japan , 2002 .

[83]  U. S. Coast.  United States Earthquakes, 1938 , 1933 .

[84]  O. Kulhánek,et al.  Spatial and temporal variations of seismicity in the Horn of Africa from 1960 to 1993 , 1997 .

[85]  Rodolfo Console,et al.  Real Time Forecasts through an Earthquake Clustering Model Constrained by the Rate-and- State Constitutive Law: Comparison with a Purely Stochastic ETAS Model , 2007 .

[86]  Suman Ahmmed,et al.  Architecture and Weight Optimization of ANN Using Sensitive Analysis and Adaptive Particle Swarm Optimization , 2010 .

[87]  Y. Kagan,et al.  California Earthquakes, 1800–2007: A Unified Catalog with Moment Magnitudes, Uncertainties, and Focal Mechanisms , 2009 .

[88]  B. Gutenberg,et al.  Seismicity of the Earth , 1970, Nature.

[89]  E. Ivo Alves,et al.  Earthquake Forecasting Using Neural Networks: Results and Future Work , 2006 .

[90]  V. Tikhomirov.  On the Representation of Continuous Functions of Several Variables as Superpositions of Continuous Functions of one Variable and Addition , 1991 .

[91]  Barbara Romanowicz,et al.  On the variation of b-values with earthquake size , 1994 .

[92]  Oscar Cordón,et al.  A Multiobjective Evolutionary Conceptual Clustering Methodology for Gene Annotation Within Structural Databases: A Case of Study on the Gene Ontology Database , 2008, IEEE Transactions on Evolutionary Computation.

[93]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[94]  J. Douglas Zechar,et al.  Risk and return: evaluating Reverse Tracing of Precursors earthquake predictions , 2010 .

[95]  Kathryn Vogelsang,et al.  On beauty... , 2004, South Dakota journal of medicine.