Vertical array records during 1995 Hyogoken-Nambu earthquake by Kobe city, KEPCO and other organizations

Author(s):  
Y Iwasaki
Keyword(s):  
2002 ◽  
Vol 6 (1) ◽  
pp. 1-15 ◽  
Author(s):  
SHIRO TAKADA∗ ◽  
NEMAT HASSANI† ◽  
KATSUMI FUKUDA‡
Keyword(s):  

2011 ◽  
Vol 6 (1) ◽  
pp. 564 ◽  
Author(s):  
Akrajas Ali Umar ◽  
Mohd Yusri Abd Rahman ◽  
Rika Taslim ◽  
Muhamad Mat Salleh ◽  
Munetaka Oyama

2013 ◽  
Vol 134 (3) ◽  
pp. 2446-2461 ◽  
Author(s):  
Delphine Mathias ◽  
Aaron M. Thode ◽  
Jan Straley ◽  
Russel D. Andrews

2016 ◽  
Vol 90 (2) ◽  
pp. 120-124 ◽  
Author(s):  
Junji TAKIGUCHI ◽  
Kenjiro OKIMURA ◽  
Mariko ISHI ◽  
Kayoko OKAMURA ◽  
Hirokazu SAKAMOTO ◽  
...  

Author(s):  
Daniel Roten ◽  
Kim B. Olsen

ABSTRACT We use deep learning to predict surface-to-borehole Fourier amplification functions (AFs) from discretized shear-wave velocity profiles. Specifically, we train a fully connected neural network and a convolutional neural network using mean AFs observed at ∼600 KiK-net vertical array sites. Compared with predictions based on theoretical SH 1D amplifications, the neural network (NN) results in up to 50% reduction of the mean squared log error between predictions and observations at sites not used for training. In the future, NNs may lead to a purely data-driven prediction of site response that is independent of proxies or simplifying assumptions.


Sign in / Sign up

Export Citation Format

Share Document