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

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

Resultado de la investigación: Capítulo del libro/informe/acta de congresoContribución a la conferencia

Resumen

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.

Idioma originalInglés
Título de la publicación alojada81st EAGE Conference and Exhibition 2019
EditorialEAGE Publishing BV
ISBN (versión digital)9789462822894
EstadoPublicada - 3 jun 2019
Evento81st EAGE Conference and Exhibition 2019 - London, Reino Unido
Duración: 3 jun 20196 jun 2019

Serie de la publicación

Nombre81st EAGE Conference and Exhibition 2019

Conferencia

Conferencia81st EAGE Conference and Exhibition 2019
PaísReino Unido
CiudadLondon
Período3/06/196/06/19

Huella dactilar

learning
education
seismic data
Neural networks
seismic tomography
shot
arrivals
Deep learning
waveforms
velocity distribution
tomography
Tomography
inversions
costs
method
cycles
cost
Costs

Citar esto

Duque, L., Gutiérrez, G., Arias, C., Rüger, A., & Jaramillo, H. (2019). Automated velocity estimation by deep learning based seismic-to-velocity mapping. En 81st EAGE Conference and Exhibition 2019 (81st EAGE Conference and Exhibition 2019). EAGE Publishing BV.
Duque, L. ; Gutiérrez, G. ; Arias, C. ; Rüger, A. ; Jaramillo, H. / Automated velocity estimation by deep learning based seismic-to-velocity mapping. 81st EAGE Conference and Exhibition 2019. EAGE Publishing BV, 2019. (81st EAGE Conference and Exhibition 2019).
@inproceedings{1615cccee28b4fd9b30dc6c815967c4a,
title = "Automated velocity estimation by deep learning based seismic-to-velocity mapping",
abstract = "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.",
author = "L. Duque and G. Guti{\'e}rrez and C. Arias and A. R{\"u}ger and H. Jaramillo",
year = "2019",
month = "6",
day = "3",
language = "Ingl{\'e}s",
series = "81st EAGE Conference and Exhibition 2019",
publisher = "EAGE Publishing BV",
booktitle = "81st EAGE Conference and Exhibition 2019",

}

Duque, L, Gutiérrez, G, Arias, C, Rüger, A & Jaramillo, H 2019, Automated velocity estimation by deep learning based seismic-to-velocity mapping. En 81st EAGE Conference and Exhibition 2019. 81st EAGE Conference and Exhibition 2019, EAGE Publishing BV, London, Reino Unido, 3/06/19.

Automated velocity estimation by deep learning based seismic-to-velocity mapping. / Duque, L.; Gutiérrez, G.; Arias, C.; Rüger, A.; Jaramillo, H.

81st EAGE Conference and Exhibition 2019. EAGE Publishing BV, 2019. (81st EAGE Conference and Exhibition 2019).

Resultado de la investigación: Capítulo del libro/informe/acta de congresoContribución a la conferencia

TY - GEN

T1 - Automated velocity estimation by deep learning based seismic-to-velocity mapping

AU - Duque, L.

AU - Gutiérrez, G.

AU - Arias, C.

AU - Rüger, A.

AU - Jaramillo, H.

PY - 2019/6/3

Y1 - 2019/6/3

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85073599084&partnerID=8YFLogxK

M3 - Contribución a la conferencia

AN - SCOPUS:85073599084

T3 - 81st EAGE Conference and Exhibition 2019

BT - 81st EAGE Conference and Exhibition 2019

PB - EAGE Publishing BV

ER -

Duque L, Gutiérrez G, Arias C, Rüger A, Jaramillo H. Automated velocity estimation by deep learning based seismic-to-velocity mapping. En 81st EAGE Conference and Exhibition 2019. EAGE Publishing BV. 2019. (81st EAGE Conference and Exhibition 2019).