Abstract

This research work employs deep-learning neural-networks in aiming to unveil the possible existence of a relation between mean rates of seismic activity among consecutive large seismic events and their interim time-intervals. The research is conducted in possibly discrete seismic areas of the steady flow of input strain energy, identified in the southern front of the seismic Hellenic arc. Periods with low-level seismicity in terms of activity result in accumulation of strain energy, which is being stored in under-ground geological faults in the Earth’s crust, which in turn are acting as energy storage elements. On the contrary, the occurrence of strong earthquakes acts as a decongestion mechanism which causes the release of significant amounts of the stored energy to the surface of the Earth. Accounting for mean seismicity rates on regular time intervals, e.g., monthly, results in a tool that enables monitoring the underlying management system of the stored seismic energy. The captured information from the processed big-data, regarding not just quantity, but mostly type variation. It was channelled to a deep-learning model whose purpose is the identification and simulation. It was aided by parallel processing training algorithms, of the potential relation of mean seismicity rates, recorded in between consecutive strong earthquakes and their interim time-intervals, in a particular possibly discrete seismic area. Successful training yields a real time dynamic mechanism able to estimate the duration period between the last recorded and next upcoming strong earthquake. The proposed model achieves noteworthy approximations, in the range of approximately two weeks to four months, of the time interval between successive large earthquakes, which reside within the foreshock-aftershock time period of each main seismic event. The obtained range falls well-short of the observed mean seismic recurrence times laying in between 1.5 to 2 years.

Keyword

Deep learning, Neural networks applications, Spatio-temporal analysis, Seismicity correlations.

Cite this article

Konstantaras A, Petrakis NS, Frantzeskakis T, Markoulakis E, Kabassi K, Vardiambasis IO, Kapetanakis T, Moshou A, Maravelakis E

Refference

[1][1]Dilek Y. Collision tectonics of the Mediterranean region: causes and consequences. Special Papers-Geological Society of America. 2006.

[2][2]Gao H, Tong X, Wen Z, Wang Z. The tectonic evolution of the eastern Mediterranean basin and its control on hydrocarbon distribution. Journal of Petroleum Science and Engineering. 2019; 178:389-407.

[3][3]Kuribayashi E. Lifeline earthquake hazard zonation in socio-economic aspects. Lifeline Systems. 1991.

[4][4]Hayakawa M. Earthquake prediction with radio techniques. John Wiley & Sons; 2015; 1-17.

[5][5]Nomura S, Ogata Y, Nadeau RM. Space‐time model for repeating earthquakes and analysis of recurrence intervals on the San Andreas Fault near Parkfield, California. Journal of Geophysical Research: Solid Earth. 2014; 119(9):7092-122.

[6][6]González Á, Serra I, Corral Á. The global statistical distribution of time intervals between consecutive earthquakes. In EGU general assembly conference abstracts 2020 (p. 13309).

[7][7]Papadimitriou P. Identification of seismic precursors before large earthquakes: decelerating and accelerating seismic patterns. Journal of Geophysical Research: Solid Earth. 2008; 113(B04):1-19.

[8][8]Chiao LY, Kuo BY. Multiscale seismic tomography. Geophysical Journal International. 2001; 145(2):517-27.

[9][9]Wyss M, Burford RO. Occurrence of a predicted earthquake on the San Andreas fault. Nature. 1987; 329(6137):323-5.

[10][10]Bodri B. A neural-network model for earthquake occurrence. Journal of Geodynamics. 2001; 32(3):289-310.

[11][11]Eneva M, Ben‐Zion Y. Application of pattern recognition techniques to earthquake catalogs generated by model of segmented fault systems in three‐dimensional elastic solids. Journal of Geophysical Research: Solid Earth. 1997; 102(B11):24513-28.

[12][12]Meyers RA. Encyclopedia of complexity and systems science. New York: Springer; 2009.

[13][13]Falcone G, Spassiani I, Ashkenazy Y, Shapira A, Hofstetter R, Havlin S, et al. An operational earthquake forecasting experiment for israel: preliminary results. Frontiers in Earth Science. 2021; 9:1-10.

[14][14]Pu Y, Chen J, Apel DB. Deep and confident prediction for a laboratory earthquake. Neural Computing and Applications. 2021; 33:1691-701.

[15][15]Shokouhi P, Girkar V, Riviere J, Shreedharan S, Marone C, Giles CL, et al. Deep learning can predict laboratory quakes from active source seismic data. Geophysical Research Letters. 2021; 48(12).

[16][16]Triep EG, Sykes LR. Frequency of occurrence of moderate to great earthquakes in intracontinental regions: implications for changes in stress, earthquake prediction, and hazards assessments. Journal of Geophysical Research: Solid Earth. 1997; 102(B5):9923-48.

[17][17]Adeli H, Panakkat A. A probabilistic neural network for earthquake magnitude prediction. Neural Networks. 2009; 22(7):1018-24.

[18][18]Asencio-cortés G, Martínez-alvarez F, Troncoso A, Morales-esteban A. Medium–large earthquake magnitude prediction in Tokyo with artificial neural networks. Neural Computing and Applications. 2017; 28(5):1043-55.

[19][19]Lakkos S, Hadjiprocopis A, Comley R, Smith P. A neural network scheme for earthquake prediction based on the seismic electric signals. In proceedings of IEEE workshop on neural networks for signal processing 1994 (pp. 681-9). IEEE.

[20][20]Yin F, Wang J, Guo C. Advances in neural networks. In international symposium on neural networks, Dalian, China. 2004.

[21][21]Konstantaras A, Vallianatos F, Varley MR, Makris JP. Soft-computing modelling of seismicity in the southern Hellenic arc. IEEE Geoscience and Remote Sensing Letters. 2008; 5(3):323-7.

[22][22]Konstantaras AJ. Expert knowledge-based algorithm for the dynamic discrimination of interactive natural clusters. Earth Science Informatics. 2016; 9(1):95-100.

[23][23]Bressan G, Barnaba C, Peresan A, Rossi G. Anatomy of seismicity clustering from parametric space-time analysis. Physics of the Earth and Planetary Interiors. 2021.

[24][24]http://www.gein.noa.gr/en. Accessed 18 August 2021.

[25][25]Haeffele BD, Vidal R. Global optimality in neural network training. In proceedings of the conference on computer vision and pattern recognition 2017 (pp. 7331-9).

[26][26]Leptokaropoulos KM, Papadimitriou EE, Orlecka-sikora B, Karakostas VG. Seismicity rate changes in association with the evolution of the stress field in northern Aegean Sea, Greece. Geophysical Journal International. 2012; 188(3):1322-38.

[27][27]Shapiro S. Fluid-induced seismicity. Cambridge University Press; 2015.

[28][28]Axaridou A, Chrysakis I, Georgis C, Theodoridou M, Doerr M, Konstantaras A, et al. 3D-SYSTEK: recording and exploiting the production workflow of 3D-models in Cultural Heritage. In IISA 2014, The 5th international conference on information, intelligence, systems and applications 2014 (pp. 51-6). IEEE.

[29][29]Maravelakis E, Konstantaras A, Kabassi K, Chrysakis I, Georgis C, Axaridou A. 3DSYSTEK web-based point cloud viewer. In the 5th international conference on information, intelligence, systems and applications 2014 (pp. 262-6). IEEE.

[30][30]Konstantaras AJ, Katsifarakis E, Maravelakis E, Skounakis E, Kokkinos E, Karapidakis E. Intelligent spatial-clustering of seismicity in the vicinity of the Hellenic seismic arc. Earth Science Research. 2012; 1(2):1-10.

[31][31]Wang J, Yi Z, Zurada JM, Lu BL, Yin H. Advances in neural networks. In third international symposium on neural networks 2006. Springer Nature.

[32][32]Shaw BE, Carlson JM, Langer JS. Patterns of seismic activity preceding large earthquakes. Journal of Geophysical Research: Solid Earth. 1992; 97(B1):479-88.

[33][33]Sergaki E, Spiliotis G, Vardiambasis IO, Kapetanakis T, Krasoudakis A, Giakos GC, et al. Application of ANN and ANFIS for detection of brain tumors in MRIs by using DWT and GLCM texture analysis. In international conference on imaging systems and techniques 2018 (pp. 1-6). IEEE.

[34][34]Urdan TC. Statistics in plain English. Routledge; 2016.

[35][35]Pereira FC, Borysov SS. Machine learning fundamentals. In mobility patterns, big data and transport analytics 2019 (pp. 9-29). Elsevier.

[36][36]James AP. Deep learning classifiers with memristive networks: theory and applications. Springer; 2019.

[37][37]Lee H. Foundations of applied statistical methods. Heidelberg: Springer; 2014.

[38][38]https://github.com/fchollet/keras. Accessed 18 August 2021.

[39][39]https://www.manning.com/books/deep-learning-with-r. Accessed 18 August 2021.

[40][40]Hara K, Saito D, Shouno H. Analysis of function of rectified linear unit used in deep learning. In international joint conference on neural networks (IJCNN) 2015 (pp. 1-8). IEEE.

[41][41]Timothy Masters. Practical neural network recipes in C++. Morgan Kaufmann; 1993.

[42][42]Liodakis G, Arvanitis D, Vardiambasis IO. Neural network- based digital receiver for radio communications. WSEAS Transactions on Systems. 2004; 3(10):3308-13.

[43][43]Kapetanakis TN, Vardiambasis IO. Radiation performance of satellite reflector antennas using neural networks. In third international conference on mathematics and computers in sciences and in industry (MCSI) 2016 (pp. 85-8). IEEE.

[44][44]Konstantaras A, Varley MR, Vallianatos F, Collins G, Holifield P. Neuro-fuzzy prediction-based adaptive filtering applied to severely distorted magnetic field recordings. IEEE Geoscience and Remote Sensing Letters. 2006; 3(4):439-41.

[45][45]Konstantaras A, Varley MR, Vallianatos F, Makris JP, Collins G, Holifield P. Detection of weak seismo-electric signals upon the recordings of the electrotelluric field by means of neuro-fuzzy technology. IEEE Geoscience and Remote Sensing Letters. 2007; 4(1):161-5.

[46][46]Kapetanakis TN, Vardiambasis IO, Ioannidou MP, Maras A. Neural network modeling for the solution of the inverse loop antenna radiation problem. IEEE Transactions on Antennas and Propagation. 2018; 66(11):6283-90.

[47][47]Kapetanakis TN, Vardiambasis IO, Lourakis EI, Maras A. Applying neuro-fuzzy soft computing techniques to the circular loop antenna radiation problem. IEEE Antennas and Wireless Propagation Letters. 2018; 17(9):1673-6.

[48][48]Tang J, Alelyani S, Liu H. Feature selection for classification: a review. Data Classification: Algorithms and Applications. 2014.

[49][49]Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research. 2014; 15(1):1929-58.

[50][50]Konstantaras AJ. Classification of distinct seismic regions and regional temporal modelling of seismicity in the vicinity of the Hellenic seismic arc. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2012; 6(4):1857-63.

[51][51]Konstantaras A. Deep learning and parallel processing spatio-temporal clustering unveil new ionian distinct seismic zone. Informatics. 2020; 4(4):1-10.

[52][52]Wang Y, Li S, Song J. Threshold-based evolutionary magnitude estimation for an earthquake early warning system in the Sichuan–Yunnan region, China. Scientific Reports. 2020; 10(1):1-12.

[53][53]Sammut C, Webb GI. Encyclopedia of machine learning. Springer Science & Business Media; 2011.

[54][54]Zubkov SI. The appearance times of earthquake precursors. Izv. Akad. Nauk SSSR Fiz. Zemli (Solid Earth). 1987; 5:87-91.

[55][55]Drakatos G, Latoussakis J. A catalog of aftershock sequences in Greece (1971–1997): their spatial and temporal characteristics. Journal of Seismology. 2001; 5(2):137-45.