A sensitivity study of seismicity indicators in supervised learning to improve earthquake prediction

The use of different seismicity indicators as input for systems to predict earthquakes is becoming increasingly popular. Nevertheless, the values of these indicators have not been systematically obtained so far. This is mainly due to the gap of knowledge existing between seismologists and data mining experts. In this work, the effect of using different parameterizations for inputs in supervised learning algorithms has been thoroughly analyzed by means of a new methodology. Five different analyses have been conducted, mainly related to the shape of training and test sets, to the calculation of the b-value, and to the adjustment of most collected indicators. Outputs sensitivity has been determined when any of these factors is not properly taken into consideration. The methodology has been applied to four Chilean zones. Given its general-purpose design, it can be extended to any location. Similar conclusions have been drawn for all the cases: a proper selection of the sets length and a careful parameterization of certain indicators leads to significantly better results, in terms of prediction accuracy.

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

[2]  Robert J. Geller,et al.  Earthquake prediction: a critical review , 1997 .

[3]  Max Wyss,et al.  Cannot Earthquakes Be Predicted , 1997 .

[4]  Αλέξανδρος Π. Αλεξανδρίδης,et al.  Large earthquake occurrence estimation based on radial basis function neural networks , 2015 .

[5]  Danijel Schorlemmer,et al.  RELM Testing Center , 2007 .

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

[7]  Qinghua Huang,et al.  Search for reliable precursors: A case study of the seismic quiescence of the 2000 western Tottori prefecture earthquake , 2006 .

[8]  P. Mora,et al.  Earthquake Trend Around Sumatra Indicated by a New Implementation of LURR Method , 2008 .

[9]  Rudolf Scitovski,et al.  A fast partitioning algorithm using adaptive Mahalanobis clustering with application to seismic zoning , 2014, Comput. Geosci..

[10]  P. Mora,et al.  Stress Reorientation and LURR: Implication for Earthquake Prediction Using LURR , 2006 .

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

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

[13]  Usman Qamar,et al.  Developing an expert system based on association rules and predicate logic for earthquake prediction , 2015, Knowl. Based Syst..

[14]  Vladimir Kossobokov,et al.  TESTING EARTHQUAKE PREDICTION ALGORITHMS : STATISTICALLY SIGNIFICANT ADVANCE PREDICTION OF THE LARGEST EARTHQUAKES IN THE CIRCUM-PACIFIC, 1992-1997 , 1999 .

[15]  Vladimir Kossobokov,et al.  Intermediate-term middle-range earthquake predictions in Italy: a review , 2005 .

[16]  Ali Akbar Safavi,et al.  Application of neural network and ANFIS model for earthquake occurrence in Iran , 2013, Earth Science Informatics.

[17]  Usman Qamar,et al.  A rule-based expert system for earthquake prediction , 2014, Journal of Intelligent Information Systems.

[18]  Francisco Martínez-Álvarez,et al.  Neural networks to predict earthquakes in Chile , 2013, Appl. Soft Comput..

[19]  David A. Rhoades,et al.  The precursory earthquake swarm in New Zealand: Hypothesis tests , 1993 .

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

[21]  Y. Tyupkin,et al.  Spatial and temporal distribution of seismicity before the Umbria-Marche September 26, 1997 earthquakes , 2000 .

[22]  G. Sobolev.  On applicability of the RTL prognostic algorithms and energy estimation to Sakhalin seismicity , 2007 .

[23]  F. Martínez-Álvarez,et al.  Earthquake prediction in seismogenic areas of the Iberian Peninsula based on computational intelligence , 2013 .

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

[25]  David Vere-Jones,et al.  THE DEVELOPMENT OF STATISTICAL SEISMOLOGY: A PERSONAL EXPERIENCE , 2006 .

[26]  T. Jordan.  Earthquake Predictability, Brick by Brick , 2006 .

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

[28]  J. Douglas Zechar,et al.  Simple smoothed seismicity earthquake forecasts for Italy , 2010 .

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

[30]  Francisco Martínez-Álvarez,et al.  Determining the best set of seismicity indicators to predict earthquakes. Two case studies: Chile and the Iberian Peninsula , 2013, Knowl. Based Syst..

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

[32]  Abdulrahman Alarifi,et al.  Earthquakes magnitude predication using artificial neural network in northern Red Sea area , 2009 .

[33]  Y. Ben-Zion,et al.  Accelerated Seismic Release and Related Aspects of Seismicity Patterns on Earthquake Faults , 2002 .

[34]  Yosihiko Ogata,et al.  Statistical Models for Earthquake Occurrences and Residual Analysis for Point Processes , 1988 .

[35]  Thomas H. Jordan,et al.  Operational Earthquake Forecasting: Some Thoughts on Why and How , 2010 .

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