Method and system for predicting geological sweet spots of low-permeability reservoir and medium

Abstract

The invention relates to the technical field of geological data processing, in particular to a low-permeability reservoir geological sweet spot prediction method and system and a medium. The method comprises the following steps: acquiring geological data of a low-permeability reservoir; preprocessing the geological data of the low-permeability reservoir to obtain standard geological data of the low-permeability reservoir; performing multi-dimensional feature recognition on the standard low-permeability reservoir geological data to obtain multi-dimensional geological feature data; key low-permeability reservoir information extraction is carried out on the multi-dimensional geologic feature data, and key low-permeability reservoir information is obtained; performing low-permeability reservoir core extraction on the key low-permeability reservoir information to generate low-permeability reservoir core data; through the data processing technology, the mode recognition technology and the machine learning technology, multi-dimensional analysis is carried out on the geologic features of the low-permeability reservoir, correlation analysis is carried out in combination with the seismic features of the low-permeability reservoir, and therefore the prediction accuracy of the geologic sweet spots of the low-permeability reservoir is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of geological data processing, and in particular to a method, system and medium for predicting geological sweet spots in low-permeability reservoirs. Background Art

[0002] Low permeability reservoir geological sweet spots refer to areas in low permeability oil and gas reservoirs that have high exploration and development value due to good physical properties and high oil and gas content; these areas usually show high porosity, permeability and gas saturation, and low bound water saturation; therefore, the prediction of low permeability reservoir geological sweet spots is of great significance for improving the success rate and development efficiency of oil and gas exploration. Traditional sweet spot prediction of low permeability reservoirs mainly relies on the experience of geologists, using geological exploration technology to measure data of low permeability reservoir geological layers, such as rock formation measurement data and low permeability reservoir downhole data; and based on these data, the prediction and analysis of low permeability reservoir geological sweet spots are carried out. However, the existing low permeability reservoir geological sweet spot prediction methods have a relatively single analysis of the geological characteristics of low permeability reservoirs; and fail to correlate the seismic characteristics of low permeability reservoirs, resulting in low accuracy in the prediction of low permeability reservoir geological sweet spots. Summary of the invention

[0003] Based on this, it is necessary to provide a method, system and medium for predicting geological sweet spots in low-permeability reservoirs to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for predicting geological sweet spots in low-permeability reservoirs is provided, the method comprising the following steps: Step S1: acquiring low permeability reservoir geological data; preprocessing the low permeability reservoir geological data to obtain standard low permeability reservoir geological data; performing multidimensional feature recognition on the standard low permeability reservoir geological data to obtain multidimensional geological feature data; extracting key low permeability reservoir information from the multidimensional geological feature data to obtain key low permeability reservoir information; Step S2: extracting low permeability reservoir cores from key low permeability reservoir information to generate low permeability reservoir core data; extracting core microstructure characteristics from multidimensional geological feature data based on the low permeability reservoir core data to obtain core microstructure characteristics; identifying low permeability reservoir structure morphology from key low permeability reservoir information based on the core microstructure characteristics to generate low permeability reservoir morphology data; Step S3: determining the low permeability reservoir range distribution of key low permeability reservoir information based on the low permeability reservoir morphology data to obtain low permeability reservoir range data; using the low permeability reservoir range data to identify seismic characteristics of key low permeability reservoir information to generate low permeability reservoir seismic data; extracting shale reservoir characteristics from the low permeability reservoir range data to obtain shale reservoir characteristic data; correlating and analyzing the shale reservoir characteristic data with the low permeability reservoir seismic data to generate low permeability reservoir seismic correlation data; Step S4: Calculate geological indicators of low permeability reservoir geological data according to low permeability reservoir seismic correlation data to generate low permeability reservoir geological indicators; construct a low permeability reservoir geological sweet spot prediction model using low permeability reservoir geological correlation indicators to obtain a low permeability reservoir geological sweet spot prediction model; perform prestack inversion on the low permeability reservoir geological sweet spot prediction model to obtain model prestack inversion data; dynamically optimize the low permeability reservoir geological sweet spot prediction model through the model prestack inversion data to obtain a low permeability reservoir geological sweet spot prediction optimization model; perform geological sweet spot prediction on low permeability reservoir geological data based on the low permeability reservoir geological sweet spot prediction optimization model to generate low permeability reservoir geological sweet spot prediction data; perform data visualization on the low permeability reservoir geological sweet spot prediction data to generate a low permeability reservoir geological sweet spot prediction report.

[0005] The present invention obtains low-permeability reservoir geological data and performs preprocessing to ensure data standardization, providing high-quality data support for subsequent analysis; multi-dimensional feature recognition enables the extraction of rich geological information from standard geological data; the extraction of key low-permeability reservoir information further focuses on factors that have an important impact on reservoir characteristics, improving the pertinence and accuracy of the analysis. Low-permeability reservoir core extraction of key low-permeability reservoir information can clarify low-permeability reservoir core information; core microstructure feature extraction of multi-dimensional geological feature data based on low-permeability reservoir core data clarifies the understanding of the internal structure of the reservoir and can reveal the microscopic characteristics of the reservoir; low-permeability reservoir structural morphology recognition of key low-permeability reservoir information based on core microstructure features clarifies the spatial distribution characteristics of the reservoir, providing a data basis for subsequent determination of reservoir range distribution. Based on the low permeability reservoir morphology data, the low permeability reservoir range distribution of key low permeability reservoir information is determined, the geographical distribution of the reservoir is determined, and thus the low permeability reservoir range is clarified; the seismic characteristics of the key low permeability reservoir information are identified using the low permeability reservoir range data, which can identify the seismic characteristics of the reservoir geological structure and further clarify the seismic situation of the low permeability reservoir; the shale reservoir characteristics are extracted from the low permeability reservoir range data to obtain shale reservoir characteristic data; the shale reservoir parameters are correlated with the low permeability reservoir seismic data for analysis, which can comprehensively understand the correlation between the geographical low permeability reservoir and the earthquake. According to the low permeability reservoir seismic correlation data, the geological index of the low permeability reservoir geological data is calculated, and a quantitative reservoir index evaluation standard is provided; the low permeability reservoir geological correlation index is used to construct a low permeability reservoir geological sweet spot prediction model to obtain a low permeability reservoir geological sweet spot prediction model; the low permeability reservoir geological sweet spot prediction model is prestack inversion to obtain the model prestack inversion data; the low permeability reservoir geological sweet spot prediction model is dynamically optimized by the model prestack inversion data, and the accuracy and applicability of the prediction model are improved, thereby improving the accuracy of the geological sweet spot prediction; based on the low permeability reservoir geological sweet spot prediction optimization model, the low permeability reservoir geological data is predicted to be geological sweet spot, and the low permeability reservoir geological sweet spot prediction data is generated; the low permeability reservoir geological sweet spot prediction data is visualized, and the prediction report can be intuitively displayed. Therefore, the present invention realizes multi-dimensional analysis of the geological characteristics of the low permeability reservoir through data processing technology, pattern recognition technology and machine learning technology, and combines the seismic characteristics of the low permeability reservoir for correlation analysis, thereby improving the accuracy of the low permeability reservoir geological sweet spot prediction.

[0006] Preferably, step S2 comprises the following steps: Step S21: performing low permeability reservoir core feature identification on key low permeability reservoir information to obtain low permeability reservoir core features; performing low permeability reservoir core data extraction on key low permeability reservoir information according to the low permeability reservoir core features to generate low permeability reservoir core data; Step S22: performing core feature enhancement on the low permeability reservoir core data to obtain core feature enhancement data; performing feature hierarchization on the core feature enhancement data to generate core feature hierarchical data; performing hierarchical structure element extraction on the core feature hierarchical data to obtain core hierarchical structure element information; Step S23: marking the core hierarchical structure of the multidimensional geological feature data through the core hierarchical structure element information to obtain core hierarchical structure marking data; identifying the core microstructure characteristics of the multidimensional geological feature data based on the core hierarchical structure marking data to obtain core microstructure characteristics; Step S24: performing feature imaging processing on key low-permeability reservoir information according to core microstructural characteristics to obtain a low-permeability reservoir structural image; performing structural image recognition on the low-permeability reservoir structural image to obtain low-permeability reservoir structural data; performing low-permeability reservoir morphology extraction on the low-permeability reservoir structural data to obtain low-permeability reservoir morphology data.

[0007] The present invention identifies the core characteristics of low permeability reservoirs on key low permeability reservoir information, and can extract representative core characteristics of low permeability reservoirs from the key low permeability reservoir information; extracts core data of low permeability reservoirs on key low permeability reservoir information according to the core characteristics of low permeability reservoirs, and can clarify the core data of low permeability reservoirs; enhances the core characteristics of low permeability reservoir core data, and improves the identifiability of the core data, making the microscopic characteristics of the core more obvious; hierarchizes the core characteristics enhanced data, and clarifies the multi-level structure of the core characteristics; extracts hierarchical elements from the hierarchical core characteristics data, and can obtain the core element information of the hierarchical structure of the core; and extracts the core hierarchical element information from the hierarchical core structure. The core hierarchical structure is marked on the multi-dimensional geological feature data, and the microstructure of the core is combined with the geological characteristics, which enhances the relevance of the data; the core microstructure characteristics are identified on the multi-dimensional geological feature data based on the core hierarchical structure marking data, which can further refine the microstructure characteristics of the core; the key low-permeability reservoir information is imaged according to the core microstructure characteristics, which can convert abstract data into intuitive images for easy analysis and understanding; structural image recognition is performed on the low-permeability reservoir structure image to clarify the key structural information and provide accurate data support for the extraction of reservoir morphology; low-permeability reservoir morphology is extracted from the low-permeability reservoir structure data to clarify the spatial morphological characteristics of the reservoir.

[0008] Preferably, step S3 comprises the following steps: Step S31: extracting geometric features from the low permeability reservoir morphological data to obtain geometric features of the low permeability reservoir; determining feature spatial relationships of the geometric features of the low permeability reservoir to generate spatial relationship data of the low permeability reservoir; dividing the spatial relationship data of the low permeability reservoir into relationship types to obtain spatial relationship type data; Step S32: performing spatial distribution identification on the low permeability reservoir morphology data according to the spatial relationship type data to generate low permeability reservoir spatial distribution information; performing low permeability reservoir boundary determination on the low permeability reservoir spatial distribution information to obtain low permeability reservoir boundary data; performing low permeability reservoir range distribution determination on the key low permeability reservoir information based on the low permeability reservoir spatial distribution information and the low permeability reservoir boundary data to obtain low permeability reservoir range data; Step S33: performing low permeability reservoir continuity measurement on the low permeability reservoir range data to generate continuity measurement data; using the continuity measurement data to determine the interlayer continuity of key low permeability reservoir information to obtain interlayer continuity data; recording the number of interlayer collision and compression times of key low permeability reservoir information according to the interlayer continuity data to obtain interlayer collision and compression data; performing seismic feature recognition on the interlayer collision and compression data to generate low permeability reservoir seismic data; Step S34: performing shape structure recognition on the low permeability reservoir range data to obtain shale reservoir shape data; performing shale reservoir parameter extraction on the shale reservoir shape data to generate shale reservoir parameter information; integrating the shale reservoir shape data and the shale reservoir parameter information to obtain shale reservoir characteristic data; Step S35: performing correlation analysis on the shale reservoir characteristic data and the low permeability reservoir seismic data to generate low permeability reservoir seismic correlation data.

[0009] The present invention extracts geometric features from low-permeability reservoir morphological data, can quantify the physical characteristics of the reservoir, and specifically extracts the geometric features of the low-permeability reservoir; determines the feature spatial relationship of the geometric features of the low-permeability reservoir, and clarifies the spatial interaction between different reservoir structures; divides the spatial relationship data of the low-permeability reservoir into relationship types, and can divide different types of relationship data; identifies the spatial distribution of the low-permeability reservoir morphological data based on the spatial relationship type data, and reveals the spatial distribution characteristics of the reservoir; determines the low-permeability reservoir boundary for the spatial distribution information of the low-permeability reservoir, clarifies the low-permeability reservoir boundary information, and provides boundary values ​​for the subsequent determination of the low-permeability reservoir range; determines the low-permeability reservoir range distribution of key low-permeability reservoir information based on the low-permeability reservoir spatial distribution information and the low-permeability reservoir boundary data, and clarifies the low-permeability reservoir range; determines the low-permeability reservoir continuity for the low-permeability reservoir range data, which is helpful for subsequent The flow and distribution of fluids in the reservoir are continuously predicted; the interlayer continuity of key low-permeability reservoir information is determined using continuity measurement data, revealing the relationship between different low-permeability reservoirs; the number of interlayer collision and extrusion of key low-permeability reservoir information is recorded based on interlayer continuity data, which can clarify the reservoir activity; seismic characteristics are identified on interlayer collision and extrusion data to obtain low-permeability reservoir seismic data; shape and structure identification is performed on low-permeability reservoir range data to clarify the geometric morphological characteristics of shale reservoirs; shale reservoir parameters are extracted from shale reservoir shape data to provide key physical parameters of shale reservoirs; shale reservoir shape data and shale reservoir parameter information are integrated to obtain shale reservoir characteristic data; shale reservoir characteristic data are correlated with low-permeability reservoir seismic data, and geological structure information is combined with seismological data to clarify the correlation between low-permeability reservoirs and seismic characteristics.

[0010] Preferably, step S35 includes the following steps: Step S351: performing porosity feature identification on the shale reservoir characteristic data to obtain porosity characteristic data; performing porosity distribution determination on the porosity characteristic data to generate porosity distribution data; performing porosity diameter measurement on the porosity characteristic data in combination with the porosity distribution data to obtain porosity diameter data; Step S352: extracting the mineral composition of the shale reservoir characteristic data to obtain the mineral composition data of the shale reservoir; identifying the rock fractures of the shale reservoir mineral composition data according to the porosity and pore size data to generate the shale reservoir fracture information; Step S353: simulate the interlayer seismic response of the shale reservoir fracture information and the low permeability reservoir seismic data to obtain the interlayer seismic response data; perform interlayer fragility determination on the interlayer seismic response data to generate interlayer fragility data; perform fracturing area surface texture identification on the shale reservoir fracture information according to the interlayer fragility data to obtain regional surface texture information; compare the regional surface texture information with the preset regional surface texture information, if the regional surface texture information is less than the preset regional surface texture information, mark the regional surface texture information as high seismic resistance layer regional information; if the regional surface texture information is greater than or equal to the preset regional surface texture information, mark the regional surface texture information as low seismic resistance layer regional information; integrate the high seismic resistance layer regional information and the low seismic resistance layer regional information to obtain the seismic resistance parameters of the low permeability reservoir; Step S354: Calculate the seismic intensity of the low permeability reservoir seismic data in combination with the inter-seismic response data to generate low permeability reservoir seismic severity data; correlate the low permeability reservoir seismic severity data with the low permeability reservoir seismic resistance parameters to generate low permeability reservoir seismic correlation data.

[0011] The present invention identifies the porosity characteristics of shale reservoir characteristic data, clarifies the porosity characteristics, and helps to evaluate the permeability of the reservoir in the future; determines the porosity distribution of the porosity characteristic data, reveals the distribution characteristics of the pores in the reservoir, and helps to understand the distribution and flow of fluids in the reservoir; calculates the porosity aperture of the porosity characteristic data in combination with the porosity distribution data, and clarifies the specific size information of the reservoir pores; extracts the mineral composition of the rock formation from the shale reservoir characteristic data, and can further analyze the rock physical properties; identifies the rock formation fractures of the rock formation mineral composition data based on the porosity aperture data, and clarifies the fracture conditions in the reservoir; simulates the interlayer seismic response of the shale reservoir fracture information and the low-permeability reservoir seismic data, and provides the response characteristics of the reservoir under the action of earthquakes; and determines the interlayer fragility of the interlayer seismic response data to evaluate the fragility of the reservoir. The invention can identify the surface texture of the fracturing area of ​​the shale reservoir fracture information according to the interlayer fragility data to obtain the regional surface texture information; compare the regional surface texture information with the preset regional surface texture information, if the regional surface texture information is less than the preset regional surface texture information, mark the regional surface texture information as the high seismic resistance layer regional information; if the regional surface texture information is greater than or equal to the preset regional surface texture information, mark the regional surface texture information as the low seismic resistance layer regional information; integrate the high seismic resistance layer regional information and the low seismic resistance layer regional information to obtain the seismic parameters of the low permeability reservoir; calculate the seismic intensity of the low permeability reservoir seismic data in combination with the inter-seismic response data, and provide the strength characteristics of the reservoir under the action of earthquake; correlate the inter-layer seismic characteristics of the low permeability reservoir seismic degree data and the low permeability reservoir seismic parameters, so as to clarify the seismic correlation of the low permeability reservoir.

[0012] Preferably, step S4 comprises the following steps: Step S41: Calculate geological indicators of low permeability reservoir geological data according to low permeability reservoir seismic correlation data to generate low permeability reservoir geological indicators; Step S42: constructing a low permeability reservoir geological sweet spot prediction model according to the low permeability reservoir geological correlation indicators to obtain a low permeability reservoir geological sweet spot prediction pre-model, and training the low permeability reservoir geological sweet spot prediction pre-model using the low permeability reservoir geological correlation indicators to obtain a low permeability reservoir geological sweet spot prediction training model; Step S43: performing model cross-validation evaluation on the low-permeability reservoir geological sweet spot prediction training model to obtain model evaluation data; adjusting model parameters of the low-permeability reservoir geological sweet spot prediction training model using the model evaluation data to obtain a low-permeability reservoir geological sweet spot prediction model; Step S44: performing prestack inversion on the low permeability reservoir geological sweet spot prediction model to obtain model prestack inversion data; dynamically optimizing the low permeability reservoir geological sweet spot prediction model through the model prestack inversion data to obtain a low permeability reservoir geological sweet spot prediction optimization model; Step S45: Predict the geological sweet spots of the low permeability reservoir geological data based on the low permeability reservoir geological sweet spot prediction optimization model to generate low permeability reservoir geological sweet spot prediction data; visualize the low permeability reservoir geological sweet spot prediction data to generate a low permeability reservoir geological sweet spot prediction report.

[0013] The present invention calculates geological indicators of low-permeability reservoir geological data based on low-permeability reservoir seismic correlation data, and can quantify key parameters of reservoir evaluation; constructs a low-permeability reservoir geological sweet spot prediction model based on low-permeability reservoir geological correlation indicators to obtain a low-permeability reservoir geological sweet spot prediction pre-model, and uses low-permeability reservoir geological correlation indicators to train the low-permeability reservoir geological sweet spot prediction pre-model to obtain a low-permeability reservoir geological sweet spot prediction training model, thereby improving the prediction accuracy of the model; performs model cross-validation evaluation on the low-permeability reservoir geological sweet spot prediction training model, and provides quantitative indicators of model performance, which can reflect the reliability and prediction ability of the model; and evaluates the low-permeability reservoir geological sweet spot prediction training model based on model evaluation data. The model parameters of the geological sweet spot prediction training model for permeable reservoirs are adjusted to further improve the prediction accuracy of the model and ensure the effectiveness and applicability of the model; the pre-stack inversion of the geological sweet spot prediction model for low permeability reservoirs is performed to enhance the model's recognition accuracy of reservoir characteristics; the low permeability reservoir geological sweet spot prediction model is dynamically optimized through the model's pre-stack inversion data to improve the model's stability and long-term prediction accuracy; the geological sweet spot prediction of low permeability reservoir geological data is carried out based on the low permeability reservoir geological sweet spot prediction optimization model to predict the specific location and characteristics of the reservoir sweet spot area; the low permeability reservoir geological sweet spot prediction data is visualized to form an intuitive report.

[0014] Preferably, step S41 includes the following steps: Step S411: measuring the seismic amplitude of the low permeability reservoir seismic correlation data to obtain interlayer seismic amplitude data; identifying the interlayer deformation degree of the low permeability reservoir morphology data according to the interlayer seismic amplitude data to generate low permeability reservoir deformation data; Step S412: Calculate the pore density of the low permeability reservoir geological data based on the low permeability reservoir deformation data to obtain the pore density of the low permeability reservoir; perform porosity identification on the pore density of the low permeability reservoir to obtain the pore parameters of the low permeability reservoir; perform low permeability reservoir inter-layer permeability measurement on the low permeability reservoir geological data according to the low permeability reservoir pore parameters to generate the low permeability reservoir inter-layer permeability; Step S413: mapping the seismic coefficient permeability of the low permeability reservoir inter-layer permeability in combination with the seismic parameters of the low permeability reservoir to obtain seismic layer permeability data; calculating the rock formation elastic modulus of the low permeability reservoir geological data according to the seismic layer permeability data to generate rock formation elastic modulus data; Step S414: extracting oil and gas characteristics from key low-permeability reservoir information to obtain low-permeability reservoir oil and gas data; calculating oil and gas saturation of the low-permeability reservoir oil and gas data based on the formation elastic modulus data to generate low-permeability reservoir oil and gas saturation data; Step S415: Integrate the low permeability reservoir deformation data, the low permeability reservoir interlayer permeability and the low permeability reservoir oil and gas saturation data to obtain the low permeability reservoir geological indicators.

[0015] The present invention measures the magnitude of seismic amplitude on seismic correlation data of low permeability reservoirs, and provides a quantitative index of reservoir seismic response; identifies the degree of interlayer deformation of low permeability reservoir morphology data based on interlayer seismic amplitude data, and reveals the deformation characteristics of the reservoir under geological action; calculates the pore density of low permeability reservoir geological data based on low permeability reservoir deformation data, and provides a quantitative description of reservoir pore density; identifies the porosity of low permeability reservoir pore density, and clarifies the pore parameters of low permeability reservoirs; measures the permeability between low permeability reservoirs on low permeability reservoir geological data based on the pore parameters of low permeability reservoirs, and can obtain the permeability between low permeability reservoirs; combines the seismic resistance parameters of low permeability reservoirs to measure the permeability of low permeability reservoirs. The permeability between reservoirs is mapped to the seismic coefficient permeability, which provides the permeability of the reservoir under earthquake action and helps to evaluate the behavioral characteristics of the reservoir in the geological dynamic process; the elastic modulus of the rock formation is calculated for the geological data of the low-permeability reservoir based on the permeability data of the seismic layer to clarify the elastic properties of the reservoir rock; the oil and gas characteristics are extracted from the key low-permeability reservoir information to obtain the oil and gas data of the low-permeability reservoir; the oil and gas saturation of the low-permeability reservoir oil and gas data is calculated based on the rock formation elastic modulus data, which can quantify the oil and gas saturation of the low-permeability reservoir; the deformation data of the low-permeability reservoir, the permeability between low-permeability reservoirs and the oil and gas saturation data of the low-permeability reservoir are integrated to obtain comprehensive low-permeability reservoir geological indicators.

[0016] Preferably, step S44 includes the following steps: Step S441: performing seismic prestack inversion processing on the low-permeability reservoir geological sweet spot prediction model to obtain model prestack inversion data; Step S442: extracting low-permeability reservoir deformation parameters from the model pre-stack inversion data to generate low-permeability reservoir deformation inversion parameters; performing permeability detection on the seismic pre-stack inversion data according to the low-permeability reservoir deformation parameters to obtain low-permeability reservoir permeability detection data; evaluating oil and gas saturation on the seismic pre-stack inversion data using the low-permeability reservoir permeability detection data to generate oil and gas saturation evaluation data; Step S443: identifying the oil and gas geological sweet spot area on the oil and gas saturation assessment data to obtain geological sweet spot area data; determining the low permeability reservoir geological sweet spot on the geological sweet spot area data based on the low permeability reservoir deformation inversion parameters, the low permeability reservoir permeability detection data and the oil and gas saturation assessment data to generate low permeability reservoir geological sweet spot determination data; Step S444: According to the low permeability reservoir geological sweet spot determination data, the low permeability reservoir geological indicator weights are adjusted for the low permeability reservoir geological sweet spot prediction model to obtain geological indicator weight adjustment data; the low permeability reservoir geological sweet spot prediction model is dynamically weight optimized using the geological indicator weight adjustment data to obtain a low permeability reservoir geological sweet spot prediction optimization model.

[0017] The present invention performs seismic prestack inversion processing on the low-permeability reservoir geological sweet spot prediction model, provides detailed information on the reservoir seismic response, and makes it clear the physical characteristics of the reservoir; extracts low-permeability reservoir deformation parameters from the model prestack inversion data, and can obtain low-permeability reservoir deformation inversion parameters; performs permeability detection on the seismic prestack inversion data according to the low-permeability reservoir deformation parameters, and provides a quantitative index of reservoir permeability; performs oil and gas saturation assessment on the seismic prestack inversion data through the low-permeability reservoir permeability detection data, and clarifies the oil and gas saturation assessment situation; performs oil and gas geological sweet spot area identification on the oil and gas saturation assessment data, and clarifies the relatively high-yield areas in the reservoir. area; based on the low permeability reservoir deformation inversion parameters, low permeability reservoir permeability detection data and oil and gas saturation assessment data, the low permeability reservoir geological sweet spot is determined on the geological sweet spot area data, which can specifically determine the low permeability reservoir geological sweet spot situation; according to the low permeability reservoir geological sweet spot determination data, the low permeability reservoir geological indicator weight adjustment of the low permeability reservoir geological sweet spot prediction model can optimize the model's parameter configuration, making the model more in line with the actual geological conditions, thereby improving the model's prediction accuracy; using the geological indicator weight adjustment data to dynamically optimize the weight of the low permeability reservoir geological sweet spot prediction model can further enhance the model's adaptability and prediction ability.

[0018] Preferably, step S45 includes the following steps: Step S451: Predicting the porosity attribute of the geological sweet spot of the low permeability reservoir geological data based on the low permeability reservoir geological sweet spot prediction optimization model to obtain porosity attribute prediction data; spatially locating the sweet spot area of ​​the low permeability reservoir geological data according to the porosity attribute prediction data to generate sweet spot area spatial prediction data; Step S452: performing regional low-permeability reservoir permeability prediction on the sweet spot area spatial prediction data to obtain regional permeability prediction data; performing oil and gas flow prediction on the low-permeability reservoir geological data using the regional permeability prediction data to generate oil and gas flow prediction data; Step S453: based on the porosity attribute prediction data, the regional permeability prediction data and the oil and gas flow prediction data, the low permeability reservoir geological data is classified into sweet spot grades to obtain geological sweet spot grade data; the geological sweet spot prediction optimization model of the low permeability reservoir is used to predict the geological sweet spot of the geological sweet spot grade data to generate the low permeability reservoir geological sweet spot prediction data; Step S454: Process the low permeability reservoir geological sweet spot prediction data into information graphics to obtain a low permeability reservoir geological sweet spot prediction chart; prepare a visualization report for the low permeability reservoir geological sweet spot prediction chart to obtain a low permeability reservoir geological sweet spot prediction report.

[0019] The present invention predicts the porosity attributes of the geological sweet spots of the low permeability reservoir geological data based on the low permeability reservoir geological sweet spot prediction optimization model, and provides a quantitative description of the reservoir pore structure; the sweet spot area of ​​the low permeability reservoir geological data is spatially located according to the porosity attribute prediction data, and the sweet spot area in the reservoir can be clearly identified; the regional low permeability reservoir permeability is predicted based on the sweet spot area spatial prediction data, and the regional permeability characteristics can be predicted; the oil and gas flow rate of the low permeability reservoir geological data is predicted through the regional permeability prediction data, and the oil and gas flow rate data can be predicted; based on the porosity attribute prediction data, the regional permeability ... The low permeability reservoir geological data are divided into sweet spot grades based on the rate prediction data and the oil and gas flow prediction data, so as to provide a grading evaluation standard for the reservoir sweet spot area; the geological sweet spot grade data are predicted by using the low permeability reservoir geological sweet spot prediction optimization model, so as to provide a comprehensive description of the reservoir sweet spot area; the low permeability reservoir geological sweet spot prediction data are processed into information charts to obtain the low permeability reservoir geological sweet spot prediction chart; the low permeability reservoir geological sweet spot prediction chart is visualized and a low permeability reservoir geological sweet spot prediction report is obtained, which can provide an intuitive and easy-to-understand chart report.

[0020] In this specification, a low permeability reservoir geological sweet spot prediction system is provided, which is used to execute the above-mentioned low permeability reservoir geological sweet spot prediction method. The low permeability reservoir geological sweet spot prediction system includes: The low-permeability reservoir geological data acquisition module is used to obtain low-permeability reservoir geological data; pre-process the low-permeability reservoir geological data to obtain standard low-permeability reservoir geological data; perform multi-dimensional feature recognition on the standard low-permeability reservoir geological data to obtain multi-dimensional geological feature data; extract key low-permeability reservoir information from the multi-dimensional geological feature data to obtain key low-permeability reservoir information; The low-permeability reservoir structure morphology recognition module is used to extract low-permeability reservoir cores from key low-permeability reservoir information to generate low-permeability reservoir core data; extract core microstructure characteristics from multi-dimensional geological feature data based on low-permeability reservoir core data to obtain core microstructure characteristics; perform low-permeability reservoir structure morphology recognition on key low-permeability reservoir information based on core microstructure characteristics to generate low-permeability reservoir morphology data; The low-permeability reservoir seismic correlation analysis module is used to determine the low-permeability reservoir range distribution of key low-permeability reservoir information based on low-permeability reservoir morphological data to obtain low-permeability reservoir range data; use the low-permeability reservoir range data to identify the seismic characteristics of key low-permeability reservoir information to generate low-permeability reservoir seismic data; extract shale reservoir characteristics from the low-permeability reservoir range data to obtain shale reservoir characteristic data; correlate and analyze shale reservoir parameters with low-permeability reservoir seismic data to generate low-permeability reservoir seismic correlation data; The low-permeability reservoir geological sweet spot prediction model module is used to calculate the geological indicators of low-permeability reservoir geological data based on the low-permeability reservoir seismic correlation data to generate low-permeability reservoir geological indicators; use the low-permeability reservoir geological correlation indicators to construct a low-permeability reservoir geological sweet spot prediction model to obtain a low-permeability reservoir geological sweet spot prediction model; perform pre-stack inversion on the low-permeability reservoir geological sweet spot prediction model to obtain the model pre-stack inversion data; dynamically optimize the low-permeability reservoir geological sweet spot prediction model through the model pre-stack inversion data to obtain a low-permeability reservoir geological sweet spot prediction optimization model; perform geological sweet spot prediction on the low-permeability reservoir geological data based on the low-permeability reservoir geological sweet spot prediction optimization model to generate low-permeability reservoir geological sweet spot prediction data; perform data visualization on the low-permeability reservoir geological sweet spot prediction data to generate a low-permeability reservoir geological sweet spot prediction report.

[0021] The present invention acquires low permeability reservoir geological data and performs preprocessing through a low permeability reservoir geological data acquisition module, thereby ensuring data standardization and providing high-quality data support for subsequent analysis; multidimensional feature recognition enables the extraction of rich geological information from standard geological data; the extraction of key low permeability reservoir information further focuses on factors that have an important impact on reservoir characteristics, thereby improving the pertinence and accuracy of the analysis. Through a low permeability reservoir structural morphology recognition module, low permeability reservoir core extraction is performed on key low permeability reservoir information, which can clarify the low permeability reservoir core information; core microstructure feature extraction is performed on multidimensional geological feature data based on low permeability reservoir core data, which clarifies the understanding of the internal structure of the reservoir and can reveal the microscopic characteristics of the reservoir; low permeability reservoir structural morphology recognition is performed on key low permeability reservoir information based on core microstructure features, which clarifies the spatial distribution characteristics of the reservoir and provides a data basis for the subsequent determination of reservoir range distribution. Through the low-permeability reservoir seismic correlation analysis module, the low-permeability reservoir range distribution of key low-permeability reservoir information is determined based on the low-permeability reservoir morphological data, and the geographical distribution of the reservoir is determined, thereby clarifying the low-permeability reservoir range; the seismic characteristics of key low-permeability reservoir information are identified using the low-permeability reservoir range data, which can identify the seismic characteristics of the reservoir geological structure and further clarify the low-permeability reservoir seismic situation; shale reservoir characteristics are extracted from the low-permeability reservoir range data to obtain shale reservoir characteristic data; shale reservoir parameters are correlated with low-permeability reservoir seismic data for analysis, which can comprehensively understand the correlation between geographical low-permeability reservoir earthquakes. Through the low permeability reservoir geological sweet spot prediction model module, the geological index of the low permeability reservoir geological data is calculated according to the low permeability reservoir seismic correlation data, and a quantitative reservoir index evaluation standard is provided; the low permeability reservoir geological correlation index is used to construct the low permeability reservoir geological sweet spot prediction model, and the low permeability reservoir geological sweet spot prediction model is obtained; the low permeability reservoir geological sweet spot prediction model is prestack inversion to obtain the model prestack inversion data; the low permeability reservoir geological sweet spot prediction model is dynamically optimized by the model prestack inversion data, and the accuracy and applicability of the prediction model are improved, thereby improving the accuracy of the geological sweet spot prediction; based on the low permeability reservoir geological sweet spot prediction optimization model, the low permeability reservoir geological data is predicted to be geological sweet spot, and the low permeability reservoir geological sweet spot prediction data is generated; the low permeability reservoir geological sweet spot prediction data is visualized, and the prediction report can be intuitively displayed. Therefore, the present invention realizes multi-dimensional analysis of the geological characteristics of the low permeability reservoir through data processing technology, pattern recognition technology and machine learning technology, and combines the seismic characteristics of the low permeability reservoir for correlation analysis, thereby improving the accuracy of the low permeability reservoir geological sweet spot prediction.

[0022] A computer-readable storage medium stores a computer program, wherein the computer program is used to execute the method for predicting geological sweet spots in low-permeability reservoirs. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the steps of a method for predicting geological sweet spots in low permeability reservoirs; Figure 2 for Figure 1 Detailed implementation steps of step S3 in FIG. Figure 3 for Figure 2 Detailed implementation steps of step S35; The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0024] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0025] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0026] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0027] To achieve this, please refer to Figures 1 to 3 , a method for predicting geological sweet spots in low-permeability reservoirs, the method comprising the following steps: Step S1: acquiring low permeability reservoir geological data; preprocessing the low permeability reservoir geological data to obtain standard low permeability reservoir geological data; performing multidimensional feature recognition on the standard low permeability reservoir geological data to obtain multidimensional geological feature data; extracting key low permeability reservoir information from the multidimensional geological feature data to obtain key low permeability reservoir information; Step S2: extracting low permeability reservoir cores from key low permeability reservoir information to generate low permeability reservoir core data; extracting core microstructure characteristics from multidimensional geological feature data based on the low permeability reservoir core data to obtain core microstructure characteristics; identifying low permeability reservoir structure morphology from key low permeability reservoir information based on the core microstructure characteristics to generate low permeability reservoir morphology data; Step S3: determining the low permeability reservoir range distribution of key low permeability reservoir information based on the low permeability reservoir morphology data to obtain low permeability reservoir range data; using the low permeability reservoir range data to identify seismic characteristics of key low permeability reservoir information to generate low permeability reservoir seismic data; extracting shale reservoir characteristics from the low permeability reservoir range data to obtain shale reservoir characteristic data; correlating and analyzing the shale reservoir characteristic data with the low permeability reservoir seismic data to generate low permeability reservoir seismic correlation data; Step S4: Calculate geological indicators of low permeability reservoir geological data according to low permeability reservoir seismic correlation data to generate low permeability reservoir geological indicators; construct a low permeability reservoir geological sweet spot prediction model using low permeability reservoir geological correlation indicators to obtain a low permeability reservoir geological sweet spot prediction model; perform prestack inversion on the low permeability reservoir geological sweet spot prediction model to obtain model prestack inversion data; dynamically optimize the low permeability reservoir geological sweet spot prediction model through the model prestack inversion data to obtain a low permeability reservoir geological sweet spot prediction optimization model; perform geological sweet spot prediction on low permeability reservoir geological data based on the low permeability reservoir geological sweet spot prediction optimization model to generate low permeability reservoir geological sweet spot prediction data; perform data visualization on the low permeability reservoir geological sweet spot prediction data to generate a low permeability reservoir geological sweet spot prediction report.

[0028] The present invention obtains low-permeability reservoir geological data and performs preprocessing to ensure data standardization, providing high-quality data support for subsequent analysis; multi-dimensional feature recognition enables the extraction of rich geological information from standard geological data; the extraction of key low-permeability reservoir information further focuses on factors that have an important impact on reservoir characteristics, improving the pertinence and accuracy of the analysis. Low-permeability reservoir core extraction of key low-permeability reservoir information can clarify low-permeability reservoir core information; core microstructure feature extraction of multi-dimensional geological feature data based on low-permeability reservoir core data clarifies the understanding of the internal structure of the reservoir and can reveal the microscopic characteristics of the reservoir; low-permeability reservoir structural morphology recognition of key low-permeability reservoir information based on core microstructure features clarifies the spatial distribution characteristics of the reservoir, providing a data basis for subsequent determination of reservoir range distribution. Based on the low permeability reservoir morphology data, the low permeability reservoir range distribution of key low permeability reservoir information is determined, the geographical distribution of the reservoir is determined, and thus the low permeability reservoir range is clarified; the seismic characteristics of the key low permeability reservoir information are identified using the low permeability reservoir range data, which can identify the seismic characteristics of the reservoir geological structure and further clarify the seismic situation of the low permeability reservoir; the shale reservoir characteristics are extracted from the low permeability reservoir range data to obtain shale reservoir characteristic data; the shale reservoir parameters are correlated with the low permeability reservoir seismic data for analysis, which can comprehensively understand the correlation between the geographical low permeability reservoir and the earthquake. According to the low permeability reservoir seismic correlation data, the geological index of the low permeability reservoir geological data is calculated, and a quantitative reservoir index evaluation standard is provided; the low permeability reservoir geological correlation index is used to construct a low permeability reservoir geological sweet spot prediction model to obtain a low permeability reservoir geological sweet spot prediction model; the low permeability reservoir geological sweet spot prediction model is prestack inversion to obtain the model prestack inversion data; the low permeability reservoir geological sweet spot prediction model is dynamically optimized by the model prestack inversion data, and the accuracy and applicability of the prediction model are improved, thereby improving the accuracy of the geological sweet spot prediction; based on the low permeability reservoir geological sweet spot prediction optimization model, the low permeability reservoir geological data is predicted to be geological sweet spot, and the low permeability reservoir geological sweet spot prediction data is generated; the low permeability reservoir geological sweet spot prediction data is visualized, and the prediction report can be intuitively displayed. Therefore, the present invention realizes multi-dimensional analysis of the geological characteristics of the low permeability reservoir through data processing technology, pattern recognition technology and machine learning technology, and combines the seismic characteristics of the low permeability reservoir for correlation analysis, thereby improving the accuracy of the low permeability reservoir geological sweet spot prediction.

[0029] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a method for predicting a low-permeability reservoir geological sweet spot according to the present invention. In this example, the method for predicting a low-permeability reservoir geological sweet spot includes the following steps: Step S1: acquiring low permeability reservoir geological data; preprocessing the low permeability reservoir geological data to obtain standard low permeability reservoir geological data; performing multidimensional feature recognition on the standard low permeability reservoir geological data to obtain multidimensional geological feature data; extracting key low permeability reservoir information from the multidimensional geological feature data to obtain key low permeability reservoir information; In an embodiment of the present invention, geological data of low permeability reservoirs are obtained through geological exploration and geophysical logging technology, and specifically logging technology, such as acoustic time difference logging technology, is used to measure low permeability reservoirs; the geological data of low permeability reservoirs are preprocessed, specifically including data cleaning, denoising and format standardization, to obtain standard low permeability reservoir geological data; multidimensional feature recognition technology, such as grey correlation discrimination technology, is used to analyze the standard low permeability reservoir geological data, specifically, to identify the porosity curve index and the fluid index, determine the multidimensional geological characteristics of the low permeability reservoir, and use nuclear magnetic resonance logging technology to identify the pore structure of the reservoir; on the basis of the multidimensional geological feature data, modern geological mathematical methods and signal analysis technology, such as wavelet analysis, are applied to specifically analyze the response characteristics of the low permeability reservoir curve, specifically identify the fluid type in the reservoir, and extract key low permeability reservoir information.

[0030] Step S2: extracting low permeability reservoir cores from key low permeability reservoir information to generate low permeability reservoir core data; extracting core microstructure characteristics from multidimensional geological feature data based on the low permeability reservoir core data to obtain core microstructure characteristics; identifying low permeability reservoir structure morphology from key low permeability reservoir information based on the core microstructure characteristics to generate low permeability reservoir morphology data; In the embodiment of the present invention, feature extraction technology is used to extract low permeability reservoir cores for key low permeability reservoir information; specifically, scanning imaging technology is used to perform three-dimensional scanning of low permeability reservoir cores to obtain the pore structure and fracture development characteristics of the cores; grayscale analysis and image segmentation are performed on the pore structure and fracture development characteristics of the cores through image processing software, such as Avizo software, so as to extract the pore and fracture network structure of the cores; the pore size distribution, pore throat radius and connectivity of the pore structure of the cores are quantitatively analyzed, and specifically through wavelet analysis technology, multi-scale refinement analysis is performed on the microstructure characteristics of the cores to extract the microstructure characteristics of the cores; based on the extracted microstructure characteristics of the cores, a support vector machine (SVM) algorithm is used to identify the structural morphology of the low permeability reservoir; by constructing different kernel functions, such as Gaussian kernel (RBF) or polynomial kernel, the nanoscale pore throat structure of the cores is classified, so as to identify the morphological characteristics of the low permeability reservoirs.

[0031] Step S3: determining the low permeability reservoir range distribution of key low permeability reservoir information based on the low permeability reservoir morphology data to obtain low permeability reservoir range data; using the low permeability reservoir range data to identify seismic characteristics of key low permeability reservoir information to generate low permeability reservoir seismic data; extracting shale reservoir characteristics from the low permeability reservoir range data to obtain shale reservoir characteristic data; correlating and analyzing the shale reservoir characteristic data with the low permeability reservoir seismic data to generate low permeability reservoir seismic correlation data; In the embodiment of the present invention, seismic attribute analysis is performed through a three-dimensional seismic data body to specifically identify the continuity and fault boundaries of the reservoir; a mathematical morphology method is used to detect and classify the configuration boundaries of the seismic data, and reservoir configuration analysis of different levels is carried out to determine the spatial distribution range of the low-permeability reservoir; seismic inversion technology is applied, combined with low-permeability reservoir range data, to identify the seismic characteristics of key low-permeability reservoir information; velocity and density attributes in the seismic data body are used to specifically reflect the physical characteristics and fluid properties of the reservoir through seismic inversion technology; digital core technology is used, combined with image processing technology, to extract shale reservoir characteristics from low-permeability reservoir range data; a three-dimensional digital core model of the reservoir is constructed through scanning technology, and the connected pore structure is specifically extracted and the microscopic pore structure characteristics of the rock sample are quantitatively characterized, thereby obtaining shale reservoir characteristic data; shale reservoir parameters are correlated with low-permeability reservoir seismic data for analysis, and support vector machine (SVM) is used to perform pattern recognition and parameter optimization; the seepage mechanism of the tight sandstone reservoir is specifically determined based on the dual-scale pore coupling seepage simulation method, thereby generating low-permeability reservoir seismic correlation data.

[0032] Step S4: Calculate geological indicators of low permeability reservoir geological data according to low permeability reservoir seismic correlation data to generate low permeability reservoir geological indicators; construct a low permeability reservoir geological sweet spot prediction model using low permeability reservoir geological correlation indicators to obtain a low permeability reservoir geological sweet spot prediction model; perform prestack inversion on the low permeability reservoir geological sweet spot prediction model to obtain model prestack inversion data; dynamically optimize the low permeability reservoir geological sweet spot prediction model through the model prestack inversion data to obtain a low permeability reservoir geological sweet spot prediction optimization model; perform geological sweet spot prediction on low permeability reservoir geological data based on the low permeability reservoir geological sweet spot prediction optimization model to generate low permeability reservoir geological sweet spot prediction data; perform data visualization on the low permeability reservoir geological sweet spot prediction data to generate a low permeability reservoir geological sweet spot prediction report.

[0033] In the embodiment of the present invention, seismic rock physics analysis technology is used in combination with geostatistical methods to calculate geological indicators of seismic correlation data of low permeability reservoirs; specifically, by analyzing seismic amplitude, frequency and waveform characteristics, combined with core analysis data, key geological indicators such as porosity and permeability of the reservoir are calculated; using the above geological indicators, combined with machine learning algorithms, such as random forests or neural networks, a prediction model for geological sweet spots of low permeability reservoirs is constructed; specifically, seismic attribute analysis is combined with geostatistical inversion methods to determine high-quality areas of the reservoir and construct a prediction model; pre-stack inversion technology, such as AVO (amplitude variation and offset) technology, is used to predict the geological sweet spots of the reservoir. The sweet spot prediction model is pre-stack inversion to obtain the model pre-stack inversion data; the low permeability reservoir geological sweet spot prediction model is dynamically optimized using the model pre-stack inversion data; the parameter modeling technology is specifically used to dynamically optimize the reservoir based on fine lithofacies unit constraints; based on the optimized low permeability reservoir geological sweet spot prediction optimization model, the geological sweet spot prediction of the low permeability reservoir geological data is performed to generate prediction data; the low permeability reservoir geological sweet spot prediction data is visualized, and specifically professional geological modeling software, such as Petrel software, is used to perform three-dimensional visualization of the data to generate a low permeability reservoir geological sweet spot prediction report.

[0034] Preferably, step S2 comprises the following steps: Step S21: performing low permeability reservoir core feature identification on key low permeability reservoir information to obtain low permeability reservoir core features; performing low permeability reservoir core data extraction on key low permeability reservoir information according to the low permeability reservoir core features to generate low permeability reservoir core data; Step S22: performing core feature enhancement on the low permeability reservoir core data to obtain core feature enhancement data; performing feature hierarchization on the core feature enhancement data to generate core feature hierarchical data; performing hierarchical structure element extraction on the core feature hierarchical data to obtain core hierarchical structure element information; Step S23: marking the core hierarchical structure of the multidimensional geological feature data through the core hierarchical structure element information to obtain core hierarchical structure marking data; identifying the core microstructure characteristics of the multidimensional geological feature data based on the core hierarchical structure marking data to obtain core microstructure characteristics; Step S24: performing feature imaging processing on key low-permeability reservoir information according to core microstructural characteristics to obtain a low-permeability reservoir structural image; performing structural image recognition on the low-permeability reservoir structural image to obtain low-permeability reservoir structural data; performing low-permeability reservoir morphology extraction on the low-permeability reservoir structural data to obtain low-permeability reservoir morphology data.

[0035] In the embodiment of the present invention, the key low-permeability reservoir information is used to identify the characteristics of the low-permeability reservoir core. Specifically, the reservoir is divided into lithological phase units of different microscales, and the pore structure of different lithological phase units is finely characterized by using nuclear magnetic resonance logging technology; the key characteristics of the low-permeability reservoir core, such as porosity and permeability, are identified, and the low-permeability reservoir core data is generated; image processing technology, such as image denoising and enhancement, is used to improve the contrast and clarity of the core image, thereby obtaining core feature enhanced data; further, the core image is hierarchically processed based on the image segmentation technology of the Unet++ network to achieve the hierarchical core feature; the hierarchical data is analyzed to extract the hierarchical structure element information of the core, such as the pore structure, distribution, pore connectivity, etc.; combine the core hierarchical structure element information, use image segmentation technology to mark the multidimensional geological feature data, and generate core hierarchical structure mark data; based on the core hierarchical structure mark data, the core microstructure characteristics are identified for the multidimensional geological feature data, such as pore structure, pore size distribution, etc.; use digital core technology, combined with high-resolution imaging technology, such as focused ion beam-scanning electron microscopy, to image the core microstructure characteristics and obtain the low permeability reservoir structure image; further, apply image recognition technology to identify the structure image and extract the morphological characteristics of the low permeability reservoir; use morphological analysis methods to perform morphological extraction on the identified structure data to obtain low permeability reservoir morphological data.

[0036] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S31: extracting geometric features from the low permeability reservoir morphological data to obtain geometric features of the low permeability reservoir; determining feature spatial relationships of the geometric features of the low permeability reservoir to generate spatial relationship data of the low permeability reservoir; dividing the spatial relationship data of the low permeability reservoir into relationship types to obtain spatial relationship type data; Step S32: performing spatial distribution identification on the low permeability reservoir morphology data according to the spatial relationship type data to generate low permeability reservoir spatial distribution information; performing low permeability reservoir boundary determination on the low permeability reservoir spatial distribution information to obtain low permeability reservoir boundary data; performing low permeability reservoir range distribution determination on the key low permeability reservoir information based on the low permeability reservoir spatial distribution information and the low permeability reservoir boundary data to obtain low permeability reservoir range data; Step S33: performing low permeability reservoir continuity measurement on the low permeability reservoir range data to generate continuity measurement data; using the continuity measurement data to determine the interlayer continuity of key low permeability reservoir information to obtain interlayer continuity data; recording the number of interlayer collision and compression times of key low permeability reservoir information according to the interlayer continuity data to obtain interlayer collision and compression data; performing seismic feature recognition on the interlayer collision and compression data to generate low permeability reservoir seismic data; Step S34: performing shape structure recognition on the low permeability reservoir range data to obtain shale reservoir shape data; performing shale reservoir parameter extraction on the shale reservoir shape data to generate shale reservoir parameter information; integrating the shale reservoir shape data and the shale reservoir parameter information to obtain shale reservoir characteristic data; Step S35: performing correlation analysis on the shale reservoir characteristic data and the low permeability reservoir seismic data to generate low permeability reservoir seismic correlation data.

[0037] In the embodiment of the present invention, digital core technology is used in combination with Micro-CT scanning technology to perform three-dimensional scanning of low-permeability reservoir cores, and specifically extract geometric morphological characteristics of pore structure, such as pore size, shape and distribution; image processing software is used to analyze CT scanning data to determine the spatial relationship of pore structure, such as connectivity between pores and complexity of pore network; spatial relationship data is classified through pattern recognition technology to obtain data of different types of spatial relationships; geostatistical methods are applied to perform spatial distribution analysis on morphological data of low-permeability reservoirs in combination with spatial relationship type data to specifically determine spatial distribution characteristics of reservoirs; geological modeling software, such as Petrel software, is used to accurately determine reservoir boundaries to obtain low-permeability reservoir boundary data; multidimensional geological modeling technology is used in combination with spatial distribution information and boundary data to determine the range distribution of low-permeability reservoirs and generate low-permeability reservoir range data; seismic interpretation technology, such as AVO analysis technology, is used to analyze the low-permeability reservoirs. The continuity analysis of the range data is carried out to generate continuity measurement data; the velocity and amplitude attributes in the seismic data body are used to generate interlayer continuity data through seismic inversion technology, and the number of interlayer collision and compression is recorded to obtain interlayer collision and compression data; the seismic characteristics of interlayer collision and compression are identified through feature analysis of the seismic data body to generate low-permeability reservoir seismic data; digital core technology is used in combination with high-resolution imaging technology, such as focused ion beam-scanning electron microscopy, to perform shape structure recognition on the range data of low-permeability reservoirs to obtain the pore and fracture network structure of shale reservoirs; image processing and analysis software, such as Avizo software, is used to extract parameters of the pore structure of shale reservoirs to generate shale reservoir parameter information; shape data and parameter information are integrated through data fusion technology to obtain shale reservoir characteristic data; data association technology is used to combine shale reservoir characteristic data and low-permeability reservoir seismic data for association analysis; low-permeability reservoir seismic association data is generated through pattern recognition and parameter optimization.

[0038] As an example of the present invention, refer to Figure 3 As shown, in this example, step S35 includes: Step S351: performing porosity feature identification on the shale reservoir characteristic data to obtain porosity characteristic data; performing porosity distribution determination on the porosity characteristic data to generate porosity distribution data; performing porosity diameter measurement on the porosity characteristic data in combination with the porosity distribution data to obtain porosity diameter data; Step S352: extracting the mineral composition of the shale reservoir characteristic data to obtain the mineral composition data of the shale reservoir; identifying the rock fractures of the shale reservoir mineral composition data according to the porosity and pore size data to generate the shale reservoir fracture information; Step S353: simulate the interlayer seismic response of the shale reservoir fracture information and the low permeability reservoir seismic data to obtain the interlayer seismic response data; perform interlayer fragility determination on the interlayer seismic response data to generate interlayer fragility data; perform fracturing area surface texture identification on the shale reservoir fracture information according to the interlayer fragility data to obtain regional surface texture information; compare the regional surface texture information with the preset regional surface texture information, if the regional surface texture information is less than the preset regional surface texture information, mark the regional surface texture information as high seismic resistance layer regional information; if the regional surface texture information is greater than or equal to the preset regional surface texture information, mark the regional surface texture information as low seismic resistance layer regional information; integrate the high seismic resistance layer regional information and the low seismic resistance layer regional information to obtain the seismic resistance parameters of the low permeability reservoir; Step S354: Calculate the seismic intensity of the low permeability reservoir seismic data in combination with the inter-seismic response data to generate low permeability reservoir seismic severity data; correlate the low permeability reservoir seismic severity data with the low permeability reservoir seismic resistance parameters to generate low permeability reservoir seismic correlation data.

[0039] In the embodiment of the present invention, the porosity characteristic data of the shale reservoir is obtained by nuclear magnetic resonance (NMR) logging technology, and the porosity distribution is determined by using the T2 spectrum distribution of NMR to generate porosity distribution data; then, in combination with the porosity distribution data, the porosity characteristic data is used to perform porosity aperture measurement using image analysis technology to obtain porosity aperture data; the shale reservoir characteristic data is used to extract the rock formation mineral composition using a core spectrum scanner to obtain rock formation mineral composition data; the rock formation mineral composition data is used to identify rock formation fractures in combination with the porosity aperture data to generate shale reservoir fracture information; in combination with the seismic data body and the shale reservoir fracture information, the regional building earthquake damage simulation method is used to perform interlayer seismic response simulation to obtain interlayer seismic response data; and the seismic response data is used to obtain the interlayer seismic response data. Earthquake disaster simulation analysis is used to determine interlayer vulnerability data; based on the interlayer vulnerability data, computer vision technology is used to identify the surface texture of the fracturing area to obtain regional surface texture information; further, the regional surface texture information is compared with the preset regional surface texture information, and according to the comparison results, the regional information of the high seismic resistance layer and the regional information of the low seismic resistance layer are marked, and these information are integrated to obtain the seismic parameters of the low permeability reservoir; using the interlayer seismic response data, the seismic intensity measurement method, such as earthquake disaster simulation analysis, is used to measure the seismic intensity of the low permeability reservoir seismic data to generate the low permeability reservoir seismic degree data; further, in combination with the low permeability reservoir seismic degree data and the low permeability reservoir seismic parameters, the interlayer seismic characteristics are correlated through seismic data analysis technology to generate low permeability reservoir seismic correlation data.

[0040] Preferably, step S4 comprises the following steps: Step S41: Calculate geological indicators of low permeability reservoir geological data according to low permeability reservoir seismic correlation data to generate low permeability reservoir geological indicators; Step S42: constructing a low permeability reservoir geological sweet spot prediction model according to the low permeability reservoir geological correlation indicators to obtain a low permeability reservoir geological sweet spot prediction pre-model, and training the low permeability reservoir geological sweet spot prediction pre-model using the low permeability reservoir geological correlation indicators to obtain a low permeability reservoir geological sweet spot prediction training model; Step S43: performing model cross-validation evaluation on the low-permeability reservoir geological sweet spot prediction training model to obtain model evaluation data; adjusting model parameters of the low-permeability reservoir geological sweet spot prediction training model using the model evaluation data to obtain a low-permeability reservoir geological sweet spot prediction model; Step S44: performing prestack inversion on the low permeability reservoir geological sweet spot prediction model to obtain model prestack inversion data; dynamically optimizing the low permeability reservoir geological sweet spot prediction model through the model prestack inversion data to obtain a low permeability reservoir geological sweet spot prediction optimization model; Step S45: Predict the geological sweet spots of the low permeability reservoir geological data based on the low permeability reservoir geological sweet spot prediction optimization model to generate low permeability reservoir geological sweet spot prediction data; visualize the low permeability reservoir geological sweet spot prediction data to generate a low permeability reservoir geological sweet spot prediction report.

[0041] In the embodiment of the present invention, the amplitude, frequency and waveform characteristics in the seismic data body are used; specifically, the porosity, permeability and other key geological indicators of the reservoir are calculated by seismic rock physics analysis technology, the seismic amplitude and frequency attributes are analyzed, and the geological indicators of the reservoir are calculated in combination with the core analysis data; a low-permeability reservoir geological sweet spot prediction model is constructed according to the low-permeability reservoir geological correlation indicators, and the LightGBM regression algorithm is specifically selected as the prediction model; the parameters are set as follows: the learning rate (learning_rate) is 0.1, the number of decision trees (num_iterations) is 200, the maximum depth (max_depth) is 5, and the minimum amount of data required for feature splitting (min_data_in_leaf) is 20; thereby constructing a low-permeability reservoir geological sweet spot prediction pre-model, and using the low-permeability reservoir geological correlation indicators for training to obtain a low-permeability reservoir geological sweet spot prediction training model; the low-permeability reservoir geological sweet spot prediction training model is subjected to model cross-validation evaluation, and the K-fold cross-validation method is specifically adopted, wherein K is set to 5; in each iteration, 4 / 5 of the data are used The remaining 1 / 5 is used for training, and the remaining 1 / 5 is used for validation; the evaluation indicators are selected as R2 score (r2_score) and mean square error (mse), where the closer the R2 score is to 1, the better the model fitting effect is, and the smaller the MSE is, the smaller the model prediction error is; the model parameters are adjusted according to the results of cross-validation; for example, the learning rate is adjusted to 0.05 to avoid overfitting; the number of decision trees is increased to 300 to improve the complexity and prediction ability of the model; through adjustment, the prediction model of low permeability reservoir geological sweet spot is finally obtained; prestack inversion technology is applied, such as AVO (Amplitude Variation and Offset) technology is used to perform prestack inversion on the geological sweet spot prediction model to obtain the model prestack inversion data; these data are used to dynamically optimize the model to improve the accuracy of reservoir oil and gas prediction; specifically, AVO technology is used to evaluate the rock properties of oil and gas reservoirs, including porosity, density, lithology and fluid content; the optimized low-permeability reservoir geological sweet spot prediction model is used to predict geological data and generate prediction data; data visualization technology is used to present the prediction results in the form of graphics and charts to obtain a geological sweet spot prediction report.

[0042] Preferably, step S41 includes the following steps: Step S411: measuring the seismic amplitude of the low permeability reservoir seismic correlation data to obtain interlayer seismic amplitude data; identifying the interlayer deformation degree of the low permeability reservoir morphology data according to the interlayer seismic amplitude data to generate low permeability reservoir deformation data; Step S412: Calculate the pore density of the low permeability reservoir geological data based on the low permeability reservoir deformation data to obtain the pore density of the low permeability reservoir; perform porosity identification on the pore density of the low permeability reservoir to obtain the pore parameters of the low permeability reservoir; perform low permeability reservoir inter-layer permeability measurement on the low permeability reservoir geological data according to the low permeability reservoir pore parameters to generate the low permeability reservoir inter-layer permeability; Step S413: mapping the seismic coefficient permeability of the low permeability reservoir inter-layer permeability in combination with the seismic parameters of the low permeability reservoir to obtain seismic layer permeability data; calculating the rock formation elastic modulus of the low permeability reservoir geological data according to the seismic layer permeability data to generate rock formation elastic modulus data; Step S414: extracting oil and gas characteristics from key low-permeability reservoir information to obtain low-permeability reservoir oil and gas data; calculating oil and gas saturation of the low-permeability reservoir oil and gas data based on the formation elastic modulus data to generate low-permeability reservoir oil and gas saturation data; Step S415: Integrate the low permeability reservoir deformation data, the low permeability reservoir interlayer permeability and the low permeability reservoir oil and gas saturation data to obtain the low permeability reservoir geological indicators.

[0043] In the embodiment of the present invention, seismic data processing software, such as RockWorks software, is used to perform amplitude analysis on seismic data, specifically to determine the magnitude of seismic amplitude, and obtain interlayer seismic amplitude data; deformation degree identification technology, such as deformation analysis method based on seismic amplitude change, is applied to determine the deformation of low-permeability reservoir morphology data, and generate low-permeability reservoir deformation data; nuclear magnetic resonance logging technology (Log-NMR) is used to measure the nuclear magnetic resonance signal of fluid in rock pores to determine pore structure and porosity; for example, by analyzing the T2 spectrum of nuclear magnetic resonance, information on the distribution of different pore sizes is obtained, and then the pore density is calculated; high-resolution array induction logging technology is used to specifically identify porosity by measuring resistivity changes at different depths; in combination with the deformation data of the low-permeability reservoir, nuclear magnetic resonance logging technology (Log-NMR) and array induction logging technology are used to calculate permeability by analyzing the pore structure and fluid distribution; for example, the T2 distribution and porosity data obtained by nuclear magnetic resonance logging , combined with core analysis data, and then calculate the permeability between low-permeability reservoirs; use the seismic parameters of low-permeability reservoirs; for example, seismic wave velocity, amplitude and frequency, etc., to perform seismic coefficient permeability mapping, so as to obtain the permeability data of seismic resistant layers; use downhole acoustic logging technology, specifically by measuring the propagation time of sound waves at different depths underground, calculate the elastic modulus of rocks; for example, use vertical seismic profiling (VSP) technology to obtain the propagation characteristics of downhole sound waves, and then calculate the elastic modulus; use downhole spectral logging technology, specifically by analyzing the absorption spectra of different elements in rocks, so as to extract oil and gas characteristics; for example, by measuring the infrared absorption spectrum of downhole rocks, identify the presence of oil and gas; combine the rock formation elastic modulus data to calculate the oil and gas saturation of low-permeability reservoir oil and gas data, so as to obtain the oil and gas saturation data of low-permeability reservoirs; through data integration technology, such as data fusion method based on geological cloud platform, the deformation data, permeability data and oil and gas saturation data of low-permeability reservoirs are integrated to finally obtain the geological indicators of low-permeability reservoirs.

[0044] Preferably, step S44 includes the following steps: Step S441: performing seismic prestack inversion processing on the low-permeability reservoir geological sweet spot prediction model to obtain model prestack inversion data; Step S442: extracting low-permeability reservoir deformation parameters from the model pre-stack inversion data to generate low-permeability reservoir deformation inversion parameters; performing permeability detection on the seismic pre-stack inversion data according to the low-permeability reservoir deformation parameters to obtain low-permeability reservoir permeability detection data; evaluating oil and gas saturation on the seismic pre-stack inversion data using the low-permeability reservoir permeability detection data to generate oil and gas saturation evaluation data; Step S443: identifying the oil and gas geological sweet spot area on the oil and gas saturation assessment data to obtain geological sweet spot area data; Based on the low-permeability reservoir deformation inversion parameters, low-permeability reservoir permeability detection data and oil and gas saturation assessment data, the low-permeability reservoir geological sweet spot is determined for the geological sweet spot area data to generate low-permeability reservoir geological sweet spot determination data; Step S444: According to the low permeability reservoir geological sweet spot determination data, the low permeability reservoir geological indicator weights are adjusted for the low permeability reservoir geological sweet spot prediction model to obtain geological indicator weight adjustment data; the low permeability reservoir geological sweet spot prediction model is dynamically weight optimized using the geological indicator weight adjustment data to obtain a low permeability reservoir geological sweet spot prediction optimization model.

[0045] In the embodiment of the present invention, it is set in the low permeability reservoir area, the input original seismic data is a specific time domain data set, and the frequency range is set to 5-60 Hz; specifically, an inversion algorithm, such as wave equation inversion and least squares method, is used to perform seismic prestack inversion processing on the low permeability reservoir geological sweet spot prediction model, and finally the model prestack inversion data is obtained; the low permeability reservoir deformation parameters are extracted from the model prestack inversion data; specifically, nuclear magnetic resonance logging and acoustic time difference logging are used to extract the low permeability reservoir deformation inversion parameters; based on the low permeability reservoir deformation inversion parameters, the seismic prestack inversion data is subjected to permeability detection, and the logging data and core analysis are used to detect the permeability of the low permeability reservoir; through the permeability detection data Generate oil and gas saturation assessment data based on the assessed oil and gas saturation; after obtaining the oil and gas saturation assessment data, identify the oil and gas geological sweet spot area; use fuzzy comprehensive evaluation method and independence weight coefficient method to identify the geological sweet spot area data; adjust the geological indicator weights of the low permeability reservoir geological sweet spot prediction model based on the low permeability reservoir geological sweet spot measurement data; use the independence weight coefficient method, combined with the correlation coefficient and the multiple correlation coefficient, to obtain the geological indicator weight adjustment data; and generate a low permeability reservoir geological sweet spot prediction optimization model through dynamic weight optimization.

[0046] Preferably, step S45 includes the following steps: Step S451: Predicting the porosity attribute of the geological sweet spot of the low permeability reservoir geological data based on the low permeability reservoir geological sweet spot prediction optimization model to obtain porosity attribute prediction data; spatially locating the sweet spot area of ​​the low permeability reservoir geological data according to the porosity attribute prediction data to generate sweet spot area spatial prediction data; Step S452: performing regional low-permeability reservoir permeability prediction on the sweet spot area spatial prediction data to obtain regional permeability prediction data; performing oil and gas flow prediction on the low-permeability reservoir geological data using the regional permeability prediction data to generate oil and gas flow prediction data; Step S453: based on the porosity attribute prediction data, the regional permeability prediction data and the oil and gas flow prediction data, the low permeability reservoir geological data is classified into sweet spot grades to obtain geological sweet spot grade data; the geological sweet spot prediction optimization model of the low permeability reservoir is used to predict the geological sweet spot of the geological sweet spot grade data to generate the low permeability reservoir geological sweet spot prediction data; Step S454: Process the low permeability reservoir geological sweet spot prediction data into information graphics to obtain a low permeability reservoir geological sweet spot prediction chart; prepare a visualization report for the low permeability reservoir geological sweet spot prediction chart to obtain a low permeability reservoir geological sweet spot prediction report.

[0047] In the embodiment of the present invention, a low-permeability reservoir geological sweet spot prediction optimization model is used to predict the porosity attributes of low-permeability reservoir geological data based on seismic data and well logging data, such as pre-stack inversion of reservoir information such as P-wave velocity and density; the sensitive parameters of the geological "sweet spot" are determined by cross-analysis of the well logging information, and the parameters are predicted; then, the porosity attribute prediction data is used; the sweet spot area is spatially located for the low-permeability reservoir geological data based on the porosity attribute prediction data, and the sweet spot area spatial prediction data is generated; for the located sweet spot area spatial prediction data, the phase-controlled permeability detection technology based on pore structure parameters is used to perform multivariate regression analysis in combination with parameters such as porosity, P-wave velocity, P-S wave velocity ratio and shear flexibility factor to predict the regional low-permeability reservoir permeability; the regional permeability prediction data is combined with Based on the fluid properties and reservoir pressure data, the oil and gas flow rate of the low permeability reservoir geological data is predicted to generate oil and gas flow rate prediction data; based on the porosity attribute prediction data, the regional permeability prediction data and the oil and gas flow rate prediction data, the fuzzy comprehensive evaluation method is used to classify the sweet spot level of the low permeability reservoir geological data; the geological sweet spot prediction optimization model of the low permeability reservoir is used to predict the geological sweet spot level data and generate the low permeability reservoir geological sweet spot prediction data; the low permeability reservoir geological sweet spot prediction data is processed into information charts, and data visualization technology, such as GIS software, is used to present the prediction results in the form of charts, curves and maps; further, a visual report is compiled for the low permeability reservoir geological sweet spot prediction chart, integrating geological, logging, seismic and experimental analysis data to form a low permeability reservoir geological sweet spot prediction report.

[0048] In this specification, a low permeability reservoir geological sweet spot prediction system is provided, which is used to execute the above-mentioned low permeability reservoir geological sweet spot prediction method. The low permeability reservoir geological sweet spot prediction system includes: The low-permeability reservoir geological data acquisition module is used to obtain low-permeability reservoir geological data; pre-process the low-permeability reservoir geological data to obtain standard low-permeability reservoir geological data; perform multi-dimensional feature recognition on the standard low-permeability reservoir geological data to obtain multi-dimensional geological feature data; extract key low-permeability reservoir information from the multi-dimensional geological feature data to obtain key low-permeability reservoir information; The low-permeability reservoir structure morphology recognition module is used to extract low-permeability reservoir cores from key low-permeability reservoir information to generate low-permeability reservoir core data; extract core microstructure characteristics from multi-dimensional geological feature data based on low-permeability reservoir core data to obtain core microstructure characteristics; perform low-permeability reservoir structure morphology recognition on key low-permeability reservoir information based on core microstructure characteristics to generate low-permeability reservoir morphology data; The low-permeability reservoir seismic correlation analysis module is used to determine the low-permeability reservoir range distribution of key low-permeability reservoir information based on low-permeability reservoir morphological data to obtain low-permeability reservoir range data; use the low-permeability reservoir range data to identify the seismic characteristics of key low-permeability reservoir information to generate low-permeability reservoir seismic data; extract shale reservoir characteristics from the low-permeability reservoir range data to obtain shale reservoir characteristic data; correlate and analyze shale reservoir parameters with low-permeability reservoir seismic data to generate low-permeability reservoir seismic correlation data; The low-permeability reservoir geological sweet spot prediction model module is used to calculate the geological indicators of low-permeability reservoir geological data based on the low-permeability reservoir seismic correlation data to generate low-permeability reservoir geological indicators; use the low-permeability reservoir geological correlation indicators to construct a low-permeability reservoir geological sweet spot prediction model to obtain a low-permeability reservoir geological sweet spot prediction model; perform pre-stack inversion on the low-permeability reservoir geological sweet spot prediction model to obtain the model pre-stack inversion data; dynamically optimize the low-permeability reservoir geological sweet spot prediction model through the model pre-stack inversion data to obtain a low-permeability reservoir geological sweet spot prediction optimization model; perform geological sweet spot prediction on the low-permeability reservoir geological data based on the low-permeability reservoir geological sweet spot prediction optimization model to generate low-permeability reservoir geological sweet spot prediction data; perform data visualization on the low-permeability reservoir geological sweet spot prediction data to generate a low-permeability reservoir geological sweet spot prediction report.

[0049] The present invention acquires low permeability reservoir geological data and performs preprocessing through a low permeability reservoir geological data acquisition module, thereby ensuring data standardization and providing high-quality data support for subsequent analysis; multidimensional feature recognition enables the extraction of rich geological information from standard geological data; the extraction of key low permeability reservoir information further focuses on factors that have an important impact on reservoir characteristics, thereby improving the pertinence and accuracy of the analysis. Through a low permeability reservoir structural morphology recognition module, low permeability reservoir core extraction is performed on key low permeability reservoir information, which can clarify the low permeability reservoir core information; core microstructure feature extraction is performed on multidimensional geological feature data based on low permeability reservoir core data, which clarifies the understanding of the internal structure of the reservoir and can reveal the microscopic characteristics of the reservoir; low permeability reservoir structural morphology recognition is performed on key low permeability reservoir information based on core microstructure features, which clarifies the spatial distribution characteristics of the reservoir and provides a data basis for the subsequent determination of reservoir range distribution. Through the low-permeability reservoir seismic correlation analysis module, the low-permeability reservoir range distribution of key low-permeability reservoir information is determined based on the low-permeability reservoir morphological data, and the geographical distribution of the reservoir is determined, thereby clarifying the low-permeability reservoir range; the seismic characteristics of key low-permeability reservoir information are identified using the low-permeability reservoir range data, which can identify the seismic characteristics of the reservoir geological structure and further clarify the low-permeability reservoir seismic situation; shale reservoir characteristics are extracted from the low-permeability reservoir range data to obtain shale reservoir characteristic data; shale reservoir parameters are correlated with low-permeability reservoir seismic data for analysis, which can comprehensively understand the correlation between geographical low-permeability reservoir earthquakes. Through the low permeability reservoir geological sweet spot prediction model module, the geological index of the low permeability reservoir geological data is calculated according to the low permeability reservoir seismic correlation data, and a quantitative reservoir index evaluation standard is provided; the low permeability reservoir geological correlation index is used to construct the low permeability reservoir geological sweet spot prediction model, and the low permeability reservoir geological sweet spot prediction model is obtained; the low permeability reservoir geological sweet spot prediction model is prestack inversion to obtain the model prestack inversion data; the low permeability reservoir geological sweet spot prediction model is dynamically optimized by the model prestack inversion data, and the accuracy and applicability of the prediction model are improved, thereby improving the accuracy of the geological sweet spot prediction; based on the low permeability reservoir geological sweet spot prediction optimization model, the low permeability reservoir geological data is predicted to be geological sweet spot, and the low permeability reservoir geological sweet spot prediction data is generated; the low permeability reservoir geological sweet spot prediction data is visualized, and the prediction report can be intuitively displayed. Therefore, the present invention realizes multi-dimensional analysis of the geological characteristics of the low permeability reservoir through data processing technology, pattern recognition technology and machine learning technology, and combines the seismic characteristics of the low permeability reservoir for correlation analysis, thereby improving the accuracy of the low permeability reservoir geological sweet spot prediction.

[0050] A computer-readable storage medium stores a computer program, wherein the computer program is used to execute the method for predicting geological sweet spots in low-permeability reservoirs.

[0051] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0052] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for predicting geological sweet spots in low-permeability reservoirs, characterized in that: The following steps are involved: Step S1: obtaining low permeability reservoir geological data; preprocessing the low permeability reservoir geological data to obtain standard low permeability reservoir geological data; Perform multi-dimensional feature recognition on standard low-permeability reservoir geological data to obtain multi-dimensional geological feature data; Extract key low-permeability reservoir information from multi-dimensional geological feature data to obtain key low-permeability reservoir information; Step S2: extracting low permeability reservoir cores from key low permeability reservoir information to generate low permeability reservoir core data; extracting core microstructure characteristics from multidimensional geological feature data based on the low permeability reservoir core data to obtain core microstructure characteristics; identifying low permeability reservoir structure morphology from key low permeability reservoir information based on the core microstructure characteristics to generate low permeability reservoir morphology data; Step S3: determining the low permeability reservoir range distribution of key low permeability reservoir information based on the low permeability reservoir morphology data to obtain low permeability reservoir range data; using the low permeability reservoir range data to identify seismic characteristics of key low permeability reservoir information to generate low permeability reservoir seismic data; extracting shale reservoir characteristics from the low permeability reservoir range data to obtain shale reservoir characteristic data; correlating and analyzing the shale reservoir characteristic data with the low permeability reservoir seismic data to generate low permeability reservoir seismic correlation data; Step S4: Calculate geological indicators of low permeability reservoir geological data according to low permeability reservoir seismic correlation data to generate low permeability reservoir geological indicators; construct a low permeability reservoir geological sweet spot prediction model using low permeability reservoir geological correlation indicators to obtain a low permeability reservoir geological sweet spot prediction model; perform prestack inversion on the low permeability reservoir geological sweet spot prediction model to obtain model prestack inversion data; dynamically optimize the low permeability reservoir geological sweet spot prediction model through the model prestack inversion data to obtain a low permeability reservoir geological sweet spot prediction optimization model; perform geological sweet spot prediction on low permeability reservoir geological data based on the low permeability reservoir geological sweet spot prediction optimization model to generate low permeability reservoir geological sweet spot prediction data; perform data visualization on the low permeability reservoir geological sweet spot prediction data to generate a low permeability reservoir geological sweet spot prediction report.

2. The method for predicting low-permeability reservoir geological sweet spots according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing low permeability reservoir core feature identification on key low permeability reservoir information to obtain low permeability reservoir core features; performing low permeability reservoir core data extraction on key low permeability reservoir information according to the low permeability reservoir core features to generate low permeability reservoir core data; Step S22: performing core feature enhancement on the low permeability reservoir core data to obtain core feature enhancement data; performing feature hierarchization on the core feature enhancement data to generate core feature hierarchical data; performing hierarchical structure element extraction on the core feature hierarchical data to obtain core hierarchical structure element information; Step S23: marking the core hierarchical structure of the multidimensional geological feature data through the core hierarchical structure element information to obtain core hierarchical structure marking data; identifying the core microstructure characteristics of the multidimensional geological feature data based on the core hierarchical structure marking data to obtain core microstructure characteristics; Step S24: performing feature imaging processing on key low-permeability reservoir information according to core microstructural characteristics to obtain a low-permeability reservoir structural image; performing structural image recognition on the low-permeability reservoir structural image to obtain low-permeability reservoir structural data; performing low-permeability reservoir morphology extraction on the low-permeability reservoir structural data to obtain low-permeability reservoir morphology data.

3. The method for predicting low-permeability reservoir geological sweet spots according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: extracting geometric features from the low permeability reservoir morphological data to obtain geometric features of the low permeability reservoir; determining feature spatial relationships of the geometric features of the low permeability reservoir to generate spatial relationship data of the low permeability reservoir; dividing the spatial relationship data of the low permeability reservoir into relationship types to obtain spatial relationship type data; Step S32: performing spatial distribution identification on the low permeability reservoir morphology data according to the spatial relationship type data to generate low permeability reservoir spatial distribution information; performing low permeability reservoir boundary determination on the low permeability reservoir spatial distribution information to obtain low permeability reservoir boundary data; performing low permeability reservoir range distribution determination on the key low permeability reservoir information based on the low permeability reservoir spatial distribution information and the low permeability reservoir boundary data to obtain low permeability reservoir range data; Step S33: performing low permeability reservoir continuity measurement on the low permeability reservoir range data to generate continuity measurement data; using the continuity measurement data to determine the interlayer continuity of key low permeability reservoir information to obtain interlayer continuity data; recording the number of interlayer collision and compression times of key low permeability reservoir information according to the interlayer continuity data to obtain interlayer collision and compression data; performing seismic feature recognition on the interlayer collision and compression data to generate low permeability reservoir seismic data; Step S34: performing shape structure recognition on the low permeability reservoir range data to obtain shale reservoir shape data; performing shale reservoir parameter extraction on the shale reservoir shape data to generate shale reservoir parameter information; integrating the shale reservoir shape data and the shale reservoir parameter information to obtain shale reservoir characteristic data; Step S35: performing correlation analysis on the shale reservoir characteristic data and the low permeability reservoir seismic data to generate low permeability reservoir seismic correlation data.

4. The method for predicting low-permeability reservoir geological sweet spots according to claim 3, characterized in that: Step S35 includes the following steps: Step S351: performing porosity feature identification on the shale reservoir characteristic data to obtain porosity characteristic data; performing porosity distribution determination on the porosity characteristic data to generate porosity distribution data; performing porosity diameter measurement on the porosity characteristic data in combination with the porosity distribution data to obtain porosity diameter data; Step S352: extracting the mineral composition of the shale reservoir characteristic data to obtain the mineral composition data of the shale reservoir; identifying the rock fractures of the shale reservoir mineral composition data according to the porosity and pore size data to generate the shale reservoir fracture information; Step S353: simulate the interlayer seismic response of the shale reservoir fracture information and the low permeability reservoir seismic data to obtain the interlayer seismic response data; perform interlayer fragility determination on the interlayer seismic response data to generate interlayer fragility data; perform fracturing area surface texture identification on the shale reservoir fracture information according to the interlayer fragility data to obtain regional surface texture information; compare the regional surface texture information with the preset regional surface texture information, if the regional surface texture information is less than the preset regional surface texture information, mark the regional surface texture information as high seismic resistance layer regional information; if the regional surface texture information is greater than or equal to the preset regional surface texture information, mark the regional surface texture information as low seismic resistance layer regional information; integrate the high seismic resistance layer regional information and the low seismic resistance layer regional information to obtain the seismic resistance parameters of the low permeability reservoir; Step S354: Calculate the seismic intensity of the low permeability reservoir seismic data in combination with the inter-seismic response data to generate low permeability reservoir seismic severity data; correlate the low permeability reservoir seismic severity data with the low permeability reservoir seismic resistance parameters to generate low permeability reservoir seismic correlation data.

5. The method for predicting low-permeability reservoir geological sweet spots according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Calculate geological indicators of low permeability reservoir geological data according to low permeability reservoir seismic correlation data to generate low permeability reservoir geological indicators; Step S42: constructing a low permeability reservoir geological sweet spot prediction model according to the low permeability reservoir geological correlation indicators to obtain a low permeability reservoir geological sweet spot prediction pre-model, and training the low permeability reservoir geological sweet spot prediction pre-model using the low permeability reservoir geological correlation indicators to obtain a low permeability reservoir geological sweet spot prediction training model; Step S43: performing model cross-validation evaluation on the low-permeability reservoir geological sweet spot prediction training model to obtain model evaluation data; adjusting model parameters of the low-permeability reservoir geological sweet spot prediction training model using the model evaluation data to obtain a low-permeability reservoir geological sweet spot prediction model; Step S44: performing prestack inversion on the low permeability reservoir geological sweet spot prediction model to obtain model prestack inversion data; dynamically optimizing the low permeability reservoir geological sweet spot prediction model through the model prestack inversion data to obtain a low permeability reservoir geological sweet spot prediction optimization model; Step S45: Predict the geological sweet spots of the low permeability reservoir geological data based on the low permeability reservoir geological sweet spot prediction optimization model to generate low permeability reservoir geological sweet spot prediction data; visualize the low permeability reservoir geological sweet spot prediction data to generate a low permeability reservoir geological sweet spot prediction report.

6. The method for predicting low-permeability reservoir geological sweet spots according to claim 5, characterized in that: Step S41 includes the following steps: Step S411: measuring the seismic amplitude of the low permeability reservoir seismic correlation data to obtain interlayer seismic amplitude data; identifying the interlayer deformation degree of the low permeability reservoir morphology data according to the interlayer seismic amplitude data to generate low permeability reservoir deformation data; Step S412: Calculate the pore density of the low permeability reservoir geological data based on the low permeability reservoir deformation data to obtain the pore density of the low permeability reservoir; perform porosity identification on the pore density of the low permeability reservoir to obtain the pore parameters of the low permeability reservoir; perform low permeability reservoir inter-layer permeability measurement on the low permeability reservoir geological data based on the low permeability reservoir pore parameters to generate the low permeability reservoir inter-layer permeability; Step S413: mapping the seismic coefficient permeability of the low permeability reservoir inter-layer permeability in combination with the seismic parameters of the low permeability reservoir to obtain seismic layer permeability data; calculating the rock formation elastic modulus of the low permeability reservoir geological data according to the seismic layer permeability data to generate rock formation elastic modulus data; Step S414: extracting oil and gas characteristics from key low-permeability reservoir information to obtain low-permeability reservoir oil and gas data; calculating oil and gas saturation of the low-permeability reservoir oil and gas data based on the rock formation elastic modulus data to generate low-permeability reservoir oil and gas saturation data; Step S415: Integrate the low permeability reservoir deformation data, the low permeability reservoir interlayer permeability and the low permeability reservoir oil and gas saturation data to obtain the low permeability reservoir geological indicators.

7. The method for predicting low-permeability reservoir geological sweet spots according to claim 5, characterized in that: Step S44 includes the following steps: Step S441: performing seismic prestack inversion processing on the low-permeability reservoir geological sweet spot prediction model to obtain model prestack inversion data; Step S442: extracting low-permeability reservoir deformation parameters from the model pre-stack inversion data to generate low-permeability reservoir deformation inversion parameters; performing permeability detection on the seismic pre-stack inversion data according to the low-permeability reservoir deformation parameters to obtain low-permeability reservoir permeability detection data; evaluating oil and gas saturation on the seismic pre-stack inversion data using the low-permeability reservoir permeability detection data to generate oil and gas saturation evaluation data; Step S443: identifying the oil and gas geological sweet spot area on the oil and gas saturation assessment data to obtain geological sweet spot area data; Based on the low-permeability reservoir deformation inversion parameters, low-permeability reservoir permeability detection data and oil and gas saturation assessment data, the low-permeability reservoir geological sweet spot is determined for the geological sweet spot area data to generate low-permeability reservoir geological sweet spot determination data; Step S444: According to the low permeability reservoir geological sweet spot determination data, the low permeability reservoir geological indicator weights are adjusted for the low permeability reservoir geological sweet spot prediction model to obtain geological indicator weight adjustment data; the low permeability reservoir geological sweet spot prediction model is dynamically weight optimized using the geological indicator weight adjustment data to obtain a low permeability reservoir geological sweet spot prediction optimization model.

8. The method for predicting low-permeability reservoir geological sweet spots according to claim 5, characterized in that: Step S45 includes the following steps: Step S451: Predicting the porosity attribute of the geological sweet spot of the low permeability reservoir geological data based on the low permeability reservoir geological sweet spot prediction optimization model to obtain porosity attribute prediction data; spatially locating the sweet spot area of ​​the low permeability reservoir geological data according to the porosity attribute prediction data to generate sweet spot area spatial prediction data; Step S452: performing regional low-permeability reservoir permeability prediction on the sweet spot area spatial prediction data to obtain regional permeability prediction data; performing oil and gas flow prediction on the low-permeability reservoir geological data using the regional permeability prediction data to generate oil and gas flow prediction data; Step S453: based on the porosity attribute prediction data, the regional permeability prediction data and the oil and gas flow prediction data, the low permeability reservoir geological data is classified into sweet spot grades to obtain geological sweet spot grade data; the geological sweet spot prediction optimization model of the low permeability reservoir is used to predict the geological sweet spot of the geological sweet spot grade data to generate the low permeability reservoir geological sweet spot prediction data; Step S454: Process the low permeability reservoir geological sweet spot prediction data into information graphics to obtain a low permeability reservoir geological sweet spot prediction chart; prepare a visualization report for the low permeability reservoir geological sweet spot prediction chart to obtain a low permeability reservoir geological sweet spot prediction report.

9. A low permeability reservoir geological sweet spot prediction system, characterized in that: Used to execute the low permeability reservoir geological sweet spot prediction method as claimed in claim 1, the low permeability reservoir geological sweet spot prediction system comprises: The low-permeability reservoir geological data acquisition module is used to obtain low-permeability reservoir geological data; pre-process the low-permeability reservoir geological data to obtain standard low-permeability reservoir geological data; perform multi-dimensional feature recognition on the standard low-permeability reservoir geological data to obtain multi-dimensional geological feature data; extract key low-permeability reservoir information from the multi-dimensional geological feature data to obtain key low-permeability reservoir information; The low-permeability reservoir structure morphology recognition module is used to extract low-permeability reservoir cores from key low-permeability reservoir information to generate low-permeability reservoir core data; extract core microstructure characteristics from multi-dimensional geological feature data based on low-permeability reservoir core data to obtain core microstructure characteristics; perform low-permeability reservoir structure morphology recognition on key low-permeability reservoir information based on core microstructure characteristics to generate low-permeability reservoir morphology data; The low-permeability reservoir seismic correlation analysis module is used to determine the low-permeability reservoir range distribution of key low-permeability reservoir information based on low-permeability reservoir morphological data to obtain low-permeability reservoir range data; use the low-permeability reservoir range data to identify the seismic characteristics of key low-permeability reservoir information to generate low-permeability reservoir seismic data; extract shale reservoir characteristics from the low-permeability reservoir range data to obtain shale reservoir characteristic data; correlate and analyze shale reservoir parameters with low-permeability reservoir seismic data to generate low-permeability reservoir seismic correlation data; The low-permeability reservoir geological sweet spot prediction model module is used to calculate the geological indicators of low-permeability reservoir geological data based on the low-permeability reservoir seismic correlation data to generate low-permeability reservoir geological indicators; use the low-permeability reservoir geological correlation indicators to construct a low-permeability reservoir geological sweet spot prediction model to obtain a low-permeability reservoir geological sweet spot prediction model; perform pre-stack inversion on the low-permeability reservoir geological sweet spot prediction model to obtain the model pre-stack inversion data; dynamically optimize the low-permeability reservoir geological sweet spot prediction model through the model pre-stack inversion data to obtain a low-permeability reservoir geological sweet spot prediction optimization model; perform geological sweet spot prediction on the low-permeability reservoir geological data based on the low-permeability reservoir geological sweet spot prediction optimization model to generate low-permeability reservoir geological sweet spot prediction data; perform data visualization on the low-permeability reservoir geological sweet spot prediction data to generate a low-permeability reservoir geological sweet spot prediction report.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed, the method for predicting geological sweet spots in low-permeability reservoirs according to any one of claims 1 to 8 is implemented.

Images