A neural network based methodology to predict site-specific spectral acceleration values

A general neural network based methodology that has the potential to replace the computationally-intensive site-specific seismic analysis of structures is proposed in this paper. The basic framework of the methodology consists of a feed forward back propagation neural network algorithm with one hidden layer to represent the seismic potential of a region and soil amplification effects. The methodology is implemented and verified with parameters corresponding to Delhi city in India. For this purpose, strong ground motions are generated at bedrock level for a chosen site in Delhi due to earthquakes considered to originate from the central seismic gap of the Himalayan belt using necessary geological as well as geotechnical data. Surface level ground motions and corresponding site-specific response spectra are obtained by using a one-dimensional equivalent linear wave propagation model. Spectral acceleration values are considered as a target parameter to verify the performance of the methodology. Numerical studies carried out to validate the proposed methodology show that the errors in predicted spectral acceleration values are within acceptable limits for design purposes. The methodology is general in the sense that it can be applied to other seismically vulnerable regions and also can be updated by including more parameters depending on the state-of-the-art in the subject.

Investigation on regional attenuation of Vrancea (Romania) intermediate-depth earthquakes

This paper aims at investigating possible regional attenuation patterns in the case of Vrancea（Romania） intermediate-depth earthquakes.Almost 500 pairs of horizontal components recorded during 13 intermediate-depth Vrancea earthquakes are employed in order to evaluate the regional attenuation patterns.The recordings are grouped according to the azimuth with regard to the Vrancea seismic source and subsequently,Q models are computed for each azimuthal zone assuming similar geometrical spreading.Moreover,the local soil amplification which was disregarded in a previous analysis performed for Vrancea intermediate-depth earthquakes is now clearly evaluated.The results show minor differences between the four regions situated in front of the Carpathian Mountains and considerable differences in attenuation of seismic waves between the forearc and backarc regions（with regard to the Carpathian Mountains）.Consequently,an average Q model of the type Q（f） = 115×f^1.25 is obtained for the four forearc regions,while a separate Q model of the type Q（f） = 70×f^0.90 is computed for the backarc region.These results highlight the need to evaluate the seismic hazard of Romania by using ground motion models which take into account the different attenuation between the forearc/backarc regions.