Neural networks to predict earthquakes in Chile

Reyes, J.; Morales‐Esteban, Antonio; Martínez‐Álvarez, Francisco

doi:10.1016/j.asoc.2012.10.014

Cited by 160 publications

(117 citation statements)

References 68 publications

Supporting

Mentioning

116

Contrasting

Order By: Relevance

“…Applications of ANNs can be found in many scientific fields for e.g. the wind power prediction [42], in cancer prediction and prognosis [43], geomagnetic activity [44], earthquakes [45], etc…”

Section: Artificial Neural Network (Anns)mentioning

confidence: 99%

Complex Systems: Phenomenology, Modeling, Analysis

Iliopoulos¹

2016

Int J Appl Exp Math

View full text Add to dashboard Cite

In this paper a short overview on complex systems and their basic features, as well as the models and mathematical tools developed for their analysis, is given. This review is formed according to the related experience, activity and scientific interests of the author, namely focused on mainly in nonlinear time series analysis and statistics and their applications on different physical systems. In particular, rough outlines are given concerning the phenomenology of complex systems, e.g. far from equilibrium thermodynamics and Tsallis statistics, power law scaling, multi-fractality, low dimensional chaos, SOC, strange kinetics and anomalous diffusion and turbulent intermittency. In addition, a non-complete list of models, based on equations or agent based, is briefly described such as Kuramoto -Sivashinsky equation, cubic complex Ginzburg-Landau Equation, reaction-diffusion Equation, fractional equations, cellular automata, complex networks and artificial neural networks. A more extended review is provided concerning the nonlinear time series analysis complex systems, describing tools like mutual information, flatness coefficient, structure functions, Tsallis q-triplet, correlation dimension and Lyapunov exponents in the reconstructed phase space, which can provide valuable information for the complex system's dynamics. Finally, applications of nonlinear time series analysis on various physical systems, such as earthquakes, Earth's magnetosphere, solar plasma and solar wind, plastic deformation of materials, epilepsy, economical indices and DNA structure, are provided. Mini ReviewOpen Access Complex SystemsIn general, even though there is no precise definition of complex systems, a complex system can be thought of as a collection of nonlinearly interacting elements summing up as a whole which is characterized by novel large scale effects. These effects arise as emergent properties related with nonlinear-complex behavior, which is the most distinguishing feature of complex systems [1]. A nonexhaustive list of complex systems contains among others (in fact most systems can be considered as complex systems): geophysical processes (earthquakes), biophysics (brain dynamics, DNA), space plasmas (solar wind, solar flares, Earth's magnetosphere), plastic deformation of materials, economy (stock indices), socio-technical systems and many others. The aforementioned complex systems, even though they are completely different in many aspects (e.g. different elements), share common characteristics such as:1. They consist of a large number of interacting elements. This fact allows the description of these systems in two different hierarchical levels, namely microscopic and macroscopic. 2. Their subsystems and their interactions are nonlinear. 3. They exhibit emergent behavior, namely a self-organizing collective behavior, which is not predictable from the knowledge of the element's behavior. 4. These systems are open, namely they interact with their environment. This allows these systems to be driven to metastable state...

show abstract

Section: Artificial Neural Network (Anns)mentioning

confidence: 99%

Complex Systems: Phenomenology, Modeling, Analysis

Iliopoulos¹

2016

Int J Appl Exp Math

View full text Add to dashboard Cite

show abstract

“…Due to the random behavior of earthquakes generation, it may never be possible to ascertain the exact time, magnitude and location of the next damaging earthquake (Reyes et al 2012).…”

Section: Introductionmentioning

confidence: 99%

Pattern recognition of seismogenic nodes using Kohonen self-organizing map: example in west and south west of Alborz region in Iran

2017

View full text Add to dashboard Cite

“…The radial basis function neural network yielded more accurate and effective prediction re-sults than adaptive neural fuzzy, a kind of artificially intelligent method, in South Iran [13]. The ANN's earthquake prediction models were used in many other regions such as Greece [14], the northern Red Sea area [15], Chile [16,17] and East Anatolian fault region [18].…”

Section: Introductionmentioning

confidence: 99%

“…This work is based on the three previous works [11,16,17] and uses Recurrent Neural Network (RNN) to predict earthquakes in the northeast seismic region of China (NSRC in brief). This work will apply feature selection techniques to obtain a better set of features for NSRC from 16 seismicity indicators which were discussed by Panakkat&Adeli (2007) [11] [16].…”

Section: Introductionmentioning

confidence: 99%

Seismotectonics Considered Artificial Neural Network Earthquake Prediction in Northeast Seismic Region of China

Sheng¹,

Mu²,

Zhang³

et al. 2015

TOCIEJ

View full text Add to dashboard Cite

Abstract:It is well known that earthquakes are a regional event, strongly controlled by local geological structures and circumstances. Reducing the research area can reduce the influence of other irrelevant seismotectonics. A new sub regiondividing scheme, considering the seismotectonics influence, was applied for the artificial neural network (ANN) earthquake prediction model in the northeast seismic region of China (NSRC). The improved set of input parameters and prediction time duration are also discussed in this work. The new dividing scheme improved the prediction accuracy for different prediction time frames. Three different research regions were analyzed as an earthquake data source for the ANN model under different prediction time duration frames. The results show: (1) dividing the research region into smaller subregions can improve the prediction accuracies in NSRC, (2) larger research regions need shorter prediction durations to obtain better performance, (3) different areas have different sets of input parameters in NSRC, and (4) the dividing scheme, considering the seismotectonics frame of the region, yields better results.

show abstract

Neural networks to predict earthquakes in Chile

Cited by 160 publications

References 68 publications

Complex Systems: Phenomenology, Modeling, Analysis

Complex Systems: Phenomenology, Modeling, Analysis

Pattern recognition of seismogenic nodes using Kohonen self-organizing map: example in west and south west of Alborz region in Iran

Seismotectonics Considered Artificial Neural Network Earthquake Prediction in Northeast Seismic Region of China

Contact Info

Product

Resources

About