Abstract
In 20 th century more than 10 strong earthquakes (EQ) of magnitude from 6 to 7 hit the South Caucasus, causing thousands of casualties and gross economic losses. Thus, the problem of strong EQs forecast is an actual problem for the region. In this direction, we developed the physical percolation model of fracture, which considers the final failure of solid as a termination of prolonged process of destruction -generation and clustering of micro-cracks -till appearance, at some critical concentration, of the infinite cluster, marking the final failure. Percolation provides a model of preparation of an individual strong event (slip, earthquake). The natural seismic process contains many such events: the appropriate model is a non-linear stick-slip model, which is a particular case of the general theory of integrate-and-fire process. Nonlinearity of seismic process is in contradiction with a memory-less Poissonian approach to seismic hazard. The complexity theory offers a chance to improve strong earthquakes' forecast using analysis of hidden (nonlinear) patterns in seismic time series, such as attractors in the phase space plot.For a regional forecast we applied Bayesian approach to assess conditional probability of expected in the next 5 years strong EQ of magnitude 5 and more. Later on, in addition to Bayesian probability, we applied the pattern recognition technique to seismic time series, based on the assessment of empirical risk function (Generalized Portrait method): nowadays this approach is known as Support Vector Machines (SVM) technique. The preliminary analysis shows that application of GP technique predicts retrospectively 80% of M5 events in Caucasus.Besides regional forecast studies, intensive work is under way on short-term EQ prediction also. Here we present the results of multi-parametrical (hydrodynamic and magnetic) monitoring carried out in 2017-2019 on the territory of Georgia. In order to assess the reliability of the precursors, we used machine learning approach, namely the algorithm of deep learning ADAM, which optimizes target function by combination of optimization algorithm designed for neural networks and a method of stochastic gradient descent with momentum. Finally, we used the method of Receiver Operating Characteristics (ROC) to assess the forecast quality of this binary classifier system.
Highlights
Caucasus is located in the central section of the AlpineHimalayan belt, namely, at the junction of its European and Asian branches
In series of papers (Chelidze, 1986, 1987; Chelidze and Kolesnikov, 1984), we developed the physical model of the fracture process based on percolation theory (Sahimi, 1994; Stauffer and Aharony, 1994; Aharony and Stauffer, 2010; Saberi, 2015), which considers the final failure as a termination of the prolonged process of damage accumulation in disordered media (Charmet et al, 1990; Herrmann and Roux, 1990)
Our goal is to reveal the change in Machine Learning (ML), using statistical characteristics of the time series of Table 3, which precede the occurrence of a seismic event of M3–4; in other words, we consider the next-day EQ forecast problem
Summary
Caucasus is located in the central section of the AlpineHimalayan belt, namely, at the junction of its European and Asian branches. The following solution to this problem seems to be rational: (i) developing appropriate theoretical models for fracture process of solids and their testing in numerical experiments; (ii) statistical/nonlinear analysis of seismic catalogs/geophysical data aiming to forecast long- and middle-term periods of increased probability of strong (say M ≥ 5) EQs, and lastly, (iii) operative forecast (short-time prediction) of the impending strong event by monitoring geophysical fields, sensitive to tectonic strain variation (hydrodynamic and magnetic fields’ variations). The following parameters of STS were varied: (i) different epicentral areas, where STS were obtained; (ii) length of the time window for the rate count; (iii) year span (periods in the catalog); (iv) periods before and after strong events; and (iv) different magnitude thresholds (Chelidze et al, 2018). The higher the AUC, the better the model predicts 0 as 0 and 1 as 1
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
