Seismic-wave traveltime computation by supervised and unsupervised training of artificial neural networks

Serafim Grubas

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

Computation of seismic-wave traveltimes is used in seismic imaging procedures such as Kirchhoff migration. For realistic applications, one has to precompute large traveltime tables (for all sources, receivers, and imaging points). This implies massive computations as well as storage of large files with these traveltime tables. One of the popular traveltime computation methods is a numerical solution of the eikonal equation. In this paper, I addressed the idea of using artificial neural networks for optimizing traveltime computations and using traveltimes in Kirchhoff migration. First, I used supervised learning for approximating and compressing the traveltime tables by artificial neural networks. Second, I used unsupervised learning for solving the eikonal equation. I used fully-connected neural networks for solving both problems. For the first problem, I used traveltimes precomputed on a coarse for supervised training of a neural network. Synthetic tests show that this neural-network approximation provides great compression of the traveltime tables (102-105 times) with reasonable accuracy of predicting traveltimes on a fine imaging grid. Overall, the use of artificial neural networks results in a speed-up of the Kirchhoff migration operator in two applications: microseismic event localization (by three times) and reflection-seismic migration (by four times). The second problem was to use artificial neural networks for solving the eikonal equation. The main result was a special design of a loss function that ensures solution of the eikonal equation and allows for neural-network unsupervised training. In the synthetic test, the neural network was successfully used for solving the eikonal equation (forward problem) with slightly better accuracy compared to the first-order Fast Sweeping Method. I also demonstrated that neural networks could also solve the inverse problem - back propagate traveltimes from the observation surface into the subsurface. Such inversion was illustrated by successfully solving the problem of microseismic event localization.

Original languageEnglish
Title of host publicationSociety of Petroleum Engineers - SPE Annual Technical Conference and Exhibition 2020, ATCE 2020
PublisherSociety of Petroleum Engineers (SPE)
ISBN (Electronic)9781613997239
Publication statusPublished - 2020
EventSPE Annual Technical Conference and Exhibition 2020, ATCE 2020 - Virtual, Online
Duration: 26 Oct 202029 Oct 2020

Publication series

NameProceedings - SPE Annual Technical Conference and Exhibition
Volume2020-October

Conference

ConferenceSPE Annual Technical Conference and Exhibition 2020, ATCE 2020
CityVirtual, Online
Period26.10.202029.10.2020

Fingerprint Dive into the research topics of 'Seismic-wave traveltime computation by supervised and unsupervised training of artificial neural networks'. Together they form a unique fingerprint.

Cite this