Physical law and data dual-driven seismic imaging method, system and device and storage medium

Abstract

The invention discloses a physical law and data dual-drive seismic imaging method, system and device and a storage medium, and belongs to the field of oil and gas geophysical prospecting engineering. The method includes the steps of: according to observation data, obtaining an underground structure imaging result through conventional reverse time migration; establishing a first data set by using demigration and conventional reverse time migration which describe a seismic wave propagation rule, and training a first neural network which can defuzzify an imaging result; establishing a second data set according to the logging data, and correcting parameters of the first neural network to obtain a second neural network; and processing the conventional reverse time migration result according to the second neural network to obtain a high-precision underground structure reflection coefficient. According to the method, the neural network is trained under a physical law and data dual-drive framework, the problem that performance is reduced due to the fact that a traditional data drive method is limited by the number of samples is solved, and the high-precision underground structure reflection coefficient can be output.

Description

technical field [0001] The invention belongs to the field of oil and gas geophysical prospecting engineering, and relates to a seismic imaging method, system, equipment and storage medium driven by physical laws and data. Background technique [0002] The focus of domestic oil and gas exploration is continuously shifting from conventional oil and gas to unconventional oil and gas. Different from conventional oil and gas, the evaluation of unconventional oil and gas focuses on attribute parameters such as lithology and physical properties. In oil and gas exploration, seismic migration is an important means to find oil and gas reservoirs by imaging underground structures based on artificial seismic data. However, the conventional migration operator is only the conjugate of the forward operator, and its imaging result is essentially the convolution of the Hessian operator and the subsurface reflection coefficient. Affected by the Hessian operator, the imaging results of conve...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a seismic imaging method, system, equipment and storage medium driven by physical laws and data, aiming at solving the limitation of the number of effective samples in the prior art, based on data The technical problems of poor generalization and low imaging precision of the driven seismic imaging method

Images