scholarly journals THE CASE STUDY OF CONVOLUTION NEURAL NETWORKS APPLICATION FOR THE PROCESSING OF REAL 3D SEISMIC DATA

2019 ◽  
Vol 2 (3) ◽  
pp. 147-153
Author(s):  
Georgy Loginov ◽  
Anton Duchkov ◽  
Dmitry Litvichenko ◽  
Sergey Alyamkin
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Quality Control ◽  
Data Quality ◽  
Seismic Data ◽  
3D Seismic ◽  
Data Quality Control ◽  
Static Corrections ◽  
3D Seismic Data

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.

Estimating the boundary surface between geologic formations from 3D seismic data using neural networks and geostatistics

Geophysics ◽  
2005 ◽  
Vol 70 (1) ◽  
pp. P1-P11 ◽  
Author(s):  
Peter A. Dowd ◽  
Eulogio Pardo-Igúzquiza
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Seismic Data ◽  
Acoustic Impedance ◽  
Boundary Surface ◽  
Boundary Detection ◽  
Geostatistical Simulation ◽  
3D Seismic ◽  
Filter Noise ◽  
3D Seismic Data

The exact locations of horizons that separate geologic sequences are known only at physically sampled locations (e.g., borehole intersections), which, in general, are very sparse. 3D seismic data, on the other hand, provide complete coverage of a volume of interest with the possibility of detecting the boundaries between formations with, for example, contrasted acoustic impedance. Detection of boundaries is hampered, however, by coarse spatial resolution of the seismic data, together with local variability of acoustic impedance within formations. The authors propose a two-part approach to the problem, using neural networks and geostatistics. First, an artificial neural network is used for boundary detection. The training set for the neural net comprises seismic traces that are collocated with the borehole locations. Once the net is trained, it is applied to the entire seismic grid. Second, output from the neural network is processed geostatistically to filter noise and to assess the uncertainty of the boundary locations. A physical counterpart is interpreted for each structure inferred from the spatial semivariogram. Factorial kriging is used for filtering, and uncertainty in the shape of the boundaries is assessed by geostatistical simulation. In this approach, the boundary locations are interpreted as random functions that can be simulated to incorporate their uncertainty in applications. A case study of boundary detection between sandstone and breccia formations in a highly faulted zone is used to illustrate the methodologies.

scholarly journals Data Quality Control For Lake Temperature by Neural Network

1999 ◽  
Vol 15 (4) ◽  
pp. 272-284
Author(s):  
Kang-Ren Jin ◽  
Der-San Chen ◽  
Lijian Fang ◽  
Hui-Chuan Chen ◽  
Jay Martin
Keyword(s):  
Neural Network ◽  
Quality Control ◽  
Data Quality ◽  
Data Quality Control ◽  
Lake Temperature
Sign in / Sign up

Export Citation Format

Share Document