Method and device for determining heterogeneity based on tidal channel and computer equipment

Abstract

The invention provides a tidal channel-based heterogeneity determination method and device and computer equipment, and before specific implementation, a preset heterogeneity classification model adaptive to a tidal channel can be obtained through training by constructing an initial classification model based on a random forest and performing supervised machine learning by using the initial classification model. During specific implementation, an instantaneous frequency data volume, an instantaneous amplitude data volume and a chaos data volume are extracted and fused by using acquired seismic data, and a multi-attribute fusion data volume with rich and comprehensive information is obtained; and determining the heterogeneity type in the tidal channel by jointly using the preset heterogeneity classification model and the multi-attribute fusion data body. Therefore, the type information of the heterogeneity in the tidal channel can be efficiently and accurately determined, quantitative description of the heterogeneity in the tidal channel is realized, and subsequent oil reservoir exploration and development for the target area can be accurately and effectively guided.

Description

Technical Field

[0001] This manual belongs to the field of reservoir exploration and development technology, and in particular relates to methods, apparatus and computer equipment for determining the heterogeneity of tidal channels. Background Technology

[0002] Tidal channels (carbonate tidal channels) are water erosion channels developed in carbonate platform or slope environments. Controlled by tidal energy, they appear as narrow, tortuous erosion channels filled with grainy limestone and exhibiting cross-bedding and erosion boundaries. Their structure is relatively complex, and they are commonly found in lagoons, tidal flats, or inner platforms. Due to their unique structural characteristics, these tidal channels are of great significance in reservoir development, influencing subsequent specific oil reservoir exploration and development.

[0003] However, due to the complex and variable structure of tidal channels, existing methods often struggle to efficiently and accurately characterize the heterogeneity within them, thus impacting subsequent reservoir exploration and development.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This specification provides a method, apparatus, and computer device for determining the heterogeneity of tidal channels, which can efficiently and accurately determine the type information of heterogeneity within tidal channels.

[0006] This specification provides a method for determining the heterogeneity of tidal channels, including:

[0007] Acquire seismic data for the target area; and perform paleogeographic reconstruction on the seismic data to obtain seismic data after paleogeographic reconstruction.

[0008] Based on the earthquake data after the ancient landform was reconstructed, the corresponding instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile were obtained;

[0009] Based on the instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile, the geometric characteristics of the tidal channel are determined;

[0010] Based on the geometric characteristics of the tidal channel, the chaotic data volume is determined using the seismic data; and based on the chaotic data volume, the internal structural characteristics of the tidal channel are determined.

[0011] By fusing the instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume, a corresponding multi-attribute fused data volume is obtained;

[0012] Based on the multi-attribute fusion data volume and seismic profile, pull-down anomaly data based on porosity correction within the tidal channel were determined;

[0013] Based on the multi-attribute fusion data volume, the geometric features of the tidal channel, the internal structural features of the tidal channel, the pull-down anomaly data based on porosity correction within the tidal channel, and the preset heterogeneity classification model, the heterogeneity type within the tidal channel is determined.

[0014] In one embodiment, determining the geometric characteristics of the tidal channel based on the instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile includes:

[0015] The distribution plane of the tidal channel is determined based on the instantaneous frequency data volume and the instantaneous amplitude data volume;

[0016] Using a preset segmented time window, the curvature of multiple segments is calculated on the distribution plane of the tidal channel to obtain the first type of geometric features of the tidal channel.

[0017] Based on the distribution plane of the tidal channel and the seismic profile, intersection processing is performed to obtain the corresponding intersection results;

[0018] Based on the intersection results, the second type of geometric features of the tidal channel are obtained by determining the width, depth, and aspect ratio of the tidal channel.

[0019] By combining the first type of geometric features and the second type of geometric features, the geometric features of the tidal channel are obtained.

[0020] In one embodiment, the step of using a preset segmented time window to calculate the curvature of multiple segments on the distribution plane of the tidal channel includes:

[0021] Based on the distribution plane of the tidal channel, determine the maximum width of the tidal channel within the target area, as well as its planar distribution characteristics;

[0022] Based on the maximum width of the tidal channel within the target area, determine the matching time window length; and construct a preset segmented time window based on this time window length.

[0023] Based on the distribution plane of the tidal channel, and according to the plane distribution characteristics and the time window length, the tidal channel is divided into multiple segments;

[0024] Using a preset segmented time window, the curvature of each segment in the plurality of segments is calculated.

[0025] In one embodiment, determining the internal structural features of the tidal channel based on the chaotic data volume includes:

[0026] Based on the geometric characteristics of the tidal channel, local seismic data corresponding to the interior of the tidal channel are determined in the chaotic data volume;

[0027] Based on the local seismic data corresponding to the interior of the tidal channel, the internal reflection characteristics of the tidal channel are extracted;

[0028] Based on the internal reflection characteristics of the tidal channel, the internal structural characteristics of the tidal channel are obtained by determining the internal structural shape of the tidal channel.

[0029] In one embodiment, the method further includes: acquiring well logging data and core data; wherein the well logging data includes at least imaging well logging data;

[0030] Accordingly, after fusing the instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume to obtain the corresponding multi-attribute fused data volume, the method further includes:

[0031] Based on the core data, key structural features of the tidal channel were determined at the core scale as auxiliary data;

[0032] The logging data is calibrated using the auxiliary data to obtain calibrated logging data.

[0033] Based on the calibrated logging data, logging interpretation results regarding the tidal channel are constructed;

[0034] The multi-attribute fused data volume is verified and updated using the well logging interpretation results.

[0035] In one embodiment, determining the pull-down anomaly data based on porosity correction within the tidal channel according to the multi-attribute fused data volume and seismic profile includes:

[0036] Based on the multi-attribute fusion data volume, the underlying layer located below the tidal channel is determined; and by interpreting the stratigraphic position of this underlying layer, the corresponding structural plane is obtained.

[0037] Based on the structural plane, anomaly regions of seismic reflection are identified on the seismic profile; and down-pulling anomaly data within the tidal channel are identified from the anomaly regions of seismic reflection.

[0038] Based on the well logging data and the pull-down anomaly data in the tidal channel, a correspondence between the pull-down anomaly data and porosity is constructed;

[0039] Based on the correspondence between the pull-down anomaly data and porosity, and the constructed plane, the corresponding pull-down anomaly plane is calculated.

[0040] Based on the aforementioned pull-down anomaly plane, pull-down anomaly data within the tidal channel, corrected for porosity, are determined.

[0041] In one embodiment, determining the type of heterogeneity within the tidal channel based on the multi-attribute fused data volume, the geometric features of the tidal channel, the internal structural features of the tidal channel, the pull-down anomaly data within the tidal channel based on porosity correction, and a preset heterogeneity classification model includes:

[0042] Based on the multi-attribute fusion data volume, the top interface image, the side interface image, and the bottom interface image of the tidal channel are obtained.

[0043] Based on the top interface diagram, side interface diagram, and bottom interface diagram of the tidal channel, a structural model of the tidal channel is established.

[0044] Based on the tidal channel construction model, the spatial coordinate parameters of the tidal channel are determined;

[0045] Based on the spatial coordinate parameters of the tidal channel, the geometric features of the tidal channel, the internal structural features of the tidal channel, and the pull-down anomaly data based on porosity correction within the tidal channel, a corresponding heterogeneous attribute matrix of the tidal channel is constructed.

[0046] By using a pre-defined heterogeneity classification model and processing the heterogeneity attribute matrix of the tidal channel, the heterogeneity type within the tidal channel is determined.

[0047] In one embodiment, the preset heterogeneous classification model is obtained in advance through supervised learning based on a random forest model.

[0048] In one embodiment, the heterogeneity type within the tidal channel includes at least one of the following: homogeneous body, weakly heterogeneous body, moderately heterogeneous body, and strongly heterogeneous body.

[0049] This specification also provides an embodiment of a device for determining the heterogeneity of tidal channels, comprising:

[0050] The first acquisition module is used to acquire seismic data of the target area; and to perform paleogeographic reconstruction on the seismic data to obtain seismic data after paleogeographic reconstruction.

[0051] The second acquisition module is used to acquire the corresponding instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile based on the seismic data after the ancient landform is restored.

[0052] The first determining module is used to determine the geometric characteristics of the tidal channel based on the instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile.

[0053] The second determining module is used to determine the chaotic data volume based on the geometric characteristics of the tidal channel and the seismic data; and to determine the internal structural characteristics of the tidal channel based on the chaotic data volume.

[0054] The fusion module is used to fuse the instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume to obtain a corresponding multi-attribute fused data volume;

[0055] The third determining module is used to determine the pull-down anomaly data based on porosity correction within the tidal channel based on the multi-attribute fusion data volume and the seismic profile.

[0056] The fourth determining module is used to determine the type of heterogeneity in the tidal channel based on the multi-attribute fusion data volume, the geometric features of the tidal channel, the internal structural features of the tidal channel, the pull-down anomaly data based on porosity correction in the tidal channel, and the preset heterogeneity classification model.

[0057] This specification also provides a computer device including a processor and a memory for storing processor-executable instructions, the processor performing the steps of the method for determining the heterogeneity based on tidal channels.

[0058] This specification also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the steps of the method for determining the heterogeneity of tidal channels.

[0059] This specification also provides a computer program product comprising a computer program that, when executed by a processor, implements the steps of the method for determining the heterogeneity of tidal channels.

[0060] Based on the method, apparatus, and computer equipment for determining the heterogeneity of tidal channels provided in this specification, before specific implementation, an initial classification model based on random forest can be constructed first; then, using supervised machine learning, a preset heterogeneous classification model adapted to the tidal channel can be trained. In specific implementation, the seismic data of the acquired target area can first be subjected to paleogeomorphological reconstruction to obtain seismic data after paleogeomorphological reconstruction; based on the seismic data after paleogeomorphological reconstruction, instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profiles are acquired and jointly used to determine the geometric characteristics of the tidal channel; then, based on the geometric characteristics of the tidal channel, the seismic data is used to determine the chaotic data volume; and based on the chaotic data volume, the internal structural characteristics of the tidal channel are determined; furthermore, by fusing the instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data... Based on these three different dimensions of data, a multi-attribute fusion data volume with relatively rich and comprehensive information is obtained, which can simultaneously represent the seismic characteristics of the tidal channel from multiple dimensions. Then, based on this multi-attribute fusion data volume and seismic profiles, the pull-down anomaly data within the tidal channel based on porosity correction is determined. Finally, based on the multi-attribute fusion data volume, the geometric characteristics of the tidal channel, the internal structural characteristics of the tidal channel, the pull-down anomaly data within the tidal channel based on porosity correction, and a pre-set heterogeneity classification model, the type of heterogeneity within the tidal channel is determined. This allows for efficient and accurate determination of the type of heterogeneity within the tidal channel, achieving a quantitative characterization of heterogeneity within the tidal channel, and providing precise and effective guidance for subsequent reservoir exploration and development in the target area. Attached Figure Description

[0061] To more clearly illustrate the embodiments of this specification, the accompanying drawings used in the embodiments will be briefly introduced below. The drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 This is a flowchart illustrating a method for determining the heterogeneity of tidal channels, provided in one embodiment of this specification.

[0063] Figure 2 This is a schematic diagram illustrating an embodiment of the method for determining the heterogeneity of tidal channels provided in this specification, applied in a scenario example.

[0064] Figure 3 This is a schematic diagram illustrating an embodiment of the method for determining the heterogeneity of tidal channels provided in this specification, applied in a scenario example.

[0065] Figure 4This is a schematic diagram illustrating an embodiment of the method for determining the heterogeneity of tidal channels provided in this specification, applied in a scenario example.

[0066] Figure 5 This is a schematic diagram illustrating an embodiment of the method for determining the heterogeneity of tidal channels provided in this specification, applied in a scenario example.

[0067] Figure 6 This is a schematic diagram illustrating an embodiment of the method for determining the heterogeneity of tidal channels provided in this specification, applied in a scenario example.

[0068] Figure 7 This is a schematic diagram of the structural composition of a computer device provided in one embodiment of this specification;

[0069] Figure 8 This is a schematic diagram of the structural composition of a device for determining the heterogeneity of tidal channels, provided in one embodiment of this specification.

[0070] Figure 9 This is a schematic diagram illustrating an embodiment of the method for determining the heterogeneity of tidal channels provided in this specification, applied in a scenario example.

[0071] Figure 10 This is a schematic diagram illustrating an embodiment of the method for determining the heterogeneity of tidal channels provided in this specification, applied in a scenario example.

[0072] Figure 11 This is a schematic diagram illustrating an embodiment of the method for determining the heterogeneity of tidal channels provided in this specification, applied in a scenario example.

[0073] Figure 12 This is a schematic diagram illustrating an embodiment of the method for determining the heterogeneity of tidal channels provided in this specification, applied in a scenario example.

[0074] Figure 13 This is a schematic diagram of an embodiment of the method for determining the heterogeneity of tidal channels provided in the embodiments of this specification, applied in a scenario example. Detailed Implementation

[0075] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0076] It should be noted that the information and data related to users involved in the embodiments of this specification are all information and data authorized by the user or fully authorized by the relevant parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with relevant laws, regulations, and standards, and necessary confidentiality measures have been taken. They do not violate public order and good morals, and corresponding operation entry points are provided for users or relevant parties to choose to authorize or refuse.

[0077] It should also be noted that in the embodiments of this specification, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0078] See Figure 1 As shown in the embodiments of this specification, a method for determining the heterogeneity of tidal channels is provided. Specifically, this method may include the following:

[0079] S101: Acquire seismic data of the target area; and perform paleogeographic reconstruction on the seismic data to obtain seismic data after paleogeographic reconstruction;

[0080] S102: Based on the earthquake data after the ancient landform reconstruction, obtain the corresponding instantaneous frequency data volume, instantaneous amplitude data volume, and earthquake profile;

[0081] S103: Determine the geometric characteristics of the tidal channel based on the instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile;

[0082] S104: Based on the geometric characteristics of the tidal channel, the chaotic data volume is determined using the seismic data; and based on the chaotic data volume, the internal structural characteristics of the tidal channel are determined.

[0083] S105: Merge the instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume to obtain the corresponding multi-attribute fused data volume;

[0084] S106: Based on the multi-attribute fusion data volume and seismic profile, determine the pull-down anomaly data in the tidal channel based on porosity correction;

[0085] S107: Based on the multi-attribute fusion data volume, the geometric features of the tidal channel, the internal structural features of the tidal channel, the pull-down anomaly data based on porosity correction in the tidal channel, and the preset heterogeneity classification model, determine the heterogeneity type in the tidal channel.

[0086] The aforementioned target areas can be understood as areas of interest for exploration and development. Specifically, these target areas can be regions with carbonate rock development, such as lagoon areas, tidal flat areas, inner platform areas, etc.

[0087] The aforementioned tidal channel (carbonate tidal channel, also known as paleotidal channel) can be understood as a water erosion channel developed in carbonate platform or slope environment, a topographic structure region formed under the control of tidal energy.

[0088] Specifically, tidal channels are typically narrow and tortuous. Further studies have revealed that tidal channels have V-shaped or U-shaped profiles, with significant erosion at the bottom, and are filled with grainy limestone (e.g., clastic limestone, oolitic limestone, etc.). Furthermore, sedimentary structures often exhibit cross-bedding, argillaceous interlayers, and bidirectional cross-bedding, reflecting the periodic alternation of tidal flows. In addition, coarse-grained, high-porosity sedimentary features can be identified in the core samples; and well logging curves show low gamma values, high porosity, and high resistivity, with a clear scour interface and a grain size sequence of fine at the top and coarse at the bottom. These characteristics make tidal channels significant in reservoirs, especially their high porosity and permeability, which often result in complex heterogeneity within them. Simultaneously, these characteristics also lead to complex reservoir connectivity, making them key heterogeneous units in reservoir modeling and development, thus affecting specific reservoir exploration and development.

[0089] The aforementioned seismic data may specifically include a three-dimensional seismic data volume. The aforementioned seismic profile may specifically include a reflection seismic profile obtained based on seismic data. The aforementioned seismic profile can be understood as a two-dimensional seismic data volume.

[0090] The aforementioned instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume can be specifically understood as data volumes extracted from the seismic data that can highlight the implicit feature information in the seismic data from different dimensions. The aforementioned chaotic data volume can specifically be understood as a three-dimensional seismic data volume.

[0091] The aforementioned multi-attribute fusion data volume can be understood as a hybrid data volume obtained by combining instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume. Based on the aforementioned multi-attribute fusion data volume, on the one hand, it can comprehensively and meticulously characterize the multi-attribute feature information hidden in the original seismic data from multiple dimensions; on the other hand, it can also better cover various states involving tidal channels and accurately represent the relevant feature information of tidal channels.

[0092] In practice, the multi-attribute fusion data volume mentioned above can more clearly and in more detail display the distribution characteristics, geometric characteristics, and internal structural characteristics of the carbonate rock tidal channel plane. In turn, it can be combined with seismic profiles to more accurately quantitatively characterize the heterogeneity within the tidal channel.

[0093] The aforementioned pre-defined heterogeneous classification model can be understood as an algorithmic model trained in advance based on a random forest model through supervised learning, capable of predicting the corresponding heterogeneous type based on input data. The training and use of the pre-defined heterogeneous classification model will be explained in detail later.

[0094] Specifically, the Random Forest model can be understood as an algorithmic model that improves the accuracy and stability of predictions by constructing multiple decision trees and combining the results of these decision trees.

[0095] In practice, the process can begin by reconstructing the paleogeography of the seismic data to obtain the reconstructed seismic data. Then, based on this reconstructed data, the corresponding instantaneous frequency and amplitude data volumes can be extracted. Simultaneously, seismic profiles (e.g., reflection seismic profiles) can be obtained from the reconstructed data. Furthermore, the advantages of instantaneous frequency and amplitude data volumes in representing the external features of the tidal channel can be comprehensively utilized. Combined with the seismic profiles, the lateral and longitudinal geometric features of the tidal channel can be determined to define its geometric characteristics. Based on these geometric characteristics, the three-dimensional amplitude data from the seismic data can be used to determine the chaotic data volume. Leveraging the three-dimensional data advantages of the chaotic data volume, the internal structural features of the tidal channel can be accurately and quantitatively determined. Finally, by fusing the instantaneous frequency, amplitude, and chaotic data volumes, a multi-attribute fusion data volume with rich and comprehensive information, capable of representing the characteristic information of the tidal channel from different dimensions, is obtained. By combining multi-attribute fusion data volumes and seismic profiles with corresponding well logging data, the pull-down anomaly data based on porosity correction within the tidal channel is identified. Furthermore, by utilizing a pre-trained, preset heterogeneity classification model, combined with multi-attribute fusion data volumes, the geometric features of the tidal channel, the internal structural features of the tidal channel, and the pull-down anomaly data based on porosity correction within the tidal channel, the heterogeneity type within the tidal channel is finally determined.

[0096] Based on the above embodiments, by introducing and using a pre-defined heterogeneity classification model based on random forest for tidal channels, and combining it with a multi-attribute fusion data volume that is rich in information, comprehensive and with good coverage, based on the fusion of instantaneous frequency data volume, instantaneous amplitude data volume and chaotic data volume, it can be well adapted to the characterization scenario of heterogeneity in tidal channels, and efficiently and accurately determine the type information of heterogeneity in tidal channels.

[0097] In some embodiments, after acquiring seismic data for the target area, noise attenuation processing can be performed on the seismic data to reduce error interference introduced by noise information in the seismic data. Specifically, this may include the following:

[0098] S1: Perform a first noise attenuation process based on median filtering on the seismic data to eliminate random noise in the seismic data and obtain the first denoised seismic data;

[0099] S2: Based on the first denoised seismic data, perform paleogeomorphological restoration of the target layer to obtain the seismic data after paleogeomorphological restoration;

[0100] S3: Perform a second noise attenuation process on the earthquake data after the ancient landform restoration based on frequency wavenumber domain filtering to eliminate coherent noise in the earthquake data and obtain the second noise-reduced earthquake data.

[0101] S4: Based on the second denoised seismic data, the seismic data is subjected to tidal channel boundary strengthening through structural smoothing to obtain seismic data that meets the requirements.

[0102] Specifically, the strengthening of the tidal channel boundary can refer to strengthening the discontinuous boundary of seismic reflection, that is, strengthening the geological boundary of the tidal channel.

[0103] The aforementioned structural smoothing specifically refers to a filtering technique designed for seismic data (especially seismic attribute volumes, horizons, or faults). Its core objective is to smooth noise and enhance the continuity of seismic axes while maximally protecting the boundaries of geological structures, such as faults, channel edges, and unconformities. Specifically, a filtering algorithm based on edge enhancement can be used, primarily through value range weighting to achieve enhancement. At the boundary, where the value differences between the two sides are large, the value range weighting effectively suppresses smoothing across the boundary, thereby protecting the boundary.

[0104] In practice, considering that random noise in seismic data is usually unrelated to geological structure, a preliminary noise attenuation process can be performed on the seismic data to specifically eliminate random noise. Specifically, median filtering can be used for this initial noise attenuation.

[0105] Furthermore, considering that coherent noise is often easily confused by reflected signals, a second noise attenuation process using frequency wavenumber domain filtering (FK) can be employed to specifically eliminate correlated noise in the seismic data. Simultaneously, considering that the second noise attenuation process, if performed after paleomorphological (or paleotectonic) restoration, can effectively reduce the damage to the effective signals in the seismic data, a second noise attenuation process can be performed after the first noise attenuation process, starting with paleomorphological restoration based on the target layer, followed by the second noise attenuation process.

[0106] In this way, random noise and coherent noise in seismic data can be effectively eliminated through two cascaded noise attenuation processes, reducing noise errors in the seismic data. At the same time, the damage to the effective signals in the seismic data caused by the noise attenuation process can also be effectively reduced, thus improving the data quality of the seismic data.

[0107] Finally, considering that paleomorphological restoration will alter the stratigraphic structure, it is advisable to perform tidal channel boundary enhancement on the seismic data after paleomorphological restoration and noise attenuation processing, thereby improving the boundary enhancement effect of the tidal channel.

[0108] Accordingly, after performing structural smoothing on the second denoised seismic data and strengthening the tidal channel boundary of the seismic data to obtain seismic data that meets the requirements, in specific implementation, the above-mentioned seismic data that meets the requirements can be used to replace the seismic data after paleogeographic restoration to obtain instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile with relatively higher accuracy.

[0109] Based on the above embodiments, seismic data can be optimized in a more comprehensive and effective manner, and error interference in seismic data can be eliminated in a targeted manner to obtain high-quality optimized seismic data suitable for processing and analyzing the heterogeneity within tidal channels.

[0110] In some embodiments, see Figure 2 As shown, the geometric characteristics of the tidal channel are determined based on the instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile. In specific implementation, this may include the following:

[0111] S1: Determine the distribution plane of the tidal channel based on the instantaneous frequency data volume and the instantaneous amplitude data volume;

[0112] S2: Using a preset segmented time window, the curvature of multiple segments is calculated on the distribution plane of the tidal channel to obtain the first type of geometric features of the tidal channel;

[0113] S3: Based on the distribution plane of the tidal channel and the seismic profile, perform intersection processing to obtain the corresponding intersection results;

[0114] S4: Based on the intersection results, the second type of geometric features of the tidal channel are obtained by determining the width, depth, and aspect ratio of the tidal channel;

[0115] S5: Combine the first type of geometric features and the second type of geometric features to obtain the geometric features of the tidal channel.

[0116] Specifically, the first type of geometric feature mentioned above can be understood as lateral geometric features. The second type of geometric feature mentioned above can be understood as longitudinal geometric features.

[0117] The above-mentioned intersection processing based on the distribution plane of the tidal channel and the seismic profile to obtain the corresponding intersection result may include the following: First, based on the position coordinates, the data points in the distribution plane of the tidal channel can be projected onto the seismic profile to obtain the intersection seismic profile; on the intersection seismic profile, the position information of the tidal channel plane and the longitudinal reflection characteristics are determined; based on the position information and reflection characteristics, data information about the tidal channel (e.g., the position information of the tidal channel) is determined as the intersection result.

[0118] Specifically, the reflection features may include: U-shaped reflection discontinuities and / or V-shaped reflection discontinuities, etc.

[0119] In practice, by projecting the data points (or sampling points) in the distribution plane of the tidal channel onto the seismic profile, the data points in the distribution plane of the seismic profile and the tidal channel can be unified into the same three-dimensional space, thereby enabling the tidal channel on the seismic profile to be identified on the plane.

[0120] Based on the intersection results, the width, depth, and aspect ratio of the tidal channel are determined. In specific implementation, this may include: determining the location of the tidal channel on the seismic profile after intersection based on the intersection results; identifying the boundary of the tidal channel based on its location; and calculating the tidal channel width, depth, and corresponding aspect ratio based on its location and boundary.

[0121] In specific implementation, when determining the location information of the tidal channel plane on the seismic profile after intersection, in addition to identifying the plane-based location information (x, y) (or plane location information) of the tidal channel after intersection, the longitudinal location information (z) can also be determined by acquiring and based on reflection characteristics. The reflection characteristics inside and outside the tidal channel differ, forming U-shaped or V-shaped reflection discontinuities. Therefore, the longitudinal location information of the tidal channel can be determined using these reflection characteristics.

[0122] Based on the above embodiments, the first type of geometric features of the tidal channel can be obtained by combining instantaneous frequency data volume and instantaneous amplitude data volume; then, by combining the distribution plane of the tidal channel determined based on the instantaneous frequency data volume and instantaneous amplitude data volume with the seismic profile, the second type of geometric features of the tidal channel can be obtained through intersection processing, thereby obtaining the geometric features of the tidal channel more comprehensively and accurately.

[0123] In some embodiments, see Figure 3 As shown, the above-mentioned method uses a preset segmented time window to calculate the curvature of multiple segments on the distribution plane of the tidal channel. In specific implementation, it may include the following:

[0124] S1: Based on the distribution plane of the tidal channel, determine the maximum width of the tidal channel within the target area, as well as its planar distribution characteristics;

[0125] S2: Determine the matching time window length based on the maximum width of the tidal channel within the target area; and construct a preset segmented time window based on this time window length;

[0126] S3: Based on the distribution plane of the tidal channel, according to the plane distribution characteristics and the time window length, the tidal channel is divided into multiple segments;

[0127] S4: Using a preset segmented time window, calculate the curvature of each segment in the plurality of segments respectively.

[0128] For specific implementation, please refer to Figure 4 As shown, the time window length can be set to an integer multiple (e.g., 10 times) of the maximum width of the tidal channel within the target area. This ensures that the channel range, including the start and end points of the tidal channel, can be covered by moving an integer number of times using the preset segmented time window.

[0129] In practice, the overall extension direction of the tidal channel in the target area can be determined first based on the planar distribution characteristics of the tidal channel. Then, on the distribution plan of the tidal channel, starting from the starting point of the tidal channel, the tidal channel can be divided into multiple segments along the overall extension direction using the time window length. The end point of the last segment is the end point of the tidal channel.

[0130] In practice, starting from the beginning of the tidal channel, the curvature of the initial segment containing the starting point of the tidal channel is calculated using a preset segmented time window. After calculating the curvature of the initial segment, the preset segmented time window is moved along the overall extension direction to calculate the curvature of the next segment. This continues until the curvature of the final segment, which includes the endpoint, is calculated. Combining the curvatures of these multiple segments yields the first type of geometric feature of the tidal channel.

[0131] When calculating the curvature of each segment, a preset segmentation time window can be used on the distribution plane of the tidal channel to determine the current segment region; and the centerline length of the tidal channel in the current segment region (e.g., Lc) and the distance between the start and end points of the tidal channel in the current segment region (e.g., Lv) can be determined; then the curvature of the current segment can be determined by calculating the ratio of the centerline length of the tidal channel in the current segment region to the distance between the start and end points of the tidal channel in the current segment region (e.g., S=Lc / Lv).

[0132] Based on the above embodiments, by introducing and using a preset segmented time window, the curvature of each segment of the supersystem can be accurately calculated, and the corresponding first-class geometric features can be obtained efficiently and accurately.

[0133] In some embodiments, the determination of the internal structural features of the tidal channel based on the chaotic data volume may include the following:

[0134] S1: Based on the geometric characteristics of the tidal channel, determine the local seismic data corresponding to the interior of the tidal channel in the chaotic data volume;

[0135] S2: Based on the local seismic data corresponding to the interior of the tidal channel, the internal reflection characteristics of the tidal channel are extracted;

[0136] S3: Based on the internal reflection characteristics of the tidal channel, the internal structural characteristics of the tidal channel are obtained by determining the internal structural shape of the tidal channel.

[0137] The internal structural shape of the tidal channel may specifically include at least one of the following: block structure, layered bedding structure, and cross-bedding structure.

[0138] In practice, based on the geometric characteristics of the tidal channel and using the seismic data, a chaotic data volume with good three-dimensional data advantages and capable of effectively reflecting the internal information of the tidal channel can be determined.

[0139] In practice, based on the geometric characteristics of the tidal channel, a qualitative analysis of the internal structural features of the tidal channel can be performed using seismic profiles from a relatively simple two-dimensional data perspective, yielding the corresponding qualitative analysis results. Then, based on the chaotic data volume and guided by the aforementioned two-dimensional data perspective, a more complex and detailed quantitative characterization of the internal structural features of the tidal channel can be performed from a three-dimensional data perspective, ultimately obtaining the internal structural features of the tidal channel.

[0140] Based on the above embodiments, the internal structural features of the tidal channel can be accurately characterized by utilizing the previously determined geometric features and combining them with the reflection features in the seismic profile.

[0141] In some embodiments, the method may further include: acquiring well logging data and core data; wherein the well logging data includes at least imaging well logging data;

[0142] Accordingly, after fusing the instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume to obtain the corresponding multi-attribute fused data volume, the method may further include the following in its specific implementation:

[0143] S1: Based on the core data, key structural features of the tidal channel are determined at the core scale as auxiliary data;

[0144] S2: Use the auxiliary data to calibrate the logging data to obtain calibrated logging data;

[0145] S3: Based on the calibrated logging data, construct logging interpretation results for the tidal channel;

[0146] S4: Using the well logging interpretation results, verify and update the multi-attribute fusion data volume.

[0147] The aforementioned logging data may specifically include one or more of the following: gamma logging data, porosity logging data, resistivity logging data, sonic logging data, density logging data, etc. It should be noted that the logging data listed above is only illustrative. In actual implementation, depending on the specific circumstances and processing requirements, the aforementioned logging data may also include other types of logging data. This specification does not limit this. In practice, various types and modalities of logging data can be acquired using different logging equipment.

[0148] The aforementioned logging data includes at least imaging logging data for subsequent verification and comparison.

[0149] The aforementioned core data may specifically include data obtained from testing core samples collected from core wells in the target area.

[0150] In practice, core interpretation can be carried out first based on core data. Based on the results of core interpretation, geometric features and typical internal structural features used to characterize and distinguish tidal channels from non-tidal channels can be determined at the core scale as key structural features of tidal channels.

[0151] Furthermore, the key structural features determined based on the core data can be used as auxiliary data; the auxiliary data can be used to calibrate the logging data; and then the logging interpretation of the tidal channel can be performed based on the calibrated logging data to determine the typical logging response features used to characterize the distinction between the tidal channel and the non-tidal channel, which can be used as the logging interpretation result of the tidal channel.

[0152] Finally, from a microscopic perspective, based on the above well logging interpretation results, the previously obtained multi-attribute fusion data volume can be verified (e.g., cross-validation) and updated. If they are consistent, the verification is considered successful, and the current multi-attribute fusion data volume can be used as the updated multi-attribute fusion data volume. If they are inconsistent, the verification is considered unsuccessful, and the above multi-attribute fusion data volume can be locally adjusted and modified based on the well logging interpretation results to obtain the updated multi-attribute fusion data volume.

[0153] In practice, auxiliary data and well logging interpretation results can be used together to jointly verify and update the distribution plane of the aforementioned tidal channels.

[0154] Therefore, the updated tidal channel distribution plane can be used to replace the original tidal channel distribution plane in subsequent related data processing.

[0155] In addition, while verifying and updating the distribution plane of the tidal channel using well logging interpretation results, reservoir attribute parameters within the tidal channel, such as porosity and longitudinal and transverse permeability, can also be calculated using the well logging interpretation results for subsequent use.

[0156] Based on the above embodiments, the distribution plane of the tidal channel can be further verified and updated from a microscopic perspective by using core data and well logging data in combination, thereby improving the data accuracy of the tidal channel distribution plane.

[0157] In some embodiments, see Figure 5 As shown, based on the multi-attribute fusion data volume and seismic profile, the pull-down anomaly data within the tidal channel based on porosity correction is determined. In specific implementation, this may include the following:

[0158] S1: Based on the multi-attribute fusion data volume, the underlying layer located below the tidal channel is determined; and by interpreting the underlying layer, the corresponding structural plane is obtained;

[0159] S2: Based on the structural plane, determine the seismic reflection anomaly region on the seismic profile; and determine the pull-down anomaly data in the tidal channel from the seismic reflection anomaly region;

[0160] S3: Based on the well logging data and the pull-down anomaly data in the tidal channel, construct the correspondence between the pull-down anomaly data and porosity;

[0161] S4: Based on the correspondence between the pull-down anomaly data and porosity, and the constructed plane, the corresponding pull-down anomaly plane is calculated;

[0162] S5: Based on the aforementioned pull-down anomaly plane, determine the pull-down anomaly data within the tidal channel based on porosity correction.

[0163] The above-mentioned method involves determining anomaly regions of seismic reflection on the seismic profile based on the structural plane, and identifying pull-down anomaly data within the tidal channel from these anomaly regions. Specifically, this can include: identifying anomaly locations of seismic reflection by detecting pull-down phenomena at the strata below the tidal channel on the seismic profile based on the structural plane, thereby determining the anomaly regions; further, detecting whether these anomaly locations are within the tidal channel. If not, they are ignored. If within the tidal channel, the anomaly value of the anomaly location is calculated based on the normal pull-down values ​​of neighboring normal locations, thus obtaining the pull-down anomaly data within the tidal channel.

[0164] The above-mentioned correspondence between pull-down anomaly data and porosity is constructed based on the well logging data and pull-down anomaly data in the tidal channel. In specific implementation, it may include: selecting corresponding normal and abnormal location points in the seismic profile; obtaining and utilizing the normal values ​​and well logging porosity of the corresponding normal location points and the abnormal values ​​and well logging porosity of the abnormal location points based on the well logging data, and constructing the correspondence between pull-down anomaly data and porosity through cross-validation.

[0165] In practice, based on the correspondence between the pull-down anomaly data and porosity, and the aforementioned structural plane, the corresponding pull-down anomaly plane can be obtained by calculating the average structural plane. Then, based on this pull-down anomaly plane, pull-down anomaly data within the tidal channel, corrected for porosity, can be acquired.

[0166] Based on the above embodiments, by constructing and using the corresponding pull-down anomaly plane, the required pull-down anomaly data based on porosity correction within the tidal channel can be obtained efficiently and comprehensively.

[0167] In some embodiments, see Figure 6 As shown, based on the multi-attribute fusion data volume, the geometric features of the tidal channel, the internal structural features of the tidal channel, the pull-down anomaly data based on porosity correction within the tidal channel, and the preset heterogeneity classification model, the heterogeneity type within the tidal channel is determined. In specific implementation, this may include the following:

[0168] S1: Based on the multi-attribute fusion data volume, the top interface image of the tidal channel, the edge interface image of the tidal channel, and the bottom interface image of the tidal channel are obtained;

[0169] S2: Based on the top interface diagram, side interface diagram, and bottom interface diagram of the tidal channel, a structural model of the tidal channel is established.

[0170] S3: Determine the spatial coordinate parameters of the tidal channel based on the tidal channel construction model;

[0171] S4: Based on the spatial coordinate parameters of the tidal channel, the geometric features of the tidal channel, the internal structural features of the tidal channel, and the pull-down anomaly data based on porosity correction within the tidal channel, the corresponding heterogeneous attribute matrix of the tidal channel is constructed.

[0172] S5: Using a preset heterogeneity classification model, the heterogeneity type within the tidal channel is determined by processing the heterogeneity attribute matrix of the tidal channel.

[0173] In practical implementation, using the aforementioned tidal channel construction model, not only can the spatial coordinate parameters of the tidal channel be determined, but also the geometric features, internal structural features, and the correspondence between the tidal channel's porosity-corrected pull-down anomaly data and spatial coordinate parameters can be simultaneously determined. Then, based on this correspondence, the geometric features, internal structural features, and porosity-corrected pull-down anomaly data of the tidal channel can be correlated with the spatial coordinate parameters. Finally, based on the spatial coordinate parameters and the correlated geometric features, internal structural features, and porosity-corrected pull-down anomaly data of the tidal channel, a relatively accurate and suitable heterogeneous attribute matrix of the tidal channel for subsequent model processing can be constructed.

[0174] In practice, the heterogeneous attribute matrix of the tidal channel can be used as the model input and fed into a preset heterogeneity classification model; the model can be run to obtain the classification results output by the model; and the heterogeneity type within the tidal channel can be determined based on the classification results.

[0175] Based on the above embodiments, by utilizing a preset heterogeneity classification model to process the information-rich heterogeneity attribute matrix of the tidal channel constructed from the spatial coordinate parameters of the tidal channel, the geometric features of the tidal channel, the internal structural features of the tidal channel, and the down-pulling anomaly data based on porosity correction within the tidal channel, the heterogeneity type within the tidal channel can be accurately predicted.

[0176] In some embodiments, the preset heterogeneous classification model may be specifically obtained by supervised learning based on a random forest model.

[0177] Before implementation, a pre-defined heterogeneous classification model can be trained using the following methods:

[0178] S1: Obtain sample reference data from the explored areas adjacent to the target area;

[0179] S2: Perform statistical analysis and cluster learning on the sample reference data to determine the number of heterogeneous types;

[0180] S3: Based on the number of heterogeneous types, determine the appropriate random forest model to construct the corresponding initial classification model;

[0181] S4: Use sample reference data to perform supervised machine learning on the initial classification model to obtain a pre-defined heterogeneous classification model that meets the requirements.

[0182] In some embodiments, the heterogeneity type within the tidal channel may specifically include at least one of the following: homogeneous body, weakly heterogeneous body, moderately heterogeneous body, strongly heterogeneous body, etc.

[0183] It should be noted that the types of heterogeneity listed above are merely illustrative. In practice, other suitable types may be included depending on the specific circumstances and processing requirements. This specification does not limit this.

[0184] In some embodiments, after determining the type of heterogeneity within the tidal channel based on the multi-attribute fusion data volume, the geometric features of the tidal channel, the internal structural features of the tidal channel, the pull-down anomaly data based on porosity correction within the tidal channel, and a preset heterogeneity classification model, the method may further include the following in its specific implementation:

[0185] Based on the heterogeneity type within the tidal channel, the location of the high-permeability zone in the target area is determined. Based on the location of this high-permeability zone, the location information of development wells and horizontal wells is optimized and adjusted to provide optimized guidance for well placement. Furthermore, after determining the location information of development wells and horizontal wells, reference information regarding the morphology, density, and orientation of the well network in the target area can be determined based on the heterogeneity type within the tidal channel. Based on this reference information, an injection-production well network is designed and deployed for the target area. This allows for better reservoir exploration and development in the target area.

[0186] As can be seen from the above, based on the method for determining the heterogeneity of tidal channels provided in the embodiments of this specification, before specific implementation, an initial classification model based on random forest can be constructed first; then, the initial classification model can be used to train a preset heterogeneous classification model adapted to the tidal channel through supervised learning. In practice, the seismic data of the target area can first be subjected to paleogeographic reconstruction to obtain the reconstructed seismic data. Based on the reconstructed seismic data, instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profiles are acquired and used to jointly determine the geometric characteristics of the tidal channel. Then, based on the geometric characteristics of the tidal channel, the seismic data is used to determine the chaotic data volume. Based on the chaotic data volume, the internal structural characteristics of the tidal channel are determined through quantitative characterization. Furthermore, the instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume are fused to obtain a more comprehensive and information-rich multi-attribute fusion data volume. Based on the multi-attribute fusion data volume and seismic profiles, the pull-down anomaly data within the tidal channel based on porosity correction is determined. Then, based on the multi-attribute fusion data volume, the geometric characteristics of the tidal channel, the internal structural characteristics of the tidal channel, the pull-down anomaly data within the tidal channel based on porosity correction, and a preset heterogeneity classification model, the heterogeneity type within the tidal channel is determined. This enables the efficient and accurate determination of the type of heterogeneity within the tidal channel, achieving a quantitative characterization of the heterogeneity within the tidal channel, and providing precise and effective guidance for subsequent reservoir exploration and development in the target area.

[0187] This specification provides an embodiment of a computer device, see below. Figure 7 As shown. The computer device includes a network communication port 701, a processor 702, and a memory 703. These structures are connected by internal cables so that they can perform specific data interaction.

[0188] Specifically, the network communication port 701 can be used to acquire seismic data of the target area and perform paleogeographic reconstruction on the seismic data to obtain seismic data after paleogeographic reconstruction.

[0189] The processor 702 can specifically be used to acquire corresponding instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile based on the seismic data after the ancient landform reconstruction; determine the geometric features of the tidal channel based on the instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile; determine the chaotic data volume using the seismic data based on the geometric features of the tidal channel; determine the internal structural features of the tidal channel based on the chaotic data volume; fuse the instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume to obtain a corresponding multi-attribute fused data volume; determine the pull-down anomaly data based on porosity correction within the tidal channel based on the multi-attribute fused data volume and the seismic profile; and determine the heterogeneity type within the tidal channel based on the multi-attribute fused data volume, the geometric features of the tidal channel, the internal structural features of the tidal channel, the pull-down anomaly data based on porosity correction within the tidal channel, and a preset heterogeneity classification model.

[0190] The memory 703 can be used to store the corresponding instruction program and related intermediate data.

[0191] Based on the above method, the relevant structural performance of computer equipment can be effectively utilized to improve the data processing speed of electronic equipment and efficiently realize the determination of data processing based on the heterogeneity of tidal channels.

[0192] In this embodiment, the network communication port 701 can be a virtual port bound to different communication protocols, thereby enabling the sending or receiving of different data. For example, the network communication port can be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for email data communication. Furthermore, the network communication port can also be a physical communication interface or communication chip. For example, it can be a wireless mobile network communication chip, such as GSM or CDMA; it can also be a Wi-Fi chip; or it can be a Bluetooth chip.

[0193] In this embodiment, the processor 702 can be implemented in any suitable manner. For example, the processor can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers, etc. This specification is not limiting.

[0194] In this embodiment, the memory 703 may include multiple layers. In a digital system, anything that can store binary data can be a memory. In an integrated circuit, a circuit with storage function but no physical form is also called a memory, such as RAM, FIFO, etc. In a system, a storage device with a physical form is also called a memory, such as a memory stick, TF card, etc.

[0195] This specification also provides a computer-readable storage medium based on the above-described method for determining the heterogeneity of tidal channels. The computer-readable storage medium stores computer program instructions that, when executed, perform the following: acquire seismic data of a target area; perform paleogeographic reconstruction on the seismic data to obtain paleogeographically reconstructed seismic data; acquire corresponding instantaneous frequency data volumes, instantaneous amplitude data volumes, and seismic profiles based on the paleogeographically reconstructed seismic data; determine the geometric characteristics of the tidal channel based on the instantaneous frequency data volumes, instantaneous amplitude data volumes, and seismic profiles; and determine the geometric characteristics of the tidal channel based on the... Using the seismic data, a chaotic data volume is determined based on geometric features. The internal structural features of the tidal channel are then determined based on this chaotic data volume. The instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume are fused to obtain a corresponding multi-attribute fused data volume. Based on this multi-attribute fused data volume and the seismic profile, pull-down anomaly data within the tidal channel based on porosity correction is determined. Finally, based on the multi-attribute fused data volume, the geometric features of the tidal channel, the internal structural features of the tidal channel, the pull-down anomaly data within the tidal channel based on porosity correction, and a pre-defined heterogeneity classification model, the type of heterogeneity within the tidal channel is determined.

[0196] In this embodiment, the storage medium includes, but is not limited to, Random Access Memory (RAM), Read-Only Memory (ROM), Cache, Hard Disk Drive (HDD), or Memory Card. The memory can be used to store computer program instructions. The network communication unit can be an interface configured according to standards specified in the communication protocol for network connection communication.

[0197] In this embodiment, the specific functions and effects implemented by the program instructions stored in the computer-readable storage medium can be explained in comparison with other embodiments, and will not be repeated here.

[0198] This specification also provides a computer program product, comprising at least a computer program, which, when executed by a processor, implements the following method steps: acquiring seismic data of a target area; performing paleogeographic reconstruction on the seismic data to obtain paleogeographically reconstructed seismic data; acquiring corresponding instantaneous frequency data volumes, instantaneous amplitude data volumes, and seismic profiles based on the paleogeographically reconstructed seismic data; determining the geometric characteristics of the tidal channel based on the instantaneous frequency data volumes, instantaneous amplitude data volumes, and seismic profiles; and utilizing the seismic data based on the geometric characteristics of the tidal channel. A chaotic data volume is identified; and based on the chaotic data volume, the internal structural features of the tidal channel are determined; the instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume are fused to obtain a corresponding multi-attribute fused data volume; based on the multi-attribute fused data volume and seismic profiles, the pull-down anomaly data within the tidal channel based on porosity correction is determined; based on the multi-attribute fused data volume, the geometric features of the tidal channel, the internal structural features of the tidal channel, the pull-down anomaly data within the tidal channel based on porosity correction, and a preset heterogeneity classification model, the heterogeneity type within the tidal channel is determined.

[0199] See Figure 8 As shown in the embodiments of this specification, an apparatus for determining the heterogeneity of tidal channels is also provided. This apparatus may specifically include the following structural modules:

[0200] The first acquisition module 801 is specifically used to acquire seismic data of the target area; and to perform paleogeographic restoration on the seismic data to obtain seismic data after paleogeographic restoration.

[0201] The second acquisition module 802 can be specifically used to acquire the corresponding instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile based on the seismic data after the ancient landform is restored.

[0202] The first determining module 803 can be specifically used to determine the geometric characteristics of the tidal channel based on the instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile.

[0203] The second determining module 804 can be specifically used to determine the chaotic data volume based on the geometric characteristics of the tidal channel and the seismic data; and to determine the internal structural characteristics of the tidal channel based on the chaotic data volume.

[0204] The fusion module 805 can be specifically used to fuse the instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume to obtain a corresponding multi-attribute fused data volume;

[0205] The third determining module 806 can be used to determine the pull-down anomaly data based on porosity correction within the tidal channel based on the multi-attribute fusion data volume and seismic profile.

[0206] The fourth determining module 807 can be used to determine the type of heterogeneity in the tidal channel based on the multi-attribute fusion data volume, the geometric features of the tidal channel, the internal structural features of the tidal channel, the pull-down anomaly data based on porosity correction in the tidal channel, and the preset heterogeneity classification model.

[0207] In some embodiments, when the first determining module 803 is specifically implemented, the geometric features of the tidal channel can be determined according to the instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile in the following manner: The distribution plane of the tidal channel is determined according to the instantaneous frequency data volume and instantaneous amplitude data volume; using a preset segmented time window, the curvature of multiple segments on the distribution plane of the tidal channel is calculated to obtain the first type of geometric features of the tidal channel; intersection processing is performed according to the distribution plane of the tidal channel and the seismic profile to obtain the corresponding intersection results; based on the intersection results, the width, depth, and aspect ratio of the tidal channel are determined to obtain the second type of geometric features of the tidal channel; the first type of geometric features and the second type of geometric features are combined to obtain the geometric features of the tidal channel.

[0208] In some embodiments, when the first determining module 803 is specifically implemented, it can use a preset segmented time window in the following manner to calculate the curvature of multiple segments on the distribution plane of the tidal channel: based on the distribution plane of the tidal channel, determine the maximum width of the tidal channel in the target area and the planar distribution characteristics; determine the matching time window length according to the maximum width of the tidal channel in the target area; and construct a preset segmented time window according to the time window length; divide the tidal channel into multiple segments based on the distribution plane of the tidal channel, according to the planar distribution characteristics and the time window length; and calculate the curvature of each segment in the multiple segments using the preset segmented time window.

[0209] In some embodiments, when the second determining module 804 is specifically implemented, the internal structural features of the tidal channel can be determined according to the chaotic data volume in the following manner: based on the geometric features of the tidal channel, local seismic data corresponding to the interior of the tidal channel is determined in the chaotic data volume; based on the local seismic data corresponding to the interior of the tidal channel, the internal reflection features of the tidal channel are extracted; based on the internal reflection features of the tidal channel, the internal structural features of the tidal channel are obtained by determining the internal structural shape of the tidal channel.

[0210] In some embodiments, when the above-described apparatus is specifically implemented, it can also acquire well logging data and core data; wherein, the well logging data includes at least imaging well logging data;

[0211] Accordingly, after fusing the instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume to obtain the corresponding multi-attribute fused data volume, the device, in its specific implementation, can also be used to: determine key structural features of the tidal channel at the core scale based on the core data, as auxiliary data; calibrate the logging data using the auxiliary data to obtain calibrated logging data; construct logging interpretation results for the tidal channel based on the calibrated logging data; and verify and update the multi-attribute fused data volume using the logging interpretation results.

[0212] In some embodiments, when the third determining module 806 is specifically implemented, it can determine the pull-down anomaly data based on porosity correction within the tidal channel according to the multi-attribute fusion data volume and the seismic profile in the following manner: Based on the multi-attribute fusion data volume, determine the underlying layer located below the tidal channel; and obtain the corresponding structural plane by performing stratigraphic interpretation on the underlying layer; based on the structural plane, determine the seismic reflection anomaly region on the seismic profile; and determine the pull-down anomaly data within the tidal channel from the seismic reflection anomaly region; construct a correspondence between the pull-down anomaly data and porosity based on the well logging data and the pull-down anomaly data within the tidal channel; calculate the corresponding pull-down anomaly plane based on the correspondence between the pull-down anomaly data and porosity and the structural plane; and determine the pull-down anomaly data based on porosity correction within the tidal channel based on the pull-down anomaly plane.

[0213] In some embodiments, when the fourth determining module 807 is specifically implemented, it can determine the heterogeneity type within the tidal channel according to the following method based on the multi-attribute fusion data volume, the geometric features of the tidal channel, the internal structural features of the tidal channel, the pull-down anomaly data based on porosity correction within the tidal channel, and a preset heterogeneity classification model: Based on the multi-attribute fusion data volume, the top interface map, the edge interface map, and the bottom interface map of the tidal channel are obtained; based on the top interface map, the edge interface map, and the bottom interface map of the tidal channel, a tidal channel construction model is established; based on the tidal channel construction model, the spatial coordinate parameters of the tidal channel are determined; based on the spatial coordinate parameters, the geometric features, the internal structural features, and the pull-down anomaly data based on porosity correction within the tidal channel, a corresponding tidal channel heterogeneity attribute matrix is ​​constructed; using the preset heterogeneity classification model, the heterogeneity type within the tidal channel is determined by processing the tidal channel heterogeneity attribute matrix.

[0214] In some embodiments, the preset heterogeneous classification model may be specifically obtained by supervised learning based on a random forest model.

[0215] In some embodiments, the heterogeneity type within the tidal channel may specifically include at least one of the following: homogeneous body, weakly heterogeneous body, moderately heterogeneous body, strongly heterogeneous body, etc.

[0216] It should be noted that the units, devices, or modules described in the above embodiments can be implemented by computer chips or physical entities, or by products with certain functions. For ease of description, the above devices are described by dividing them into various modules according to their functions. Of course, in implementing this specification, the functions of each module can be implemented in one or more software and / or hardware, or the module that implements the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection between the devices or units shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0217] As can be seen from the above, the device for determining the heterogeneity of tidal channels provided in the embodiments of this specification can efficiently and accurately determine the type information of heterogeneity within tidal channels, realize the quantitative characterization of heterogeneity within tidal channels, and accurately and effectively guide subsequent reservoir exploration and development in the target area.

[0218] In a specific scenario example, the method for determining the heterogeneity of tidal channels based on the tidal channel provided in this manual can be used to quantitatively characterize the heterogeneity of paleotidal channels in carbonate rocks. The specific implementation process can be found below.

[0219] In this scenario example, considering the unique sedimentary and geomorphological characteristics of carbonate tide channels, they typically exhibit narrow, tortuous V- or U-shaped profiles with a distinct erosion interface at the bottom. The filling material is mostly clastic limestone, oolitic limestone, or shell fragments, often accompanied by sedimentary structures such as cross-bedding, mudstone interlayers, and bioturbation. Coarse-grained, highly rounded retention layers are visible in the core, indicating strong hydrodynamic activity. Well logging responses show low gamma, high porosity, high resistivity, and a clear separation between the RHOB and NPHI curves. On seismic profiles, larger tide channels may appear as trough-shaped reflections or amplitude anomalies, often identified using seismic attribute volumes. Tide channels are often an important component of high-permeability "sweet spot" reservoirs, possessing significant hydrocarbon geological importance. While conventional carbonate tide channel detection methods can predict the planar spatial distribution of tide channels relatively well, they lack rapid and effective methods for detecting the longitudinal and lateral heterogeneity of reservoirs within the tide channels.

[0220] To address the aforementioned issues, this scenario example proposes a quantitative characterization method for reservoir structure and heterogeneity in tidal channels within carbonate rock regions. The main steps include:

[0221] (1) Paleogeomorphological restoration based on seismic data (obtaining seismic data after paleogeomorphological restoration). Restoring the tectonic structure during the formation period of the tidal channel is a key step in revealing the deposition and distribution of the tidal channel. First, the geological strata of the target carbonate rock (tidal channel development strata) are determined, and the strata on the top surface of the tidal channel or the nearest overlying marker strata are selected for geological strata interpretation and flattening, thereby restoring the original morphology of the carbonate rock paleotidal channel on the seismic profile; second, the morphological characteristics of the tidal channel are enhanced to prepare data for subsequent carbonate rock tidal channel identification and analysis. This mainly includes two aspects. The first is to improve the quality of seismic data. Due to the inherent differences in the quality of seismic data, it is often affected by random noise and linear noise, so the calculated attributes often cannot accurately reflect the geological characteristics. For the target of tidal channel identification, targeted optimization processing - series noise attenuation - is carried out to improve the accuracy and precision of seismic data for carbonate rock tidal channel identification. This mainly includes two aspects of technical processing. The first is series noise attenuation (random noise and coherent noise). For random noise, specific methods include fast random noise attenuation techniques such as median filtering. For coherent noise, which is often easily confused with reflected signals, the frequency-wavenumber domain filtering (FK) method can be used here; the second is the enhancement treatment of the tidal channel boundary. This mainly involves strengthening the discontinuous boundaries of seismic reflections, i.e., the geological tidal channel boundary, using structural smoothing techniques. Because the flattening process along the stratigraphic level changes the stratigraphic structure, thus affecting the effect of structural smoothing, boundary enhancement treatment is placed after paleotectonic restoration, which can more effectively enhance the boundary of the paleotidal channel. For details, please refer to... Figure 9 As shown.

[0222] (2) Tidal channel morphology characterization based on seismic reflection. First, for the target geological strata, the distribution and morphology of tidal channels are identified on the plane. Using the seismic data volume after paleogeomorphological reconstruction, the seismic attribute volume is calculated to obtain the instantaneous amplitude volume (e.g., instantaneous amplitude data volume) and instantaneous frequency volume (e.g., instantaneous frequency data volume). Another approach is to select three seismic frequencies on the spectrum: low frequency band (F1), main frequency band (F2), and high frequency band (F3). It is important to note that these three frequencies are three frequency bands rather than a single frequency. Typically, the bandwidth of a frequency band is 2-3 Hz. This is done to reduce frequency leakage caused by time-frequency analysis while generating three frequency volumes representing different geological features at different scales. Second, data fusion is performed on multiple seismic attributes by fusing information from the three high, medium, and low frequency volumes to generate a more information-rich multi-attribute display image. The specific method is three-color fusion technology.

[0223] In practical implementation, multi-attribute analysis can be used to more clearly and meticulously demonstrate the distribution characteristics and lateral patterns of carbonate rock tidal channels. To quantitatively characterize the lateral variation of tidal channels, the channel curvature parameter is used to innovatively design and calculate the curvature of the tidal channel in segments (e.g., pre-defined time windows): S = Lc / Lv; where Lc is the length along the centerline of the tidal channel; and Lv is the straight-line distance between the start and end points of the tidal channel. For details, please refer to [reference needed]. Figure 2 As shown. Next, the longitudinal geometric features of the tidal channel are characterized. The planar distribution of the tidal channel is intersected with the seismic reflection profile (e.g., a seismic profile). The location of the tidal channel is located on the seismic profile, and the boundary of the tidal channel is identified. The geometric features of the tidal channel are quantitatively characterized in three aspects: channel width, channel depth, and corresponding aspect ratio. Finally, based on the reflection characteristics of the seismic data, the internal structure of the tidal channel is characterized as blocky structure, layered bedding, and cross-bedding, etc., and the heterogeneity is quantitatively expressed as 1, 2, and 3. Simultaneously, a seismic attribute chaotic volume (e.g., a chaotic data volume) is generated, and the average chaotic value within the tidal channel is calculated along the seismic profile. For details, please refer to [reference needed]. Figure 10 As shown.

[0224] (3) Characterization of the internal structure of carbonate tidal channels based on core and imaging logging data. First, collect cored wells, imaging logging data, and conventional logging data (e.g., well logging data) from the work area, and interpret the core and logging data (imaging logging and conventional logging) to obtain core data. Identify tidal channels on the core and logging data, and cross-validate the interpretation results with seismic identification of tidal channels to improve the accuracy of tidal channel identification. Second, for well data within the tidal channels, identify and characterize the internal structural features of the tidal channels at the core and imaging logging scale: blocky structure, layered bedding, and cross-bedding, etc., and cross-validate and fuse the core and logging features with the corresponding seismic reflection features. Finally, calculate the reservoir properties (porosity and longitudinal and transverse permeability) within the tidal channels on the logging data. For details, please refer to [reference needed]. Figure 11 and Figure 12 .

[0225] (4) Heterogeneous analysis of carbonate tidal channel reservoirs based on seismic reflection. First, an underlying stratum beneath a carbonate tidal channel is selected for stratigraphic interpretation, resulting in a structural plan (e.g., structural plane) of that stratum. Second, on the seismic profile, seismic reflection anomalies of that stratum beneath the carbonate tidal channel are identified, such as the seismic reflection "pull-down" phenomenon. The correspondence between this anomaly and the carbonate tidal channel is examined. If it is located within the tidal channel, the pull-down value relative to adjacent normal reflections is measured, and the anomaly value is quantitatively expressed. Then, for anomaly and non-anomaly points within the tidal channel, well logging porosity at the corresponding locations is selected for cross-validation to establish the correspondence between pull-down anomaly values ​​and porosity. Finally, based on the structural plan of the underlying stratum, the average structural surface is calculated to finally generate a pull-down anomaly plan (e.g., pull-down anomaly plane). For details, please refer to [reference needed]. Figure 13 .

[0226] (5) Modeling of the heterogeneity of carbonate tidal channels. First, based on the multi-seismic attribute fusion data volume from the previous steps, the top surface map of the tidal channel is extracted, and a "discontinuous" seismic attribute volume is generated to extract the edges and bottom interfaces of the tidal channel. Second, using the top surface structural map and the edge and bottom interface maps of the tidal channel, a paleotidal channel structural model is established, in which the width and depth of the tidal channel are reflected. Then, a heterogeneous attribute matrix of the tidal channel is established, mainly including the spatial coordinates of the tidal channel, the geometric parameters of the tidal channel (curvature, aspect ratio), the internal structural parameters of the channel, and the down-pulling anomalies corrected for porosity, while generating the corresponding attribute model. Finally, based on the porosity and permeability data of the well points, the random forest algorithm (e.g., a pre-defined heterogeneous classification model) is used to classify the various attributes of the heterogeneous attribute matrix.

[0227] Through the above scenario examples, it is verified that the method for determining the heterogeneity of tidal channels provided in this specification, by employing multi-frequency fusion based on paleogeographic reconstruction and unsupervised machine learning techniques, can quickly and accurately identify the distribution of sweet spots within carbonate paleotidal channels and quantitatively characterize their development types. Furthermore, by proposing a method for identifying and quantitatively characterizing sweet spots within carbonate paleotidal channels, the distribution of sweet spots within these channels can be quickly and accurately predicted, quantitatively characterized, and classified, providing data support for subsequent well location optimization and reservoir development.

[0228] While this specification provides the steps of operation for the methods described in the embodiments or flowcharts, more or fewer steps may be included based on conventional or non-inventive means. The order of steps listed in the embodiments is merely one possible order of execution among many steps and does not represent the only possible order. In actual device or client product execution, the methods shown in the embodiments or drawings may be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed data processing environment). The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitations, the presence of other identical or equivalent elements in a process, method, product, or apparatus that includes said elements is not excluded. The terms "first," "second," etc., are used to denote names and do not indicate any particular order.

[0229] Those skilled in the art will also know that, besides implementing the controller using purely computer-readable program code, the same functions can be achieved by logically programming the method steps, making the controller function as logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices within it used to implement various functions can also be considered structures within that hardware component. Alternatively, the devices used to implement various functions can be considered as both software modules implementing the method and structures within a hardware component.

[0230] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer-readable storage media, including storage devices.

[0231] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this specification can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions of this specification can essentially be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, mobile terminal, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments of this specification.

[0232] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. This specification can be used in numerous general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices, etc.

[0233] Although this specification has been described by way of examples, those skilled in the art will recognize that many variations and modifications are possible without departing from the spirit of this specification, and it is intended that the appended claims cover such variations and modifications without departing from the spirit of this specification.

Claims

1. A method for determining the heterogeneity of tidal channels, characterized in that, include: Acquire seismic data for the target area; and perform paleogeographic reconstruction on the seismic data to obtain seismic data after paleogeographic reconstruction. Based on the earthquake data after the ancient landform was reconstructed, the corresponding instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile were obtained; Based on the instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile, the geometric characteristics of the tidal channel are determined; Based on the geometric characteristics of the tidal channel, the chaotic data volume is determined using the seismic data; and based on the chaotic data volume, the internal structural characteristics of the tidal channel are determined. By fusing the instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume, a corresponding multi-attribute fused data volume is obtained; Based on the multi-attribute fusion data volume and seismic profile, pull-down anomaly data based on porosity correction within the tidal channel were determined; Based on the multi-attribute fusion data volume, the geometric features of the tidal channel, the internal structural features of the tidal channel, the pull-down anomaly data based on porosity correction within the tidal channel, and the preset heterogeneity classification model, the heterogeneity type within the tidal channel is determined.

2. The method according to claim 1, characterized in that, The determination of the geometric characteristics of the tidal channel based on the instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile includes: The distribution plane of the tidal channel is determined based on the instantaneous frequency data volume and the instantaneous amplitude data volume; Using a preset segmented time window, the curvature of multiple segments is calculated on the distribution plane of the tidal channel to obtain the first type of geometric features of the tidal channel. Based on the distribution plane of the tidal channel and the seismic profile, intersection processing is performed to obtain the corresponding intersection results; Based on the intersection results, the second type of geometric features of the tidal channel are obtained by determining the width, depth, and aspect ratio of the tidal channel. By combining the first type of geometric features and the second type of geometric features, the geometric features of the tidal channel are obtained.

3. The method according to claim 2, characterized in that, The method of using a preset segmented time window to calculate the curvature of multiple segments on the distribution plane of the tidal channel includes: Based on the distribution plane of the tidal channel, determine the maximum width of the tidal channel within the target area, as well as its planar distribution characteristics; Based on the maximum width of the tidal channel within the target area, determine the matching time window length; and construct a preset segmented time window based on this time window length. Based on the distribution plane of the tidal channel, and according to the planar distribution characteristics and the time window length, the tidal channel is divided into multiple segments; Using a preset segmented time window, the curvature of each segment in the plurality of segments is calculated.

4. The method according to claim 1, characterized in that, The determination of the internal structural features of the tidal channel based on the chaotic data volume includes: Based on the geometric characteristics of the tidal channel, local seismic data corresponding to the interior of the tidal channel are determined in the chaotic data volume; Based on the local seismic data corresponding to the interior of the tidal channel, the internal reflection characteristics of the tidal channel are extracted; Based on the internal reflection characteristics of the tidal channel, the internal structural characteristics of the tidal channel are obtained by determining the internal structural shape of the tidal channel.

5. The method according to claim 1, characterized in that, The method further includes: acquiring well logging data and core data; wherein the well logging data includes at least imaging well logging data; Accordingly, after fusing the instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume to obtain the corresponding multi-attribute fused data volume, the method further includes: Based on the core data, key structural features of the tidal channel were determined at the core scale as auxiliary data; The logging data is calibrated using the auxiliary data to obtain calibrated logging data. Based on the calibrated logging data, logging interpretation results regarding the tidal channel are constructed; The multi-attribute fused data volume is verified and updated using the well logging interpretation results.

6. The method according to claim 5, characterized in that, The step of determining the pull-down anomaly data based on porosity correction within the tidal channel, based on the multi-attribute fused data volume and seismic profile, includes: Based on the multi-attribute fusion data volume, the underlying layer located below the tidal channel is determined; and by interpreting the stratigraphic position of this underlying layer, the corresponding structural plane is obtained. Based on the structural plane, anomaly regions of seismic reflection are identified on the seismic profile; and down-pulling anomaly data within the tidal channel are identified from the anomaly regions of seismic reflection. Based on the well logging data and the pull-down anomaly data in the tidal channel, a correspondence between the pull-down anomaly data and porosity is constructed; Based on the correspondence between the pull-down anomaly data and porosity, and the constructed plane, the corresponding pull-down anomaly plane is calculated. Based on the aforementioned pull-down anomaly plane, pull-down anomaly data within the tidal channel, corrected for porosity, are determined.

7. The method according to claim 1, characterized in that, The process involves determining the type of heterogeneity within the tidal channel based on the multi-attribute fusion data volume, the geometric features of the tidal channel, the internal structural features of the tidal channel, the pull-down anomaly data within the tidal channel based on porosity correction, and a preset heterogeneity classification model. This includes: Based on the multi-attribute fusion data volume, the top interface image, the side interface image, and the bottom interface image of the tidal channel are obtained. Based on the top interface diagram, side interface diagram, and bottom interface diagram of the tidal channel, a structural model of the tidal channel is established. Based on the tidal channel construction model, the spatial coordinate parameters of the tidal channel are determined; Based on the spatial coordinate parameters of the tidal channel, the geometric features of the tidal channel, the internal structural features of the tidal channel, and the pull-down anomaly data based on porosity correction within the tidal channel, a corresponding heterogeneous attribute matrix of the tidal channel is constructed. By using a pre-defined heterogeneity classification model and processing the heterogeneity attribute matrix of the tidal channel, the heterogeneity type within the tidal channel is determined.

8. The method according to claim 7, characterized in that, The preset heterogeneous classification model is obtained in advance through supervised learning based on a random forest model.

9. The method according to claim 1, characterized in that, The heterogeneity type within the tidal channel includes at least one of the following: homogeneous body, weakly heterogeneous body, moderately heterogeneous body, and strongly heterogeneous body.

10. A device for determining the heterogeneity of tidal channels, characterized in that, include: The first acquisition module is used to acquire seismic data for the target area; The earthquake data was then subjected to paleogeographic reconstruction to obtain the earthquake data after paleogeographic reconstruction. The second acquisition module is used to acquire the corresponding instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile based on the seismic data after the ancient landform is restored. The first determining module is used to determine the geometric characteristics of the tidal channel based on the instantaneous frequency data volume, instantaneous amplitude data volume, and seismic profile. The second determining module is used to determine the chaotic data volume based on the geometric characteristics of the tidal channel and the seismic data; and to determine the internal structural characteristics of the tidal channel based on the chaotic data volume. The fusion module is used to fuse the instantaneous frequency data volume, instantaneous amplitude data volume, and chaotic data volume to obtain a corresponding multi-attribute fused data volume; The third determining module is used to determine the pull-down anomaly data based on porosity correction within the tidal channel based on the multi-attribute fusion data volume and the seismic profile. The fourth determining module is used to determine the type of heterogeneity in the tidal channel based on the multi-attribute fusion data volume, the geometric features of the tidal channel, the internal structural features of the tidal channel, the pull-down anomaly data based on porosity correction in the tidal channel, and the preset heterogeneity classification model.

11. A computer device, characterized in that, It includes a processor and a memory for storing processor-executable instructions, wherein the processor, when executing the instructions, implements the steps of the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, It stores computer instructions that, when executed by a processor, implement the steps of the method according to any one of claims 1 to 9.

13. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1 to 9.

Images