Modeling earthquake clustering using machine learning methods.
Keywords:
machine learning, seismic analysis, mainshock processes, clustering, stochastic t-distribution.
Abstract
Seismic analysis is to study the propagation of elastic waves in the bedrock. Based on the principles of this analysis, it is advisable to build a model that would describe the basic metrics of the behavior of terrestrial soils during earthquakes and that could be used for tasks of predicting seismic activity in further research. The work is devoted to modeling clustering of earthquakes and visualization of the distribution of main shock processes using modern machine learning methods, such as stochastic t-distribution and clustering. The main stages of model construction for a more accurate result are considered. Modeling on data samples for the last hundred years is carried out to check the adequacy of the developed model.
References
Hussain, Mohammad & Ramancharla, Pradeep. (2016). Modeling of Reverse Dip-Slip Faults Using 3D Applied Element Method. Frontiers in Geotechnical Engineering. 4.1.10.14355 / fge.2016.04.001.Gronroos C. Service management and marketing / C. Gronroos. - West Sussex, 2000. p. 496.
Adeli, Hojjat & Asce, F & Jiang, Xiaomo. (2006). Dynamic Fuzzy Wavelet Neural Network Model for Structural System Identification. Journal of Structural Engineering-asce. J STRUCT ENG-ASCE. 132.10.1061. (ASCE) 0733-9445 (2006) 132:1(102).
Trunev AP, Lutsenko EV Prediction of earthquakes based on astronomical data using an artificial intelligence system. Scientific Journal of KubSAU. 2009. No. 52. URL: https://cyberleninka.ru/article/n/prognozirovanie-zemletryaseniy-po-astronomicheskim-dannym-s-ispolzovaniem-sistemy-iskusstvennogo-intellekta (date accessed: 1.10.2020).
Daskalaki, Eleni & Spiliotis, Konstantinos & Siettos, Constantinos & Minadakis, George & Papadopoulos, Gerassimos. (2016). Foreshocks and Short-Term Hazard Assessment to Large Earthquakes using Complex Networks: the Case of the 2009 L'Aquila Earthquake. Nonlinear Processes in Geophysics Discussions. 1-20. 10.5194 / npg-2015-80.
Andreeva M.Yu., Patrikeev V.N. Modeling zones of sources of potential earthquakes for territories near the Benioff zone. Geodynamics and tectonophysics. 2012. T. 3. No. 1. P. 69–76. DOI: 10.5800 / GT-2012-3-1-0063.
Schäfer, Andreas & Wenzel, Friedemann. (2019). Global Megathrust Earthquake Hazard – Maximum Magnitude Assessment Using Multi-Variate Machine LearningTable_1.csv. Frontiers in Earth Science. 7.10.3389 / feart.2019.00136.
Rouet-Leduc, Bertrand & Hulbert, Claudia & Lubbers, Nicholas & Barros, Kipton & Humphreys, Colin & Johnson, Paul. (2017). Machine Learning Predicts Laboratory Earthquakes. Geophysical Research Letters. 44.10.1002 / 2017gl074677.
Mikumo, Takeshi & Miyatake, Takashi. (2009). Numerical modeling of space and time variations of seismic activity before major earthquakes. Geophysical Journal of the Royal Astronomical Society. 74.559 - 583.
Matcharashvili, Teimuraz & Hatano, Takahiro & Chelidze, T. & Zhukova, Natalia. (2018). Simple statistics for complex Earthquake time distributions. Nonlinear Processes in Geophysics. 25.497-510. 10.5194 / npg-25-497-2018.
Abdelkrim A, Ghorbel C, Benrejeb M, etal. Lmi-based tracking control for takagi-sugeno fuzzy model [J]. International Journal of Control & Automation, 2010, No. 3 (2). P. 21 - 36.
Adeli, Hojjat & Asce, F & Jiang, Xiaomo. (2006). Dynamic Fuzzy Wavelet Neural Network Model for Structural System Identification. Journal of Structural Engineering-asce. J STRUCT ENG-ASCE. 132.10.1061. (ASCE) 0733-9445 (2006) 132:1(102).
Trunev AP, Lutsenko EV Prediction of earthquakes based on astronomical data using an artificial intelligence system. Scientific Journal of KubSAU. 2009. No. 52. URL: https://cyberleninka.ru/article/n/prognozirovanie-zemletryaseniy-po-astronomicheskim-dannym-s-ispolzovaniem-sistemy-iskusstvennogo-intellekta (date accessed: 1.10.2020).
Daskalaki, Eleni & Spiliotis, Konstantinos & Siettos, Constantinos & Minadakis, George & Papadopoulos, Gerassimos. (2016). Foreshocks and Short-Term Hazard Assessment to Large Earthquakes using Complex Networks: the Case of the 2009 L'Aquila Earthquake. Nonlinear Processes in Geophysics Discussions. 1-20. 10.5194 / npg-2015-80.
Andreeva M.Yu., Patrikeev V.N. Modeling zones of sources of potential earthquakes for territories near the Benioff zone. Geodynamics and tectonophysics. 2012. T. 3. No. 1. P. 69–76. DOI: 10.5800 / GT-2012-3-1-0063.
Schäfer, Andreas & Wenzel, Friedemann. (2019). Global Megathrust Earthquake Hazard – Maximum Magnitude Assessment Using Multi-Variate Machine LearningTable_1.csv. Frontiers in Earth Science. 7.10.3389 / feart.2019.00136.
Rouet-Leduc, Bertrand & Hulbert, Claudia & Lubbers, Nicholas & Barros, Kipton & Humphreys, Colin & Johnson, Paul. (2017). Machine Learning Predicts Laboratory Earthquakes. Geophysical Research Letters. 44.10.1002 / 2017gl074677.
Mikumo, Takeshi & Miyatake, Takashi. (2009). Numerical modeling of space and time variations of seismic activity before major earthquakes. Geophysical Journal of the Royal Astronomical Society. 74.559 - 583.
Matcharashvili, Teimuraz & Hatano, Takahiro & Chelidze, T. & Zhukova, Natalia. (2018). Simple statistics for complex Earthquake time distributions. Nonlinear Processes in Geophysics. 25.497-510. 10.5194 / npg-25-497-2018.
Abdelkrim A, Ghorbel C, Benrejeb M, etal. Lmi-based tracking control for takagi-sugeno fuzzy model [J]. International Journal of Control & Automation, 2010, No. 3 (2). P. 21 - 36.
Abstract views: 104 PDF Downloads: 177
Published
2020-12-27
How to Cite
Pronina, O., & YakinК. (2020). Modeling earthquake clustering using machine learning methods. COMPUTER-INTEGRATED TECHNOLOGIES: EDUCATION, SCIENCE, PRODUCTION, (41), 191-197. https://doi.org/10.36910/6775-2524-0560-2020-41-30
Section
Computer science and computer engineering
