Experience of applying convolutional neural networks to inverse problems of seismic exploration

V. I. Golubev; M. I. Anisimov

Geodesic

Parcourir par

Experience of applying convolutional neural networks to inverse problems of seismic exploration

V. I. Golubev ; M. I. Anisimov

Numerical methods and programming, Tome 25 (2024) no. 5, pp. 46-61.

Voir la notice de l'article provenant de la source Math-Net.Ru

Résumé

The paper is devoted to the study of the possibility of using modern convolutional neural networks to solve problems of reconstructing the position of geological inclusions and estimating the scalar parameters of the models used based on seismic exploration data. Synthetic seismograms calculated by explicit-implicit grid-characteristic schemes are used to form training and validation samples. The paper considers two network architectures for joint machine learning problems and compares the results of the calculated estimates with single forecast models. A significant increase in forecast quality is demonstrated.

Keywords: seismic survey, fractured media, mathematical simulation, convolutional neural networks, multi-task machine learning.

@article{VMP_2024_25_5_a3,
     author = {V. I. Golubev and M. I. Anisimov},
     title = {Experience of applying convolutional neural networks to inverse problems of seismic exploration},
     journal = {Numerical methods and programming},
     pages = {46--61},
     publisher = {mathdoc},
     volume = {25},
     number = {5},
     year = {2024},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/VMP_2024_25_5_a3/}
}

TY  - JOUR
AU  - V. I. Golubev
AU  - M. I. Anisimov
TI  - Experience of applying convolutional neural networks to inverse problems of seismic exploration
JO  - Numerical methods and programming
PY  - 2024
SP  - 46
EP  - 61
VL  - 25
IS  - 5
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/VMP_2024_25_5_a3/
LA  - ru
ID  - VMP_2024_25_5_a3
ER  -

%0 Journal Article
%A V. I. Golubev
%A M. I. Anisimov
%T Experience of applying convolutional neural networks to inverse problems of seismic exploration
%J Numerical methods and programming
%D 2024
%P 46-61
%V 25
%N 5
%I mathdoc
%U http://geodesic.mathdoc.fr/item/VMP_2024_25_5_a3/
%G ru
%F VMP_2024_25_5_a3

V. I. Golubev; M. I. Anisimov. Experience of applying convolutional neural networks to inverse problems of seismic exploration. Numerical methods and programming, Tome 25 (2024) no. 5, pp. 46-61. http://geodesic.mathdoc.fr/item/VMP_2024_25_5_a3/