Backpropagation neural network as earthquake early warning tool using a new modified elementary Levenberg–Marquardt Algorithm to minimise backpropagation errors

Lin, Jyh-Woei; Chao, Chun-Tang; Chiou, Juing-Shian

doi:https://doi.org/10.5194/gi-7-235-2018

Articles | Volume 7, issue 3

https://doi.org/10.5194/gi-7-235-2018

© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gi-7-235-2018

© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 7, issue 3

Research article

|

16 Aug 2018

Research article |

| 16 Aug 2018

Backpropagation neural network as earthquake early warning tool using a new modified elementary Levenberg–Marquardt Algorithm to minimise backpropagation errors

Jyh-Woei Lin, Chun-Tang Chao, and Juing-Shian Chiou

Download

Final revised paper (published on 16 Aug 2018)
Preprint (discussion started on 09 May 2018)

Interactive discussion

Status: closed

AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment

- Printer-friendly version

- Supplement

RC1: 'comments to the authors', Anonymous Referee #1, 20 May 2018
- AC1: 'Respond to Reviewer#1', Jyh-Woei Lin, 22 May 2018
  - RC2: 'I recommend this paper to publication', Anonymous Referee #1, 23 May 2018
    - RC5: 'I suggest citing the Web and attached ducument for Free Field Strong Earthquake Observation Network', Anonymous Referee #1, 08 Jun 2018
      - AC4: 'reply', Jyh-Woei Lin, 08 Jun 2018
        
        RC6: 'It can be accepted, could you let me know your comments about AI', Anonymous Referee #1, 09 Jun 2018
        
        AC5: 'reply', Jyh-Woei Lin, 10 Jun 2018
        
        RC8: 'Thank', Anonymous Referee #1, 12 Jun 2018
RC3: 'After addressing my following questions, the paper can be accepted for publication.', Anonymous Referee #2, 25 May 2018
- AC2: 'Respond to Reviewer#2', Jyh-Woei Lin, 26 May 2018
  - RC4: 'accepted for publication!', Anonymous Referee #2, 26 May 2018
AC3: 'final revise paper after addressing two reviewers', Jyh-Woei Lin, 29 May 2018
- RC7: 'Congratulation to authors.', Anonymous Referee #2, 10 Jun 2018
AC6: 'A Document about AI, AI is very hot.', Jyh-Woei Lin, 12 Jun 2018
AC7: 'Final responds for two reviewere', Jyh-Woei Lin, 05 Jul 2018
EC1: 'Independent opinion of Dr. Matthias Meyer', Lev Eppelbaum, 04 Aug 2018
- AC8: 'reply', Jyh-Woei Lin, 04 Aug 2018

Short summary

This BPNN approach with two alarms was well suited, and it was not necessary to consider the problems of characterising the wave phases and pre-processing, as stated previously. Furthermore, BPNN is a mature technology, which is expected to develop rapidly in the future, and does not require complex hardware. Determining an initial location and magnitude of the event was not necessary for this technique. An existing seismic monitoring network can be used.