136 results about "Seismic attribute" patented technology

The invention provides an oil-gas exploration data rapid integration method and system based on bidirectional cascading, and the method comprises the steps: S1, obtaining an original exploration data flow, and carrying out the normalization processing, and forming a standardized initial data body; s2, transversely distributed seismic reflection interface feature points and longitudinally distributed logging lithology turning points are extracted, and a bidirectional cascade topology framework is constructed; s3, waveform similarity propagation of seismic attributes is executed in the transverse direction, rock physical parameter recursion of logging attributes is executed in the longitudinal direction, and an intermediate integrated data set is generated; s4, acquiring gravity and magnetic exploration data, generating a geologic structure background field, performing space registration and weight superposition, and correcting stratum boundary drift; and S5, reversely backtracking and updating the point-to-point constraint relationship in the bidirectional cascade topology skeleton, and generating high-precision oil-gas exploration integrated data after closed-loop verification. The method has the advantages that the precision of integrated data can be effectively improved, and therefore the actual requirement of high-precision oil-gas exploration is met.

The present invention belongs to the technical field of petroleum and natural gas exploration. Provided are an intelligent seismic high-frequency sequence interpretation method and apparatus using logging information. The method comprises: inputting, into a sequence stratigraphy prediction model in a current state, seismic attribute data of determined point locations, which are determined on the basis of a sequential path, along a well-tie seismic trace of a known conditioning well in a target block, so as to obtain high-frequency sequence stratigraphy data of the determined point locations; and determining whether any high-frequency sequence stratigraphy data of a point location in the target block has not been obtained, and if any high-frequency sequence stratigraphy data of a point location in the target block has not been obtained, adding the high-frequency sequence stratigraphy data of the determined point locations to sequential simulation conditioning data, using updated sequential simulation conditioning data to construct a learning sample to train the sequence stratigraphy prediction model in the current state, and then jumping to the previous step to perform high-frequency sequence stratigraphy prediction on the next determined point location determined on the basis of the sequential path. The method can be applied to onshore early-exploration blocks and offshore sparse-well blocks, etc., so as to realize high-frequency sequence interpretation of these blocks with high efficiency, low costs and high accuracy.

The invention relates to a thin interbed clay mineral content prediction method based on an RBF neural network, and the method mainly improves the longitudinal resolution through the inversion of the RBF neural network on the basis of multiple attributes, and compared with the conventional research, the method directly uses the seismic attributes, such as amplitude, as the input to learn a target curve, and improves the prediction efficiency. According to the method, the seismic frequency division reconstruction data body and the inversion body are selected as input, so that the longitudinal resolution and the well coincidence rate are greatly improved; in addition, the inversion body is used as input, so that the problem that neural network inversion geological laws are poor in previous research is solved, and an important basis can be provided for reservoir assessment and development; examples prove that the method disclosed by the invention is higher in precision of inverting the clay mineral content compared with a simulation method directly using waveform indication, and is suitable for reservoir parameter prediction of a thin interbed.

This invention provides a method for characterizing sedimentary microfacies distribution based on comprehensive geological and seismic analysis. By studying the sedimentary environment and surrounding tectonic background of the entire block, this invention calculates the cumulative percentage of channel and shoal body types based on sedimentary microfacies and grain size analysis. Based on a comprehensive analysis of the lithofacies of drill cores and corresponding well logging curves and seismic response characteristics, it establishes a comprehensive response model of the main sedimentary facies-well logging facies of the target stratigraphic group in the study area. Furthermore, based on the fusion of seismic attributes, it characterizes sand bodies in seismic profiles. By integrating the sand body characterization results, the comprehensive response model of sedimentary facies-well logging facies, and the sedimentary microfacies types, a method for characterizing sedimentary microfacies distribution in tight sandstone reservoirs using comprehensive seismic and geological analysis is established.

This invention relates to the field of geophysical exploration and oil and gas geological analysis technology, and discloses a method for predicting fractured reservoirs in carbonate buried hills based on geological guidance and multi-scale fusion. The method includes: constructing a three-dimensional geological guidance constraint body using paleogeography and fault systems as geological priors; characterizing the fracture response mechanism using Gabor wavelet frequency division and structural tensor; constructing sensitive attributes and predicting the fracture body using a multi-branch convolutional neural network that fuses multi-source seismic attributes; and calculating the fracture complexity index based on the predicted fracture body to classify and zone the buried hill fractures. This invention introduces geological guidance constraints to improve the geological consistency of the prediction results; utilizes multi-scale Gabor frequency division and structural tensor analysis to achieve multi-scale fracture characterization; enhances model interpretability and prediction accuracy by fusing multi-source attributes through a multi-branch convolutional neural network; and achieves quantitative reservoir classification through the fracture complexity index, effectively guiding well location deployment and drilling decisions.

The application discloses a low-angle fault automatic identification method based on seismic data driving, which comprises the following steps: obtaining original seismic data and carrying out fracture enhancement processing; extracting fracture attributes of different fracture scales based on the fracture enhancement processed seismic data, and carrying out grid segmentation on the fracture attributes to form a fracture spatial breakpoint data body; recombining and arranging the fracture spatial breakpoint data body, and setting a fracture seed point of a low-angle fracture surface position; guiding seismic attributes based on the fracture seed point, re-searching a low-angle fracture surface, and forming new low-angle fracture seismic attributes. The low-angle fault automatic identification method based on seismic data driving can greatly improve the prediction accuracy of fractures.

The invention discloses a deep learning fracture prediction method based on interpretability, and the method comprises the following steps: S1, obtaining the seismic attribute and fracture density of a research region, carrying out the normalization processing of the seismic attribute, and carrying out the grid processing and smoothing processing of the fracture density; s2, analyzing the correlation between the seismic attribute and the fracture density, and obtaining a preferred seismic attribute; s3, performing fracture cause seismic attribute analysis on the optimal seismic attributes to obtain seismic attributes after dimension reduction; s4, establishing a deep learning neural network, and training to obtain a trained deep learning neural network; and S5, carrying out fracture prediction on the target stratum, and carrying out interpretability analysis by adopting a local interpretability analysis method to obtain reservoir fracture causes. According to the method, three-dimensional space accurate prediction of the fracture density can be realized, a master control mechanism of fracture development can be disclosed through quantitative evaluation of cause attributes, and the geological credibility of a prediction result is effectively improved.

The invention discloses a paleo-gradient constraint reservoir characterization attribute for deep fan delta sedimentary facies characterization. The paleo-gradient constraint reservoir characterization attribute comprises the following steps: 1) carrying out multiple seismic attributes of a target stratum and carrying out normalization processing; 2) seismic attribute optimization is carried out by using the correlation with the sandstone thickness; 3) fitting a multiple linear regression relationship between the sandstone thickness and the optimized seismic attributes; 4) drawing a whole-area sandstone thickness prediction contour map; 5) solving an ancient slope on the ancient landform map; 6) drawing a whole-region ancient slope contour map; 7) acquiring a relation inflection point between the sandstone thickness and the paleo-slope in the research area; 8) predicting sandstone thickness and paleo-gradient by using seismic attributes to establish paleo-gradient constrained reservoir characterization attributes; and 9) calculating all-region paleo-gradient constraint reservoir representation attributes, and drawing a contour map as a basis for depicting the deep fan delta sedimentary facies. The method solves the problem that seismic attribute representation sedimentary facies lacks environmental information and the problem of multiplicity of solutions of deep fan delta seismic reflection representation sedimentary facies.

The application discloses a sparse well area hydrocarbon source rock TOC prediction method and system, an electronic device and a medium, relates to the technical field of hydrocarbon source rock carbon content prediction, and comprises the following steps: establishing a virtual well in a well-free area; determining the seismic attribute of the virtual well based on a seismic attribute extraction method; determining the lithology of the virtual well based on the seismic attribute of the virtual well and a sandstone and mudstone lithology prediction model, and extracting the mudstone section of the virtual well; determining the longitudinal continuous TOC prediction value of the hydrocarbon source rock in the mudstone section of the virtual well based on a single-well longitudinal continuous TOC prediction model; and combining the longitudinal continuous TOC prediction value and the measured TOC value of the hydrocarbon source rock in the mudstone section of the virtual well to construct a three-dimensional TOC attribute body of the target sparse well area based on a preset geological condition constraint, so as to predict the TOC of the hydrocarbon source rock in the target sparse well area. The application realizes higher-precision quantitative evaluation and prediction of the TOC of the hydrocarbon source rock in the sparse well area.

The application discloses a method and device for identifying gas-bearing reservoirs, and the method comprises the following steps: establishing a reservoir longitudinal identification criterion according to well logging data and seismic data of a study area; extracting a plurality of seismic attributes from each seismic survey line in two-dimensional seismic data of the study area; determining optimal seismic attributes from the plurality of seismic attributes through comparative analysis; and determining a favorable reservoir distribution area according to the reservoir longitudinal identification criterion and the optimal seismic attributes.

The invention discloses a fractured-vuggy reservoir comprehensive prediction method and device based on diffracted wave seismic attributes, electronic equipment and a storage medium. The method comprises the following steps: carrying out diffracted wave separation on a first full-wave-field three-dimensional seismic data volume to obtain a first diffracted wave three-dimensional seismic data volume; performing inclination angle guided filtering on the two three-dimensional seismic data volumes to obtain a second full-wave-field three-dimensional seismic data volume and a second diffracted wave three-dimensional seismic data volume, extracting full-wave-field coherent attributes, and solving a full-wave-field amplitude envelope and a diffracted wave amplitude envelope; carrying out ant tracking on the two amplitude envelopes to obtain a full-wave-field ant body and a diffracted wave ant body; and based on the full-wave-field coherent attributes, the two amplitude envelopes and the two ant bodies, fracture-cavity identification and fracture comprehensive prediction are carried out. According to the method, fracture-cavity identification and fracture crack comprehensive prediction are carried out by using the diffracted wave amplitude envelope body and the diffracted wave ant body, and the prediction precision of the carbonate rock fracture-cavity reservoir is improved.

The invention discloses a seismic data removal processing method, system and device and a medium, and the method comprises the following steps: S1, analyzing and processing seismic data, and generating a minimum offset seismic attribute; s2, determining a'full coverage 'boundary and a'primary coverage' boundary by using the minimum offset seismic attribute, giving a corresponding water bottom removal time, and calculating an unknown water bottom removal time by using an isoline interpolation method; s3, smoothing the calculated water bottom removal time; and S4, applying a removal time table: writing all the water bottom removal time into a seismic trace header in a trace-by-trace matching mode, and carrying out zero filling processing on the amplitude value of the part above the water bottom removal time. The method is high in adaptability to irregular boundary three-dimensional seismic data, and the purposes of shortening the data processing period, reducing the labor intensity of processing personnel and improving the project operation efficiency can be achieved.

The application discloses a multi-azimuth post-stack seismic attribute interpretation method, device, medium and equipment, and the method comprises the following steps: acquiring a target layer seismic interpretation horizon and a plurality of azimuth seismic attribute data bodies; setting a window used for calculating eigenvalues; selecting an eigenvalue; for the selected eigenvalue, in the window, based on the plurality of azimuth seismic attribute data bodies, attribute optimal eigenvalues of each position point in the plurality of azimuth seismic attribute data body spaces are obtained; based on the attribute optimal eigenvalues of each position point, an eigenvalue data body is obtained; and an attribute plan view is extracted in the eigenvalue data body along the target layer seismic interpretation horizon. The application acquires the most representative attribute advantage eigenvalues in different azimuths, and constructs a new data body from the eigenvalues, so that the purpose of highlighting the geological abnormal response characteristics and reducing the dimension interpretation is achieved, and the efficiency and precision of the post-stack multi-azimuth seismic interpretation are effectively improved.

The invention provides an inter-well logging curve prediction method and system. The prediction method comprises the following steps: predicting an inter-well logging curve through a deep learning model according to seismic data and two known logging wells; wherein the seismic attributes of the seismic data are extracted; extracting seismic features according to the seismic attributes and the feature extraction backbone network; the feature extraction backbone network is constructed based on an attention mechanism; performing feature extraction on the seismic features to obtain a plurality of seismic features of different scales of the seismic section; performing longitudinal axis attention calculation and transverse axis attention calculation on the three-layer features and the four-layer features to obtain updated three-layer features and updated four-layer features; the longitudinal axis attention calculation is used for learning precision improvement and curve change from the seismic attribute to the logging longitudinal direction; the transverse axis attention calculation is used for learning the geological gradual change process of the seismic section response in the transverse direction; and predicting an inter-well logging curve according to the updated three-layer features and the updated four-layer features.

This invention discloses an attribute fusion method and system based on unsupervised hybrid multimodal and ternary adaptive transfer autoencoder, belonging to the fields of artificial intelligence and seismic exploration. The method includes: constructing an unsupervised hybrid multimodal adaptive weighted feature fusion autoencoder (UHM-AWFFA) network, where the encoder uses a multi-branch independent encoder to extract deep independent features of multiple seismic attributes and dynamically fuses them through a weighted feature fusion layer; the decoder performs hierarchical reconstruction of the fused features, simultaneously outputting the reconstruction results of each attribute and the fused attribute profile; training is performed using an interactive reconstruction loss function, and fine-tuning is performed using a ternary multimodal adaptive dynamic transfer learning (TE-MADT) strategy, including a gradient-driven adaptive thawing mechanism, a multimodal collaborative transfer strategy, and a cross-modal knowledge distillation mechanism. This invention achieves nonlinear intelligent fusion of seismic attributes, effectively uncovers deep coupling relationships between attributes, and improves the geological interpretation accuracy of the fused profile.

The application provides an inversion method for describing the connectivity of the internal reservoir of a faulted karst body. The method uses seismic attributes reflecting the outline of the faulted karst body, the holes and cracks in the faulted karst body, establishes a comprehensive low-frequency model reflecting the carbonate bedrock, the faulted karst body, and the crack and hole system in the faulted karst body, uses the model to perform post-stack constrained sparse pulse inversion, obtains a longitudinal wave impedance data body of the underground, and uses the longitudinal wave impedance data to give a longitudinal wave impedance threshold value of the reservoir, and describe the connectivity of the internal reservoir of the faulted karst body in space.

The invention discloses a low-frequency model construction method, device and equipment and a storage medium, and the method comprises the steps: determining a straight-plate low-frequency model and a seismic attribute body based on original geological data corresponding to a carbonate reservoir; performing post-stack inversion on the straight plate low-frequency model based on the original geological data, and determining a cave low-frequency model; based on the seismic attribute body, determining a fracture low-frequency model and a reservoir boundary low-frequency model; performing fusion processing on the straight plate low-frequency model, the cave low-frequency model, the crack low-frequency model and the reservoir boundary low-frequency model to obtain an original low-frequency model; and performing post-stack inversion on the original low-frequency model based on the original geological data, and determining a target low-frequency model corresponding to the carbonate reservoir. Through the technical scheme of the embodiment of the invention, automatic construction of the carbonate rock earthquake low-frequency model is realized, the carbonate rock earthquake low-frequency model can adapt to complex topographic changes of a carbonate rock reservoir, complex geologic features of the carbonate rock reservoir can be reflected, and comprehensiveness and accuracy of the low-frequency model are improved.

The invention provides a carbonate rock seismic lithology depicting method and system, a storage medium and equipment. The method comprises the following steps: collecting basic geological data of a research area; lithology identification is carried out on the rock core and the slice of the target layer based on drilling and logging data, the calibration relation between different lithology and a logging curve is obtained, and the content of different lithology in the target layer is calculated; establishing a through-well seismic synthesis record based on the logging curve data, performing target stratum top and bottom stratum tracking in the three-dimensional seismic data volume, and extracting the internal seismic attributes of the target stratum; performing correlation analysis on the contents of the different lithologies and the seismic attributes, obtaining a correlation coefficient between the lithology contents and the seismic attributes, selecting the seismic attributes based on the correlation coefficient, and determining a lithology regression equation; and calculating and acquiring content ratio results of different lithologic components, and integrating the content ratio results to obtain stratum lithofacies distribution characteristics of the target stratum. According to the carbonate rock seismic lithology depicting method, the depicting accuracy is improved.

The invention discloses a gas reservoir three-dimensional geological modeling method and system and a medium. The method comprises the following steps: acquiring multi-source data of a target work area; in combination with vertical seismic section data and virtual well data, depth correction is performed on the horizon after time-depth conversion, and a three-dimensional tectonic framework model is established based on the corrected horizon and fault data; fusing and generating a sand body space development probability trend body based on the seismic attribute body, the seismic inversion body and the determined optimal weight coefficients of the seismic attribute body and the seismic inversion body; a three-dimensional tectonic framework model is used as a space framework, a sand body space development probability trend body is used as a transverse soft constraint, a plurality of isoprobable lithofacies model initial implementation is established, and a three-dimensional lithofacies model is obtained; a three-dimensional distribution model of reservoir physical property parameters is generated; and importing the three-dimensional lithofacies model and the three-dimensional distribution model into a numerical simulator, performing historical fitting by using gas reservoir dynamic production data, analyzing fitting differences, and performing iterative modeling to obtain a high-precision and low-uncertainty three-dimensional gas reservoir geologic model.

The invention belongs to the technical field of oil exploration and development, and discloses a method for identifying volcanic rock weathering crust and interior periods based on multiple seismic attributes, which comprises the following steps: determining a logging chart division boundary; a seismic data volume corresponding to the logging data is read, a cross plot is drawn, and a seismic data volume correction formula is obtained through linear fitting; correcting the seismic data volume of the research area; dividing the corrected data volume through a logging plate division boundary to obtain a first probability volume P1; determining an impedance plate division boundary; performing inversion to obtain an inversion resistance body; dividing the inversion impedance body according to an impedance plate division boundary to obtain a second probability body P2; performing weighted calculation on the P1 and the P2 to obtain a volcanic rock interior period identification parameter body P3; and establishing a recognition plate by using the P3, and determining a division boundary of the recognition plate to obtain a volcanic rock interior period recognition probability body P4. According to the method, well-seismic data unification is realized, and the weathering crust and the inner curtain period can be effectively identified in combination with an impedance inversion data body prediction result.

The invention discloses an attribute analysis method and device based on information entropy, electronic equipment and a medium. The method comprises the following steps: establishing a training data set of a plurality of well-side seismic attributes and a plurality of targets obtained based on an experiment; according to the training data set, first relevancy between the same target and different well-side seismic attributes is calculated, and second relevancy between each well-side seismic attribute and other attributes is calculated; according to the first correlation degree, the second correlation degree and the entropy of the attribute, calculating the sensitivity degree of the well-side seismic genus and the target; wherein the higher the sensitivity degree is, the higher the relevancy between the well-side seismic attribute and the target is, and the lower the relevancy between the well-side seismic attribute and other attributes is. According to the method, on the basis of the information entropy, the attribute relation with the minimum redundancy among the attributes and the maximum correlation between the attributes and the reservoir characteristics is obtained through analysis.

The application relates to the technical field of seismic reservoir prediction, and discloses a multi-attribute fusion seismic reservoir prediction method and system, which comprises the following steps: a target layer system is divided into a plurality of mutually independent sublayer sections in the longitudinal direction; in-seam effective energy and interlayer interference energy are respectively calculated for each seismic attribute; the in-seam effective energy and the interlayer interference energy are compared, and effective seismic attributes are screened out; the fusion weight of the effective seismic attributes is determined based on the correlation between the effective seismic attributes and reservoir parameters; local reservoir prediction results are obtained by using each effective seismic attribute and the fusion weight; and the local reservoir prediction results are longitudinally spliced and processed to generate reservoir prediction results. The application can effectively avoid prediction errors caused by interlayer interference and attribute response differences under a unified processing mode by specifically identifying and using seismic attributes with different geological meanings in different layer sections, fundamentally solves the layer section mismatch problem in the prediction of superimposed thin reservoirs, and significantly improves the prediction accuracy and fineness.

The invention relates to the technical field of oil and gas reservoir exploration and development, in particular to a wrinkle strength calculation method. The wrinkle strength calculation method comprises the following steps: firstly, intercepting a seismic trace coordinate point set based on a target layer wrinkle zone plane range, and obtaining the wrinkle width of a corresponding wrinkle zone on each seismic survey line; secondly, calculating the relative amplitude of a target layer fold zone by utilizing a structural trend surface method; assigning the relative amplitude to a seismic trace coordinate point set according to a coordinate corresponding relation to obtain a wrinkle amplitude of each seismic survey line in a corresponding wrinkle zone; and finally, dividing the wrinkle amplitude by the wrinkle width to obtain the wrinkle strength of the corresponding wrinkle zone on each seismic survey line. According to the method, seismic attributes, horizon interpretation and three-dimensional seismic survey network information are comprehensively utilized, the wrinkle range is quantitatively delineated through curvature attributes, horizon is interpreted, the wrinkle amplitude is calculated, and an objective wrinkle strength evaluation result can be obtained.

This application discloses a lithofacies analysis system and method based on a shale geological-mechanical coupled lithofacies classification system, relating to the field of shale lithofacies analysis. The system construction module determines the geological-mechanical coupled lithofacies classification system based on information data from the data acquisition module; the prediction module determines single-well lithofacies prediction information; the feedback adjustment module adjusts the single-well lithofacies prediction information based on set rock mechanics and geostress parameter ranges to obtain adjusted information; the three-dimensional model construction module uses a genetic algorithm to perform seismic attribute embedding and integrated inversion based on seismic attribute data and adjusted information, and uses a co-kriging method to construct a three-dimensional model of well-seismic co-modeling of geological-mechanical coupled lithofacies; the parameter model determination module uses a layer-control-facies dual-control method to control constraints and determine the heterogeneity of the geological-mechanical characteristics of shale layers in three-dimensional space, providing a basis for establishing production areas for the exploration and development of artificial oil and gas reservoirs.

A method of obtaining a relative amplitude preserving seismic volume acquired in time domain for a subsurface region of interest and transforming it into a low frequency monopolar amplitude volume. The method also determines a seismic attenuation volume from the relative amplitude preserving seismic volume acquired in time domain. Further, the method generates a low frequency monopolar amplitude map of a surface of interest by averaging the low frequency monopolar amplitude volume over a depth window around the surface of interest and generates a seismic attenuation map of the surface of interest by averaging the seismic attenuation volume over the depth window around the surface of interest. The method also determines an attribute map of the surface of interest based on the seismic attenuation map and the low frequency monopolar amplitude map and determines a presence of a gas in the subsurface region of interest based on the attribute map.

The invention discloses a reservoir parameter prediction method and device, electronic equipment and a medium. The method comprises the following steps: determining seismic attribute parameters capable of reflecting reservoir parameter essential characteristics, and predicting a seismic facies through a self-organizing competitive neural network algorithm; adding the seismic facies as transverse constraints into the low-frequency model, and constructing a phase-controlled low-frequency model; and carrying out reservoir parameter inversion through a self-adaptive pre-stack mixed domain inversion method. According to the method, low-frequency information containing seismic facies constraints is added in low-frequency model construction, in addition, in the inversion process, through self-adaption of prior information of different distributions, and meanwhile, mixed domain constraints are added in a likelihood function, the inversion result resolution and transverse continuity are improved, the reservoir description precision is greatly improved, and the method is suitable for large-scale popularization and application. And good support is provided for high-quality reservoir prediction.

The application discloses a kind of seismic facies drive deep carbonate high-precision sedimentary microfacies recovery methods, comprising: basic data collection;Well-seismic calibration;Establish regional isochronous sequence stratigraphic framework;Logging interpretation;Sequence framework within sedimentary facies division: seismic facies division;Establish seismic facies-sedimentary facies conversion relationship;Isochronous sequence stratigraphic framework within division strata slice;Optimization seismic attribute;Establish single factor sedimentary index-seismic attribute relationship;Attribute volume isochronous strata slice;Seismic facies-sedimentary facies under the constraint of high-precision isochronous sedimentary microfacies drawing.The application can accurately predict sequence within sedimentary facies belt boundary by establishing sedimentation-seismic correlation under the condition of less drilling, outcrop;Further optimization can reflect the seismic attribute of sedimentary characteristics, calculate isochronous strata slice;Isochronous sedimentary facies map is obtained by attribute-sedimentary correlation conversion.In practical application, good effect is obtained, and the coincidence rate with actual drilling is high.

The invention discloses a prediction method and system for an extrusion background broken slope fan body and electronic equipment, and belongs to the technical field of oil-gas exploration evaluation.The prediction method for the extrusion background broken slope fan body comprises the steps that the stratigraphic position and fault data of a target area are determined, and an ancient landform plane graph and an ancient landform dip angle map are correspondingly drawn; and the prediction of the broken slope fan body is realized. Through comprehensive analysis of ancient landform features, fracture evolution periods, stratigraphic slices and seismic attributes, the prediction precision of the broken slope sector is improved.

The present application relates to the field of oil and gas exploration and development, and in particular to a method for predicting multi-scale fractures of volcanic reservoirs based on intelligent fusion strategies. The method comprises the following steps: obtaining five-dimensional seismic data collected at multiple azimuths and multiple incidence angles; standardizing the five-dimensional seismic data to obtain a dataset with multi-scale fracture seismic attributes; inputting the dataset with multi-scale fracture seismic attributes into a pre-trained bidirectional recurrent-convolutional neural network model to obtain a dataset representing multi-scale fracture seismic attributes after fusion of multiple azimuths and multiple incidence angles; standardizing the dataset representing multi-scale fracture seismic attributes after fusion of multiple azimuths and multiple incidence angles; and inputting the standardized dataset representing multi-scale fracture seismic attributes after fusion of multiple azimuths and multiple incidence angles into a pre-trained gated recurrent neural network model to obtain a dataset representing fused multi-scale fracture seismic attributes.

The invention relates to the technical field of shale gas geology, in particular to a method for depicting a breaking joint body in a breaking joint body development area, and the method comprises the steps: firstly, generating an initial breaking joint body probability body based on interpretable machine learning fusion seismic attributes, and building a three-dimensional space distribution model containing large and medium faults after manual interactive interpretation and well seismic calibration; on the basis, large and medium-sized faults serve as a deterministic skeleton, a fracture development rule is predicted in combination with paleotectonic stress field simulation and a rock fracture criterion, a three-dimensional discrete fracture network model constrained by geomechanics is constructed and then coupled with a matrix model, and a model set is generated by defining an uncertainty parameter space. And screening out an equivalent model group through historical matching, performing prediction verification and iterative optimization by using recent production data, and finally obtaining a three-dimensional space distribution model of the high-precision breaking joint body. According to the method, closed loop of static identification and dynamic verification is realized, and the depicting precision and the geological reliability are remarkably improved.