Automated velocity estimation by deep learning based seismic-to-velocity mapping

Duque L.; Gutiérrez G.; Arias C.; Rüger A.; Jaramillo H.

dc.creator	Duque L.
dc.creator	Gutiérrez G.
dc.creator	Arias C.
dc.creator	Rüger A.
dc.creator	Jaramillo H.
dc.date	2019
dc.date.accessioned	2020-04-29T14:53:58Z
dc.date.available	2020-04-29T14:53:58Z
dc.identifier.isbn	9789462822894
dc.identifier.uri	http://hdl.handle.net/11407/5775
dc.description	We propose a novel method for velocity estimation that leverages the newest advances in Deep Learning (DL) technology. This method is fully automatic and maps seismic shot-domain data to corresponding depth-domain velocity fields via two neural networks. Our new method is conceptually different from conventional methods such as seismic tomography or Full Waveform Inversion (FWI) that minimize a fixed objective function. Here, a system of neural networks automatically and continuously learns an objective function while training the seismic-to-velocity mapping. The newly introduced method avoids many of the drawbacks of conventional velocity estimation techniques, such as dependence on initial models or cycle-skipping. It uses the full seismic wavefield and avoids picking of first-arrival traveltimes. The system needs to be trained with hundreds or thousands of examples of seismic data paired with their corresponding velocity models relevant for the current project. Training the system is the main computationally demanding step and produces a mapping function that contains the seismic know-how for the presumed geologic setting. The computational cost of the subsequent estimation of velocity from new seismic data is negligent. Our first tests on complex two-dimensional synthetic data produce impressive results, underlining the potential of DL for velocity analysis. © 81st EAGE Conference and Exhibition 2019. All rights reserved.
dc.language.iso	eng
dc.publisher	EAGE Publishing BV
dc.relation.isversionof	https://www.scopus.com/inward/record.uri?eid=2-s2.0-85073599084&partnerID=40&md5=f022ea7847272e7a984047f35b0b574a
dc.source	81st EAGE Conference and Exhibition 2019
dc.title	Automated velocity estimation by deep learning based seismic-to-velocity mapping
dc.type	Conference Paper	eng
dc.rights.accessrights	info:eu-repo/semantics/restrictedAccess
dc.publisher.program	Facultad de Ciencias Básicas
dc.publisher.faculty	Facultad de Ciencias Básicas
dc.affiliation	Duque, L., Instituto Tecnológico Metropolitano, Colombia; Gutiérrez, G., MOONBLOCK; Arias, C., Instituto Tecnológico Metropolitano, Colombia; Rüger, A., Colorado School of Mines, United States; Jaramillo, H., University of Medellín, Colombia
dc.relation.references	Aminzadeh, F., Jean, B., Kunz, T., 3-D salt and overthrust models (1997) Society of Exploration Geophysicists
dc.relation.references	Araya-Polo, M., Jennings, J., Adler, A., Dahlke, T., Deep-learning tomography (2018) The Leading Edge, 37 (1), pp. 58-66. , https://doi.org/10.1190/tle37010058.1
dc.relation.references	Huang, Z., Shimeld, J., Williamson, M., Katsube, J., Permeability prediction with artificial neural network modeling in the Venture gas field, offshore eastern Canada (1996) Geophysics, 61 (2), pp. 422-436. , https://doi.org/10.1190/1.1443970
dc.relation.references	Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A., (2016) Image-to-Image Translation with Conditional Adversarial Networks, , arXiv preprint
dc.relation.references	Michelsanti, D., Tan, Z.H., (2017) Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification, , arXiv preprint
dc.relation.references	Murat, M.E., Rudman, A.J., Automated first arrival picking: A neural network approach (1992) Geophysical Prospecting, 40 (6), pp. 587-604. , https://doi.org/10.1111/j.13652478.1992.tb00543.x
dc.relation.references	Röth, G., Tarantola, A., Neural networks and inversion of seismic data (1994) Journal of Geophysical Research: Solid Earth, 99 (B4), pp. 6753-6768. , https://doi.org/10.1029/93JB01563
dc.type.version	info:eu-repo/semantics/publishedVersion
dc.type.driver	info:eu-repo/semantics/article

Ficheros en el ítem

Ficheros	Tamaño	Formato	Ver
No hay ficheros asociados a este ítem.

Este ítem aparece en la(s) siguiente(s) colección(ones)

Indexados Scopus [1632]

Mostrar el registro sencillo del ítem