CN-121978756-A - Data processing method, electronic device, storage medium, and computer program product

CN121978756ACN 121978756 ACN121978756 ACN 121978756ACN-121978756-A

Abstract

The application discloses a data processing method, electronic equipment, storage medium and computer program product, wherein the method comprises the steps of converting first seismic data into corresponding first wave field data, performing curved wave transformation on the first wave field data to obtain a first curved wave coefficient set, extracting one or more first curved wave coefficients corresponding to first diffracted waves from the first curved wave coefficient set through a first model, and processing the one or more first curved wave coefficients to obtain imaging of the first diffracted waves. According to the application, the diffracted waves in the seismic data can be separated more accurately, so that the accuracy of diffracted wave imaging is improved.

Inventors

Jia Shixuan
HUANG ZHIGUO
YE ZHONGQIANG
ZHANG ZENGBIN
LI MINGYUE

Assignees

中移(苏州)软件技术有限公司
中国移动通信集团有限公司

Dates

Publication Date: 20260505
Application Date: 20260115

Claims (12)

1. A data processing method, characterized in that the data processing method comprises: Converting the first seismic data into corresponding first wavefield data; performing curvelet transformation on the first wave field data to obtain a first curvelet coefficient set; Extracting one or more first curvelet coefficients corresponding to a first diffracted wave from the first curvelet coefficient set through a first model; and processing the one or more first curvelet coefficients to obtain an image of the first diffracted wave.
2. The method of claim 1, wherein processing the one or more first curvelet coefficients to obtain an image of the first diffracted wave comprises: Performing inverse curvelet transformation on the one or more first curvelet coefficients to obtain second wave field data; And carrying out least square inverse time migration imaging on the second wave field data to obtain the imaging of the first diffracted wave.
3. The method of claim 1, wherein the first model is obtained by training one or more first training data and a first label corresponding to each first training data, the first training data is obtained by performing a curvelet conversion on data in a first data set, and the first label is used for identifying a curvelet coefficient corresponding to a diffracted wave in the corresponding first training data.
4. A method according to claim 3, wherein the first model comprises one or more of the following modules: A channel attention module for enhancing one or more first channels, the one or more first channels are used to identify diffraction wave-related features; and the spatial attention module is used for retaining the spatial position information related to the first diffracted wave.
5. The method of claim 2, wherein performing a curvelet transform on the first wavefield data results in a first set of curvelet coefficients, comprising: performing generalized curvelet transformation on the first wave field data to obtain the first curvelet coefficient set; Said inverse curvelet transforming said one or more first curvelet coefficients to obtain second wavefield data, comprising: And performing inverse generalized curvelet transformation on the one or more first curvelet coefficients to obtain the second wave field data.
6. The method according to claim 1, wherein the method further comprises: Adjusting a first parameter according to a first index, wherein the first index comprises one or more of the following components of distinguishing capability of the generalized curvelet transformation on different angle directions, distinguishing capability of the generalized curvelet transformation on different scale components, residual computing power resources, computing power resources occupied by running the first model, residual memory resources, memory resources occupied by running the first model, and one or more of radial scaling parameters, angle scaling parameters; the performing a curvelet transform on the first wavefield data includes: and performing curvelet transformation on the first wave field data based on a broad-meaning mother curvelet, wherein the representation of the broad-meaning mother curvelet on a frequency domain is determined according to the adjusted first parameter.
7. The method of claim 1, wherein after the converting the first seismic data into corresponding first wavefield data, the method further comprises: Performing first processing on the first seismic data to obtain a corresponding first processing result, wherein the first processing comprises one or more of tau-p transformation, singular spectrum analysis; Extracting transform domain data corresponding to a second diffracted wave from the first processing result through a first model, wherein the transform domain data corresponding to the second diffracted wave comprises tau-p domain data corresponding to the second diffracted wave when the first processing comprises tau-p transformation; and processing the transformation domain data corresponding to the second diffracted wave to obtain the imaging of the second diffracted wave.
8. A method according to claim 3, wherein the first data set comprises one or more of: Forward modeling a second model, wherein the second model only comprises a reflecting layer and diffraction points; Forward modeling the salt structure model to obtain data; and converting the second seismic data to obtain wave field data.
9. A data processing apparatus, comprising: a first conversion unit for converting the first seismic data into corresponding first wavefield data; the second conversion unit is used for performing curvelet transformation on the first wave field data to obtain a first curvelet coefficient set; a first extraction unit, configured to extract one or more first curvelet coefficients corresponding to a first diffracted wave from the first curvelet coefficient set through a first model; and the first processing unit is used for processing the one or more first curvelet coefficients to obtain an image of the first diffraction wave.
10. An electronic device comprising a processor and a memory for storing a computer program capable of running on the processor, Wherein the processor is adapted to perform the steps of the method of any of claims 1 to 8 when the computer program is run.
11. A storage medium having stored thereon a computer program, which when executed by a processor performs the steps of the method according to any of claims 1 to 8.
12. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 8.

Description

Data processing method, electronic device, storage medium, and computer program product Technical Field The present application relates to the field of computer technology, and in particular, to a data processing method, an electronic device, a storage medium, and a computer program product. Background Diffracted waves are seismic responses of subsurface discontinuities such as scatterers, cracks, faults, and river channels, and are closely related to hydrocarbon transport and accumulation. However, the diffracted wave energy is typically much weaker than the reflected wave produced by the large scale reflective construction, and therefore subsurface discontinuities are inevitably masked by the large scale reflectors in seismic offset imaging. In order to characterize subsurface discontinuities, it is necessary to separate the diffracted wave from the seismic data and perform the diffracted wave imaging, but the accuracy of separating the diffracted wave is low, resulting in a low accuracy of the resulting diffracted wave imaging. Disclosure of Invention To solve the related technical problems, embodiments of the present application provide a data processing method, an electronic device, a storage medium, and a computer program product. The technical scheme of the embodiment of the application is realized as follows: the embodiment of the application provides a data processing method, which comprises the following steps: Converting the first seismic data into corresponding first wavefield data; performing curvelet transformation on the first wave field data to obtain a first curvelet coefficient set; Extracting one or more first curvelet coefficients corresponding to a first diffracted wave from the first curvelet coefficient set through a first model; and processing the one or more first curvelet coefficients to obtain an image of the first diffracted wave. In the above aspect, the processing the one or more first curvelet coefficients to obtain the image of the first diffracted wave includes: Performing inverse curvelet transformation on the one or more first curvelet coefficients to obtain second wave field data; And carrying out least square inverse time migration imaging on the second wave field data to obtain the imaging of the first diffracted wave. In the above scheme, the first model is obtained by training one or more first training data and a first label corresponding to each first training data, the first training data is a set of curvelet coefficients obtained by curvelet conversion of data in the first data set, and the first label is used for identifying a curvelet coefficient corresponding to a diffracted wave in the corresponding first training data. In the above aspect, the first model includes one or more of the following modules: A channel attention module for enhancing one or more first channels, the one or more first channels are used to identify diffraction wave-related features; and the spatial attention module is used for retaining the spatial position information related to the first diffracted wave. In the above scheme, performing curvelet transformation on the first wave field data to obtain a first curvelet coefficient set includes: performing generalized curvelet transformation on the first wave field data to obtain the first curvelet coefficient set; Said inverse curvelet transforming said one or more first curvelet coefficients to obtain second wavefield data, comprising: And performing inverse generalized curvelet transformation on the one or more first curvelet coefficients to obtain the second wave field data. In the above scheme, the method further comprises: Adjusting a first parameter according to a first index, wherein the first index comprises one or more of the following components of distinguishing capability of the generalized curvelet transformation on different angle directions, distinguishing capability of the generalized curvelet transformation on different scale components, residual computing power resources, computing power resources occupied by running the first model, residual memory resources, memory resources occupied by running the first model, and one or more of radial scaling parameters, angle scaling parameters; the performing a curvelet transform on the first wavefield data includes: and performing curvelet transformation on the first wave field data based on a broad-meaning mother curvelet, wherein the representation of the broad-meaning mother curvelet on a frequency domain is determined according to the adjusted first parameter. In the foregoing aspect, after the converting the first seismic data into the corresponding first wavefield data, the method further includes: Performing first processing on the first seismic data to obtain a corresponding first processing result, wherein the first processing comprises one or more of tau-p transformation, singular spectrum analysis; Extracting transform domain data corresponding to a second diffracted wave