Application of neural network based on genetic algorithm in predicting magnitude of earthquake in North Tabriz Fault (NW Iran)

作者：Zakeri, Negar Sadat Soleimani^*; Pashazadeh, Saeid

来源：Current Science, 2015, 109(9): 1715-1722.

DOI：10.18520/v109/i9/1715-1722

• Artificial neural network
• earthquake magnitude
• genetic algorithm
• temporal seismicity features

Here we present an application of a supervised feed forward artificial neural network (ANN) that is trained on the basis of genetic algorithm (GA). The network model is used for predicting the magnitude of earthquakes in the North Tabriz Fault (NTF) Northwest Iran. The earthquake database was derived from the catalogues of both the International Institute of Earthquake Engineering and Seismicity of Iran and the Iranian Seismological Center. For this purpose, three temporal seismicity parameters were calculated using the ZMAP MATLAB toolbox. The performance of the artificial neural network (ANN) model was measured in terms of accuracy by a ten-fold cross-validation as 99.11%. Another evaluation method was predicting a case event that occurred on 11 August 2012 in Ahar-Varzeghan in Iran. Results showed that the ANN optimized with GA (ANNGA) learning optimization model is suitable and may be useful for predicting future earthquakes, especially in active seismologic regions.

• 出版日期2015-11-10