Abstract

The strategy of earthquake-proof construction and seismic risk reduction requires constant improvement of methods of calculation and compilation of increasingly informative normative forecast maps of seismic hazards. Despite the wide range of available methods for fixing deformations of the earth's crust, a reliable seismic forecast is still not possible because local changes in parameters do not always lead to earthquakes, and environmental heterogeneity does not allow to single out any bright shift that can make one think about future earthquakes. The introduction of modern mathematical methods and the development of the newest computer technologies based on artificial intelligence (AI) give a chance to predict the occurrence of natural disasters, in particular, earthquakes. This study aims to build a mathematical apparatus for earthquake prediction, which is based on the use of neural networks (NNs) to process large amounts of information. Artificial neural networks (ANNs) can be used to approximate any complex functional connections. The article presents the results of developing a neural network model (NNM) for forecasting occurrence numbers and sizes of medium-strong earthquakes (Mw >=4 on the Richter scale). To build a forecast NN, data on earthquakes recorded in Greece for the period 2000-2020 (about 2,500 events) were used. The NN receives input from three independent variables: geographical coordinates of the earthquake's latitude, geographical coordinates of the earthquake's longitude, and the earthquake's depth. The construction of a NN to predict strong earthquakes was implemented in the development environment RStudio programming language R. Neuralnet package was used to build the required NN, which contains a very flexible function for training feed-forward neural networks (FFNNs) and allows you to simulate many internal hidden layers and hidden network neurons. We have also used the nnet package, which is a universal tool for building predictive models in NN programming. The result is a NN of the multilayer perceptron type, which includes 2 hidden layers consisting of 5 and 3 neurons, respectively, which generate input data at the output of the network. The NN perceived model of seismicity not only describes the process of occurrence (generation) of earthquakes in Greece, but can also be used to estimate magnitudes of forthcoming seismic events.

Keyword

Artificial intelligence, Neural networks, Seismic behaviour modelling, Magnitude forecasting, Earthquakes, Hellenic Arc.

Cite this article

Voloshchuk D, Konstantaras AJ, Moshou A, Kasianova N, Skorniakova I, Argyrakis P, Petrakis NS

Refference

[1][1]http://natcatservice.munichre.com/. Accessed 20 May 2022.

[2][2]Musson RM. Intensity-based seismic risk assessment. Soil Dynamics and Earthquake Engineering. 2000; 20(5-8):353-60.

[3][3]http://static.seismo.ethz.ch/GSHAP/eu-af-me/euraf.html. Accessed 15 May 2022.

[4][4]Goldberg DE, Melgar D, Hayes GP, Crowell BW, Sahakian VJ. A ground‐motion model for GNSS peak ground displacement. Bulletin of the Seismological Society of America. 2021; 111(5):2393-407.

[5][5]Yeats RS. Living with earthquakes in the Pacific Northwest: Chapter 9: Tsunami!.

[6][6]Huang F, Li M, Ma Y, Han Y, Tian L, Yan W, et al. Studies on earthquake precursors in China: A review for recent 50 years. Geodesy and Geodynamics. 2017; 8(1):1-2.

[7][7]Mubarak MA, Riaz MS, Awais M, Jilani Z, Ahmad N, Irfan M, et al. Earthquake prediction: a global review and local research. Proceedings of the Pakistan Academy of Science. 2009; 46(4):233-46.

[8][8]Gitis V, Derendyaev A, Petrov K. Analyzing the performance of GPS Data for earthquake prediction. Remote Sensing. 2021; 13(9).

[9][9]https://science.nasa.gov/technology/technology-highlights/new-radar-to-monitor-volcanoes-and-earthquakes-from-space. Accessed 13 September 2022.

[10][10]Alvan HV, Azad FH. Satellite remote sensing in earthquake prediction. a review. In national postgraduate conference 2011 (pp. 1-5). IEEE.

[11][11]https://medium.com/intuitionmachine/deep-learning-and-semiotics-b9bb16045005. Accessed 20 May 2022.

[12][12]https://blogs.microsoft.com/on-the-issues/2017/12/11/ai-for-earth-can-be-a-game-changer-for-our-planet/. Accessed 15 May 2022.

[13][13]Al Banna MH, Taher KA, Kaiser MS, Mahmud M, Rahman MS, Hosen AS, et al. Application of artificial intelligence in predicting earthquakes: state-of-the-art and future challenges. IEEE Access. 2020; 8:192880-923.

[14][14]Maravelakis E, Konstantaras A, Kabassi K, Chrysakis I, Georgis C, Axaridou A. 3DSYSTEK web-based point cloud viewer. In IISA 2014, the 5th international conference on information, intelligence, systems and applications 2014 (pp. 262-6). IEEE.

[15][15]Axaridou A, Chrysakis I, Georgis C, Theodoridou M, Doerr M, Konstantaras A, Maravelakis E. 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.

[16][16]Amit DJ, Tsodyks MV. Effective neurons and attractor neural networks in cortical environment. Network: Computation in Neural Systems. 1992; 3(2).

[17][17]Derbal I, Bourahla N, Mebarki A, Bahar R. Neural network-based prediction of ground time history responses. European Journal of Environmental and Civil Engineering. 2020; 24(1):123-40.

[18][18]Moustra M, Avraamides M, Christodoulou C. Artificial neural networks for earthquake prediction using time series magnitude data or seismic electric signals. Expert systems with applications. 2011; 38(12):15032-9.

[19][19]Zhou H, Li J, Chen X. Establishment of a seismic topographic effect prediction model in the Lushan M s 7.0 earthquake area. Geophysical Journal International. 2020; 221(1):273-88.

[20][20]Ghorbani S, Barari M, Hoseini M. Presenting a new method to improve the detection of micro-seismic events. Environmental Monitoring and Assessment. 2018; 190(8):1-3.

[21][21]Liu Q, Sun P, Fu X, Zhang J, Yang H, Gao H, Li Y. Comparative analysis of BP neural network and RBF neural network in seismic performance evaluation of pier columns. Mechanical Systems and Signal Processing. 2020.

[22][22]Xiaoshu G, Cheng C, Hetao H, Shenghu J. Response prediction using the PC-NARX model for SDOF systems with degradation and parametric uncertainties. Earthquake Engineering and Engineering Vibration. 2022; 21(2):325-40.

[23][23]Ye T, Shu T, Li J, Zhao P, Wang Y. Study on dynamic stability prediction model of slope in eastern Tibet section of Sichuan-Tibet highway. Mathematical Problems in Engineering. 2022.

[24][24]Huang Y, Han X, Zhao L. Recurrent neural networks for complicated seismic dynamic response prediction of a slope system. Engineering Geology. 2021.

[25][25]Datta A, Wu DJ, Zhu W, Cai M, Ellsworth WL. DeepShake: shaking intensity prediction using deep spatiotemporal RNNs for earthquake early warning. Seismological Society of America. 2022; 93(3):1636-49.

[26][26]Fayaz J, Xiang Y, Zareian F. Generalized ground motion prediction model using hybrid recurrent neural network. Earthquake Engineering & Structural Dynamics. 2021; 50(6):1539-61.

[27][27]Oh BK, Park Y, Park HS. Seismic response prediction method for building structures using convolutional neural network. Structural Control and Health Monitoring. 2020; 27(5).

[28][28]Zhang R, Liu Y, Sun H. Physics-guided convolutional neural network (PhyCNN) for data-driven seismic response modeling. Engineering Structures. 2020; 215:110704.

[29][29]Zhang X, Zhang J, Yuan C, Liu S, Chen Z, Li W. Locating induced earthquakes with a network of seismic stations in Oklahoma via a deep learning method. Scientific reports. 2020; 10(1):1-2.

[30][30]Linville LM. Event‐based training in label‐limited regimes. Journal of Geophysical Research: Solid Earth. 2022; 127(1).

[31][31]Kim T, Song J, Kwon OS. Probabilistic evaluation of seismic responses using deep learning method. Structural Safety. 2020.

[32][32]Jain R, Nayyar A, Arora S, Gupta A. A comprehensive analysis and prediction of earthquake magnitude based on position and depth parameters using machine and deep learning models. Multimedia Tools and Applications. 2021; 80(18):28419-38.

[33][33]Sreejaya KP, Basu J, Raghukanth ST, Srinagesh D. Prediction of ground motion intensity measures using an artificial neural network. Pure and Applied Geophysics. 2021; 178(6):2025-58.

[34][34]Ida Y, Ishida M. Analysis of seismic activity using self-organizing map: implications for earthquake prediction. Pure and Applied Geophysics. 2022; 179(1):1-9.

[35][35]Kail R, Burnaev E, Zaytsev A. Recurrent convolutional neural networks help to predict location of earthquakes. IEEE Geoscience and Remote Sensing Letters. 2021; 19:1-5.

[36][36]Akram J, Ovcharenko O, Peter D. A robust neural network-based approach for microseismic event detection. In SEG technical program expanded abstracts 2017 (pp. 2929-33). Society of Exploration Geophysicists.

[37][37]Rundle JB, Stein S, Donnellan A, Turcotte DL, Klein W, Saylor C. The complex dynamics of earthquake fault systems: new approaches to forecasting and nowcasting of earthquakes. Reports on Progress in Physics. 2021; 84(7).

[38][38]Lior I, Ziv A. Generic source parameter determination and ground‐motion prediction for earthquake early warninggeneric source parameter determination and ground‐motion prediction for earthquake early warning. Bulletin of the Seismological Society of America. 2020; 110(1):345-56.

[39][39]Chong KD. Research and application of neural network technologies in the problem of earthquake forecasting: (on the example of the northwestern region of Vietnam). Dissertations, 2013. Moskow, RUDN University.

[40][40]Nicolis O, Plaza F, Salas R. Prediction of intensity and location of seismic events using deep learning. Spatial Statistics. 2021.

[41][41]Segou M, Parsons T. A new technique to calculate earthquake stress transfer and to probe the physics of aftershocks. Bulletin of the Seismological Society of America. 2020; 110(2):863-73.

[42][42]Holyoak KJ. Parallel distributed processing: explorations in the microstructure of cognition. Science. 1987; 236:992-7.

[43][43]Rumelhart D, Mcclelland J, PDP Research Group. parallel distributed processing: explorations in the microstructures of cognition. MIT Press; Cambridge MA. 1986.

[44][44]Su YP, Zhu QJ. Application of ANN to prediction of earthquake influence. In second international conference on information and computing science 2009 (pp. 234-7). IEEE.

[45][45]Itai A, Yasukawa H, Takumi I, Hata M. Multi-layer neural network for precursor signal detection in electromagnetic wave observation applied to great earthquake prediction. In IEEE-Eurasip nonlinear signal and image processing 2005.

[46][46]Shahi S, Fenton FH, Cherry EM. Prediction of chaotic time series using recurrent neural networks and reservoir computing techniques: a comparative study. Machine Learning with Applications. 2022.

[47][47] Adeli H, Panakkat A. A probabilistic neural network for earthquake magnitude prediction. Neural networks. 2009; 22(7):1018-24.

[48][48]Panakkat A, Adeli H. Recurrent neural network for approximate earthquake time and location prediction using multiple seismicity indicators. Computer‐Aided Civil and Infrastructure Engineering. 2009; 24(4):280-92.

[49][49]Lakshmi SS, Tiwari RK. Model dissection from earthquake time series: a comparative analysis using modern non-linear forecasting and artificial neural network approaches. Computers & Geosciences. 2009; 35(2):191-204.

[50][50]Negarestani A, Setayeshi S, Ghannadi-maragheh M, Akashe B. Layered neural networks based analysis of radon concentration and environmental parameters in earthquake prediction. Journal of Environmental Radioactivity. 2002; 62(3):225-33.

[51][51]Ozerdem MS, Ustundag B, Demirer RM. Self-organized maps based neural networks for detection of possible earthquake precursory electric field patterns. Advances in Engineering Software. 2006; 37(4):207-17.

[52][52]Voloshchuk D, Kasіanova N. Machine learning as an earthquake prediction tool: current and future challenges for the global economy. International scientific-practical conference “economic and business administration development: scientific currencies and solutions” 2022 (рр. 26-8), Kyiv, NAU

[53][53]Krinitzsky EL. How to combine deterministic and probabilistic methods for assessing earthquake hazards. Engineering Geology. 2003; 70(1-2):157-63.

[54][54]Zechar JD, Hardebeck JL, Michael AJ, Naylor M, Steacy S, Wiemer S, et al. Community online resource for statistical seismicity analysis. Seismological Research Letters. 2011; 82(5):686-90.

[55][55]Stabile TA, Serlenga V, Satriano C, Romanelli M, Gueguen E, Gallipoli MR, et al. The INSIEME seismic network: a research infrastructure for studying induced seismicity in the High Agri Valley (southern Italy). Earth System Science Data. 2020; 12(1):519-38.

[56][56]Zaliapin I, Ben-Zion Y. Artefacts of earthquake location errors and short-term incompleteness on seismicity clusters in southern California. Geophysical Journal International. 2015; 202(3):1949-68.

[57][57]Abbott LF. Learning in neural network memories. Network: Computation in Neural Systems. 1990; 1(1).

[58][58]León SM, Calviño BO, Vivas LA, Corretger RC, Ulacio OR. Small-layered feed-forward and convolutional neural networks for efficient P wave earthquake detection. Expert Systems with Applications. 2022.

[59][59]Byrne JH, Berry WO. Neural models of plasticity: experimental and theoretical approaches. Academic Press; 2013.

[60][60]http://dggsl.geol.uoa.gr/en_index.html. Accessed 20 May 2022.

[61][61]https://www.gein.noa.gr/services/cat.html. Accessed 20 May 2022.

[62][62]Mignan A, Broccardo M. Neural network applications in earthquake prediction (1994–2019): meta‐analytic and statistical insights on their limitations. Seismological Research Letters. 2020; 91(4):2330-42.

[63][63]Bodri B. A neural-network model for earthquake occurrence. Journal of Geodynamics. 2001; 32(3):289-310.

[64][64]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.

[65][65]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.

[66][66]Konstantaras A, Petrakis NS, Frantzeskakis T, Markoulakis E, Kabassi K, Vardiambasis IO, et al. Deep learning neural network seismic big-data analysis of earthquake correlations in distinct seismic regions. International Journal of Advanced Technology and Engineering Exploration. 2021; 8(84):1410-23.

[67][67]http://www.utstat.toronto.edu/~brunner/oldclass/2201s11/readings/glmbook.pdf. Accessed 15 May 2022.

[68][68]Van der Baan M, Jutten C. Neural networks in geophysical applications. Geophysics. 2000; 65(4):1032-47.

[69][69]Huang SC, Huang YF. Bounds on number of hidden neurons of multilayer perceptrons in classification and recognition. In international symposium on circuits and systems 1990 (pp. 2500-3). IEEE.

[70][70]https://www.v7labs.com/blog/train-validation-test-set. Accessed 17 May 2022.

[71][71]Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Networks. 1989; 2(5):359-66.

[72][72]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.

[73][73]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.

[74][74]Geman S, Bienenstock E, Doursat R. Neural networks and the bias/variance dilemma. Neural Computation. 1992; 4(1):1-58.

[75][75]Scales JA, Snieder R. What is a wave? Nature. 1999; 401(6755):739-40.

[76][76]Hai DT, Vinh ND, Trieu CD. Long-term earthquake prediction in Lai Chau-Dien Bien region on the basis of time-magnitude model. Journal of Science and Technology. 2002; 40(4):45-53.

[77][77]Günther F, Fritsch S. Neuralnet: training of neural networks. The R Journal. 2010; 2(1):30-8.

[78][78]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.

[79][79]Konstantaras A. Deep learning and parallel processing spatio-temporal clustering unveil new Ionian distinct seismic zone. Informatics. 2020; 7(4):1-10.

[80][80]Konstantaras AJ. Expert knowledge-based algorithm for the dynamic discrimination of interactive natural clusters. Earth Science Informatics. 2016; 9(1):95-100.

[81][81]Yang L, Liu X, Zhu W, Zhao L, Beroza GC. Toward improved urban earthquake monitoring through deep-learning-based noise suppression. Science Advances. 2022; 8(15):1-9.

[82][82]Moshou A, Argyrakis P, Konstantaras A, Daverona AC, Sagias NC. Characteristics of recent aftershocks sequences (2014, 2015, 2018) derived from new seismological and geodetic data on the Ionian islands, Greece. Data. 2021; 6(2):1-27.