Peak ground velocity evaluation by artificial neural network for west america region

  • Authors:

  • Ben-yu Liu;Liao-yuan Ye;Mei-ling Xiao;Sheng Miao

  • Affiliations:

  • Institute of Public Safety and Disaster Prevention, Yunnan University, Kunming, China;Institute of Public Safety and Disaster Prevention, Yunnan University, Kunming, China;Institute of Public Safety and Disaster Prevention, Yunnan University, Kunming, China;Institute of Public Safety and Disaster Prevention, Yunnan University, Kunming, China

  • Venue:
  • ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

With the Peak Ground Velocity 283 records in three dimensions, the velocity attenuation relationship with distance was discussed by neural network in this paper. The earthquake magnitude, epicenter distance, site intensity and site condition were considered as basic input element for the network. By using Bayesian Regularization Back Propagation Neural Networks (BRBPNN), the over-fitting phenomenon was reduced to some extent. The horizontal velocity was discussed. The PGV predicted by neural networks can simulate the detail difference with distance, while the PGV given by other traditional attenuation relationship only give a reduction relation with distance. The importance of each input factor was compared by the square weight of the input layer of the network. The order may be earthquake magnitude, epicenter distance and soil condition.