Journal cover Journal topic
Solid Earth An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 2.380 IF 2.380
  • IF 5-year value: 3.147 IF 5-year
    3.147
  • CiteScore value: 3.06 CiteScore
    3.06
  • SNIP value: 1.335 SNIP 1.335
  • IPP value: 2.81 IPP 2.81
  • SJR value: 0.779 SJR 0.779
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 32 Scimago H
    index 32
  • h5-index value: 31 h5-index 31
Discussion papers
https://doi.org/10.5194/se-2019-58
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/se-2019-58
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Research article 04 Apr 2019

Research article | 04 Apr 2019

Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Solid Earth (SE).

Prediction of seismic p-wave velocity using machine learning

Ines Dumke and Christian Berndt Ines Dumke and Christian Berndt
  • GEOMAR Helmholtz Centre for Ocean Research Kiel, Kiel, Germany

Abstract. Measurements of seismic velocity as a function of depth are generally restricted to borehole locations and are therefore sparse in the world's oceans. Consequently, in the absence of measurements or suitable seismic data, studies requiring knowledge of seismic velocities often obtain these from simple empirical relationships. However, empirically derived velocities may be inaccurate, as they are typically limited to certain geological settings, and other parameters potentially influencing seismic velocities, such as depth to basement, crustal age, or heatflow, are not taken into account. Here, we present a machine learning approach to predict seismic p-wave velocity (vp) as a function of depth (z) for any marine location. Based on a training dataset consisting of vp(z) data from 333 boreholes and 38 geological and spatial predictors obtained from publically available global datasets, a prediction model was created using the Random Forests method. In 60 % of the tested locations, the predicted seismic velocities were superior to those calculated empirically. The results indicate a promising potential for global prediction of vp(z) data, which will allow improving geophysical models in areas lacking first-hand velocity data.

Ines Dumke and Christian Berndt
Interactive discussion
Status: final response (author comments only)
Status: final response (author comments only)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Login for Authors/Topical Editors] [Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement
Ines Dumke and Christian Berndt
Ines Dumke and Christian Berndt
Viewed  
Total article views: 321 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
262 58 1 321 0 1
  • HTML: 262
  • PDF: 58
  • XML: 1
  • Total: 321
  • BibTeX: 0
  • EndNote: 1
Views and downloads (calculated since 04 Apr 2019)
Cumulative views and downloads (calculated since 04 Apr 2019)
Viewed (geographical distribution)  
Total article views: 222 (including HTML, PDF, and XML) Thereof 222 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Cited  
Saved  
No saved metrics found.
Discussed  
Latest update: 19 Jul 2019
Publications Copernicus
Download
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, but also 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.
Knowing the velocity with which seismic waves travel through the top of the crust is important...
Citation