Assessment of Arias Intensity of historical earthquakes using modified Mercalli intensities and artificial neural networks

Abstract

Abstract. This paper presents the development of a nonparametric forecast model based on artificial neural networks for the direct assessment of Arias Intensity corresponding to a historic earthquake using seismic intensity data. The neural models allow complex and nonlinear behaviour to be tracked. Application of this methodology on earthquakes with known instrumental data from Greece, showed that the artificial neural network forecast model have excellent data synthesis capability.

Sistema de monitoreo acelerográfico del Laboratorio de Ingeniería Sísmica

“…La Intensidad de Arias (IA) es una medida instrumental que sirve para determinar los daños que un terremoto provoca en las estructuras y edificaciones. El SMA-LIS muestra el cálculo de la IA para la componente norte-sur (NS) y este-oeste (EW) de los registros de aceleración que tuvieron valores superiores a los 2,0 cm/s2, así como el valor total de esta que corresponde a la sumatoria de componentes horizontales (Tselentis, 2011). La tabla 1 muestra los valores de la IA calculados para el mismo evento de la figura 7.…”

Relationship between isoseismal area and magnitude of historical earthquakes in Greece by a hybrid fuzzy neural network method

“…Suhadolc et al, 1988;Zahradnic, 1989;Sirovich, 1996) and compare it with observed data throughout a trial and error process. Recently, for non-linear modelling, neural networks and neuro-fuzzy modelling approaches have received a great deal of attention (Huang and Leung, 1999;Tselentis and Vladutu, 2010;Tselentis, 2011). Neuro-fuzzy modelling is concerned with the extraction of models from numerical data representing the behaviour of a system.…”

“…Since the relation between isoseismal area and seismic magnitude is strongly nonlinear, artificial neural networks (ANN) are particularly suited for treating macroseismic data (Tung et al, 1994;Davenport, 2004;Tselentis 2011). An ANN is an information processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information.…”

“…Tselentis and Danciu, 2008;Tselentis and Vladutu, 2010;Tselentis, 2011). Furthermore, the empirical relationships derived from this types of analyses are normally characterized by large scattering of the data due to the inherent uncertainty of the intensity parameter and by the uncertainty on the hypocentral depths.…”