Nonlinear Methodologies for Identifying Seismic Event and Nuclear Explosion Using Random Forest, Support Vector Machine, and Naive Bayes Classification

The discrimination of seismic event and nuclear explosion is a complex and nonlinear system. The nonlinear methodologies including Random Forests (RF), Support Vector Machines (SVM), and Naive Bayes Classifier (NBC) were applied to discriminant seismic events. Twenty earthquakes and twenty-seven explosions with nine ratios of the energies contained within predetermined “velocity windows” and calculated distance are used in discriminators. Based on the one out cross-validation, ROC curve, calculated accuracy of training and test samples, and discriminating performances of RF, SVM, and NBC were discussed and compared. The result of RF method clearly shows the best predictive power with a maximum area of 0.975 under the ROC among RF, SVM, and NBC. The discriminant accuracies of RF, SVM, and NBC for test samples are 92.86%, 85.71%, and 92.86%, respectively. It has been demonstrated that the presented RF model can not only identify seismic event automatically with high accuracy, but also can sort the discriminant indicators according to calculated values of weights.

[1]  Won-Young Kim,et al.  Discrimination of small earthquakes and artificial explosions in the Korean Peninsula using Pg/Lg ratios , 1998 .

[2]  Moisés Goldszmidt,et al.  Short term performance forecasting in enterprise systems , 2005, KDD '05.

[3]  Hsiang-Chieh Lee,et al.  Resilience and extreme events: Example on nursing home flood evacuation in Taiwan , 2013 .

[4]  Stephen J. Arrowsmith,et al.  Discrimination of Delay-Fired Mine Blasts in Wyoming Using an Automatic Time-Frequency Discriminant , 2006 .

[5]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[6]  Albert T. Smith,et al.  Discrimination of explosions from simultaneous mining blasts , 1993, Bulletin of the Seismological Society of America.

[7]  Cesare Furlanello,et al.  Modern data mining tools in descriptive sensory analysis: A case study with a Random forest approach , 2007 .

[8]  Douglas R. Baumgardt,et al.  Regional seismic waveform discriminants and case-based event identification using regional arrays , 1990 .

[9]  Dario Gregori,et al.  Naïve Bayes classifiers with feature selection to predict hospitalization and complications due to objects swallowing and ingestion among European children , 2013 .

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

[11]  R. Blandford,et al.  Discrimination Between Earthquakes and Underground Explosions , 1977 .

[12]  Jean-Michel Poggi,et al.  Variable selection using random forests , 2010, Pattern Recognit. Lett..

[13]  Igor Kononenko,et al.  Inductive and Bayesian learning in medical diagnosis , 1993, Appl. Artif. Intell..

[14]  Longjun Dong,et al.  Comparison of Two Methods in Acoustic Emission Source Location Using Four Sensors Without Measuring Sonic Speed , 2011 .

[15]  A. Booker,et al.  An application of statistical discrimination to classify seismic events , 1964 .

[16]  Yefim Gitterman,et al.  Spectral discrimination analysis of Eurasian nuclear tests and earthquakes recorded by the Israel Seismic Network and the NORESS array , 1999 .

[17]  Steven R. Taylor,et al.  Regional discrimination between NTS explosions and western U.S. earthquakes , 1989 .

[18]  Yefim Gitterman,et al.  Spectra of quarry blasts and microearthquakes recorded at local distances in Israel , 1993, Bulletin of the Seismological Society of America.

[19]  Kathleen A. Ziegler,et al.  Spectral evidence for source multiplicity in explosions: Application to regional discrimination of earthquakes and explosions , 1988 .

[20]  Pedro M. Domingos,et al.  On the Optimality of the Simple Bayesian Classifier under Zero-One Loss , 1997, Machine Learning.

[21]  Li Qiyue,et al.  Comparisons of Random Forest and Support Vector Machine for Predicting Blasting Vibration Characteristic Parameters , 2011 .

[22]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[23]  Dong Long-jun.  Bayes Discriminant Analysis Model and Its Application to the Prediction and Classification of Rockburst , 2009 .

[24]  Jan Wüster,et al.  Discrimination of chemical explosions and earthquakes in central Europe—a case study , 1993 .

[25]  Mario Chica-Olmo,et al.  An assessment of the effectiveness of a random forest classifier for land-cover classification , 2012 .

[26]  Xibing Li,et al.  Comprehensive Models for Evaluating Rockmass Stability Based on Statistical Comparisons of Multiple Classifiers , 2013 .

[27]  Xibing Li,et al.  A Microseismic/Acoustic Emission Source Location Method Using Arrival Times of PS Waves for Unknown Velocity System , 2013, Int. J. Distributed Sens. Networks.

[28]  Li Xibing,et al.  Prediction of rockburst classification using Random Forest , 2013 .

[29]  M. E. Maron,et al.  Automatic Indexing: An Experimental Inquiry , 1961, JACM.

[30]  John A. Orcutt,et al.  An automatic means to discriminate between earthquakes and quarry blasts , 1990, Bulletin of the Seismological Society of America.

[31]  Li Xibing,et al.  Three-dimensional analytical solution of acoustic emission or microseismic source location under cube monitoring network , 2012 .