Neural network approach to precursor signal detection

It is well known that the electromagnetic waves that radiate from the earth´s crust are useful for predicting earthquakes. We observe electromagnetic waves in the extremely low frequency (ELF) band of 223 Hz. These observed signals contain several undesired signals due to the events in the magnetosphere or the ionized layer, lightning radiation from the tropics, and so on. This paper proposes a multi-layer neural network for precursor signal detection. It is shown that the proposed method is useful for precursor signal detection.