39 results about "Reservoir modeling" patented technology

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.

Provided herein are systems and methods for generating reservoir models including the SOC nature of the Earth's crust. The methods employ seismic emission tomography (SET) to generate three dimensional models of a formation providing permeability without the need for traditional reservoir modeling techniques and allowing for the identification of naturally-occurring permeability pathways that provide accurate and precise locations for the efficient recovery of hydrocarbons or other fluids.

The invention belongs to the technical field of oil-gas exploration and development, and particularly relates to a method and a device for calculating physical properties of gypsum sandstone and a storage medium, the method comprises the following steps: S1, acquiring logging data of a target well section, establishing a first model of the target well section, and calculating to obtain porosity # imgabs0 #; if so, executing the step S3; if not, the permeability of the target well section is calculated, and the porosity # imgabs1 # and the permeability are determined as the porosity and the permeability of the target well section; s3, block gypsum in the first model is removed, a second model of the target well section is established, and the porosity and the permeability are calculated; and S4, the permeability K of the target well section is calculated, and the porosity # imgabs2 # and the permeability K serve as the porosity and the permeability of the target well section. According to the method, physical property calculation of the lump sandstone is realized, the accuracy of physical property calculation of the lump pasty sandstone is improved, and an important technical support is provided for later well completion and oil reservoir modeling.

The invention discloses a continental facies shale condensate gas reservoir horizontal well productivity numerical simulation method which comprises the following steps: 1) obtaining production characteristic related data of related wells in a continental facies shale condensate gas reservoir research area, and comparing and analyzing the production characteristics of the wells; 2) carrying out gas reservoir modeling according to the production characteristic related data, and establishing a matrix and crack system multiphase multicomponent model; 3) solving the gas reservoir numerical model according to fluid-rock physical property parameters, well and production plan related data and initial condition related data; 4) on the basis of the established gas reservoir numerical model, fitting production history of each well, analyzing fluid phase state characteristics, and fitting phase state parameters of the gas reservoir numerical model; 5, productivity simulation is carried out through the optimized gas reservoir numerical model, development dynamic prediction is carried out on all wells, and a corresponding reasonable production allocation plant.The model established through the method is more suitable for the gas reservoir type of shale condensate gas reservoirs.

The invention discloses a three-dimensional reservoir modeling method cooperatively driven by geostatistics and deep learning, and the method comprises the steps: generating a plurality of three-dimensional reservoir structure simulation results with equal probabilities according to the logging data and seismic data of a known reservoir through employing a multi-point geostatistics random simulation method; selecting a three-dimensional reservoir structure with good global connectivity from the simulation result to construct a reservoir structure mode library; constructing a generative adversarial network model, training the generative adversarial network model by using the reservoir structure pattern library, and constructing a three-dimensional reservoir structure model of a target reservoir by using the trained generative adversarial network model; the problems that the global connectivity of a simulation result of multi-point geostatistics is poor and a deep learning modeling method is difficult to train and optimize are solved.

The invention discloses a multi-modal geologic feature fusion method and a multi-modal geologic feature fusion system based on a discrete wavelet transform (CLIP)-Stable Diffusion model. The method comprises the following steps: reconstructing multi-modal geological data through differential wavelet transformation, extracting a low-frequency trend from earthquake and deposition data by adopting a Daubechies wavelet, capturing high-frequency details from deposition numerical simulation and logging data by adopting a Coiflets wavelet, and vectorizing a geological text through an orthogonal basis matrix; a CLIP-Stable Diffusion fusion model is constructed, a text encoder is utilized to analyze geological semantic features, an image encoder is utilized to extract spatial features, and a U-net diffusion generator realizes cross-modal alignment under the guidance of text conditions through a cross attention mechanism; and adopting a loss threshold termination mechanism constrained by a geological law in diffusion training, and finally outputting fusion data through wavelet inverse transformation. According to the method, cross-scale correlation deficiency and semantic segmentation limitation of a traditional method are broken through, and reservoir modeling precision and exploration efficiency are remarkably improved.

The invention belongs to the technical field of oilfield development, and discloses an oil and gas reservoir modeling processing system based on clastic rocks and a use method of the oil and gas reservoir modeling processing system. The data processing system is used for processing fault and logging data, geological stratification data and well perforation data, the grid management system is used for dividing and encrypting grid types, the model building system is used for building a digital-analog model and an oil-gas reservoir relation model, and the digital-analog management system is used for outputting the built model. And the established digital model is convenient to modify and reconstruct, so that the digital model pretreatment work requirement of complex oil and gas reservoir types is met, the historical fitting speed of subsequently realizing numerical simulation is improved, and the modeling treatment of clastic rock oil and gas reservoirs is facilitated.

The invention discloses a geological point cloud extraction method and system, and relates to the field of exploration, and the method comprises the steps: standardizing to-be-extracted geological point cloud data to a range of (-1, 1); clustering the standardized point cloud data to obtain a plurality of geological clusters; each point is transformed and projected to a high-dimensional feature space, centroid information of each geological cluster is integrated through position coding, the points with enhanced feature information are obtained, and then the geological clusters with the enhanced feature information are obtained; performing feature extraction on the geological cluster with enhanced feature information through a stacked Transform layer to obtain a target feature; and carrying out dimension reduction on the target features to obtain a geological point cloud thinning result. According to the method, reservoir boundary and structure details are reserved while efficient thinning is performed, the calculation cost of subsequent three-dimensional modeling and numerical simulation is greatly reduced, and a high-quality data basis is provided for digital reservoir modeling and rapid visualization.

The embodiment of the invention provides a thin interlayer and phase control physical property cause sand body configuration model construction method and system, and belongs to the technical field of reservoir modeling. The method comprises the following steps: identifying fluvial facies reservoir distribution characteristics based on exploration data, and constructing a corresponding cause sand body reservoir configuration model; obtaining a corresponding small-layer sand body deterministic model based on the cause sand body reservoir configuration model; on the basis of the deterministic model of the small-layer sand body, performing representation of an internal configuration interface of the sand body based on a lateral lamination model and an adaptive triangular mesh generation algorithm; and generating a distribution model of each lithofacies unit based on representation of a configuration interface in the sand body, and constructing a physical property model for fine modeling and heterogeneity description of high and low permeability sections in the configuration based on a phase control stochastic simulation method. According to the scheme, the limitations of insufficient precision, unreasonable transition and low calculation efficiency in traditional modeling are effectively overcome, and high-precision geologic model support is provided for reservoir management and oil reservoir development.

The invention discloses a river reservoir modeling method based on a Monte Carlo tree, a product, a medium and equipment, and belongs to the technical field of oil and gas reservoir modeling. The method comprises the following steps: establishing a riverway point and non-riverway point well location distribution diagram through logging identification, searching from riverway wells by utilizing a Monte Carlo tree to generate a riverway main stream line trajectory, and traversing all the riverway wells to obtain a main stream line distribution diagram; in the process, a specific protection mechanism and an optimization mechanism are adopted, and non-riverway well mispenetration is avoided, so that the modeling precision and efficiency are improved; the method comprises the following steps: S1, establishing a well location distribution diagram: determining whether each well is a river channel well or a non-river channel well, and establishing a river channel point and non-river channel point well location distribution diagram; s2, generating a main stream line of a single riverway: starting from a selected riverway well to carry out Monte Carlo tree search to obtain a main stream line track of the single riverway; and S3, traversing all the riverway wells to generate a main stream line distribution diagram. According to the method, the problem of errors possibly caused by complex large-scale gridding migration can be solved.

The application discloses a reservoir intelligent inversion method and related device, relates to the technical field of reservoir intelligent inversion, and comprises the following steps: obtaining multi-source heterogeneous data of a target area and preprocessing; constructing an initial geological model generator based on a conditional diffusion model, and optimizing hidden space parameters in a manner of seismic wave forward simulation; constructing a reservoir knowledge graph and adaptively pretraining and migrating the model online; performing task demand analysis, task decomposition and dynamic collaborative execution on a reservoir modeling task based on a thinking chain technology and a language large model technology, and obtaining iteratively optimized hidden space parameters; inputting the iteratively optimized hidden space parameters into the optimized geological model generator, outputting a three-dimensional distribution model, and extracting a confidence interval feature; incrementally updating the reservoir knowledge graph, determining a reservoir model conforming to a geological mode feature and matching a seismic waveform, and realizing reservoir intelligent inversion. The application can improve the accuracy and efficiency of reservoir inversion.

The invention discloses a reservoir porosity real-time prediction method and system based on alkane gas curvature and a storage medium, relates to the technical field of oil and gas reservoir development, and aims to solve the problems of insufficient utilization of dynamic characteristics of alkane gas curvature, poor real-time performance and limited heterogeneous reservoir modeling capability of an existing method. According to the technical key points, the method comprises the following steps: S100, acquiring alkane gas concentration and carbon isotope ratio data in a drilling process in real time, and calculating a curvature characteristic of the alkane gas concentration; s200, performing dynamic feature extraction on the alkane gas curvature; s300, performing dynamic weighted feature fusion on the curvature dynamic feature and the carbon isotope ratio to obtain fusion data; s400, constructing a BiLSTM model, training the BiLSTM model based on the fusion data, generating a hidden state, introducing an attention mechanism to perform dynamic weighting, and combining with an adjacent matrix of a reservoir geological unit to realize space enhancement; and S500, on the basis of the BiLSTM model, in combination with physical constraints, performing real-time prediction on the porosity of the reservoir.

The invention relates to the technical field of oil field reservoir geological modeling, in particular to a reservoir modeling method and device based on automatic calculation of a Kriging variation function. The method comprises the following steps: acquiring work area logging data and corresponding hard data thereof, and seismic data and corresponding soft data thereof, and performing grid division on the hard data and the soft data; dividing the data into training data and verification data; inputting the training data into an established reservoir geologic model based on a Kriging variation function, and training the model; and if the error between the trained model and the well point corresponding part of the verification data is greater than a first predetermined percentage, optimizing the trained model by using an optimization algorithm. The problems that an existing reservoir geologic model establishing method seriously depends on prior cognition of geologic experts, and the subjectivity of an interpretation result is high are solved; the problems that the uncertainty of model feature distribution performance is too large and reliability evaluation is difficult due to the fact that a trained model lacks effective verification are solved.

The invention discloses a reservoir modeling task processing method based on a mixed domain parallel perception generative adversarial network, and relates to the technical field of geostatistics, and the method comprises the steps: carrying out the parameter migration and expansion of original sample data through a cross-domain migration-driven lightweight reservoir configuration sample enhancement model on the basis of the training parameters of an existing sample; a multi-dimensional mixed domain joint representation module is utilized, a parallel attention mechanism supporting multi-source features and a multi-scale feature deep fusion mechanism are introduced, and a mixed domain-based parallel perception fusion generative adversarial network is constructed; inputting the sample data into the generative adversarial network, outputting target data, and performing consistency comparison on the target data and the expanded sample data set; and if the comparison is passed and the model evaluation of the generative adversarial network is passed, the reservoir configuration modeling task is processed, so that the problems of large demand of training data and insufficient feature mode mining capability are solved, the multi-scale characterization capability of the model is improved, and the model applicability and accuracy in a complex actual scene are improved.

This invention relates to the field of oil and gas reservoir modeling technology, and discloses a method for real-time calibration and trend prediction of oil and gas reservoir models that integrates dynamic production data. The invention aims to solve the technical problem that the prediction accuracy of existing reservoir models gradually decreases with changes in oilfield production dynamics after a one-time calibration, and lacks an automated, continuous correction mechanism. The method involves initial calibration of the reservoir model and generation of a baseline prediction; continuous monitoring of the deviation between actual production data and the baseline prediction; automatic calibration of the reservoir model to reduce the deviation when the deviation exceeds a preset threshold; and generation of a new production trend prediction based on the calibrated model, which replaces the baseline prediction, forming a closed loop. This invention enables the reservoir model to dynamically reflect production changes, achieves automated and rolling updates of model parameters, and provides a way to generate probabilistic prediction results, improving the timeliness of predictions and the reliability of decision support.

The invention provides a carbonate rock hard bottom surface rapid identification method and device and a storage medium, and belongs to the technical field of oil and gas reservoir exploration and development. The method comprises the following steps: acquiring core image data; preprocessing the core image to obtain a processed core image; performing color identification according to the processed core image, and marking biological disturbance in the core image; image segmentation is carried out according to the hard bottom surface features and the core image marked with the biological disturbance, and a hard bottom surface area in the core image is marked. The core image is used for color identification, the corresponding biological disturbance is marked from the core image, and the biological disturbance in the core image is identified and segmented based on the hard bottom surface features, so that the hard bottom surface area in the core image is marked, manual identification is not needed, the hard bottom surface identification precision and efficiency are improved, and the identification efficiency is improved. Hard bottom distribution can be quickly and accurately positioned, and reliable data support is provided for reservoir modeling, well drilling design and development planning; and the subjectivity of manual interpretation is reduced.

The embodiment of the invention provides a carbon sequestration geological exploration method and device, a storage medium and electronic equipment, and the method comprises the steps: carrying out the three-dimensional reservoir modeling of a carbon sequestration region according to the three-dimensional geophysical prospecting data of a target resolution of the carbon sequestration region, so as to obtain a three-dimensional model of the carbon sequestration region; performing carbon dioxide migration numerical simulation based on a migration rule of supercritical carbon dioxide and the three-dimensional model to obtain a distribution condition of the supercritical carbon dioxide in the carbon sequestration area; and according to the distribution condition, a target horizon is determined in the carbon sequestration area, and the target horizon is the horizon where the supercritical carbon dioxide is injected.

It is disclosed a computer-implemented method for modelling a reservoir comprising fault zones, comprising: - Obtaining an initial model of the reservoir (100) and ground data (200), - Implementing (300) at least one set of fault zones generation in the initial model, comprising receiving input parameters (310), and, based on the received ground data and input parameters: o generating at least one core zone (322) of a fault zone, and a damage zone extending around the core zone, and o Generating a plurality of fault segments (324) within the damage zone.

The invention relates to the technical field of resource exploration and development, in particular to a high-precision dynamic acquisition method for barite precipitation capacity in reservoir modeling, which comprises the following steps of: loading key reaction parameters of a fluid-rock system of a reservoir into a three-dimensional pore model; and carrying out numerical simulation of mineral dissolution and barite precipitation processes by using the three-dimensional pore model loaded with the key reaction parameters, and calculating the barite precipitation amount based on the numerical simulation of the mineral dissolution and barite precipitation processes. Through calculation of the barite precipitation amount, the reservoir damage risk caused by barite precipitation can be effectively identified, decision support is provided for reservoir protection measures, and potential loss in the reservoir development process is reduced; and an injection-production scheme can be optimized, the oil and gas recovery efficiency is improved, and the economic life of a reservoir is prolonged. Besides, by calculating the precipitation amount in the barite precipitation simulation process, development and evolution of the reservoir can be accurately predicted, and a reliable basis is provided for reservoir modeling and simulation.

The application provides a three-dimensional reservoir modeling method based on semantic rule guidance and multi-point geostatistics, relates to the geological field, and the method comprises the following steps: arranging strata in reverse order according to deposition time, iteratively executing a finite difference interpolation algorithm from the newest stratum, and taking the current stratum as a normal vector constraint of the next stratum; quantifying the constraint of fault kinematics on the surrounding deformation zone; under the support of an implicit structure model, adopting a two-dimensional parameter optimization strategy to dynamically configure the parameters of a fast sampling algorithm; adaptively matching the local structure features of a training image through a kernel function, and globally searching for an optimal combination in a grid; finally, taking a structural model as a spatial boundary constraint, performing collaborative simulation of lithofacies parameters, generating an attribute field according to the quantile sampling rule of Euclidean distance and Hamming distance, until all grid nodes are simulated and a three-dimensional reservoir model is output. The technical problem of collaborative fusion of multi-source heterogeneous data and geological semantic rules in a complex heterogeneous reservoir is effectively solved.

The application discloses a multi-layered shale reservoir automatic modeling method based on bedding identification, specifically comprising the following steps: obtaining core samples from a shale reservoir, recording interval information, and obtaining core images; carrying out denoising processing on the core images and carrying out contrast enhancement; using a Canny edge detection algorithm to identify bedding edges of the core images; using a Hough line transformation algorithm to detect straight lines and identify bedding structure lines; judging whether the lines are straight by calculating the change of adjacent pixel points on the y-axis, calculating the depth of the lines according to the pixel coordinates of the lines; creating planes representing different beddings according to the depth values of each bedding, generating color of brightness and darkness, and further obtaining a shale multi-layered reservoir model. The automatic modeling method significantly improves the accuracy and efficiency of shale reservoir modeling, accurately identifies shale bedding characteristics by combining the bedding identification technology, and provides more detailed and reliable basic data for reservoir modeling.

The present invention relates to a method and system for reducing the uncertainty interval of sandstone proportion based on Bayesian theorem, and the method comprises: selecting a distribution of sandstone phase ratio from geological data of a target reservoir, and using it as a priori probability distribution of the net-to-gross ratio of a lithofacies model of the target reservoir; based on the discretized prior probability distribution, using it and a multi-point geostatistical method to perform lithofacies simulation, and obtaining a plurality of random lithofacies models of the target reservoir with different net-to-gross ratio values; performing spatial resampling on each random lithofacies model, and obtaining a plurality of estimated values ​​of the net-to-gross ratio of sandstone; calculating the likelihood probability distribution of the net-to-gross ratio of sandstone according to the estimated values ​​of the plurality of net-to-gross ratios of sandstone; performing Bayesian transformation on the likelihood probability distribution of the net-to-gross ratio of sandstone, and obtaining the posterior probability distribution of the net-to-gross ratio of the lithofacies model of the target reservoir. The present invention combines mathematical statistics, a multi-point geostatistical model and Bayesian theorem, and reduces the uncertainty of sandstone proportion in the reservoir modeling process.

The invention provides a reservoir modeling parameter pushing system and method, and relates to the technical field of reservoir modeling knowledge pushing, and the system comprises a query module, a display module and a reservoir modeling parameter knowledge base; the query module is used for receiving a query instruction of a user, the query instruction at least comprises a to-be-queried target keyword, a target reservoir modeling parameter matched with the target keyword is queried from the reservoir modeling parameter knowledge base according to the target keyword, and the queried target reservoir modeling parameter is displayed to the user through the display module; the reservoir modeling parameter knowledge base is used for storing different reservoir modeling parameters; wherein the target keywords at least comprise keywords of professional entries, keywords of literature and keywords of analogy cases, and the reservoir modeling parameters at least comprise professional entry parameters, literature parameters and analogy case parameters. The query accuracy and utilization rate of the digital assets can be improved.

The invention relates to the field of oil and gas resource exploration and development, and discloses a carbonate fractured-vuggy reservoir body modeling method and device, a storage medium and a processor, and the method comprises the steps: explaining a reservoir body corresponding to a first single well in a target area, and obtaining a hierarchical division result of the reservoir body corresponding to the first single well; performing three-dimensional structure analysis to obtain a three-dimensional geologic model corresponding to a strike-slip fracture fracture zone reservoir body in a hierarchical division result; and establishing three-dimensional geologic models corresponding to the rest of the reservoir bodies in the hierarchical division result, and fusing the three-dimensional geologic models corresponding to the reservoir bodies in the hierarchical division result to obtain the three-dimensional geologic model of the carbonate fractured-vuggy reservoir body corresponding to the first single well. According to the scheme provided by the embodiment of the invention, the presentation of the characteristics of the grid-cluster-shaped reservoir structure in the three-dimensional geologic model can be enhanced and refined, so that better modeling can be carried out aiming at the carbonate rock fault control grid-cluster-shaped structure fracture-cavity reservoir body.

Implementations provide a method that includes: accessing data comprising records of measurements from a plurality of wells of a reservoir over a period of time; removing statistical outliers from the records to generate clean records, wherein the statistical outliers represent a probability lower than a threshold; grouping, based on the clean records, the plurality of wells into a set of clusters, each cluster comprising one or more wells whose corresponding records exhibit a shared trend over at least a portion of the period of time; conducting, for each cluster, a history matching simulation using a corresponding model, wherein the corresponding model is calibrated; launching, based on results of the history matching simulation, a prediction simulation to identify at least one of an infill well and a sidetrack well within each cluster; and generating an integrated visualization for results of the prediction simulation as the prediction simulation advances.

The present invention discloses a modeling method, a reservoir prediction method, and a system for reservoir prediction. The method first prepares an observation sample dataset containing seismic attributes, then uses a clustering method to select variables and extract key variables to construct a working dataset. Through pseudo-labeling technology, limited labeled samples are expanded into fully labeled samples, and information from unlabeled data is used to optimize model training. The introduction of pseudo-labels significantly improves the recognition accuracy of categories with a small number of samples when labeled data is insufficient. The present invention is particularly suitable for practical scenarios such as oil and gas prediction, reservoir modeling, and well logging data analysis, and effectively solves the problem of reduced prediction accuracy due to label scarcity.

The invention relates to the field of underground reservoir modeling and numerical simulation, and provides an oil reservoir model scale upgrading parameter iterative optimization method, which comprises the following steps: executing scale upgrading on a fine-scale oil reservoir model to obtain initial coarse-scale model parameters; taking a flow simulation result of the fine-scale oil reservoir model as input data, performing iterative correction on the initial upscale single-phase flow scale parameter, and generating a corrected upscale single-phase flow scale parameter; on the basis of the corrected upscaling single-phase flow scale parameter, bottom hole pressure difference correction calculation is carried out on the initial upscaling well index, and a corrected upscaling well index is obtained; the corrected upscaling single-phase flow scale parameter and the corrected upscaling well index are utilized to construct a current iteration coarse-scale oil reservoir model, the current iteration coarse-scale oil reservoir model is evaluated through relative errors, and final coarse-scale model parameters are output based on the coarse-scale oil reservoir model meeting a preset precision threshold value. According to the method, coarse scale parameters are dynamically corrected through an iterative optimization mechanism, and the scale upgrading precision is remarkably improved.

A method for generating one or more reservoir models using machine learning is provided. Generating reservoir models is typically a time-intensive idiosyncratic process. However, machine learning may be used to generate one or more reservoir models that characterize the subsurface. The machine learning may use geological data, geological concepts, reservoir stratigraphic configurations, and one or more input geological models in order to generate the one or more reservoir models. As one example, a generative adversarial network (GAN) may be used as the machine learning methodology. The GAN includes two neural networks, including a generative network (which generates candidate reservoir models) and a discriminative network (which evaluates the candidate reservoir models), contest with each other in order to generate the reservoir models.

The invention discloses a thin reservoir modeling method capable of accurately meeting well point and geological map constraints, relates to a geological modeling method, and particularly relates to a thin reservoir modeling method capable of accurately meeting the well point and geological map constraints, which can keep various attribute thicknesses calculated by a model consistent with constrained original maps. Comprising the following steps that basic information of a block is loaded into modeling software, and the basic information comprises a seismic interpretation result, a coordinate well position, well deviation, well logging curve data and well point layering data; according to the method, a logging curve and test analysis data are comprehensively utilized, firstly, making of a four-relation chart and establishment of an interpretation model are completed, then logging data are processed and interpreted, and finally all parameters are subjected to layered statistics; according to the method, the quality of the model can be controlled by adopting a phase control and trend body modeling method, so that the model at the well point is ensured to be consistent with actually measured data, and the model can be matched with a constraint map in a predicted calculation area.