Magnitude of Earthquake Prediction Using Neural Network

This paper presents a new method for earthquake prediction. In the proposed method the variation of geomagnetic field declination, horizontal component and hourly relative humidity, temperature ground, rainy rate per day such as hum, rrr (the average of rainy hours time per day), and tgtg (temperature ground) are used to predict magnitude of earthquake 2 days before the occurrence of earthquake occurrence by using a neural network. As a case study, earth geomagnetic field measured data is used. The data are driven from the measurements collected in Tehran Geophysics Research Center in 1970 - 1976. Simulation results are very promising.