A neural-network model for earthquake occurrence

Changes in seismic activity patterns can occur during the process of preparation of large earthquakes, and such changes possibly are the most reliable long-term earthquake precursor examined to date. In the present work, seismicity rate variations in the Carpathian-Pannoman region, Hungary, and the Peloponnesos-Aegean area, Greece, have been used to develop neural network models for the prediction of the origin times of large (M>6.0) earthquakes. Three-layer feed-forward neural network models were constructed to analyse earthquake occurrences. Numerical experiments have been performed with the aim to find the optimum input set configuration which provides the best performance of a neural network. It was possible to reach sufficient training tolerance for the constructed networks (correspondence between predicted by the model outputs and known from experience outputs within the limits of given error thresholds) only when the input set contained seismicity rate values for different magnitude bands (when such data appeared representative enough) and also for more than one time intervals between large earthquakes. The specific structure of the network input generates the question of whether this configuration has some relationship to the physics of the strain accumulation and/or release process. The remarkably satisfactory performance of the constructed neural networks suggests the usefulness of the application of this tool in earthquake prediction problems.