Seismic Inversion with Deep Neural Networks: a Feasibility Analysis
dc.contributor.author | Puzyrev, Vladimir | |
dc.contributor.author | Egorov, Anton | |
dc.contributor.author | Pirogova, Anastasia | |
dc.contributor.author | Elders, Christopher | |
dc.contributor.author | Otto, Claus | |
dc.date.accessioned | 2019-10-01T06:00:46Z | |
dc.date.available | 2019-10-01T06:00:46Z | |
dc.date.issued | 2019 | |
dc.identifier.citation | Puzyrev, V. and Egorov, A. and Pirogova, A. and Elders, C. and Otto, C. 2019. Seismic Inversion with Deep Neural Networks: a Feasibility Analysis. In: 81st EAGE Conference and Exhibition 2019, 3rd Jun 2019, London, UK. | |
dc.identifier.uri | http://hdl.handle.net/20.500.11937/76413 | |
dc.identifier.doi | 10.3997/2214-4609.201900765 | |
dc.description.abstract |
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. | |
dc.title | Seismic Inversion with Deep Neural Networks: a Feasibility Analysis | |
dc.type | Conference Paper | |
dcterms.source.conference | 81st EAGE Conference and Exhibition 2019 | |
dcterms.source.conference-start-date | 3 Jun 2019 | |
dcterms.source.conferencelocation | London, UK | |
dc.date.updated | 2019-10-01T06:00:46Z | |
curtin.department | School of Earth and Planetary Sciences (EPS) | |
curtin.accessStatus | Fulltext not available | |
curtin.faculty | Faculty of Science and Engineering | |
curtin.contributor.orcid | Puzyrev, Vladimir [0000-0002-0264-6126] | |
dcterms.source.conference-end-date | 6 Jun 2019 | |
curtin.contributor.scopusauthorid | Puzyrev, Vladimir [36020700900] |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |