Prediction of seismic P-wave velocity using machine learning
<p>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 t...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2019-11-01
|
Series: | Solid Earth |
Online Access: | https://www.solid-earth.net/10/1989/2019/se-10-1989-2019.pdf |
Summary: | <p>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 heat flow, are not
taken into account. Here, we present a machine learning approach to predict
the overall trend of seismic P-wave velocity (<span class="inline-formula"><i>v</i><sub>p</sub></span>) as a function of
depth (<span class="inline-formula"><i>z</i></span>) for any marine location. Based on a training dataset consisting of
<span class="inline-formula"><i>v</i><sub>p</sub>(<i>z</i>)</span> data from 333 boreholes and 38 geological and spatial predictors
obtained from publicly 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 <span class="inline-formula"><i>v</i><sub>p</sub>(<i>z</i>)</span> data, which will allow the improvement of geophysical
models in areas lacking first-hand velocity data.</p> |
---|---|
ISSN: | 1869-9510 1869-9529 |