التعامل مع التعقيدات الزلزالية باستخدام التقنيات الحاسوبية العصبية وتحديد قدرها الزلزالي ببعض المتوقعات منخفضة المقارنة

Abstract

Earthquake, being one of the most hazardous geophysical events, has fascinated the scientists all over the globe to investigate an efficient predictive methodology. In India, earthquake is not a rare event. Purpose of the present paper is to view the earthquake as a complex system and then to estimate the magnitude of earthquake over Indian subcontinent using artificial neural network with backpropagation learning. The day, month, and year of occurrence of the earthquake, latitude of the place, and the longitude of the place are considered as the predictor variables. After considering various sizes of the hidden layer, it has been found that artificial neural network in the form of multilayer perceptron with two hidden nodes and sigmoid nonlinearity can be used to anticipate the magnitude of earthquake over Indian subcontinent. The paper concludes with an outline for future work.

Principal component analysis and neurocomputing-based models for total ozone concentration over different urban regions of India

“…Relevance of the said predictors in prediction of TO time series in daily scale has been discussed thoroughly in Chattopadhyay and Chattopadhyay (2009a). The correlation matrices for the said variables are found to be the following:…”

“…In the hidden layer, we have taken four nodes and for this number of hidden nodes the ANN remains free from the problem of over parameterization. To avoid the asymptotic effect, the data are standardized to [0,1] as follows (Chattopadhyay and Chattopadhyay 2009a):…”

“…The present paper deviates from earlier studies on TO over India in the following aspects: (1) instead of trend analysis (Sahoo et al 2005;Patil and Revadekar 2009), this study has intended to model TO over various urban regions of India through artificial neural network; (2) Chattopadhyay and Chattopadhyay (2009b) developed predictive model for TO over Kolkata, India in autoregressive manner. However, the present study has developed artificial neural network model for TO in multivariate manner, and (3) in the earlier multivariate predictive models for TO in India, the independent variables were selected based on their correlations with TO (e.g., Chattopadhyay and Chattopadhyay 2009a). However, in the present study, we have executed principal component analysis to select independent variables.…”

Estimating the Probability of Earthquake Magnitude Between Mw = 4 and Mw = 5 for Turkey

“…This method was tested within different years with wide time and location perspective. Chattopadhyays [10] predicted the magnitude of earthquake over Indian subcontinent benefitting artificial neural network with backpropagation learning. ANN model established by Gul and Guneri [11] for the earthquake casualty estimation, which takes into account earthquake time, earthquake magnitude, and population frequency as the parameters for training network in Turkey from 1975.…”

Determining the best set of seismicity indicators to predict earthquakes. Two case studies: Chile and the Iberian Peninsula

“…Another hazardous area, India, has been subjected to study by means of ANN's [9]. After evaluating several architectures, the authors concluded that the best one must include two hidden layers and the sigmoid transfer function.…”