Statistical Prediction of Probable Seismic Hazard Zonation of Iran Using Self-organized Artificial Intelligence Model

Abstract

T he Iranian plateau has been known as one of the most seismically active regions of the world, and it frequent ly suffers dest ructive and cat astrophic earthquakes t hat cause heavy loss of human life and widespread damage. Earthquakes are regularly felt on all sides of the region. Prediction of the occurrence locat ion of t he fut ure earthquakes along wit h det ermining t he probabilit y percentage can be very useful in decreasing t he seismic risks. Determining predicted locations causes increasing attention to design, seismic rehabilit ation and evaluating t he reliability of t he present structures in these locations. No exact met hod has been approved for predict ing fut ure eart hquake parameters yet. In recent years, more at t ention is paid t o t he earthquake magnitude prediction, but no st udy has been done in t he field of probable eart hquake occurrence hazard zonation. In this st udy, locations of future earthquakes in Iran were predict ed by self-organized artificial neural networks (ANN). Then probable seismic risk zoning map was drawn by t he st at istical analyses, and t he result s indicated t hat t he maps ca n properly predict fut ure seismic event s.