Search

Triaxial acelerografic data related to replies of Armenia earthquake in Colombia (25-01-99, Mw=6.2) have been used to determine the transfer function of Soft Formation I Hard Rock in two sites of Armenia city by using a neuronal network. This network was trained with spectral data of HARD ROCK as input parameter and spectral data of Soft Formation as output parameter for N-S and Z components. The error of the neuronal network respect to the training data was of 0,01%. It allowed to simulate spectral data for the E-W component of registries with a quadratic mean error minor to 8%. It was possible to observe that with these few records used, the neuronal networks facilitate the process of deduction of transference functions linear and not-linear oriented to the dynamic ground evaluation.Se han utilizado datos acelerográficos triaxiales relacionados con replicas del terremoto de Armenia, Colombia (25-01-99, Mw = 6.2), para determinar la función de transferencia Formaciones blandas/Roca dura en dos sitios de la ciudad de Armenia mediante el uso de una red neuronal. Dicha red fue entrenada con datos espectrales de Roca dura como parámetro de entrada y de Formaciones blandas como parámetro de salida para las componentes N-S y Z. EI comportamiento de la red neuronal respecto a los datos de entrenamiento fue 0.01 %. Y permitió simular datos espectrales para la componente E-W de los mismos registros con un error medio cuadrático menor que 8%. Se pudo observar que a pesar de los pocos registros utilizados, las redes neuronales facilitan el proceso de deducción de funciones de transferencia lineales y no lineales orientadas a la evaluación dinámica de suelos.

Triaxial acelerografic data related to replies of Armenia earthquake in Colombia (25-01-99, Mw=6.2) have been used to determine the transfer function of Soft Formation / Hard Rock in two sites of Armenia city by using a neuronal network. This network was trained with spectral data of HARD ROCK as input parameter and spectral data of Soft Formation as output parameter for N-S and Z components. The error of the neuronal network respect to the training data was of 0,01%. It allowed to simulate spectral data for the E-W component of registries with a quadratic mean error minor to 8%. It was possible to observe that with these few records used, the neuronal networks facilitate the process of deduction of transference functions linear and not-linear oriented to the dynamic ground evaluation. [ABSTRACT FROM AUTHOR]

A letter to the editor is presented about the lithospheric structure of the Latin American and Caribbean territory.