The prediction of the earthquake based on neutral networks

In order to predict the magnitude of the serious earthquake in future time in a seismic area, the probabilistic neutral network was established depending on mathematically computed parameters known as seismicity indicators. The indicators concerned are the time elapsed during a especial number (n) of critical seismic events before the day in question, the inclination of the Gutenberg_Richter inverse power rule curve for the n events, the average deviation relative to the regression limit depended on the Gutenberg_Richter inverse power rule for the n events, the mean magnitude of the last n events, the variable between the observed maximum magnitude for the last n events and that expected based on the Gutenberg_Richter relationship named the magnitude deficit, the rate of square root of seismic energy released in the procession of the n events, the average time between characteristic events, and the coefficient of variation of the average time. The PNN model can be used to predict earthquakes with magnitude effectively.