Applicability of NDM-Net Simulated Data to Prestack Depth Migration

Applicability of NDM-Net Simulated Data to Prestack Depth Migration Full article

Conference

The 26th International Conference on Computational Science and Its Applications
30 Jun - 3 Jul 2026 , Braga, University of Minho

Journal

Lecture Notes in Computer Science
ISSN: 0302-9743 , E-ISSN: 1611-3349

Output data

Year: 2026, Volume: 16761, Pages: 58-69 Pages count : 12 DOI: 10.1007/978-3-032-30527-5_4

Authors

Gondyul Elena ¹ , Dubrovina Valeria ² , Lisitsa Vadim ¹ , Vishnevsky Dmitry ¹

Affiliations

1	Sobolev Institute of Mathematics SB RAS, Novosibirsk, 630090, Russia
2	LLC PetroTrace, Moscow, 115114, Russia

Funding (1)

Russian Science Foundation

22-11-00004-П

We present an analysis of the applicability of previously reported approach (NDM-net) to the construction of depth seismic images. The NDM-net allows us to simulate seismic data by combining finite differences with deep learning method. Coarse computational grids are used for the fast generation of inaccurate datasets. After that, the training dataset is simulated for a small number of shot points on fine grids. Then, the NDM-net is trained to map inaccurate data to accurate common shot gathers. Previously, we illustrated the high quality of the generated shot gathers. In this research, we applied the prestack depth migration to estimate the effect of the NDM-net numerical errors on the resulting seismic images.

Gondyul E. , Dubrovina V. , Lisitsa V. , Vishnevsky D.
Applicability of NDM-Net Simulated Data to Prestack Depth Migration
Lecture Notes in Computer Science. 2026. V.16761. P.58-69. DOI: 10.1007/978-3-032-30527-5_4 Scopus OpenAlex

Published online:

Jul 3, 2026

≡ Scopus:	2-s2.0-105044908558
≡ OpenAlex:	W7167092820