Layered neural networks based analysis of radon concentration and environmental parameters in earthquake prediction

Negarestani, Ali; Setayeshi, Saeed; Ghannadi-Maragheh, M; Akashe, B

doi:10.1016/s0265-931x(01)00165-5

Cited by 58 publications

(21 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The aim is to identify radon anomalies which might be caused by seismic events. The application of artificial neural networks (Negarestani et al, 2002(Negarestani et al, , 2003Torkar et al, 2010), regression and model trees Sikder & Munakata, 2009;Zmazek et al, 2003;Zmazek et al, 2006) and some other methods (Sikder & Munakata, 2009;Steinitz et al, 2003) have proven to be useful means of extracting radon anomalies caused by seismic events.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

Radon as an Earthquake Precursor – Methods for Detecting Anomalies

Gregorič¹,

Zmazek²,

Džeroski³

et al. 2012

Earthquake Research and Analysis - Statistical Studies, Observations and Planning

View full text Add to dashboard Cite

Section: Machine Learning Methodsmentioning

confidence: 99%

Radon as an Earthquake Precursor – Methods for Detecting Anomalies

Gregorič¹,

Zmazek²,

Džeroski³

et al. 2012

Earthquake Research and Analysis - Statistical Studies, Observations and Planning

View full text Add to dashboard Cite

“…ANN exists in many configurations and can provide methods to solve problems involving complex systems. The decisive property of the ANN can be used for earthquake prediction studies (Lakkos et al 1994;Adeli and Hung 1995;Adeli and Park 1998;Negarestani et al 2002;Sharma and Arora 2005;Kerh and Chu 2002;Panakkat and Adeli 2008). Arora and Sharma (1998) demonstrated the use of ANN for earthquake prediction.…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

“…Characteristics earthquake distribution makes use of cyclic behavior of earthquake occurrence when earthquakes occur in a cyclic manner in each section of the fault boundary as a result of seismic energy built up in locked tectonic plates and its subsequent release when the stored energy reaches a threshold as postulated in the elastic rebound theory (Reid 1906). When such studies could not capture the trends using classical statistics/probabilistic, artificial neural networks or the Artificial Intelligence has been used very often (Lakkos et al 1994;Adeli and Hung 1995;Adeli and Park 1998;Negarestani et al 2002;Sharma and Arora 2005;Kerh and Chu 2002;Panakkat and Adeli 2008). Panakkat and Adeli (2008) presented three neural network models for earthquake magnitude prediction using eight seismicity indicators or parameters: A feed-forward back propagation neural network, a recurrent neural network, and a radial basis function neural network.…”

mentioning

confidence: 99%

Cyclic behavior of seismogenic sources in India and use of ANN for its prediction

Sharma

Tyagi

2010

Nat Hazards

View full text Add to dashboard Cite

Endeavors to realistically model physical processes responsible for earthquake occurrence and sustained large uncertainties in the results have lead to the application of techniques like artificial neural network for estimation of rate/probability of earthquake occurrence in future. The earthquake occurrence in India has been re-visited and artificial neural networks have been applied to learn the cyclic behavior of seismicity in the independent seismogenic sources to predict their future trends. As a prerequisite, the whole country has been divided into 24 seismogenic sources for which the seismicity cycles were studied. Their cyclic behavior has been captured in form of four stages of earthquake occurrence and the future trends have been predicted using ANN. To validate the trained ANN model, testing has been carried out in two ways: first, by giving the samples that are not used in training (NT) and second, by giving the total samples (T). As a method of testing, standard errors and correlation coefficients between the network output patterns and observed patterns of the testing sample given were considered. The outcome of the ANN is used to interpret the future seismicity of each of the 24 seismogenic zones in terms of various stages of the future seismicity cycles.

show abstract

“…It has been proposed that radon concentration is sensitive to crustal stress/strain variations, and could reveal earthquake preparatory mechanisms [11]. The amplitude of the temporal variations of the soil gas radon concentration depends on the meteorological conditions [12][13][14][15][16], geological features in a given area, and distance from the epicenter of an earthquake [7,9]. Further studies are needed to differentiate the changes that are due to tectonic disturbances from other causes, and to determine the effect of the meteorological parameters, geological features and distance from the epicenter on the measured radon concentration.…”

Section: Introductionmentioning

confidence: 99%