Presentation 2021-10-14
A Consideration of Seismic Detection with Distributed Acoustic Sensor using Image Processing and Recognition
Takahiro Arioka, Kentaro Nakamura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Distributed acoustic sensor (DAS) observes the intensity and phase of Rayleigh backscattered light to measure the strain caused along with the optical fiber at intervals of several meters. In this article, we analyzed DAS measurement data performed from November 8 to December 2, 2019, using the dark fiber of the Sanriku offshore optical communication cable for the submarine earthquake and tsunami observation system owned by the Earthquake Research Institute, the University of Tokyo for seismic detection. We utilized an image processing (Hough transform) and recognition (Convolutional Neural Network) method using images obtained by converting the vibration data into a frequency-wavenumber spectrum. The accuracy was 94.7%.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Fiber Sensing / Distributed Acoustic Sensing / Seismic Observation / Hough transform / Convolutional Neural Network
Paper # OFT2021-42
Date of Issue 2021-10-07 (OFT)

Conference Information
Committee OFT
Conference Date 2021/10/14(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yuji Matsuura(Tohoku Univ.)
Vice Chair
Secretary (NTT)
Assistant Yukihiro Goto(NTT) / Minoru Takahashi(Fujikura)

Paper Information
Registration To Technical Committee on Optical Fiber Technology
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Consideration of Seismic Detection with Distributed Acoustic Sensor using Image Processing and Recognition
Sub Title (in English)
Keyword(1) Fiber Sensing
Keyword(2) Distributed Acoustic Sensing
Keyword(3) Seismic Observation
Keyword(4) Hough transform
Keyword(5) Convolutional Neural Network
1st Author's Name Takahiro Arioka
1st Author's Affiliation Tokyo Institute of Technology(Tokyo Tech)
2nd Author's Name Kentaro Nakamura
2nd Author's Affiliation Tokyo Institute of Technology(Tokyo Tech)
Date 2021-10-14
Paper # OFT2021-42
Volume (vol) vol.121
Number (no) OFT-199
Page pp.pp.79-84(OFT),
#Pages 6
Date of Issue 2021-10-07 (OFT)