The Behavior of VLF/LF Variations Associated with Geomagnetic Activity, Earthquakes, and the Quiet Condition Using a Neural Network Approach

The neural network approach is proposed for studying very-low- and low-frequency (VLF and LF) subionospheric radio wave variations in the time vicinities of magnetic storms and earthquakes, with the purpose of recognizing anomalies of different types. We also examined the days with quiet geomagnetic conditions in the absence of seismic activity, in order to distinguish between the disturbed signals and the quiet ones. To this end, we trained the neural network (NN) on the examples of the representative database. The database included both the VLF/LF data that was measured during four-year monitoring at the station in Petropavlovsk-Kamchatsky, and the parameters of seismicity in the Kuril-Kamchatka and Japan regions. It was shown that the neural network can distinguish between the disturbed and undisturbed signals. Furthermore, the prognostic behavior of the VLF/LF variations indicative of magnetic and seismic activity has a different appearance in the time vicinity of the earthquakes and magnetic storms.

[1]  M. I. Shimelevich,et al.  Rapid neuronet inversion of 2D magnetotelluric data for monitoring of geoelectrical section parameters , 2007 .

[2]  An approximation method for solving the inverse MTS problem with the use of neural networks , 2009 .

[3]  Efthimios S. Skordas,et al.  Seismic Electric Signals: An additional fact showing their physical interconnection with seismicity☆ , 2013 .

[5]  V. Spichak,et al.  Artificial neural network inversion of magnetotelluric data in terms of three‐dimensional earth macroparameters , 2000 .

[6]  Pier Francesco Biagi,et al.  Observation evidences of atmospheric Gravity Waves induced by seismic activity from analysis of subionospheric LF signal spectra , 2007 .

[7]  Masashi Hayakawa,et al.  On the correlation between ionospheric perturbations as detected by subionospheric VLF/LF signals and earthquakes as characterized by seismic intensity , 2010 .

[8]  S. Ma,et al.  Prediction of SYM-H index during large storms by NARX neural network from IMF and solar wind data , 2010 .

[9]  T. Kikuchi.  VLF Phase Anomalies Associated with Substorm , 1981 .

[10]  Masashi Hayakawa,et al.  Middle latitude LF (40 kHz) phase variations associated with earthquakes for quiet and disturbed geomagnetic conditions , 2004 .

[11]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[12]  M. Hayakawa,et al.  Disturbances in a VLF radio signal prior the M=4.7 offshore Anzio (central Italy) earthquake on 22 August 2005 , 2008 .

[13]  Nicholas V. Sarlis,et al.  Visualization of the significance of Receiver Operating Characteristics based on confidence ellipses , 2014, Comput. Phys. Commun..

[14]  Michael E. Fitzpatrick,et al.  Detecting anomalies in time series data via a deep learning algorithm combining wavelets, neural networks and Hilbert transform , 2017, Expert Syst. Appl..

[15]  Alejandro Ramírez-Rojas,et al.  The Complexity Measures Associated with the Fluctuations of the Entropy in Natural Time before the Deadly México M8.2 Earthquake on 7 September 2017 , 2018, Entropy.

[16]  Stelios M. Potirakis,et al.  Criticality Analysis of the Lower Ionosphere Perturbations Prior to the 2016 Kumamoto (Japan) Earthquakes as Based on VLF Electromagnetic Wave Propagation Data Observed at Multiple Stations , 2018, Entropy.

[17]  M. Hayakawa,et al.  Correlation of very low and low frequency signal variations at mid-latitudes with magnetic activity and outer-zone particles , 2014 .

[18]  P. Varotsos,et al.  Natural time analysis: On the deadly Mexico M8.2 earthquake on 7 September 2017 , 2018, Physica A: Statistical Mechanics and its Applications.

[19]  M. Hayakawa,et al.  Sensitivity of LF signal to global ionosphere and atmosphere perturbations in the network of stations , 2006 .

[20]  Astarita Vittorio,et al.  Automated Sensing System for Monitoring of Road Surface Quality by Mobile Devices , 2014 .

[21]  T. Rosenberg,et al.  VLF propagation disturbances and electron precipitation at mid‐latitudes , 1973 .

[22]  Jukka Riekki,et al.  Applying Wavelet Packet Decomposition and One-Class Support Vector Machine on Vehicle Acceleration Traces for Road Anomaly Detection , 2013, ISNN.

[23]  S. Sokolov.  Magnetic storms and their effects in the lower ionosphere: Differences in storms of various types , 2011 .

[25]  L. Thomas,et al.  Ionization changes in the middle lattitude D-region associated with geomagnetic storms , 1968 .

[26]  Mary M. Poulton,et al.  Neural network pattern recognition of subsurface EM images , 1992 .

[27]  George E. Nasr,et al.  Cross Entropy Error Function in Neural Networks: Forecasting Gasoline Demand , 2002, FLAIRS.

[28]  Farbod Setoudeh,et al.  Magnitude of Earthquake Prediction Using Neural Network , 2008, 2008 Fourth International Conference on Natural Computation.

[29]  M. Hayakawa,et al.  Subionospheric VLF signal perturbations possibly related to earthquakes , 1998 .