UNSUPERVISED LEARNING APPROACH TO DETECT OMPLEX NETWORKS OF EARTHQUAKE IN THE VICINITY OF IRAN

The results of the application of an unsupervised learning approach, Self Organizing Maps, to visualize the networks of earthquakes based on distance between two events. The knowledge can be extracted from the number of aftershocks and links in their networks. This paper is proposed a new self-organizing network model for growing networks of small earthquakes which can automatically determine the concentration of future earthquakes, it is shown strong correlation among earthquakes (M>4.5) that are very important to the stress transfers. It is demonstrated that the synthetic clustering in space and time of earthquakes is useful for seismic hazard assessment and intermediate-range earthquake forecasting.

کلیدواژه ها:

Self-Organize ، Neural Networks ، Clustering ، Hazard Assessment ، Orecasting