US 12,748,231 B2Granted

Machine learning-based two-step impedance inversion method and apparatus using seismic data

AssigneesSK Earthon Co., Ltd., Iucf-Hyu (Industry-University Cooperation Foundation Hanyang University)

InventorsJun Hwan Choi, Chang Ho Jeong, Hyung Wook Choi, Joong Moo Byun, Jeong Hun Yoo, Do Wan Kim

Life of this patent

Estimating the term…

Loading patent…

Abstract

Techniques for a machine learning-based two-step impedance inversion method using seismic data are disclosed. In some embodiments of the disclosed technology, an impedance inversion method includes generating a domain adaptation model configured to predict, based on source data associated with a source area that includes a well, a P-impedance value of a target area that does not include a well, and generating, using the P-impedance value generated by the domain adaptation model, a P-impedance low frequency model configured to predict a final P-impedance value of the target area by performing an inversion. In this way, it is possible to accurately predict P-impedance value of an area where a well does not exist.

Claims13

Dependent claims

A machine learning-based two-step impedance inversion method for identifying a presence of subsurface gas or oil reservoirs in a target area that does not include a well using seismic data, comprising:

directing seismic energy into the target area and detecting reflected seismic waves;
generating a domain adaptation model based on a source data associated with a source area that includes a well and the detected reflected seismic waves from the target area, and predicting a P-impedance value of the target area;
generating, using the P-impedance value generated by the domain adaptation model, a P-impedance low frequency model configured to predict a final P-impedance value of the target area by performing an inversion, the generating the P-impedance low frequency model comprising performing a preprocessing operation by generating the P-impedance low frequency model using the P-impedance value, the preprocessing operation comprising:
performing a smoothing operation by obtaining a smoothed P-impedance value by smoothing the P-impedance value;
and
performing a filtering operation by obtaining the P-impedance low frequency model by applying a filter to the smoothed P-impedance value;
and
displaying a prediction result for the presence of the subsurface gas or oil to a user.

5 more elements

A machine learning-based two-step impedance inversion apparatus configured to identify a presence of subsurface gas or oil reservoirs in a target area that does not include a well using seismic data, comprising:

a processor;
a storage unit communicatively connected to the processor, the storage unit being configured to store:
program codes operating in the processor,
data defining reflected seismic waves resulting from directing seismic energy in the target area, and
source data associated with a source area that includes a well
the program codes comprising:
a training module configured to generate a domain adaptation model for predicting a P-impedance value of a target area that does not include a well by using source data obtained from a source area that includes a well and target data obtained from the target area;
a preprocessing module configured to generate a P-impedance low frequency model by using the P-impedance value generated by the domain adaptation model, the preprocessing module being further configured to:
obtain a smoothed P-impedance value by smoothing the P-impedance value;
and
obtain a P-impedance low frequency model by applying a filter to the smoothed P-impedance value;
and
an inversion module configured to generate a final P-impedance value by performing an inversion using the P-impedance low frequency model and the target data;
and
an input/output interface configured to display a prediction result for the presence of the subsurface gas or oil to a user.

12 more elements

Dependencies are inferred from the claim text.