Open AccessTHE CASE STUDY OF CONVOLUTION NEURAL NETWORKS APPLICATION FOR THE PROCESSING OF REAL 3D SEISMIC DATA
Author(s) -
G. Loginov,
Anton A. Duchkov,
D.A. Litvichenko,
Sergey Alyamkin
Publication year - 2019
Publication title -
interèkspo geo-sibirʹ
Language(s) - English
Resource type - Journals
ISSN - 2618-981X
DOI - 10.33764/2618-981x-2019-2-3-147-153
Subject(s) - seismic trace , convolution (computer science) , computer science , trace (psycholinguistics) , artificial neural network , data set , set (abstract data type) , convolutional neural network , algorithm , data processing , data mining , geology , artificial intelligence , database , linguistics , philosophy , wavelet , programming language
The paper considers the use of a convolution neural network for detecting first arrivals for a real set of 3D seismic data with more than 4.5 million traces. Detection of the first breaks for each trace is carried out independently. The error between the original and the predicted first breaks is no more than 3 samples for 95% of the data. Quality control is performed by calculating static corrections and seismic stacks, which showed the effectiveness of the proposed approach.