Geophysical model generation with generative adversarial networks
Abstract With the rapid development of deep learning technologies, data-driven methods have become one of the main research focuses in geophysical inversion. Applications of various neural network architectures to the inversion of seismic, electromagnetic, gravity and other types of data confirm the...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-08-01
|
| Series: | Geoscience Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40562-022-00241-y |
| _version_ | 1811297546603069440 |
|---|---|
| author | Vladimir Puzyrev Tristan Salles Greg Surma Chris Elders |
| author_facet | Vladimir Puzyrev Tristan Salles Greg Surma Chris Elders |
| author_sort | Vladimir Puzyrev |
| collection | DOAJ |
| description | Abstract With the rapid development of deep learning technologies, data-driven methods have become one of the main research focuses in geophysical inversion. Applications of various neural network architectures to the inversion of seismic, electromagnetic, gravity and other types of data confirm the potential of these methods in real-time parameter estimation without dependence on the starting subsurface model. At the same time, deep learning methods require large training datasets which are often difficult to acquire. In this paper, we present a generator of 2D subsurface models based on deep generative adversarial networks. Several networks are trained separately on realistic density and stratigraphy models to reach a sufficient degree of accuracy in generation of new highly detailed and varied models in real-time. This allows for creation of large synthetic training datasets in a cost-effective manner, thus facilitating the development of better deep learning algorithms for real-time inversion and interpretation. |
| first_indexed | 2024-04-13T06:06:01Z |
| format | Article |
| id | doaj.art-54c3d0a47aac462787f821c78d9d0bcf |
| institution | Directory Open Access Journal |
| issn | 2196-4092 |
| language | English |
| last_indexed | 2024-04-13T06:06:01Z |
| publishDate | 2022-08-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Geoscience Letters |
| spelling | doaj.art-54c3d0a47aac462787f821c78d9d0bcf2022-12-22T02:59:15ZengSpringerOpenGeoscience Letters2196-40922022-08-01911910.1186/s40562-022-00241-yGeophysical model generation with generative adversarial networksVladimir Puzyrev0Tristan Salles1Greg Surma2Chris Elders3School of Earth and Planetary Sciences and Curtin University Oil and Gas Innovation Centre, Curtin UniversitySchool of Geosciences, The University of SydneyPolish-Japanese Academy of Information TechnologySchool of Earth and Planetary Sciences and Curtin University Oil and Gas Innovation Centre, Curtin UniversityAbstract With the rapid development of deep learning technologies, data-driven methods have become one of the main research focuses in geophysical inversion. Applications of various neural network architectures to the inversion of seismic, electromagnetic, gravity and other types of data confirm the potential of these methods in real-time parameter estimation without dependence on the starting subsurface model. At the same time, deep learning methods require large training datasets which are often difficult to acquire. In this paper, we present a generator of 2D subsurface models based on deep generative adversarial networks. Several networks are trained separately on realistic density and stratigraphy models to reach a sufficient degree of accuracy in generation of new highly detailed and varied models in real-time. This allows for creation of large synthetic training datasets in a cost-effective manner, thus facilitating the development of better deep learning algorithms for real-time inversion and interpretation.https://doi.org/10.1186/s40562-022-00241-yConvolutional neural networkGenerative adversarial networkDeep learningInverse problem |
| spellingShingle | Vladimir Puzyrev Tristan Salles Greg Surma Chris Elders Geophysical model generation with generative adversarial networks Geoscience Letters Convolutional neural network Generative adversarial network Deep learning Inverse problem |
| title | Geophysical model generation with generative adversarial networks |
| title_full | Geophysical model generation with generative adversarial networks |
| title_fullStr | Geophysical model generation with generative adversarial networks |
| title_full_unstemmed | Geophysical model generation with generative adversarial networks |
| title_short | Geophysical model generation with generative adversarial networks |
| title_sort | geophysical model generation with generative adversarial networks |
| topic | Convolutional neural network Generative adversarial network Deep learning Inverse problem |
| url | https://doi.org/10.1186/s40562-022-00241-y |
| work_keys_str_mv | AT vladimirpuzyrev geophysicalmodelgenerationwithgenerativeadversarialnetworks AT tristansalles geophysicalmodelgenerationwithgenerativeadversarialnetworks AT gregsurma geophysicalmodelgenerationwithgenerativeadversarialnetworks AT chriselders geophysicalmodelgenerationwithgenerativeadversarialnetworks |