Seismic Inversion with Deep Neural Networks: a Feasibility Analysis

We investigate deep learning approaches to inversion of a 1D model of the subsurface using synthetic surface seismic and VSP data. Several deep neural networks based on three different architectures are developed and tested. The matrix propagator technique is used to generate the synthetic data for...

Full description

Bibliographic Details
Main Authors: Puzyrev, Vladimir, Egorov, Anton, Pirogova, Anastasia, Elders, Christopher, Otto, Claus
Format: Conference Paper
Published: 2019
Online Access:http://hdl.handle.net/20.500.11937/76413
_version_ 1848763676792717312
author Puzyrev, Vladimir
Egorov, Anton
Pirogova, Anastasia
Elders, Christopher
Otto, Claus
author_facet Puzyrev, Vladimir
Egorov, Anton
Pirogova, Anastasia
Elders, Christopher
Otto, Claus
author_sort Puzyrev, Vladimir
building Curtin Institutional Repository
collection Online Access
description We investigate deep learning approaches to inversion of a 1D model of the subsurface using synthetic surface seismic and VSP data. Several deep neural networks based on three different architectures are developed and tested. The matrix propagator technique is used to generate the synthetic data for network training. The pre-trained deep neural networks can instantly predict velocity models from new data in a single step. The synthetic datasets used in training can be extended by adding random noise to the existing data, thus making the method closer to real-world conditions.
first_indexed 2025-11-14T11:07:15Z
format Conference Paper
id curtin-20.500.11937-76413
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:07:15Z
publishDate 2019
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-764132019-10-28T03:19:34Z Seismic Inversion with Deep Neural Networks: a Feasibility Analysis Puzyrev, Vladimir Egorov, Anton Pirogova, Anastasia Elders, Christopher Otto, Claus We investigate deep learning approaches to inversion of a 1D model of the subsurface using synthetic surface seismic and VSP data. Several deep neural networks based on three different architectures are developed and tested. The matrix propagator technique is used to generate the synthetic data for network training. The pre-trained deep neural networks can instantly predict velocity models from new data in a single step. The synthetic datasets used in training can be extended by adding random noise to the existing data, thus making the method closer to real-world conditions. 2019 Conference Paper http://hdl.handle.net/20.500.11937/76413 10.3997/2214-4609.201900765 restricted
spellingShingle Puzyrev, Vladimir
Egorov, Anton
Pirogova, Anastasia
Elders, Christopher
Otto, Claus
Seismic Inversion with Deep Neural Networks: a Feasibility Analysis
title Seismic Inversion with Deep Neural Networks: a Feasibility Analysis
title_full Seismic Inversion with Deep Neural Networks: a Feasibility Analysis
title_fullStr Seismic Inversion with Deep Neural Networks: a Feasibility Analysis
title_full_unstemmed Seismic Inversion with Deep Neural Networks: a Feasibility Analysis
title_short Seismic Inversion with Deep Neural Networks: a Feasibility Analysis
title_sort seismic inversion with deep neural networks: a feasibility analysis
url http://hdl.handle.net/20.500.11937/76413