Regional level forecasting of seismic energy release

Abstract

This article explores a new strategy for forecasting of earthquake energy release in the seismogenic zones of the world. A total of 41 active seismogenic zones are identified with the help of past seismicity data. The magnitudes of individual events occurred in each zone are converted into seismic energy using an empirical relation. The annual earthquake energy time series is constructed by adding the energy releases of all the events in a particular year. The technique of principal component analysis is employed for the regionalization of these seismogenic zones using seismic energy time series. The annual energy time series of seismogenic zones are decomposed into finite number of intrinsic mode functions (IMFs) using ensemble empirical mode decomposition technique. The periodicities of the IMFs and their contribution to the total variance of the earthquake energy release are examined. The artificial neural network technique is used for modeling and forecasting the energy-time series of seismogenic zones. The model is verified with an independent subset of data and validated using statistical parameters. The forecast of the annual earthquake energy release in each seismogenic zone is provided for the year 2015.