Seismic attribute inversion and ancient karst form modeling fused reservoir identification method

Abstract

The invention discloses a reservoir identification method fusing seismic attribute inversion and ancient karst form modeling, and relates to the technical field of reservoir identification and modeling, and the method comprises the steps: carrying out the multi-modal fusion processing of a standardized image data set through an image sensor, obtaining the multi-modal fusion image data, executing the high-precision texture sampling and space alignment processing, and obtaining a multi-modal image data set; generating a cross-modal image fusion matrix; inputting the cross-modal image fusion matrix into an image topological graph structure construction process, establishing an image block node relationship and a spatial connection edge weight, and generating an ancient karst topological graph; and coupling the karst earthquake joint matching graph with the comprehensive reservoir attribute data, establishing an effective reservoir evaluation model, and generating a multi-stage reservoir prediction layer set through weighted fusion and multi-parameter spatial analysis. By constructing an ancient karst topological graph and a karst earthquake joint matching graph, spatial modeling of a complex karst structure and cross-modal correlation analysis of earthquake abnormal attributes are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of reservoir identification and modeling, and in particular to a reservoir identification method integrating seismic attribute inversion and paleokarst morphology modeling. Background Art

[0002] With the continuous exploration and development of unconventional oil and gas resources, reservoir identification technology under complex geological conditions has gradually become a research hotspot in the fields of oil and gas geophysics and geological modeling. Seismic attribute inversion technology, as a key bridge connecting seismic data with geological attribute parameters, can effectively mine various subsurface information contained in seismic data, such as lithology, porosity, and fracture development, and has been widely used in reservoir prediction and fine structural interpretation.

[0003] Existing technologies still have certain limitations in fusing paleokarst morphology with seismic attribute inversion data. Most current methods focus on extracting features from a single modality for modeling. They lack in-depth fusion mechanisms for multi-source geological data, especially cross-modal collaboration between image data and seismic attribute volumes. This makes it difficult to fully present the coupling relationship between karst structural characteristics and seismic anomaly attributes. In addition, in the process of establishing paleokarst spatial morphology maps, existing technologies often rely on traditional geometric modeling methods and fail to fully introduce graph structure theory to characterize the topological relationship between image blocks. As a result, it is difficult to accurately express the spatial connectivity and weight distribution between key nodes in the karst system. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a reservoir identification method that integrates seismic attribute inversion and paleokarst morphology modeling to solve the problems of insufficient cross-modal fusion between multi-source data and inaccurate expression of karst structure topological relationships.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a reservoir identification method that integrates seismic attribute inversion and paleokarst morphology modeling, which includes collecting multi-source geological image datasets, performing format unification, spatial label binding, image enhancement and scale normalization processing to construct a standardized image dataset, and combining it with seismic inversion calculation to generate a structured seismic inversion attribute volume;

[0008] The standardized image dataset is processed by multimodal fusion using an image sensor to obtain multimodal fusion image data and perform high-precision texture sampling and spatial alignment processing to generate a cross-modal image fusion matrix.

[0009] The cross-modal image fusion matrix is ​​input into the image topology structure construction process to establish the image block node relationship and spatial connection edge weight to generate the paleokarst topology map;

[0010] The paleokarst topology map is spatially superimposed with the structured seismic inversion attribute volume. Through spatial position correspondence and feature matching, the correlation between the topological structure and seismic anomaly attributes is analyzed to generate a karst-seismic joint matching map.

[0011] The karst seismic joint matching map is coupled with the comprehensive reservoir attribute data to establish an effective reservoir evaluation model, and a multi-level reservoir prediction layer set is generated through weighted fusion and multi-parameter spatial analysis.

[0012] As a preferred solution of the reservoir identification method integrating seismic attribute inversion and paleokarst morphology modeling described in the present invention, the specific steps of constructing a standardized image dataset are as follows:

[0013] Collect core section images, drilling profile images, landform outcrop remote sensing images, well logging curve images, and seismic profile images of the target area to construct an original multi-source geological image dataset;

[0014] The original multi-source geological image data set is uniformly converted into a grayscale image format to obtain a unified format original geological grayscale image set;

[0015] The unified format original geological grayscale image set is processed by format unification, spatial label binding, image enhancement and scale normalization to generate a standardized image dataset.

[0016] As a preferred solution of the reservoir identification method integrating seismic attribute inversion and paleokarst morphology modeling described in the present invention, the specific steps of generating a structured seismic inversion attribute volume are as follows:

[0017] Extract the 3D seismic reflection data corresponding to the target area from the standardized image dataset and perform spatial coordinate alignment to obtain a spatially aligned seismic data volume. Then perform pixel position mapping and sampling point number matching operations to establish a structural index table.

[0018] Through the structure index table, the reflection waveform extraction and physical attribute function calculation are performed on the spatially aligned seismic data volume to obtain the initial seismic attribute volume set;

[0019] Multi-attribute fusion processing is performed on the initial seismic attribute volume set to obtain a fused seismic feature volume, which is then resampled and archived according to the spatial voxel structure to form a structured seismic inversion attribute volume.

[0020] As a preferred solution of the reservoir identification method of the present invention that integrates seismic attribute inversion and paleokarst morphology modeling, the method uses an image sensor to perform multimodal fusion processing on a standardized image data set to obtain multimodal fusion image data. The specific steps are as follows:

[0021] Using image sensors, digitally read and extract multimodal information from multi-source geological image information in standardized image datasets, extracting multi-scale texture features and spatial structure features;

[0022] Multi-scale texture features and spatial structure features are combined through spatial registration, feature extraction and weighted fusion operations to generate multimodal fused image data.

[0023] As a preferred solution of the reservoir identification method of the present invention that integrates seismic attribute inversion and paleokarst morphology modeling, the specific steps of performing high-precision texture sampling and spatial alignment processing to generate a cross-modal image fusion matrix are as follows:

[0024] According to the spatial range of the multimodal fusion image data, a unified reference grid is constructed through boundary coordinate extraction and regular grid division operations. Local resampling processing is performed on the texture channels in the multimodal fusion image data to obtain a multimodal texture resampled image set.

[0025] Extract spatial structure direction information from a multimodal texture resampled image set, and construct the main texture direction field through multi-scale gradient tensor analysis and direction consistency interpolation operations;

[0026] The main texture direction field is aligned with the spatial normal distribution of the unified reference grid to obtain the texture direction field, and a cross-modal image fusion matrix is ​​generated through feature mapping and weighted fusion operations.

[0027] As a preferred solution of the reservoir identification method of the present invention that integrates seismic attribute inversion and paleokarst morphology modeling, the specific steps of generating the paleokarst topology map are as follows:

[0028] Adaptive region growing algorithm is used to spatially segment the cross-modal image fusion matrix to form multiple spatially connected image block nodes, and texture intensity mean, local geometric parameters and spatial three-dimensional coordinates are extracted. Feature vector normalization and fusion processing are then performed to construct a multi-dimensional feature vector.

[0029] Calculate the similarity and spatial adjacency between multi-dimensional feature vector nodes, generate weighted connection edges, combine image block nodes with weighted connection edges, and generate image topology structure;

[0030] The low-weight edges and isolated nodes in the image topology structure graph are removed to generate a paleokarst topology map.

[0031] As a preferred solution of the reservoir identification method integrating seismic attribute inversion and paleokarst morphological modeling described in the present invention, the paleokarst topological map and the structured seismic inversion attribute volume are spatially superimposed, and the correlation between the topological structure and the seismic anomaly attributes is analyzed through spatial position correspondence and feature matching to generate a karst-seismic joint matching map. The specific steps are as follows:

[0032] The paleokarst topological map and the spatial coordinates of the structured seismic inversion attribute volume are converted into a unified coordinate basis and rigidly registered to build a spatial alignment fusion model, and the topological node structure feature vectors and seismic attribute volume anomaly characteristics are extracted;

[0033] The normalized fraction function is used to calculate the joint matching weight of the topological node structure feature vector and the seismic attribute body anomaly characteristics to construct the karst seismic matching map;

[0034] The karst-seismic matching graph is input into the graph clustering algorithm. Based on the joint matching weight, topological node structure feature vector and seismic attribute body anomaly characteristics, the karst anomaly high matching area is identified and the karst-seismic joint matching graph is generated.

[0035] As an optimal solution for the reservoir identification method of the present invention that integrates seismic attribute inversion and paleokarst morphological modeling, the spatial alignment fusion model is based on the core node coordinates in the karst seismic joint matching graph and the spatial voxels of the structured seismic inversion attribute volume, and is constructed through rigid alignment and multidimensional attribute fusion to form a spatially consistent fusion representation.

[0036] As a preferred solution of the reservoir identification method of the present invention that integrates seismic attribute inversion and paleokarst morphology modeling, the method couples the karst seismic joint matching map with the comprehensive reservoir attribute data to establish an effective reservoir evaluation model, and generates a multi-level reservoir prediction layer set through weighted fusion and multi-parameter spatial analysis. The specific steps are as follows:

[0037] Filter the key node sets whose joint matching weights exceed the preset matching strength threshold from the karst-seismic joint matching graph, extract the corresponding spatial coordinates, and construct a spatial index mapping table;

[0038] Collect comprehensive reservoir attribute data and perform attribute sampling at the key node spatial positions marked in the spatial index mapping table to form a multi-parameter attribute vector set;

[0039] Using nonlinear multi-parameter fusion function, the multi-parameter attribute vector set is coupled with the node weights in the karst seismic joint matching graph to construct an effective reservoir evaluation model.

[0040] Spatial adaptive smoothing and multi-scale interpolation processing are implemented on the effective reservoir evaluation models at different spatial locations to obtain comprehensive reservoir evaluation results. A hierarchical threshold system is constructed to semantically classify high-quality reservoir areas, potential areas and inefficient areas, and a multi-level reservoir prediction layer set is generated through three-dimensional slicing technology.

[0041] As a preferred solution of the reservoir identification method of the present invention that integrates seismic attribute inversion and paleokarst morphology modeling, the comprehensive reservoir attribute data includes porosity, permeability, fluid saturation, lithology type, fracture characteristics, wave impedance, elastic parameters and multi-dimensional physical and structural properties of formation pressure and temperature.

[0042] The beneficial effects of the present invention are as follows: by constructing a paleokarst topological map and a karst-seismic joint matching map, spatial modeling of complex karst structures and cross-modal correlation analysis of seismic anomaly attributes are realized; among them, the former effectively improves the structural authenticity and connectivity expression ability of karst morphology identification through multi-dimensional feature extraction and graph structure construction, and the latter establishes a coupling channel between structural information and seismic attributes through coordinate superposition and feature matching, thereby enhancing the spatial consistency and physical property matching of reservoir identification, and finally forms a multi-level reservoir prediction layer set based on the integration of standardized image processing and reservoir attribute data analysis, which significantly improves the accuracy and practicality of reservoir prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 Flowchart of the reservoir identification method integrating seismic attribute inversion and paleokarst morphology modeling;

[0045] Figure 2 Build a flow chart for a standardized image dataset;

[0046] Figure 3 Generate flow charts for structured seismic inversion attribute volumes;

[0047] Figure 4 Flowchart for matrix generation for cross-modal image fusion. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0050] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0051] Reference Figures 1 to 4 , is an embodiment of the present invention, which provides a reservoir identification method integrating seismic attribute inversion and paleokarst morphology modeling, comprising the following steps:

[0052] S1. Collect multi-source geological image datasets and perform format unification, spatial label binding, image enhancement and scale normalization to construct a standardized image dataset. Combined with seismic inversion calculations, a structured seismic inversion attribute volume is generated.

[0053] S1.1. Collect core section images, drilling profile images, landform outcrop remote sensing images, well logging curve images, and seismic profile images of the target area to construct an original multi-source geological image dataset.

[0054] Furthermore, when acquiring core cross-section images of the target area, the core samples obtained by drilling are longitudinally cut and cross-section images are acquired using high-resolution image acquisition equipment, preserving the lithologic bedding and pore structure characteristics. When acquiring drilling profile images, the cross-sectional structure diagram formed by drilling operation is obtained, preserving stratigraphic boundaries and depth annotation information. When acquiring geomorphological outcrop remote sensing images, high-resolution remote sensing images covering the target area are extracted, preserving typical outcrop morphology and spatial resolution information. When acquiring well logging curve images, logging parameter curves such as resistivity, acoustic wave travel time, and gamma are visualized and scaled according to well depth. When acquiring seismic profile images, two-dimensional seismic reflection images are derived and spatial coordinate information is preserved. The above core cross-section images, drilling profile images, geomorphological outcrop remote sensing images, well logging curve images, and seismic profile images together constitute the original multi-source geological image dataset.

[0055] S1.2. Convert the original multi-source geological image dataset into a grayscale image format to obtain a unified format original geological grayscale image set.

[0056] Furthermore, the process of converting the original multi-source geological image dataset into a unified grayscale image format includes: applying channel compression to core section images to convert color images into grayscale images, preserving bedding and pore contrast information; extracting color layer information from drilling profile images and converting them into grayscale value matrices to preserve depth and structural relationships; grayscale conversion of landform outcrop remote sensing images using spectral compression methods, such as average weighted or maximum component methods, to preserve landform boundary features; mapping the contrast between the curve and the background of well logging curve images to grayscale levels to maintain clear curve trends; and applying linear weighting to seismic profile images to convert color gradients into grayscale intensity distributions to preserve reflective interface features. After completing the above processing, the core section images, drilling profile images, landform outcrop remote sensing images, well logging curve images, and seismic profile images are unified into a single-channel grayscale image format, forming a unified format original geological grayscale image set.

[0057] S1.3. Perform format unification, spatial label binding, image enhancement and scale normalization on the unified format original geological grayscale image set to generate a standardized image dataset.

[0058] Furthermore, the process of performing format unification, spatial label binding, image enhancement and scale normalization on the unified format original geological grayscale image set includes: performing format unification processing on the images in the unified format original geological grayscale image set, unifying the image encoding format, resolution and bit depth; performing spatial label binding operation, binding the core section images, drilling profile images, geomorphic outcrop remote sensing images, logging curve images and seismic profile images to corresponding spatial coordinates, depth information or projection information respectively; performing image enhancement processing according to the image type, such as edge enhancement of seismic profile images, contrast stretching of logging curve images, and histogram equalization of core section images; after completing image enhancement, performing scale normalization processing, and unifying the images to a consistent spatial resolution or depth ratio through bilinear interpolation or cubic convolution interpolation method, and finally generating a standardized image data set.

[0059] S1.4. Extract the three-dimensional seismic reflection data corresponding to the target area from the standardized image data set, perform spatial coordinate alignment processing to obtain a spatially aligned seismic data volume, and perform pixel position mapping and sampling point number matching operations to establish a structure index table.

[0060] Furthermore, the process of extracting three-dimensional seismic reflection data corresponding to the target area from the standardized image dataset includes: determining the geological coordinate range of the target area by reading the spatial label field in the standardized image dataset, and extracting the three-dimensional seismic reflection profile image of the corresponding area to reconstruct it into a three-dimensional seismic reflector; performing spatial coordinate alignment processing on the three-dimensional seismic reflector, using a spatial affine transformation or a rigid transformation method, and keeping the spatial reference consistent with the standardized image dataset; after the alignment is completed, performing a pixel position mapping operation to establish a spatial correspondence between the voxels in the three-dimensional seismic reflector and the pixels in the standardized image dataset; finally, assigning a sampling point number to each valid voxel according to the spatial correspondence, organizing the voxel coordinates, pixel positions and sampling numbers, and constructing a structure index table.

[0061] It should also be explained that the target area refers to the geological spatial range related to the reservoir to be identified in the standardized image dataset, which is obtained by screening spatial labels in core sections, drilling profiles, remote sensing images, well log curves and seismic profile images.

[0062] S1.5. Using the structure index table, perform reflection waveform extraction and physical attribute function calculation on the spatially aligned seismic data volume to obtain an initial seismic attribute volume set.

[0063] Furthermore, through the structural index table, the reflection waveform information is first extracted for each valid voxel in the spatially aligned seismic data volume, specifically including the calculation of the amplitude, phase and frequency characteristics of the reflection wave to reflect the changes in the underground geological interface.

[0064] Then, based on the extracted reflection waveforms, physical attribute functions are applied to calculate corresponding seismic physical attributes, such as wave impedance, elastic modulus, and velocity. These physical attributes are derived from the known correspondence between waveforms and seismic physical properties. All calculated reflection waveform features and physical attribute data are associated with the voxel spatial coordinates defined in the structural index table to form an initial seismic attribute volume set, which provides the basis for subsequent multi-attribute fusion and spatial resampling.

[0065] S1.6. Perform multi-attribute fusion processing on the initial seismic attribute volume set to obtain a fused seismic feature volume, and resample and archive it according to the spatial voxel structure to form a structured seismic inversion attribute volume.

[0066] Furthermore, a weighted fusion method is used to perform multi-attribute fusion processing on the various seismic attribute data in the initial seismic attribute volume set. Specifically, the fusion weights are determined based on attribute correlation and spatial consistency, and each attribute is weighted averaged at the same spatial voxel position to enhance the stability and accuracy of the seismic characteristics. After fusion, the fused seismic feature volume is resampled in three dimensions according to the preset spatial voxel structure, and the data resolution and consistency are adjusted using an interpolation algorithm to ensure continuous spatial distribution and uniform resolution. Finally, the resampled fused seismic feature volume is archived and managed according to spatial voxel coordinates to form a structured seismic inversion attribute volume, which provides a basis for subsequent reservoir identification and analysis.

[0067] It should also be noted that spatial voxel structure refers to the division of seismic reflection data and corresponding attributes into regular blocks at fixed intervals, based on the spatial coordinates and sampling point numbers in the standardized image dataset, according to a unified 3D grid partitioning rule. Each regular block has a clear spatial location and volume range, and has a clear adjacent relationship with each other, thus constructing a well-structured 3D voxel grid. The spatial voxel structure ensures the continuity and integrity of the fused seismic features in the spatial dimension, facilitating resampling, archiving, and subsequent spatial analysis operations.

[0068] S2. Use image sensors to perform multimodal fusion processing on standardized image datasets to obtain multimodal fusion image data and perform high-precision texture sampling and spatial alignment processing to generate a cross-modal image fusion matrix.

[0069] S2.1. Use image sensors to digitally read and extract multimodal information from multi-source geological image information in standardized image datasets, and extract multi-scale texture features and spatial structure features.

[0070] Furthermore, image sensors are used to digitally read multi-source geological image information from standardized image datasets. Acquisition equipment converts the image's grayscale values ​​and spatial coordinates into digital signals. Based on the digitized images, a multiscale texture analysis method is employed to extract multiscale texture features, including gray-level co-occurrence matrices, local binary patterns, and frequency domain transforms, to describe the image's detailed structure and texture distribution.

[0071] At the same time, spatial structure analysis methods are used to calculate the edge direction, spatial frequency, and spatial correlation in the image to obtain spatial structural features, reflecting the structural morphology of different spatial scales in the geological image. Ultimately, multi-scale texture features and spatial structure features are used as multimodal information extraction results to provide a basis for subsequent fusion processing.

[0072] S2.2. Multi-scale texture features and spatial structure features are combined through spatial registration, feature extraction and weighted fusion operations to generate multimodal fused image data.

[0073] Furthermore, the multi-scale texture features and spatial structure features are geometrically corrected based on a unified spatial coordinate system through a spatial registration method to eliminate spatial deviations and scale differences between different modalities and ensure accurate spatial correspondence of features. Subsequently, key features are extracted from the registered multi-scale texture features and spatial structure features respectively. Statistics are calculated using a sliding window to extract characteristic values ​​such as the mean, variance, and skewness of the local area. Spatial frequency analysis uses Fourier transform to identify the frequency distribution pattern of texture and structure features to extract the main characterization information. Based on the importance of the features and their contribution to reservoir identification, a weighted fusion operation is used to weightedly superimpose the multi-scale texture features and spatial structure features at the corresponding spatial locations to form fused multimodal fusion image data, achieving effective integration and enhancement of information from different modalities.

[0074] S2.3. Based on the spatial range of the multimodal fusion image data, a unified reference grid is constructed through boundary coordinate extraction and regular grid division operations, and local resampling processing is performed on the texture channels in the multimodal fusion image data to obtain a multimodal texture resampled image set.

[0075] Furthermore, based on the spatial extent of the multimodal fused image data, boundary coordinates are first extracted to clarify the spatial coverage of the fused image. Based on these boundary coordinates, a unified reference grid is constructed using a regular 3D grid partitioning method. This unified reference grid consists of equally spaced spatial nodes, ensuring that each spatial location is uniquely identified and precisely located.

[0076] Subsequently, the texture channels in the multimodal fusion image data are locally resampled, and an interpolation algorithm is used to spatially adjust and refine the texture information to ensure the continuity and consistency of the texture data on a unified reference grid. Through these steps, a multimodal texture resampled image set with spatial uniformity and high resolution is generated.

[0077] It should also be noted that the spatial extent of the multimodal fused image data is derived from the spatial label fields of various multi-source geological images in the standardized image dataset. These spatial labels include the spatial coordinates, well depths, and geological unit boundary information recorded in core section images, drilling profile images, remote sensing images of geomorphic outcrops, well logging curve images, and seismic profile images. By unifying the spatial reference systems of these various images and registering and aligning the spatial coordinates, well depths, and geological boundary information, the overall spatial coverage of the multimodal fused image data is determined, ensuring the spatial consistency and integrity of the fused data with the original geological information.

[0078] S2.4. Extract spatial structure direction information from the multimodal texture resampled image set, and construct the main texture direction field through multi-scale gradient tensor analysis and direction consistency interpolation operations.

[0079] Furthermore, from a multimodal texture resampled image set, a multiscale gradient tensor analysis method is used to construct a multiscale gradient tensor field within a local area of ​​the image. The gradient magnitude and directional angle in each direction are calculated to extract local gradient information. By taking a weighted average of the gradient tensor fields at different scales, the directional information of the spatial structure is extracted. Based on the directional information of the spatial structure, a directional consistency interpolation operation is used to smooth and compensate for the continuity of the directional information of adjacent pixels, eliminating the effects of noise and local inconsistencies. Finally, the interpolated directional information is integrated to construct a main texture direction field reflecting the dominant direction of the multimodal texture, providing a precise directional reference for spatial alignment and fusion of texture directions.

[0080] S2.5. Align the main texture direction field with the spatial normal distribution of the unified reference grid to obtain the texture direction field, and generate a cross-modal image fusion matrix through feature mapping and weighted fusion operations.

[0081] Furthermore, the main texture direction field is mapped to the spatial normal distribution of a unified reference grid. By calculating the angular difference between the main texture direction and the spatial normal vector, the two are spatially aligned, ensuring that the texture direction is consistent with the geological spatial structure. Based on the alignment results, two key features of the texture direction field—the main direction angle and directional consistency—are extracted. Combined with the geometric properties of the spatial normal, a weighted fusion method is used to perform a weighted superposition of these features, enhancing directional consistency and spatial continuity. Ultimately, a cross-modal image fusion matrix is ​​generated, reflecting the comprehensive information of texture direction and spatial structure in images of different modalities, supporting subsequent topological structure construction and spatial analysis.

[0082] It should also be noted that the spatial normal distribution is derived from the spatial coordinates and three-dimensional geological structure information of a unified reference grid and is obtained by calculating the geological interface normal vectors at the grid nodes. Specifically, based on the spatial range and regular grid division of the multimodal fusion image data, and utilizing the spatial variation gradient of the geological structure within the local neighborhood, the finite difference method is used to calculate the attribute differences between neighboring nodes to obtain the normal direction. This forms a spatial normal distribution covering the entire reference grid, which is used to assist in the spatial alignment and fusion of texture directions.

[0083] S3. Input the cross-modal image fusion matrix into the image topology structure construction process, establish the image block node relationship and spatial connection edge weight, and generate the paleokarst topology map.

[0084] S3.1. Adaptive region growing algorithm is used to perform spatial segmentation on the cross-modal image fusion matrix to form multiple spatially connected image block nodes, and texture intensity mean, local geometric parameters and spatial three-dimensional coordinates are extracted. Feature vector normalization and fusion processing are then performed to construct a multi-dimensional feature vector.

[0085] Furthermore, an adaptive region growing algorithm is used to spatially segment the cross-modal image fusion matrix. By setting a similarity threshold and neighborhood connection rules, pixels with similar texture and structural features within the space are recursively merged to form multiple spatially connected image patch nodes. For each image patch node, the mean texture intensity is calculated, local geometric parameters such as shape compactness and surface curvature are extracted, and the node's three-dimensional spatial coordinates are obtained. The texture intensity mean, local geometric parameters, and three-dimensional spatial coordinates are normalized to eliminate dimensional differences. After that, a feature fusion method is used to synthesize a multidimensional feature vector, which comprehensively represents the comprehensive spatial properties and texture characteristics of each image patch node.

[0086] It should also be noted that the adaptive region growing algorithm is based on the pixel texture intensity and spatial adjacency in the cross-modal image fusion matrix. It first selects spatially adjacent pixels with small texture intensity variations as initial growth seeds. Then, according to a preset similarity threshold, neighboring pixels with similar texture intensity and spatial continuity are gradually merged into the corresponding region. The adaptive region growing algorithm dynamically adjusts the similarity threshold to adapt to the texture complexity of different regions, avoiding over-segmentation or under-segmentation and ensuring the spatial coherence and texture uniformity of the segmented region. Through iterative growth, multiple spatially connected image block nodes with consistent texture features are eventually formed, supporting subsequent feature extraction and multi-dimensional feature vector construction.

[0087] The similarity threshold is set based on the statistical characteristics of the matching weights in the karst-seismic joint matching graph. By combining the overall balance and dispersion of the matching weights, a representative weight limit is determined. The similarity threshold is used to identify key nodes with high matching weights and significant correlations between seismic anomaly manifestations and topological structures, thereby ensuring the accuracy and stability of subsequent spatial index mapping and reservoir attribute sampling.

[0088] S3.2. Calculate the similarity and spatial adjacency between nodes of the multidimensional feature vector, generate weighted connection edges, combine the image block nodes with the weighted connection edges, and generate an image topology structure.

[0089] Furthermore, based on the multidimensional feature vector, the similarity between each image block node is calculated, and the expression is:

[0090]

[0091] Among them, S mn It is expressed as the similarity between image block node m and image block node n, where m is the index of the first image block node, n is the index of the second image block node, and v m Represented as the multidimensional feature vector of the mth image block node, v n Represented as the multidimensional feature vector of the nth image block node, ||vm -v n || represents the Euclidean distance between the feature vectors of image patch nodes m and n.

[0092] Methods such as Euclidean distance or cosine similarity are used to quantify the similarity of node features. The spatial adjacency between nodes is determined by combining the three-dimensional coordinates of the image patch nodes, identifying adjacent node pairs. Based on similarity and adjacency, edge weights are calculated, which comprehensively reflect the similarity of node features and spatial proximity. Image patch nodes are treated as nodes in the topological graph, and the edges and weights are used as weighted edges. Nodes and weighted edges are combined to construct an image topological graph structure that reflects the spatial structure and feature relationships of the image patch, supporting subsequent topological analysis and node screening.

[0093] S3.3. Remove low-weight edges and isolated nodes in the image topology structure diagram to generate a paleokarst topology map.

[0094] Furthermore, edge weight and node distribution analysis is performed on the image topology structure graph, edges with edge weights lower than the weight distribution threshold in the image topology structure graph are eliminated, and isolated nodes that have no connection relationship in the image topology structure graph are removed, while retaining the stable topological connection structure and main texture path, and finally generating a paleokarst topology map.

[0095] It should also be noted that the weight distribution threshold is set based on the statistical characteristics of all edge weights in the image topology structure diagram. It is usually determined by calculating the mean and standard deviation of the edge weights and combining them with the adjustment coefficient. It is used to distinguish important connections from weak connections and ensure that key topological structures and texture paths are retained.

[0096] S4. Overlay the ancient karst topological map with the structured seismic inversion attribute volume in spatial coordinates. Through spatial position correspondence and feature matching, analyze the correlation between the topological structure and seismic anomaly attributes to generate a karst-seismic joint matching map.

[0097] S4.1. Perform unified coordinate datum conversion and rigid transformation registration on the spatial coordinates of the paleokarst topological map and the structured seismic inversion attribute volume, construct a spatial alignment fusion model, and extract the topological node structure feature vectors and seismic attribute volume anomaly features.

[0098] Furthermore, the spatial coordinates of the paleokarst topology map and the structured seismic inversion attribute volume were transformed to a unified coordinate datum, and a rigid transformation method was used to complete the registration correction to achieve consistency in their spatial positions. Based on the registration results, the structural feature vectors of the topological nodes in the paleokarst topology map were extracted, including the node's geometric properties, connectivity, and texture characteristics. Anomalous seismic attribute features, such as reflection intensity anomalies and wave impedance changes, were also extracted from the structured seismic inversion attribute volume. These operations formed a spatial alignment fusion model, providing the spatial and feature foundation for subsequent joint matching analysis.

[0099] It should also be explained that the setting of the spatial alignment fusion model includes: taking the coordinates of the key nodes of the paleokarst topological map and the spatial voxel coordinates of the structured seismic inversion attribute volume as the benchmark, using rigid transformation for rotation, translation and scaling to achieve coordinate alignment; extracting the structural feature vectors of the topological nodes and the abnormal characteristics of the seismic attributes, performing normalized weighted fusion, and forming a spatially consistent fusion representation, which provides a basis for the karst-seismic joint matching map.

[0100] S4.2. Use the normalized fraction function to calculate the joint matching weight of the topological node structure feature vector and the seismic attribute body anomaly characteristics to construct a karst seismic matching map.

[0101] Furthermore, the normalized fraction function is used to quantify the topological node structure feature vector and the seismic attribute body anomaly feature, and the weighted matching score of the two is calculated. The expression is:

[0102]

[0103] Among them, P represents the total weighted matching score, i represents the feature dimension index, Z represents the total number of feature dimensions, and w i Represents the weight coefficient of the i-th feature dimension, p i Represents the matching score on the i-th feature dimension;

[0104] The contribution ratio of structural features and abnormal features is adjusted by the weight coefficient to obtain the joint matching weight value; based on the joint matching weight value, the topological nodes are connected with the corresponding seismic attribute bodies to form a karst seismic matching map, which reflects the matching strength and spatial correlation relationship between nodes.

[0105] S4.3. Input the karst-seismic matching map into the graph clustering algorithm, identify the karst anomaly high matching area based on the joint matching weight, topological node structure feature vector and seismic attribute body anomaly characteristics, and generate a karst-seismic joint matching map.

[0106] Furthermore, the karst-seismic matching graph is input into the graph clustering algorithm. Based on the joint matching weight, topological node structure feature vector and seismic attribute body anomaly characteristics, the similarity between nodes is calculated through the weighted distance of the multidimensional feature vector, and the adjacency relationship determines the connection edge according to the node spatial distance and topological connection, forming the clustering basis; through iterative division and aggregation, nodes with high joint matching weight and similar characteristics are grouped into the same cluster, and the high matching area of ​​karst anomaly is identified. The high matching intensity nodes are divided into feature-similar clusters through the graph clustering algorithm, and the subgraph structure is constructed based on the topological connection relationship of the nodes in each cluster. Finally, the high matching subgraphs are merged to form a complete karst-seismic joint matching graph, which reflects the spatial distribution characteristics of the karst anomaly area and provides a basis for subsequent reservoir identification and evaluation.

[0107] S5. Couple the karst seismic joint matching map with the comprehensive reservoir attribute data to establish an effective reservoir evaluation model, and generate a multi-level reservoir prediction layer set through weighted fusion and multi-parameter spatial analysis.

[0108] S5.1. Filter the key node sets whose joint matching weights exceed a preset matching strength threshold from the karst-seismic joint matching graph, extract the corresponding spatial coordinates, and construct a spatial index mapping table.

[0109] Furthermore, from the karst-seismic joint matching map, a preset matching strength threshold is first set to screen out the key node set whose joint matching weight exceeds the preset matching strength threshold; then the spatial coordinates of the screened key node set are extracted to obtain the three-dimensional geographic spatial position corresponding to each node; based on the spatial coordinates of the key nodes, a spatial index mapping table is constructed to realize the registration of the corresponding relationship between the key nodes and the spatial positions, providing basic support for subsequent spatial retrieval and positioning.

[0110] The preset matching strength threshold is based on the statistical distribution of the matching weights of all nodes in the karst-seismic joint matching graph. By combining the average matching weight with the standard deviation and adjusting it according to the adjustment coefficient, an adaptive matching strength threshold is determined to screen high matching strength nodes with high spatial and feature correlation, thereby ensuring that key nodes with high matching strength are representative and improving the accuracy of subsequent analysis.

[0111] S5.2. Collect comprehensive reservoir attribute data and perform attribute sampling at the key node spatial positions marked in the spatial index mapping table to form a multi-parameter attribute vector set.

[0112] Furthermore, comprehensive reservoir attribute data is collected, covering multi-dimensional parameters such as porosity, permeability, rock density and wave impedance. According to the spatial position of the key nodes marked in the spatial index mapping table, the corresponding geological spatial coordinates are accurately located for each high-matching strength node, and attribute sampling operations are performed. The reservoir attributes around the high-matching strength key nodes are estimated by spatial interpolation methods, and the multi-dimensional attributes are fused according to weights to form a comprehensive attribute vector that accurately represents the key nodes. The multi-parameter attribute information at each key node is obtained to ensure the integrity and accuracy of the attribute data. The sampled porosity, permeability, wave impedance and other reservoir attribute data are matched one by one according to the spatial position and fused to form a multi-parameter attribute vector set corresponding to the high-matching strength node, providing multi-dimensional attribute basic support for subsequent karst reservoir identification and analysis.

[0113] S5.3. Using the nonlinear multi-parameter fusion function, the multi-parameter attribute vector set is coupled with the node weights in the karst seismic joint matching graph to construct an effective reservoir evaluation model.

[0114] Furthermore, a nonlinear multi-parameter fusion function is used to couple the multi-parameter attribute vector set with the joint matching weights of the corresponding nodes in the karst-seismic joint matching graph. First, each reservoir attribute in the multi-parameter attribute vector is weighted according to a preset weight. Combined with the node joint matching weights, a nonlinear multi-parameter fusion function is used, taking the weighted multi-parameter attribute vector and the node joint matching weights as input. Through function mapping, nonlinear coupling is achieved between the two, comprehensively reflecting the correlation strength between reservoir attributes and matching characteristics, thereby generating a unified comprehensive evaluation score. This coupling process emphasizes the mutual influence of reservoir attributes and the correlation between seismic matching characteristics. Through nonlinear mapping, the discriminative power and accuracy of reservoir evaluation are enhanced, forming an effective reservoir evaluation model that reflects karst reservoir characteristics. The fusion results generate corresponding comprehensive reservoir evaluation indicators for each key node, supporting subsequent reservoir distribution analysis and optimization decisions.

[0115] It should also be explained that the effective reservoir evaluation model couples the multi-parameter attribute vector with the node weights in the karst seismic joint matching diagram through a nonlinear multi-parameter fusion function, comprehensively considers the correlation between reservoir physical properties and joint matching weights, and obtains the comprehensive reservoir evaluation score by performing nonlinear mapping calculation on the weighted multi-parameter attributes and node weights, thereby realizing the quantitative evaluation of reservoir effectiveness.

[0116] S5.4. Spatial adaptive smoothing and multi-scale interpolation processing are performed on the effective reservoir evaluation models at different spatial locations to obtain comprehensive reservoir evaluation results. A hierarchical threshold system is constructed to semantically classify high-quality reservoir areas, potential areas, and low-efficiency areas, and a multi-level reservoir prediction layer set is generated through three-dimensional slicing technology.

[0117] Furthermore, for the effective reservoir evaluation models at different spatial locations, spatial adaptive smoothing is first implemented to adjust the continuity of the reservoir comprehensive evaluation scores at adjacent spatial locations. Subsequently, a multi-scale interpolation method is used to fill in missing values ​​in the spatial distribution and refine the score distribution to obtain the reservoir comprehensive evaluation results. Based on the reservoir comprehensive evaluation results, a hierarchical threshold system is constructed to divide the reservoir into high-quality areas, potential areas, and inefficient areas to achieve semantic grading. Finally, the grading results are spatially displayed using three-dimensional slicing technology to generate a multi-level reservoir prediction layer set to support intuitive analysis of reservoir spatial characteristics and development planning.

[0118] It should also be explained that the stratification threshold system is set based on the distribution characteristics of the comprehensive reservoir evaluation results to determine the statistical interval range of the evaluation scores; secondly, based on the experience of geological experts and reservoir development needs, multiple stratification thresholds are set to distinguish between high-quality reservoir areas, potential areas, and inefficient reservoir areas; then, the comprehensive reservoir evaluation results after spatial adaptive smoothing and multi-scale interpolation processing are used to classify and label each spatial unit to ensure that the stratification threshold matches the spatial characteristics of the reservoir; finally, the stratification results are visualized through three-dimensional slicing technology to form a multi-level reservoir prediction layer set to facilitate subsequent reservoir development analysis and decision-making.

[0119] This embodiment also provides a computer device suitable for the reservoir identification method that integrates seismic attribute inversion and paleokarst morphological modeling, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the reservoir identification method that integrates seismic attribute inversion and paleokarst morphological modeling proposed in the above embodiment.

[0120] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0121] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the reservoir identification method for integrating seismic attribute inversion with paleokarst morphology modeling as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0122] In summary, the present invention realizes the spatial modeling of complex karst structures and cross-modal correlation analysis of seismic anomaly attributes by constructing paleokarst topological maps and karst seismic joint matching maps; the former effectively improves the structural authenticity and connectivity expression ability of karst morphology identification through multi-dimensional feature extraction and graph structure construction, and the latter establishes a coupling channel between structural information and seismic attributes through coordinate superposition and feature matching, thereby enhancing the spatial consistency and physical property matching of reservoir identification. Finally, based on the integration of standardized image processing and reservoir attribute data analysis, a multi-level reservoir prediction layer set is formed, which significantly improves the accuracy and practicality of reservoir prediction.

[0123] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A reservoir identification method integrating seismic attribute inversion and paleokarst morphology modeling, characterized by: include, Collect multi-source geological image datasets and perform format unification, spatial label binding, image enhancement and scale normalization to construct a standardized image dataset. Combined with seismic inversion calculations, a structured seismic inversion attribute volume is generated. The standardized image dataset is processed by multimodal fusion using an image sensor to obtain multimodal fusion image data and perform high-precision texture sampling and spatial alignment processing to generate a cross-modal image fusion matrix. The cross-modal image fusion matrix is ​​input into the image topology structure construction process to establish the image block node relationship and spatial connection edge weight to generate the paleokarst topology map; The paleokarst topology map is spatially superimposed with the structured seismic inversion attribute volume. Through spatial position correspondence and feature matching, the correlation between the topological structure and seismic anomaly attributes is analyzed to generate a karst-seismic joint matching map. The karst seismic joint matching map is coupled with the comprehensive reservoir attribute data to establish an effective reservoir evaluation model, and a multi-level reservoir prediction layer set is generated through weighted fusion and multi-parameter spatial analysis.

2. The reservoir identification method integrating seismic attribute inversion and paleokarst morphology modeling according to claim 1 is characterized in that: The specific steps of constructing a standardized image dataset are as follows: Collect core section images, drilling profile images, landform outcrop remote sensing images, well logging curve images, and seismic profile images of the target area to construct an original multi-source geological image dataset; The original multi-source geological image data set is uniformly converted into a grayscale image format to obtain a unified format original geological grayscale image set; The unified format original geological grayscale image set is processed by format unification, spatial label binding, image enhancement and scale normalization to generate a standardized image dataset.

3. The reservoir identification method integrating seismic attribute inversion and paleokarst morphology modeling according to claim 1 is characterized in that: The specific steps of generating a structured seismic inversion attribute volume are as follows: Extract the 3D seismic reflection data corresponding to the target area from the standardized image dataset and perform spatial coordinate alignment to obtain a spatially aligned seismic data volume. Then perform pixel position mapping and sampling point number matching operations to establish a structural index table. Through the structure index table, the reflection waveform extraction and physical attribute function calculation are performed on the spatially aligned seismic data volume to obtain the initial seismic attribute volume set; Multi-attribute fusion processing is performed on the initial seismic attribute volume set to obtain a fused seismic feature volume, which is then resampled and archived according to the spatial voxel structure to form a structured seismic inversion attribute volume.

4. The reservoir identification method integrating seismic attribute inversion and paleokarst morphology modeling according to claim 3 is characterized by: The method of using an image sensor to perform multimodal fusion processing on a standardized image data set to obtain multimodal fusion image data is as follows: Using image sensors, digitally read and extract multimodal information from multi-source geological image information in standardized image datasets, extracting multi-scale texture features and spatial structure features; Multi-scale texture features and spatial structure features are combined through spatial registration, feature extraction and weighted fusion operations to generate multimodal fused image data.

5. The reservoir identification method integrating seismic attribute inversion and paleokarst morphology modeling according to claim 4 is characterized in that: The high-precision texture sampling and spatial alignment processing are performed to generate a cross-modal image fusion matrix. The specific steps are as follows: According to the spatial range of the multimodal fusion image data, a unified reference grid is constructed through boundary coordinate extraction and regular grid division operations. Local resampling processing is performed on the texture channels in the multimodal fusion image data to obtain a multimodal texture resampled image set. Extract spatial structure direction information from a multimodal texture resampled image set, and construct the main texture direction field through multi-scale gradient tensor analysis and direction consistency interpolation operations; The main texture direction field is aligned with the spatial normal distribution of the unified reference grid to obtain the texture direction field, and a cross-modal image fusion matrix is ​​generated through feature mapping and weighted fusion operations.

6. The reservoir identification method integrating seismic attribute inversion and paleokarst morphology modeling according to claim 1 is characterized in that: The specific steps of generating the paleokarst topological map are as follows: Adaptive region growing algorithm is used to spatially segment the cross-modal image fusion matrix to form multiple spatially connected image block nodes, and texture intensity mean, local geometric parameters and spatial three-dimensional coordinates are extracted. Feature vector normalization and fusion processing are then performed to construct a multi-dimensional feature vector. Calculate the similarity and spatial adjacency between multi-dimensional feature vector nodes, generate weighted connection edges, combine image block nodes with weighted connection edges, and generate image topology structure; The low-weight edges and isolated nodes in the image topology structure graph are removed to generate a paleokarst topology map.

7. The reservoir identification method integrating seismic attribute inversion and paleokarst morphology modeling according to claim 6 is characterized in that: The above-mentioned method is to superimpose the spatial coordinates of the paleokarst topological map and the structured seismic inversion attribute volume, analyze the correlation between the topological structure and the seismic anomaly attributes through spatial position correspondence and feature matching, and generate a karst-seismic joint matching map. The specific steps are as follows: The paleokarst topological map and the spatial coordinates of the structured seismic inversion attribute volume are converted into a unified coordinate basis and rigidly registered to build a spatial alignment fusion model, and the topological node structure feature vectors and seismic attribute volume anomaly characteristics are extracted; The normalized fraction function is used to calculate the joint matching weight of the topological node structure feature vector and the seismic attribute body anomaly characteristics to construct the karst seismic matching map; The karst-seismic matching graph is input into the graph clustering algorithm. Based on the joint matching weight, topological node structure feature vector and seismic attribute body anomaly characteristics, the karst anomaly high matching area is identified and the karst-seismic joint matching graph is generated.

8. The reservoir identification method integrating seismic attribute inversion and paleokarst morphology modeling according to claim 7 is characterized in that: The spatial alignment fusion model is based on the core node coordinates in the karst seismic joint matching graph and the spatial voxels of the structured seismic inversion attribute volume, and is constructed through rigid alignment and multi-dimensional attribute fusion to form a spatial consistent fusion representation.

9. The reservoir identification method integrating seismic attribute inversion and paleokarst morphology modeling according to claim 7 is characterized in that: The karst seismic joint matching map is coupled with the comprehensive reservoir attribute data to establish an effective reservoir evaluation model, and a multi-level reservoir prediction layer set is generated through weighted fusion and multi-parameter spatial analysis. The specific steps are as follows: Filter the key node sets whose joint matching weights exceed the preset matching strength threshold from the karst-seismic joint matching graph, extract the corresponding spatial coordinates, and construct a spatial index mapping table; Collect comprehensive reservoir attribute data and perform attribute sampling at the key node spatial positions marked in the spatial index mapping table to form a multi-parameter attribute vector set; Using nonlinear multi-parameter fusion function, the multi-parameter attribute vector set is coupled with the node weights in the karst seismic joint matching graph to construct an effective reservoir evaluation model. Spatial adaptive smoothing and multi-scale interpolation processing are implemented on the effective reservoir evaluation models at different spatial locations to obtain comprehensive reservoir evaluation results. A hierarchical threshold system is constructed to semantically classify high-quality reservoir areas, potential areas and inefficient areas, and a multi-level reservoir prediction layer set is generated through three-dimensional slicing technology.

10. The reservoir identification method integrating seismic attribute inversion and paleokarst morphology modeling according to claim 9, characterized in that: The comprehensive reservoir attribute data includes porosity, permeability, fluid saturation, lithology type, fracture characteristics, wave impedance, elastic parameters and multi-dimensional physical and structural properties of formation pressure and temperature.

Images