Localization of microseismic events using physics-informed neural networks for traveltime computation

Standard

Localization of microseismic events using physics-informed neural networks for traveltime computation. / Grubas, S.; Yaskevich, S.; Duchkov, A.

82nd EAGE Conference and Exhibition 2021. European Association of Geoscientists and Engineers, EAGE, 2021. стр. 5228-5232 (82nd EAGE Conference and Exhibition 2021; Том 7).

Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование

Harvard

Grubas, S, Yaskevich, S & Duchkov, A 2021, Localization of microseismic events using physics-informed neural networks for traveltime computation. в 82nd EAGE Conference and Exhibition 2021. 82nd EAGE Conference and Exhibition 2021, Том. 7, European Association of Geoscientists and Engineers, EAGE, стр. 5228-5232, 82nd EAGE Conference and Exhibition 2021, Amsterdam, Virtual, Нидерланды, 18.10.2021.

APA

Grubas, S., Yaskevich, S., & Duchkov, A. (2021). Localization of microseismic events using physics-informed neural networks for traveltime computation. в 82nd EAGE Conference and Exhibition 2021 (стр. 5228-5232). (82nd EAGE Conference and Exhibition 2021; Том 7). European Association of Geoscientists and Engineers, EAGE.

Vancouver

Grubas S, Yaskevich S , Duchkov A. Localization of microseismic events using physics-informed neural networks for traveltime computation. в 82nd EAGE Conference and Exhibition 2021. European Association of Geoscientists and Engineers, EAGE. 2021. стр. 5228-5232. (82nd EAGE Conference and Exhibition 2021).

Author

Grubas, S. ; Yaskevich, S. ; Duchkov, A. / Localization of microseismic events using physics-informed neural networks for traveltime computation. 82nd EAGE Conference and Exhibition 2021. European Association of Geoscientists and Engineers, EAGE, 2021. стр. 5228-5232 (82nd EAGE Conference and Exhibition 2021).

BibTeX

@inproceedings{6829666ad7b3479f834253b509311460,

title = "Localization of microseismic events using physics-informed neural networks for traveltime computation",

abstract = "The paper demonstrates an algorithm for using physics-informed neural networks in the workflow of microseismic data processing and more specifically the problem of localization of microseismic events. The proposed algorithm involves the use of a physics-informed neural network solution to the eikonal equation to calculate the traveltimes of the first arrivals. As a result, the network solution is compared with the observed arrival times to solve the inverse kinematic problem to determine the coordinates of the event locations. Using a synthetic 3D example, it was shown that the average absolute error of the arrival time misfit was less than 0.25 ms, and the average localization error did not exceed 4.5 meters.",

author = "S. Grubas and S. Yaskevich and A. Duchkov",

note = "Publisher Copyright: {\textcopyright} (2021) by the European Association of Geoscientists & Engineers (EAGE)All rights reserved.; 82nd EAGE Conference and Exhibition 2021 ; Conference date: 18-10-2021 Through 21-10-2021",

year = "2021",

language = "English",

series = "82nd EAGE Conference and Exhibition 2021",

publisher = "European Association of Geoscientists and Engineers, EAGE",

pages = "5228--5232",

booktitle = "82nd EAGE Conference and Exhibition 2021",

}

RIS

TY - GEN

T1 - Localization of microseismic events using physics-informed neural networks for traveltime computation

AU - Grubas, S.

AU - Yaskevich, S.

AU - Duchkov, A.

PY - 2021

Y1 - 2021

N2 - The paper demonstrates an algorithm for using physics-informed neural networks in the workflow of microseismic data processing and more specifically the problem of localization of microseismic events. The proposed algorithm involves the use of a physics-informed neural network solution to the eikonal equation to calculate the traveltimes of the first arrivals. As a result, the network solution is compared with the observed arrival times to solve the inverse kinematic problem to determine the coordinates of the event locations. Using a synthetic 3D example, it was shown that the average absolute error of the arrival time misfit was less than 0.25 ms, and the average localization error did not exceed 4.5 meters.

AB - The paper demonstrates an algorithm for using physics-informed neural networks in the workflow of microseismic data processing and more specifically the problem of localization of microseismic events. The proposed algorithm involves the use of a physics-informed neural network solution to the eikonal equation to calculate the traveltimes of the first arrivals. As a result, the network solution is compared with the observed arrival times to solve the inverse kinematic problem to determine the coordinates of the event locations. Using a synthetic 3D example, it was shown that the average absolute error of the arrival time misfit was less than 0.25 ms, and the average localization error did not exceed 4.5 meters.

UR - http://www.scopus.com/inward/record.url?scp=85127887862&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85127887862

T3 - 82nd EAGE Conference and Exhibition 2021

SP - 5228

EP - 5232

BT - 82nd EAGE Conference and Exhibition 2021

PB - European Association of Geoscientists and Engineers, EAGE

T2 - 82nd EAGE Conference and Exhibition 2021

Y2 - 18 October 2021 through 21 October 2021

ER -

ID: 35877804