468 results about "Seismic attribute" patented technology

The invention provides a method and a device for establishing a three-dimensional sandstone probability body. The method comprises the following steps: integrating a well-seismic database; constructing a three-dimensional construction framework model; converting the time domain seismic data volume into a depth domain seismic data volume; extracting a target seismic attribute according to a preset rule; sampling a target seismic attribute to a three-dimensional construction framework model; performing multi-attribute clustering fusion on the seismic attribute values of the three-dimensional construction framework model by using a preset neural network model, and establishing a sedimentary unit model; calculating a variation function between the sandstone content data for each partition of the sedimentary unit model; and performing interpolation by using a Kriging algorithm, and predicting the sandstone content of an unknown point to obtain a three-dimensional sandstone probability body model. According to the method, a multi-type and multi-attribute fused three-dimensional sandstone probability body is established, the value type of reservoir facies and the value of reservoir parameters are constrained by endowing each grid with a probability value, and reliable trend constraint conditions are provided for geologic modeling of low-well-control and strong-heterogeneous reservoirs.

The invention discloses an offshore oil and gas resource efficient evaluation method based on a well-free / few-well condition, and the method comprises the steps: S10, carrying out the collection of seabed multi-field coupling data, and obtaining an original data flow; s20, performing multi-source data intelligent fusion processing: performing data space-time alignment, performing electromagnetic seismic joint inversion by using a joint objective function, performing leakage path analysis, and extracting reservoir physical property parameters and a leakage network; s30, dynamic geological knowledge graph construction: constructing a graph neural network and establishing a cross-regional reservoir parameter prediction model through transfer learning to obtain a dynamic geological model and transfer learning parameters; s40, virtual well intelligent generation: guiding virtual well generation to obtain a virtual well data set; and S50, reservoir modeling evaluation: training reservoir modeling together with the virtual well data and the real seismic attributes to obtain resource probability distribution and sweet spot division. According to the method, the dependence on dense drilling is reduced, the defect of multiplicity of solutions of geophysical data is overcome, and the technical bottleneck of modeling under the condition of less wells / no wells is broken through.

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

The invention discloses a geological modeling method for fusing remote sensing and seismic data based on a multi-mode auto-encoder, and the method comprises the steps: collecting a remote sensing image covering a target area and seismic exploration data, and converting the attribute of the seismic exploration data into a resolution consistent with the remote sensing image; respectively extracting remote sensing image features and seismic attribute features by using a parallel double-branch coding structure of a multi-mode encoder; a fusion module is arranged in the middle layer of the remote sensing image encoder and the seismic attribute encoder, fusion is carried out in the fusion module, remote sensing images and seismic data are reconstructed by using a decoder based on fusion features, and difference data between reconstructed data and the remote sensing images and the seismic data are calculated based on a combined loss function introducing regular terms. Training a multi-modal encoder by using the difference data to obtain an encoding feature and a difference heat map; and on the basis of the coding features and the difference heat map, key geological structure region identification and visual display are carried out, and key geological structures comprise faults and lithology.

The invention discloses a weak signal compensation method based on seismic attribute analysis, which belongs to the field of seismic data processing, and comprises the following steps: processing post-stack data through a radial prediction filtering technology to obtain data with a high signal-to-noise ratio, gridding two-dimensional seismic data, and interpolating to form a three-dimensional data volume; then carrying out attribute analysis according to the signal-to-noise ratio and the continuity factor of the seismic data, scanning grid data of an inclination angle in a given range on the basis of the three-dimensional grid data, solving the signal-to-noise ratio and the continuity factor of the data, and selecting and extracting required superposition data according to attributes; and finally, correlation analysis is carried out through the CMP gather and extracted target superposition data, and weighted compensation of signals is carried out, so that effective seismic weak reflection signals are compensated, deep imaging quality is improved, and effective compensation of deep weak signals of seismic data is realized.

The invention discloses a method for predicting a favorable area of a thin-layer stacked sand body, and relates to the technical field of exploration and development of oil and gas reservoirs, and the method comprises the steps: generating a synthetic seismic record through well-seismic combination by using interval transit time and a density curve, aligning the synthetic seismic record with an actual seismic record, and building a three-dimensional frame model of a target layer of a research area; performing abnormal value elimination and standardization processing on the logging curve, making a statistical histogram, comparing peak separation degrees of sandstone and mudstone, and selecting the most sensitive curve to distinguish the sandstone and mudstone; and realizing well-side seismic trace waveform dynamic clustering analysis through singular value decomposition, and determining the number of effective samples. Based on the result of waveform indication simulation, the method is combined with the optimized seismic attribute to predict the thin-layer stacked sand body together, a systematic method is provided, the multiplicity of solutions of predicting the thin-layer stacked favorable sand body through the seismic attribute and the uncertainty of depicting the sand body by the sedimentary facies in the area with few wells can be reduced, and the prediction accuracy of the thin-layer stacked favorable sand body is improved. Therefore, the precision and reliability of thin-layer stacked sand body prediction are improved.

The present invention discloses a method for predicting mud loss before drilling in complex well conditions based on BP neural network, the method comprising: S1, collecting historical seismic attribute data of the target area, engineering and geological data materials corresponding to the loss cases; S2, standardizing the collected data, and converting all data for the convenience of implementing the method; S3, taking the pre-processed historical seismic data as input, the loss situation as output, and the real loss state as the standard value, supervising training and optimizing to obtain a loss prediction neural network model; S4, inputting the real-time seismic data of the target area, and the model automatically judges the loss situation corresponding to each depth in this area. The present invention solves the problem that it is difficult to accurately predict the well conditions before drilling in existing complex well conditions and mud loss is easy to occur.

The invention provides a geophysical recognition method for medium-deep under-compacted low-speed mudstone, which comprises the following steps of: obtaining representative longitudinal wave velocity, transverse wave velocity and density of low-speed mudstone and gas-bearing sandstone in logging information through statistical analysis of data, and designing a theoretical model of a superposition relationship between the low-speed mudstone and the gas-bearing sandstone in combination with geological information, so as to obtain the geophysical recognition result of the low-speed mudstone and the gas-bearing sandstone. Performing convolution forward modeling and pre-stack forward modeling on the model, respectively calculating to obtain post-stack seismic attributes and pre-stack seismic attributes of the model, performing sensitive attribute optimization on the attributes, taking the obtained sensitive attributes as learning samples, and identifying the superposition relationship by using probability self-organizing neural network clustering. According to the method, the pre-stack attributes are added into sensitive attribute optimization, so that the fuzzy self-organizing neural network can more accurately recognize the gas-bearing sandstone and low-speed mudstone stacking relation, the low-speed mudstone and the gas-bearing sandstone can be effectively distinguished, and support is provided for subsequent effective reservoir prediction.

The invention relates to a well-seismic combined reservoir fracture prediction method based on an artificial neural network, and the method comprises the steps: determining a plurality of fracture parameters representing the fracture development degree based on the obtained logging information of a research region; determining a comprehensive crack prediction index based on the plurality of crack parameters; seismic attributes are extracted by using the acquired seismic data, and target seismic attributes sensitive to the change of the comprehensive fracture prediction index are optimized; based on the seismic attribute data set corresponding to the target seismic attribute, training a pre-established artificial neural network to obtain a comprehensive fracture prediction model; and reservoir fracture prediction is carried out based on the comprehensive fracture prediction model, and a fracture prediction result is obtained. According to the method, fracture information reflected by the seismic data and the logging data is fused through machine learning, so that more comprehensive underground fracture development information is obtained. According to the method, the precision of the logging data and the breadth of the seismic data are integrated, fracture prediction is carried out on the spatial scale, and reservoir fractures can be effectively identified and predicted.

The invention relates to the technical field of geophysical exploration data processing, and discloses a multi-element prospecting data cleaning and feature extraction system based on machine learning, and the system comprises a structure field generation unit which is used for constructing a multi-scale structure tensor field according to three-dimensional seismic data and extracting a structure vector representing a geological structure; the self-adaptive cleaning unit is used for carrying out abnormal value judgment and interpolation on non-seismic data by using the structural vector as prior guide information; the coupling feature generation unit is used for generating single-scale and cross-scale coupling features capable of deeply quantizing the relationship between the attribute change and the structure by calculating the projection of the non-seismic data gradient on different-scale structure vectors; and the feature output unit is used for combining the cleaned data, coupling the features and the original seismic attributes and constructing a high-dimensional final feature vector. According to the method, input with more geological significance is provided for machine learning, so that the precision and reliability of prospecting prediction are remarkably improved.

The invention discloses a remaining oil distribution prediction method and system, a control device and a storage medium, and the method comprises the steps: obtaining a multi-scale fusion feature vector according to wide-area apparent resistivity data, seismic attribute data, optical fiber time sequence signal data, nano tracer tracking data and pore network point cloud data, inputting a physical constraint neural network to obtain a residual oil saturation initial value and a pressure gradient initial value of each region of the target layer, wherein a loss function comprises data fitting item loss, Darcy law physical constraint loss and mass conservation constraint loss; the real-time water content and the bottomhole flowing pressure of the production well serve as observation data, and a static parameter correction value, a remaining oil saturation correction value and a pressure gradient correction value are obtained through correction based on an ensemble Kalman filtering algorithm; the static parameter correction value and the pressure gradient correction value are fed back to a physical constraint neural network for loss function updating; and determining a remaining oil distribution result of the target layer. According to the invention, the accuracy and timeliness of residual oil distribution prediction can be improved.

The invention relates to the technical field of oil-gas exploration, and discloses a strike-slip fracture identification method and device based on a multi-seismic attribute fusion technology, and the method comprises the steps: firstly obtaining the seismic data and geological background data of a target region, and then carrying out the recognition of a strike-slip fracture based on the geological background and seismic data; seismic section interpretation is carried out, coherence, curvature, tensor thickness, symmetry illuminance attributes and maximum likelihood attributes are calculated, and finally, according to the fracture scale, optimal attributes are determined and quantitative fusion is carried out to identify the strike-slip fault zone. According to the method, for fractures of different scales, different attributes are preferably selected for quantitative fusion, the advantage complementation effect between different features is achieved, the fracture recognition precision and sensitivity are improved, and researchers are effectively assisted in research work in the aspects of fracture and well location.

The invention provides a fracture-vug reservoir inter-well three-dimensional communication path multi-target search method and system, and the method comprises the steps: building a three-dimensional space model of a fracture-vug reservoir based on seismic multi-attribute data, mapping a carbonate reservoir to a three-dimensional space, and carrying out the grid division; according to the coherent amplitude data and the well distribution condition of each well pair in the search space, adaptively optimizing a coherent amplitude threshold and a seismic attribute fusion weight by adopting a multi-objective optimization algorithm by taking the communication length and the volume as optimization objectives, and searching to obtain grouped inter-well communication paths meeting set requirements corresponding to the current well pair; according to the method, an evaluation function improved heuristic search algorithm is designed to search a single path in a search space, and a self-adaptive crossover and mutation probability improved multi-objective algorithm is proposed to optimize threshold parameters to obtain a plurality of inter-well communication paths conforming to a real seismic structure, so that the problems of limited path analysis and poor reliability in the prior art can be solved; and efficient and comprehensive search of inter-well communication paths is realized.

The invention discloses an underground crack prediction method and device based on multi-scale information fusion. The method comprises the following steps: acquiring a construction pattern of a research area; obtaining a fracture analysis result of the research area, and obtaining fracture development characteristics and a fracture density curve of each single well; performing model forward modeling based on the seismic data of the research area to determine a fracture grading standard; based on the post-stack seismic data of the research area, obtaining large-scale and medium-scale fractures according to seismic attributes; according to the post-stack seismic data, obtaining a small-scale crack based on a preset crack prediction model; based on the pre-stack seismic data of the research area and the fracture density curve of each single well, obtaining a micro-scale fracture according to a pre-stack azimuth anisotropic fracture prediction technology; and taking the large and medium-scale fractures, the small-scale fractures and the micro-scale fractures as input variables, and fusing the input variables by adopting a fuzzy neural network to obtain a fracture prediction data volume. A complex network and a multi-information fusion method are combined with a big data technology to carry out high-precision crack identification so as to realize multi-scale characterization of shale cracks.

The invention discloses a seismic fault identification method based on Bayesian optimization and an interpretable tree model, and belongs to the technical field of seismic exploration, and the method comprises the following steps: S1, synthesizing seismic data through a convolution model; s2, extracting seismic attributes related to a fault by using the synthesized seismic data obtained in S1; s3, performing feature selection on the seismic attributes by using the maximum information coefficient to obtain a feature subset; s4, constructing an integrated tree learning model of Bayesian optimization, and automatically searching an optimal hyper-parameter combination through a Bayesian optimization algorithm; s5, explaining the optimal integrated tree model; and S6, preprocessing the actual seismic data set, inputting the actual seismic data set into the final model, and obtaining a fault identification result. According to the seismic fault identification method based on Bayesian optimization and the interpretable tree model, the fault identification precision and reliability are improved, the fault identification accuracy is improved, and the specific influence of different types of seismic attributes on the prediction result is explained.

The invention discloses a method for predicting a river channel in a high sand-to-ground ratio stratum in a down-down period, and belongs to the technical field of oil-gas exploration. In a method for predicting a river channel sand body in a deep stratum in the down-down period, a lithologic model is established by utilizing an earthquake forward modeling technology to identify a river channel sand earthquake response characteristic; the method comprises the following steps: determining a river channel sand body distribution range and a sand body thickness distribution trend by using seismic attributes and a stratigraphic slicing technology, then determining a river channel sand body space distribution form by using a waveform indication inversion technology, and finally carrying out hydrocarbon detection on the basis of a fluid replacement forward modeling technology. And completing depiction of a favorable area with sand body distribution by combining attribute fusion clustering analysis with a seismic facies method. According to the method, seismic sedimentology and geomorphology are used as theoretical guidance, seismic forward modeling, attribute analysis and inversion technologies are used as technical supports, qualitative description of river channel sand body distribution is converted into specific quantitative analysis, the multiplicity of solutions of conventional river channel sand reservoir prediction is theoretically reduced, the error between the predicted thickness and the actual thickness is reduced, and the prediction accuracy of the river channel sand reservoir is improved. The problem of low prediction precision of the deep riverway type reservoir is solved.

The invention discloses a lithofacies analysis system and method based on a shale geology-mechanics coupling lithofacies classification system, and relates to the field of shale lithofacies analysis. The system construction module determines a geology-mechanics coupling lithofacies classification system according to the information data of the data acquisition module; the prediction module determines single well lithofacies prediction information; the feedback adjustment module performs feedback adjustment on the single well lithofacies prediction information according to a set rock mechanics and ground stress parameter range to obtain adjustment information; the three-dimensional model construction module adopts a genetic algorithm to perform seismic attribute embedding and integrated inversion according to the seismic attribute data and the adjustment information, and adopts a collaborative Kriging method to construct a three-dimensional model of geological-mechanical coupling lithofacies well-seismic collaborative modeling; and the parameter model determination module adopts a layer control-phase control double-control method to control constraints, determines the heterogeneity of shale bed geological-mechanical characteristics in three-dimensional space distribution, and is used for providing a basis for a building and producing area so as to explore and develop artificial oil and gas reservoirs.

The invention discloses a phase-control intelligent seismic reservoir prediction method and device, electronic equipment and a medium. The method comprises the steps of obtaining target data; performing single-well rock structure component phase identification based on the target data, and determining a single-well rock phase; interpreting a sequence structure of the target layer section based on the target data, and establishing a sequence model; establishing seismic lithofacies plane distribution according to the sequence model and the single well lithofacies; establishing an artificial intelligence deep learning neural network prediction model based on seismic data, logging data and sedimentary facies data in seismic lithofacies plane distribution under the constraint of a sequence structure; and seismic reservoir inversion prediction is carried out according to the artificial intelligence deep learning neural network prediction model. According to the technical scheme, through artificial intelligence deep learning neural network model learning training, a complex nonlinear mapping relation between seismic attributes and logging correspondence is directly established, the method has the advantages of natural robustness, parallelism and adaptivity in the aspect of realizing any complex mapping, and the reservoir prediction efficiency is high.

The proposed technique introduces embodiments of a computer-implemented method for interpreting image delineations as vector objects and topological extraction from segmentation by visual computational methods applied to sections (slices) of seismic volumes, in order to aid geological interpretation and sampling of parameters originating from the fracture network and its topology. Embodiments of a developed method integrates a software / application that allows the loading and generation of statistical data related to the fracture network while maintaining georeferencing and scale of the two-dimensional input data. In addition, a fracture segmentation method is shown that uses pyramid image smoothing (decomposition into hierarchical levels of resolution) in order to reduce the amount of details and aid the identification of main faults or fractures. The segmentation after this smoothing is based on adaptive thresholding segmentation.

The invention relates to the field of oil and gas field exploration and development, in particular to a fracture-cavity type reservoir mechanical parameter seismic inversion method based on logging ground stress constraint. On the basis of array acoustic logging, the current crustal stress is calculated; inverting different types of seismic attributes based on the pre-stack seismic data; by optimizing the seismic attribute and the threshold value, the geometric shape carving of the fracture-cavity body is realized; based on the fracture-cavity body seismic attribute sensitivity degree, different types of fracture-cavity body seismic recognition standards are established; establishing rock mechanical parameter assignment models of different types of fractured-vuggy bodies through rock mechanical parameter inversion cycle verification; and considering stress constraint to optimize different types of fracture-vug body rock mechanical parameter assignment models, and finally realizing fracture-vug type reservoir three-dimensional rock mechanical parameter inversion. The invention provides a fracture-vug reservoir mechanical parameter seismic inversion method based on logging ground stress constraint. The method has reference value in multiple aspects of fracture-vug reservoir geomechanical modeling, ground stress field numerical simulation, engineering dessert evaluation and the like.

The invention belongs to the field of petroleum and natural gas exploration and development, and particularly discloses a multi-attribute fusion thin reservoir prediction method which comprises the following steps: S1, calibrating a well-to-seismic combined synthetic record, performing seismic structure interpretation on a near-well structure in combination with a through-well seismic section, and comparing the actual drilling depth of a seismic marker bed with the seismic structure interpretation horizon depth to obtain a well-to-seismic combined synthetic record; determining a well trajectory position; s2, seismic attributes reflecting reservoir features are extracted through seismic data; s3, compressing the seismic attribute space extracted in the step S2 by using a principal component analysis technology, and preferably selecting effective seismic attributes; s4, performing further optimization on the effective seismic attributes, and performing reservoir distribution prediction according to the optimized effective seismic attributes; and S5, analyzing whether a prediction result accords with geological expectation or not. The drilling efficiency, the well bore quality and the exploration benefits are improved, and the oil-gas exploration process is accelerated. The method is suitable for reservoir distribution prediction in seismic exploration.

The present invention provides a geophysical identification method for mid-deep undercompacted low-velocity mudstone. By statistically analyzing data, representative P-wave velocity, S-wave velocity, and density of low-velocity mudstone and gas-bearing sandstone in well logging data are obtained. Combining geological information, a theoretical model of the superimposed relationship between low-velocity mudstone and gas-bearing sandstone is designed, and convolution forward modeling and prestack forward modeling are carried out on it. The post-stack and prestack seismic attributes of the model are calculated respectively. Then, sensitive attributes are optimized from these attributes, and the obtained sensitive attributes are used as learning samples, and the superimposed relationship is identified by probability self-organizing neural network clustering. The present invention adds prestack attributes to the optimization of sensitive attributes, making the fuzzy self-organizing neural network more accurate in identifying the superimposed relationship between gas-bearing sandstone and low-velocity mudstone, effectively distinguishing low-velocity mudstone from gas-bearing sandstone, and providing support for subsequent effective reservoir prediction.

The invention discloses an effective hydrocarbon source rock development condition prediction method and a related device, and relates to the geophysical exploration and comprehensive technical field, the method comprises the following steps: capturing spatial feature processing sequence data through a total organic carbon content prediction model, training a strong complex mapping relation between the total organic carbon content and seismic attributes, and determining the effective hydrocarbon source rock development condition; meanwhile, a support vector machine classification model is utilized to analyze a mapping relation between seismic attributes and lithology data of a virtual well in a research area, intelligent prediction of the total organic carbon content and intelligent judgment and identification of lithology are completed respectively, the generalization ability of the model is improved, regional distribution of the total organic carbon content and the lithology can be predicted more effectively, and the prediction accuracy of the total organic carbon content and the lithology is improved. Therefore, high accuracy is kept in a complex geological environment. And finally, determining the thickness and position of the effective hydrocarbon source rock of the target layer section based on the lithology identification result and the total organic carbon content prediction result, thereby realizing accurate evaluation of the development condition of the effective hydrocarbon source rock.

The embodiment of the invention provides a reservoir heterogeneous region identification method and device, a storage medium and a processor, and belongs to the field of data processing. The method comprises the following steps: calculating a statistical metric of each seismic attribute pre-selected in a reservoir seismic horizon; and drawing the reservoir according to the statistical metric of each seismic attribute to identify the heterogeneous region of the reservoir. According to the method, the limitation of the prior art is solved, and meanwhile, the innovation capability is provided for reservoir characterization.

The invention relates to the technical field of energy storage, and provides a compressed air energy storage salt cavern volume estimation method and system based on multi-seismic attribute fusion. The method comprises the following steps: S1, data acquisition: acquiring three-dimensional seismic data, logging data and actually measured salt well volume data; s2, extracting data characteristic parameters; s3, constructing and training a salt cavern volume estimation model: establishing the salt cavern volume estimation model by adopting a Gaussian process regression algorithm, wherein an algorithm kernel function is a linear combination of a plurality of seismic attribute kernel functions; performing data training on the estimation model to obtain optimization parameters; and S4, estimating the volume of the to-be-measured salt cavern: inputting the processed seismic attribute features into the trained salt cavern volume estimation model to obtain an estimated value of the volume of the to-be-measured salt cavern. By establishing the mapping relation between various seismic attributes and the salt cavern volume, a quick estimation method is provided, the calculation speed is high, and the calculation precision is high; not only is a salt cavern volume prediction value given, but also probability distribution can be given, and a decision maker is helped to better consider risk factors.

The invention relates to the technical field of oil and gas geophysical exploration, in particular to a dolomite reservoir fracture-cavity system prediction method and device, equipment and a medium. The method comprises the steps that large-scale fractures of a reservoir in a research area are described by extracting seismic attributes, small-scale fractures of the reservoir in the research area are described by solving attenuation gradient attributes of different azimuth angles, and hole bodies of the reservoir in the research area are described by conducting pre-stack total porosity inversion. Therefore, large-scale and small-scale crack and hole body depicting results are obtained; and the dolomite reservoir fracture-cavity system prediction result in the research area is obtained through fusion. The problems that when a dolomite fracture-cavity system is depicted through logging data or seismic data in the prior art, fracture-cavity development characteristics cannot be described and predicted on the whole, fine depiction of fracture-cavity body seismic response outer contours cannot be achieved, and the accuracy of hole recognition and fracture depiction is relatively low are solved.

The invention discloses an effective crack identification method and device based on a random forest, equipment and a medium. The method comprises the following steps: establishing a crack effectiveness evaluation standard based on logging information, and determining a crack effectiveness index; establishing a fracture prediction data set according to the seismic attributes representing the fractures of different scales and the inversion results, and labeling by using the effective indexes of the fractures; training a random forest effective fracture prediction model, and predicting an unknown fracture effective index; and based on the trained random forest effective fracture prediction model, predicting three-dimensional whole-area effective fractures. According to the method, the improved random forest model is built on the basis of logging fracture effectiveness evaluation and supported by earthquake multi-attribute analysis, effective fracture automatic identification is achieved, and reference is provided for reservoir effective fracture evaluation.

The present invention discloses a method and system for identifying low-velocity mudstone based on attribute clustering. It includes: by analyzing the logging data and seismic data of exploration wells in the work area, dividing the low-velocity mudstone into bright spot type and non-bright spot type, and analyzing their characteristics. Establishing a three-layer medium model and conducting seismic forward modeling to obtain the seismic response characteristics of different models. Then, extracting and optimizing seismic attributes from the forward modeling results. Using the CLARA clustering algorithm and the PAM method to conduct clustering analysis on the attributes to identify the types of low-velocity mudstone and gas-bearing sandstone. The present invention improves the identification accuracy of low-velocity mudstone and gas-bearing sandstone, and provides technical support for exploration and well location deployment.

The invention discloses a physical property parameter inversion method combining domain knowledge and a deep network, and relates to the technical field of reservoir prediction. The method comprises the following steps: performing fine well-seismic calibration by using logging, earthquake, geology and other information in combination with seismic geological conditions of a target area; on the basis of model seismic response and actual reservoir earthquake and well data analysis, multiple seismic attributes are extracted, and attribute combinations which are sensitive to lithological characters and physical properties and are not highly correlated with each other are screened out; fusing multiple networks and a progressive hierarchical extraction strategy to construct a multi-task deep network inversion model, and performing model training by taking a rock physical parameter statistical relationship and low-frequency information as constraints; and performing reservoir physical property inversion by using the trained inversion model, and performing constraint improvement on an inversion result in combination with actual exploration data and prior information. Compared with the prior art, the method can solve the problems of lack of data and poor robustness and interpretability to a certain extent, and improves the physical property inversion precision and reliability.

A computer implemented method provides for detecting a geological object in a geological formation by processing a seismic 3D image, said seismic 3D image comprising a plurality of pixels representing seismic measurements performed on the geological formation. The method includes computing, based on the seismic 3D image, a geological-time (GT) isochronous surface of the geological formation, wherein the GT isochronous surface corresponds to the coordinates of pixels of the seismic 3D image which represent portions of the geological formation considered to have a same geological age, computing a seismic attribute 2D image representing at least one seismic attribute of the geological formation on the GT isochronous surface, and detecting, by image segmentation, pixels of the seismic attribute 2D image which represent the geological object.