Support vector evaluation of the unpredictability of the electrotelluric field variations signal before major earthquakes
2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628) - Tập 2 - Trang 917-921 vol.2
Tóm tắt
Observations of electrotelluric field (ETF) variations (long-term geoelectric potential difference) were conducted for a five year period (1993-97), in western Greece. During this time interval, 18 large earthquakes, M>4.8, took place in the vicinity of Patras, within 150 km of the VAN station. This work investigates the nonlinear predictability of the ETF signal. Support vector machines trained on a signal window have been used to predict the next sample. We observe a significant increase at this short-term unpredictability of the ETF signal at about 2 weeks before many major earthquakes. This fact can be attributed to a quick time variation of the dynamics that produce the ETF signal due to the earthquake generation process. This unpredictability increase can be taken advantage of for signaling an increased possibility of a large earthquake within the next few days.
Từ khóa
#Earthquakes #Support vector machines #Educational technology #Seismic measurements #Information management #Signal processing #Signal generators #Frequency measurement #Magnetic field measurement #Electric variables measurementTài liệu tham khảo
10.1016/0040-1951(86)90172-1
10.1016/0040-1951(87)90034-5
varotsos, 1984, Physical properties of the variations of the electric field of the earth preceding earthquakes I & II, Tectonophysics 110 73–125
economou, 1996, Multichannel distance filtering of seismic electric signals, EUSIPCO
10.1785/gssrl.71.4.423
bartlett, 1999, Generalization Performance of Support Vector Machines and Other Pattern Classifiers, Advances in Kernel Methods Support Vector Learning, 43
10.1007/BF00994018
haykin, 1999, Neural Networks
joachims, 1998, Making Large-Scale SVM Learning Practical, Advances in Kernel Methods Support Vector Learning
mattera, 1999, Support vector machines for dynamic reconstruction of a chaotic system, Advances in Kernel Methods - Support Vector Learning, 211
10.1029/94GL00694
10.1016/0040-1951(77)90054-3
10.1007/BF01592913
10.1029/96GL01477
meyer, 1984, Large variations of the clcetrotclluric field prior to a major earthquake in Greece, Froc 19 Gen Assoc EGS Moscow, 158
10.1016/0040-1951(72)90077-7
moroz, 1995, On the technique for tracking brief precursors of strong earthquake in the low-frequency telluric field of Kamchatka, Phys Solid Earth (Eng Transl ) 30, 30, 830
ifantis, 1993, Long-term variations of the earth's electric field preceding two earthquakes in Greece, Acta Geophysica Polonica, 41, 337
10.1016/0040-1951(93)90059-S
10.1109/NNSP.1997.622408
vapnik, 1998, Statistical Learning Theory
10.1109/72.788641
10.1007/BFb0091924
10.1109/72.788640
ott, 1993, Chaos in Dynamical Systems
tsonis, 1992, Chaos From Theory to Applications