CN-122017966-A - Determination method and device based on heterogeneity of tidal channel and computer equipment

CN122017966ACN 122017966 ACN122017966 ACN 122017966ACN-122017966-A

Abstract

The specification provides a method, a device and a computer device for determining the heterogeneity based on a tidal channel, which can be used for obtaining a preset heterogeneity classification model suitable for the tidal channel by constructing an initial classification model based on random forests and performing supervised machine learning by utilizing the initial classification model before specific implementation. In the specific implementation, the instantaneous frequency data body, the instantaneous amplitude data body and the chaotic data body are extracted and fused by utilizing the obtained seismic data, the multi-attribute fusion data body with rich and comprehensive information is obtained, and the type of the heterogeneity in the tidal channel is determined by jointly using the preset heterogeneous classification model and the multi-attribute fusion data body. Therefore, the type information of the heterogeneity in the tidal channel can be determined efficiently and accurately, quantitative characterization of the heterogeneity in the tidal channel is realized, and subsequent oil reservoir exploration and development aiming at a target area are guided accurately and effectively.

Inventors

ZHANG SIHAI
HE E
XU JIACHENG
DAI JUNWEN
ZHAO HANTING

Assignees

中国石油天然气股份有限公司
中国石油迪拜研究院

Dates

Publication Date: 20260512
Application Date: 20251209

Claims (13)

1. A method of determining heterogeneity based on a tidal channel, comprising: obtaining seismic data of a target area, performing paleo-landform restoration on the seismic data, and obtaining seismic data after paleo-landform restoration; acquiring corresponding instantaneous frequency data bodies, instantaneous amplitude data bodies and seismic sections according to the seismic data after the paleo-topography recovery; Determining geometrical characteristics of the tidal channel according to the instantaneous frequency data volume, the instantaneous amplitude data volume and the seismic profile; Determining a chaotic data body by utilizing the seismic data according to the geometric characteristics of the tidal channel, and determining the internal structural characteristics of the tidal channel according to the chaotic data body; Fusing the instantaneous frequency data body, the instantaneous amplitude data body and the chaotic data body to obtain a corresponding multi-attribute fused data body; determining pull-down abnormal data based on porosity correction in the tidal channel according to the multi-attribute fusion data body and the seismic section; Determining the type of the heterogeneity in the tidal channel according to the multi-attribute fusion data body, the geometric characteristics of the tidal channel, the internal structural characteristics of the tidal channel, the pulldown abnormal data based on the porosity correction in the tidal channel and a preset heterogeneity classification model.
2. The method of claim 1, wherein determining the geometry of the tidal channel from the instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile comprises: determining a distribution plane of the tidal channel according to the instantaneous frequency data body and the instantaneous amplitude data body; calculating the bending degree of a plurality of segments on a distribution plane of the tidal channel by using a preset segment time window to obtain a first type of geometric feature of the tidal channel; According to the distribution plane and the seismic section of the tidal channel, carrying out intersection processing to obtain a corresponding intersection result; obtaining a second type of geometric feature of the tidal channel by determining the width, depth, and aspect ratio of the tidal channel based on the intersection; and combining the first type of geometric features and the second type of geometric features to obtain the geometric features of the tidal channel.
3. The method of claim 2, wherein calculating the curvature of the plurality of segments by using a predetermined segment time window in a distribution plane of the tidal channel comprises: Determining a maximum width of the tidal channel in the target area and a planar spread feature based on the distribution plane of the tidal channel; Determining the length of a matched time window according to the maximum width of the tidal channel in the target area, and constructing a preset segmented time window according to the length of the time window; dividing the tidal channel into a plurality of segments according to the plane spreading characteristics and the time window length based on the distribution plane of the tidal channel; And respectively calculating the bending degree of each of the plurality of segments by using a preset segment time window.
4. The method of claim 1, wherein determining internal structural features of the tidal channel from the chaotic data volumes comprises: determining local seismic data corresponding to the interior of the tidal channel in the chaotic data volume according to the geometric characteristics of the tidal channel; Extracting internal reflection characteristics of the tidal channel according to local seismic data corresponding to the inside of the tidal channel; and according to the internal reflection characteristics of the tidal channel, determining the internal structural shape of the tidal channel, and obtaining the internal structural characteristics of the tidal channel.
5. The method of claim 1, further comprising obtaining well log data and core data, wherein the well log data comprises at least imaging well log data; correspondingly, after the instantaneous frequency data body, the instantaneous amplitude data body and the chaotic data body are fused to obtain corresponding multi-attribute fusion data bodies, the method further comprises the steps of: According to the core data, key structural features related to the tidal channel are determined on the core scale and used as auxiliary data; Calibrating the logging data by using the auxiliary data to obtain calibrated logging data; According to the calibrated logging data, a logging interpretation result about the tidal channel is constructed and obtained; and verifying and updating the multi-attribute fusion data body by using the logging interpretation result.
6. The method of claim 5, wherein determining porosity correction based pulldown anomaly data in a tidal channel from the multi-attribute fusion data volume, seismic profile, comprises: Determining an underlying layer below the tidal channel according to the multi-attribute fusion data body, and performing horizon interpretation on the underlying layer to obtain a corresponding construction plane; determining an abnormal seismic reflection area on the seismic section according to the construction plane, and determining pulldown abnormal data in the tidal channel from the abnormal seismic reflection area; Constructing a corresponding relation between the pulldown abnormal data and the porosity according to the logging data and the pulldown abnormal data in the tidal channel; According to the corresponding relation between the pull-down abnormal data and the porosity and the construction plane, calculating to obtain a corresponding pull-down abnormal plane; and determining the pull-down abnormal data based on the porosity correction in the tidal channel according to the pull-down abnormal plane.
7. The method of claim 1, wherein determining the type of non-uniformity within the tidal channel based on the multi-attribute fusion data volume, the geometry of the tidal channel, the internal structural features of the tidal channel, the porosity correction based pulldown anomaly data within the tidal channel, and a pre-set non-uniformity classification model comprises: Picking up and obtaining a tidal channel top interface diagram, a tidal channel side interface diagram and a tidal channel bottom interface diagram according to the multi-attribute fusion data body; establishing and obtaining a tidal channel construction model according to the top interface diagram, the tidal channel side interface diagram and the tidal channel bottom interface diagram of the tidal channel; Determining space coordinate parameters of the tidal channel according to the tidal channel construction model; Constructing and obtaining a corresponding tidal channel heterogeneous attribute matrix according to the space coordinate parameters of the tidal channel, the geometric characteristics of the tidal channel, the internal structural characteristics of the tidal channel and the pull-down abnormal data based on the porosity correction in the tidal channel; And determining the type of the heterogeneity in the tidal channel by processing the matrix of the heterogeneity attributes of the tidal channel by using a preset heterogeneity classification model.
8. The method of claim 7, wherein the pre-set non-homogeneity classification model is pre-trained by supervised learning based on a random forest model.
9. The method of claim 1, wherein the type of inhomogeneity within the tidal channel comprises at least one of a homogeneous mass, a weak heterogeneous mass, a medium heterogeneous mass, a strong heterogeneous mass.
10. A tidal channel based heterogeneity determination apparatus, comprising: The first acquisition module is used for acquiring the seismic data of the target area, and performing paleo-landform restoration on the seismic data to obtain seismic data after paleo-landform restoration; the second acquisition module is used for acquiring corresponding instantaneous frequency data bodies, instantaneous amplitude data bodies and seismic profiles according to the seismic data after the paleo-topography is restored; The first determining module is used for determining the geometrical characteristics of the tidal channel according to the instantaneous frequency data body, the instantaneous amplitude data body and the seismic profile; the second determining module is used for determining a chaotic data body by utilizing the seismic data according to the geometric characteristics of the tidal channel and determining the internal structural characteristics of the tidal channel according to the chaotic data body; The fusion module is used for fusing the instantaneous frequency data body, the instantaneous amplitude data body and the chaotic data body to obtain a corresponding multi-attribute fusion data body; The third determining module is used for determining pull-down abnormal data based on porosity correction in the tidal channel according to the multi-attribute fusion data body and the seismic section; And the fourth determining module is used for determining the type of the heterogeneity in the tidal channel according to the multi-attribute fusion data body, the geometric characteristics of the tidal channel, the internal structural characteristics of the tidal channel, the pull-down abnormal data based on the porosity correction in the tidal channel and a preset heterogeneity classification model.
11. A computer device comprising a processor and a memory for storing processor-executable instructions which when executed by the processor implement the steps of the method of any one of claims 1 to 9.
12. A computer readable storage medium, having stored thereon computer instructions which, when executed by a processor, implement the steps of the method of any of claims 1 to 9.
13. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the method of any one of claims 1 to 9.

Description

Determination method and device based on heterogeneity of tidal channel and computer equipment Technical Field The specification belongs to the technical field of oil reservoir exploration and development, and particularly relates to a method, a device and computer equipment for determining heterogeneity based on a tidal channel. Background Tidal channels (carbonate TIDAL CHANNEL) are water flow flushing channels developed in carbonate terraces or sloped environments, are controlled by tidal energy, represent narrow and curved erosion channels, are filled with granular limestone and have staggered layers and eroded bottom boundaries, are relatively complex in structure, and are commonly found in lagoons, tidal flat or inland other areas. The tidal channel has important significance in reservoir development due to the structural specificity of the tidal channel, and influences the subsequent specific oil reservoir exploration and development. However, because the tidal channel has a complex and variable structure, the conventional method is difficult to effectively and accurately describe the heterogeneity in the tidal channel, so that the subsequent oil reservoir exploration and development are affected. In view of the above problems, no effective solution has been proposed at present. Disclosure of Invention The specification provides a method, a device and computer equipment for determining the heterogeneity based on a tidal channel, which can efficiently and accurately determine the type information of the heterogeneity in the tidal channel. The present specification provides a method of determining heterogeneity based on a tidal channel, comprising: obtaining seismic data of a target area, performing paleo-landform restoration on the seismic data, and obtaining seismic data after paleo-landform restoration; acquiring corresponding instantaneous frequency data bodies, instantaneous amplitude data bodies and seismic sections according to the seismic data after the paleo-topography recovery; Determining geometrical characteristics of the tidal channel according to the instantaneous frequency data volume, the instantaneous amplitude data volume and the seismic profile; Determining a chaotic data body by utilizing the seismic data according to the geometric characteristics of the tidal channel, and determining the internal structural characteristics of the tidal channel according to the chaotic data body; Fusing the instantaneous frequency data body, the instantaneous amplitude data body and the chaotic data body to obtain a corresponding multi-attribute fused data body; determining pull-down abnormal data based on porosity correction in the tidal channel according to the multi-attribute fusion data body and the seismic section; Determining the type of the heterogeneity in the tidal channel according to the multi-attribute fusion data body, the geometric characteristics of the tidal channel, the internal structural characteristics of the tidal channel, the pulldown abnormal data based on the porosity correction in the tidal channel and a preset heterogeneity classification model. In one embodiment, the determining the geometrical feature of the tidal channel based on the instantaneous frequency data volume, the instantaneous amplitude data volume, the seismic profile comprises: determining a distribution plane of the tidal channel according to the instantaneous frequency data body and the instantaneous amplitude data body; calculating the bending degree of a plurality of segments on a distribution plane of the tidal channel by using a preset segment time window to obtain a first type of geometric feature of the tidal channel; According to the distribution plane and the seismic section of the tidal channel, carrying out intersection processing to obtain a corresponding intersection result; obtaining a second type of geometric feature of the tidal channel by determining the width, depth, and aspect ratio of the tidal channel based on the intersection; and combining the first type of geometric features and the second type of geometric features to obtain the geometric features of the tidal channel. In one embodiment, the calculating the curvature of the plurality of segments by using a predetermined segment time window on a distribution plane of the tidal channel comprises: Determining a maximum width of the tidal channel in the target area and a planar spread feature based on the distribution plane of the tidal channel; Determining the length of a matched time window according to the maximum width of the tidal channel in the target area, and constructing a preset segmented time window according to the length of the time window; dividing the tidal channel into a plurality of segments according to the plane spreading characteristics and the time window length based on the distribution plane of the tidal channel; And respectively calculating the bending degree of each of the plurality of segments by using a preset