Saved in:
Bibliographic Details
Main Authors: Moseley, Benjamin, Markham, Andrew, Nissen-Meyer, Tarje
Format: Preprint
Published: 2018
Subjects:
Online Access:https://arxiv.org/abs/1807.06873
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909227235147776
author Moseley, Benjamin
Markham, Andrew
Nissen-Meyer, Tarje
author_facet Moseley, Benjamin
Markham, Andrew
Nissen-Meyer, Tarje
contents We simulate the response of acoustic seismic waves in horizontally layered media using a deep neural network. In contrast to traditional finite-difference modelling techniques our network is able to directly approximate the recorded seismic response at multiple receiver locations in a single inference step, without needing to iteratively model the seismic wavefield through time. This results in an order of magnitude reduction in simulation time from the order of 1 s for FD modelling to the order of 0.1 s using our approach. Such a speed improvement could lead to real-time seismic simulation applications and benefit seismic inversion algorithms based on forward modelling, such as full waveform inversion. Our proof of concept deep neural network is trained using 50,000 synthetic examples of seismic waves propagating through different 2D horizontally layered velocity models. We discuss how our approach could be extended to arbitrary velocity models. Our deep neural network design is inspired by the WaveNet architecture used for speech synthesis. We also investigate using deep neural networks for simulating the full seismic wavefield and for carrying out seismic inversion directly.
format Preprint
id arxiv_https___arxiv_org_abs_1807_06873
institution arXiv
publishDate 2018
record_format arxiv
spellingShingle Fast approximate simulation of seismic waves with deep learning
Moseley, Benjamin
Markham, Andrew
Nissen-Meyer, Tarje
Geophysics
Computational Physics
We simulate the response of acoustic seismic waves in horizontally layered media using a deep neural network. In contrast to traditional finite-difference modelling techniques our network is able to directly approximate the recorded seismic response at multiple receiver locations in a single inference step, without needing to iteratively model the seismic wavefield through time. This results in an order of magnitude reduction in simulation time from the order of 1 s for FD modelling to the order of 0.1 s using our approach. Such a speed improvement could lead to real-time seismic simulation applications and benefit seismic inversion algorithms based on forward modelling, such as full waveform inversion. Our proof of concept deep neural network is trained using 50,000 synthetic examples of seismic waves propagating through different 2D horizontally layered velocity models. We discuss how our approach could be extended to arbitrary velocity models. Our deep neural network design is inspired by the WaveNet architecture used for speech synthesis. We also investigate using deep neural networks for simulating the full seismic wavefield and for carrying out seismic inversion directly.
title Fast approximate simulation of seismic waves with deep learning
topic Geophysics
Computational Physics
url https://arxiv.org/abs/1807.06873