Article Per Year (5 Year)
p-Index From 2019 - 2024
0
P-Index
This Author published in this journals
All Journal Journal of Engineering and Technological Sciences
Rachmat Sule
Department of Geophysical Engineering, Institute of Technology Bandung
Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Comparing Models GRM, Refraction Tomography and Neural Network to Analyze Shallow Landslide Sompotan, Armstrong F.; Pasasa, Linus A.; Sule, Rachmat
Journal of Engineering and Technological Sciences Vol 43, No 3 (2011)
Publisher : ITB Journal Publisher, LPPM ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (397.02 KB) | DOI: 10.5614/itbj.eng.sci.2011.43.3.1

Abstract

Detailed  investigations  of  landslides  are  essential  to  understand fundamental landslide  mechanisms.  Seismic  refraction  method  has been  proven as a useful geophysical tool for investigating shallow landslides. The objective of this  study  is  to  introduce  a  new  workflow  using  neural  network  in  analyzing seismic  refraction  data  and  to  compare  the  result  with  some  methods;  that  are general  reciprocal  method  (GRM)  and  refraction  tomography.  The  GRM  is effective when the velocity structure is relatively simple and refractors are gently dipping.  Refraction  tomography  is  capable  of  modeling  the  complex  velocity structures  of  landslides.  Neural  network  is  found  to  be  more  potential  in application  especially  in  time  consuming  and  complicated  numerical  methods. Neural network  seem to have the  ability to establish a relationship between an input  and  output  space  for  mapping  seismic  velocity.  Therefore,  we  made  a preliminary attempt to evaluate the applicability of neural network to determine velocity  and  elevation  of  subsurface  synthetic  models  corresponding  to  arrival times.  The  training  and  testing  process  of  the  neural  network  is  successfully accomplished  using  the  synthetic  data.  Furthermore,  we  evaluated  the  neural network  using  observed  data.  The  result  of  the  evaluation  indicates  that  the neural  network  can  compute  velocity  and  elevation  corresponding  to  arrival times. The similarity of those models shows the success of neural network as a new alternative in seismic refraction data interpretation.
Co-Authors Armstrong F. Sompotan Linus Pasasa