Numerical dispersion mitigation neural network with velocity model correction | Sciact - Система учета научной деятельности ИМ СО РАН

Numerical dispersion mitigation neural network with velocity model correction Научная публикация

Журнал

Computers and Geosciences
ISSN: 0098-3004

Вых. Данные

Год: 2025, Том: 196, Номер статьи : 105806, Страниц : 12 DOI: 10.1016/j.cageo.2024.105806

Ключевые слова

Seismic modeling U-net NDM-net Numerical dispersion Deep learning Digital earth model

Авторы

Gondyul E ¹ , Lisitsa V ¹ , Gadylshin K ¹ , Vishnevsky D ¹

Организации

1	Institute of Petroleum Geology and Geophysics SB RAS, 3 Koptug ave., Novosibirsk, 630090, Russia

Информация о финансировании (1)

Российский научный фонд

22-11-00004

The paper presents the Numerical Dispersion Mitigation neural network (NDM-net) to speed up seismic modeling. The idea of the NDM-net is to simulate the common-shot gathers for the entire set of source positions using a coarse grid. This solution can be computed fast but inaccurately. In addition, a small number of seismograms are generated using a fine enough grid to get an accurate solution. After that, the NDM-net is trained to map numerically polluted solutions to the accurate one and applied to correct the entire dataset. Previously, it was shown that NDM-net allows to speed up seismic modeling up to six times without noticeable loss of accuracy if the velocity model is fixed. In this paper, we focus on the applicability of NDM-net to the case where both the velocity model discretization and computational grid are corrected. We apply the NDM-net to suppress two types of numerical error: the numerical dispersion and the interface error.

Gondyul E. , Lisitsa V. , Gadylshin K. , Vishnevsky D.
Numerical dispersion mitigation neural network with velocity model correction
Computers and Geosciences. 2025. V.196. 105806 :1-12. DOI: 10.1016/j.cageo.2024.105806 РИНЦ

Поступила в редакцию:	19 янв. 2024 г.
Принята к публикации:	29 нояб. 2024 г.
Опубликована online:	9 дек. 2024 г.
Опубликована в печати:	12 дек. 2024 г.

РИНЦ:

80743181

Пока нет цитирований