Prediction of seismic P-wave velocity using machine learning

Dumke, Ines; Berndt, Christian

doi:https://doi.org/10.5194/se-10-1989-2019

Articles | Volume 10, issue 6

https://doi.org/10.5194/se-10-1989-2019

© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/se-10-1989-2019

© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 10, issue 6

Research article

|

15 Nov 2019

Research article |

| 15 Nov 2019

Prediction of seismic P-wave velocity using machine learning

Ines Dumke and Christian Berndt

Download

Final revised paper (published on 15 Nov 2019)
Preprint (discussion started on 04 Apr 2019)

Interactive discussion

Status: closed

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

- Printer-friendly version

- Supplement

RC1: 'Review of Dumke and Berndt', Taylor Lee, 07 May 2019
- AC1: 'Reply to reviewer 1 (Taylor Lee)', Christian Berndt, 09 Aug 2019
RC2: 'Comments on prediction of seismic p-wave velocity using machine learning', Anonymous Referee #2, 15 Jul 2019
- AC2: 'Reply to reviewer 2 (anonymous)', Christian Berndt, 09 Aug 2019

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision

AR by Christian Berndt on behalf of the Authors (09 Aug 2019) Manuscript

ED: Referee Nomination & Report Request started (10 Sep 2019) by Tarje Nissen-Meyer

RR by Taylor Lee (25 Sep 2019)

ED: Publish subject to technical corrections (02 Oct 2019) by Tarje Nissen-Meyer

ED: Publish subject to technical corrections (02 Oct 2019) by Federico Rossetti (Executive editor)

AR by Christian Berndt on behalf of the Authors (08 Oct 2019) Author's response Manuscript

Short summary

Knowing the velocity with which seismic waves travel through the top of the crust is important both for identifying anomalies, e.g. the presence of resources, and for geophysical data evaluation. Traditionally this has been done by using empirical functions. Here, we use machine learning to derive better seismic velocity estimates for the crust below the oceans. In most cases this methods performs better than empirical averages.