54 results about "Unconventional oil" patented technology

This invention relates to the field of unconventional oil and gas development technology, and to a device and method for quantitatively evaluating the permeability enhancement caused by oxidative thermal stress in shale oil. The former includes a triaxial core holder housed within a constant-temperature chamber, and confining pressure injection system, oxidation medium injection system, detection medium injection system, gas collector, upstream storage tank, downstream storage tank, chromatograph, and acoustic emission sensor spaced apart outside the chamber. This application provides a dynamic multi-field coupled physical simulation system capable of simulating real formation conditions. By collecting pressure, product composition, acoustic signals, and nuclear magnetic resonance relaxation data, it utilizes a mathematical model for dynamic inversion of porosity and permeability using the pressure pulse attenuation method. It integrates acoustic emission RA-AF source identification and nuclear magnetic resonance fractal evaluation to analyze the multi-field coupling effects of thermal, flow, force, and chemical fields generated during air injection, and quantitatively evaluates the degree of improvement in shale permeability and pore structure caused by oxidative expansion.

A kind of method for discriminating cementation natural fracture control hydraulic fracture propagation mode, the present application belongs to the field of unconventional oil and gas reservoir fracturing reconstruction;By obtaining hydraulic diffusion parameter and crack front dynamic motion parameter, local pore fluid pressure is obtained by diffusion analysis, and then effective normal stress is obtained by correcting macroscopic normal total stress;And it is compared with the crack threshold to generate damage accumulation factor, and the interface mechanical parameter is obtained by combining the tensile reference value;Then compared with local tip tensile stress, the propagation mode result is output, and the crack threshold is updated by using feedback optimization parameter;By constructing the causal coupling link of crack tip motion-forepoling seepage-damage accumulation-strength attenuation, the actual mechanical state of natural fracture interface can be dynamically characterized, so that the accuracy of propagation mode discrimination can be greatly improved.

This invention belongs to the field of petrochemical new materials technology, specifically relating to a novel oil displacement agent and its preparation method. The novel oil displacement agent comprises the following raw materials in parts by weight: 3-7 parts of either acrylic acid or methacrylic acid, 20-30 parts of acrylamide, 1.1-2.3 parts of octadecyl acrylate, 10-21 parts of polymeric oil, 1-3 parts of emulsifier, 0.05-0.08 parts of initiator, and 1.7-2.4 parts of phase inverting agent. The oil displacement agent provided by this invention is suitable for 5-50 mD low-to-medium permeability reservoirs, does not cause pore throat blockage, can be mixed online without human intervention, effectively improves the oil-water mobility ratio, enhances oil washing efficiency, and significantly improves crude oil recovery. It is suitable for fracture network fracturing of continental sedimentary unconventional oil and gas reservoirs and the development of low-to-medium permeability reservoirs, solving the problems of difficult injection, easy blockage, and high cost of traditional polymer flooding.

This invention relates to the field of unconventional shale oil and gas exploration and development, and proposes a multi-scale three-dimensional fracture modeling method and system. The method includes: acquiring geological data, well logging data, seismic data, and microseismic data of the study block; establishing a natural fracture DFN model based on the acquired geological, well logging, and seismic data, and establishing a microseismic pressure fracture DFN model based on the acquired microseismic data; and fusing the natural fracture DFN model and the microseismic pressure fracture DFN model to obtain a multi-scale three-dimensional fracture model. This invention efficiently integrates various geological and engineering information and rapidly establishes fracture models, showing great application potential in unconventional oil and gas reservoir fracturing monitoring and numerical simulation of oil and gas reservoir development.

The invention provides a shale oil multi-well crosstalk diagnosis and optimization method based on EDFM and oil-water two-phase coupling, and belongs to the technical field of unconventional oil and gas development. According to the method, an embedded discrete fracture model (EDFM) is utilized to construct a multi-well platform physical model comprising a horizontal shaft, discrete hydraulic fracture networks and a shale matrix, the model is coupled with an oil-water two-phase flow conservation equation, fluid compressibility and fracture pressure sensitivity, and a non-adjacent connection conductivity operator between adjacent well fracture networks is innovatively introduced; the characterization module is used for characterizing a fracturing crosstalk path; and by simulating a double logarithmic pressure drop derivative curve in a multi-well soaking period, identifying pressure balance abnormity caused by adjacent well crosstalk. The defect that a traditional grid encryption technology is large in calculation amount and cannot process complex intersecting cracks is overcome, the position and the flow conductivity of the crosstalk cracks can be accurately recognized, and a scientific basis is provided for evaluating the platform well scale, optimizing the well spacing and the channeling prevention technology.

This invention discloses a method for distinguishing and quantifying the enhanced oil recovery (EOR) mechanism of CO2 huff and puff in unconventional oil reservoirs, relating to the field of oil and gas extraction technology. The method is based on nuclear magnetic resonance (NMR) experiments to determine the T2 spectrum and one-dimensional frequency coding of saturated oil cores. By analyzing the T2 spectrum and one-dimensional frequency coding of saturated oil cores, the CO2 huff and puff recovery rate and the effective CO2 reach distance are calculated. Based on the experimental data, a component model is established and calibrated to fit the experimental recovery rate and effective CO2 reach distance, thereby distinguishing and quantifying the EOR mechanism at different stages of CO2 huff and puff. This method can accurately classify the enhanced oil recovery mechanism during CO2 huff and puff into oil expansion, oil molecule diffusion, elastic energy release, and dissolved gas drive, effectively identifying the main controlling mechanism of CO2 huff and puff enhancement, providing a basis for optimizing field operations.

The application discloses a high-strength casing for deep oil and gas reservoir exploitation, which is composed of the following raw material components in percentage by mass: C: 0.27%-0.30%, Si: 0%-0.2%, Mn: 0%-0.45%, Cr: 1.0%-1.5%, Mo: 0.5%-0.8%, Nb: 0.05%-0.08%, V: 0.02%-0.03%, Ti: 0.01%-0.05%, Al: 0.01%-0.04%, Ca: 0.001%-0.003%, N: 0%-0.0003%, B: 0.0008%-0.001%, RE: 0.02%-0.05%, P content is not more than 0.008%, S content is not more than 0.003%, and the balance is Fe, and the total of the content of the above raw materials is 100%. The application further discloses a preparation method of the casing steel and a manufacturing method of the high-strength casing. The high-strength casing produced by the component system and the manufacturing method has good matching of strength and toughness, excellent anti-collapse performance, and good stress corrosion resistance, and can meet the requirements of high-strength casing with high anti-collapse strength and stress corrosion resistance in the exploitation of unconventional oil and gas resources such as deep shale oil and gas, deep wells or ultra-deep wells.

The application discloses a horizontal well section interval optimization method based on cement ring integrity dynamic constraint, and belongs to the technical field of unconventional oil and gas development engineering. The method constructs a non-uniform cementing mechanics model based on a casing eccentricity to lock a stress target, activates a transient fluid-solid coupling mechanism to solve an expansion load, and extracts a spatial stress disturbance scalar. Nonlinear fatigue evolution under alternating load is tracked, and a double-mode safety tolerance limit that locks the body damage and interface anti-channeling is constructed. Finally, the optimal section interval is output by taking the rigid constraint as the driving force for multi-objective optimization. The application optimizes the yield target and wellbore integrity, accurately avoids hidden engineering risks such as annular pressure from the source, and maximizes the comprehensive development benefit of a single well.

The application discloses a kind of based on reduced-order model retraining's fractured reservoir injection-production parameter optimization method, it is related to unconventional oil and gas development technical field, including: establishing fractured reservoir full-order numerical simulation model, setting initial injection-production control parameter, running main, vice training simulation;Snapshot matrix is executed singular value decomposition, and reduced-order basis matrix is constructed;Snapshot matrix and the gradient information of main training simulation are executed reduced-order preprocessing, and reduced-order model is constructed;Based on reduced-order model, injection-production parameter optimization iteration is executed and is dynamically judged, until cumulative adjustment step is not more than pre-set allowable value and has reached pre-set maximum iteration step number, then with current optimal injection-production parameter operation verification, output optimal injection-production parameter and objective function value, otherwise using current optimal injection-production parameter updates main training simulation and retraining reduced-order model.The application is through simulation, reduced-order, optimization, update closed loop process, ensure accuracy while greatly improving the calculation efficiency of fractured reservoir production optimization.

This invention relates to the field of unconventional oil and gas field development technology, specifically to a method for determining dynamic capillary force in coal and rock. The method includes: selecting target core samples to prepare coal samples and obtaining the full-scale pore size distribution of the coal samples; constructing a three-dimensional random pore network model based on the full-scale pore size distribution; obtaining a topology-corrected static pore network model; establishing a dynamic model of contact angle variation with pore pressure; establishing dynamic deformation equations for pore and throat radii variation with effective stress; and simulating the gas-driven water process under different pore pressures based on an intrusion permeation algorithm, outputting capillary force-saturation curves under different pore pressure conditions, and forming a dynamic capillary force surface plot. This application has significant application value and promising prospects in the field of unconventional oil and gas field development, significantly improving the scientific nature of reservoir seepage behavior characterization and the rationality of development engineering decisions.

The embodiment of the invention provides a compact conglomerate reservoir identification method and system, and belongs to the field of unconventional oil-gas exploration and reservoir transformation. The method comprises the following steps: acquiring logging data of a reservoir section to be identified, and preprocessing the logging data; calling a corresponding lithology identification model based on the preprocessed logging data, and determining a conglomerate identification result of the corresponding reservoir section based on the lithology identification model; wherein the lithology identification model is obtained based on BP neural network training; based on the conglomerate identification result, corresponding compact conglomerate reservoir type matching is carried out in a pre-constructed compact conglomerate reservoir type library; and outputting a compact conglomerate reservoir identification result of the reservoir section to be identified based on the matched compact conglomerate reservoir type. According to the scheme, the method can effectively support the fracturing transformation decision of the reservoir, the development strategy is optimized, the oil and gas exploitation risk is reduced, and the production efficiency is improved.

The invention belongs to the technical field of imbibition oil extraction, and provides a water-based nano-emulsion imbibition oil displacement agent and a preparation method thereof. According to the preparation method of the water-based nano-emulsion imbibition oil displacement agent, polyoxyethylene lauryl ether, sorbitan monopalmitate, mahogany petroleum sulfonate, an oily solvent, nano silicon oxide and water are uniformly mixed through a phase transition component method to prepare the water-based nano-emulsion imbibition oil displacement agent. The preparation method of the water-based nano-emulsion imbibition oil-displacing agent can effectively improve the crude oil recovery rate of unconventional oil reservoirs.

This invention relates to an evaluation method and system for hydrocarbon generation and pressurization in shale oil, belonging to the field of oil and gas geological evaluation and unconventional oil and gas accumulation simulation technology. The method includes: Step 1: Obtaining input parameters of the target shale layer; Step 2: Calculating the generated oil mass based on mass balance; Step 3: Establishing the first relationship between crude oil volume and overpressure; Step 4: Establishing the volume conservation relationship; Step 5: Establishing the relationship between formation water volume and kerogen volume and overpressure; Step 6: Simultaneously solving for hydrocarbon generation overpressure; Step 7: Introducing hydrocarbon expulsion feedback to correct the hydrocarbon generation overpressure calculation; Step 8: Calculating formation pressure, determining breakthrough hydrocarbon expulsion, and performing pressure release and state update; Step 9: Iteratively calculating multiple maturity nodes and outputting the episodic hydrocarbon expulsion evolution results. This invention quantitatively evaluates the overpressure accumulation process of shale layers during thermal evolution, improving the computability of shale oil accumulation dynamics analysis.

The application discloses a method for optimizing the interval distance of horizontal well multiple-cutoff multi-fracturing clusters, and belongs to the technical field of oil and gas reservoir reconstruction. The method comprises the following steps: S1, establishing a full-coupling numerical model for horizontal well multiple-cutoff multi-fracture propagation under the consideration of stress interference; S2, discretely solving the fracture propagation numerical model by using the finite element method; S3, establishing a geology-engineering integrated productivity numerical model based on the simulated fracture shape; S4, comprehensively analyzing the fracture propagation and productivity contribution results, and optimizing the interval distance of horizontal well multiple-cutoff multi-fracturing clusters. The method can realize the comprehensive analysis of the influence of different cluster interval distances on the fracture shape, stress interference, productivity contribution and the like from the two aspects of finite element fracture propagation and productivity contribution results based on the parameters of logging, rock and fluid, and can interactively simulate and optimize the interval distance of the clusters, so that a more reliable theoretical basis is provided for the optimization of the cluster interval distance of horizontal well multiple-cutoff multi-fracturing of unconventional oil and gas resources.

A fire extinguishing system for unconventional oil production plants comprises a rail provided at a predetermined height above a ground around facilities of a plant for producing unconventional oil; a fire suppression mobile robot configured to monitor in real time whether a fire has occurred in the facility and in a vicinity of the facility while moving along the rail, to transmit a fire signal via a network upon detecting occurrence of the fire, and to spray a fire extinguishing agent onto an object where the fire has occurred; and a control server configured to activate a fire alarm in the plant upon receiving the fire signal from the fire suppression mobile robot, to transmit the fire situation externally via the network, and to control movement and operation of the fire suppression mobile robot.

The present application relates to the technical field of unconventional reservoir development and drainage, and provides a hydrophilic unconventional oil horizontal well volume fracturing post-soaking time design method, which comprises the following steps: S100, evaluating reservoir wettability and determining that the reservoir is a hydrophilic reservoir; S200, establishing a horizontal well segmented cluster fracturing post-reservoir fluid seepage basic physical model and determining basic conditions of the soaking time design method; S300, determining a soaking time calculation formula based on Darcy's law and seepage velocity; S400, collecting data values of parameters of the soaking time calculation formula; and S500, substituting the data values into the soaking time calculation formula to calculate equivalent reasonable soaking time. The method can achieve the technical effect that unconventional reservoir volume fracturing horizontal wells can be opened and oil can be seen.

This invention discloses a method for optimizing well layout parameters in a three-dimensional well network for fracturing in thick shale oil reservoirs. The optimization method includes: Step S1: Inputting the logging curve interpretation results of the pilot test well, and calculating the physical and geomechanical parameters of the target reservoir rock; Step S2: Calculating the reservoir quality, completion quality, and overall quality based on the physical and geomechanical parameters, and initially selecting the vertical landing sites for horizontal wells; Step S3: Establishing a reservoir fracturing geological model based on the physical and geomechanical parameters, building an unconventional oil and gas fracturing fracture propagation model, and simulating the vertical fracture height propagation of the initially selected vertical landing sites for horizontal wells; Step S4: Determining the optimal lateral well network density for each sub-layer based on single-well productivity; Step S5: Outputting the three-dimensional well network layout results. This method maximizes reservoir stimulation volume by drilling the fewest horizontal wells, meeting the needs of cost reduction and efficiency improvement.

This invention discloses a metal-anchored carbon nanocluster catalyst, its preparation method, and its application, belonging to the field of unconventional oil and gas resource development technology. The metal-anchored carbon nanocluster catalyst provided by this invention consists of amorphous nanoparticles without pore confinement, with all active sites exposed on the surface. It can directly adsorb and activate macromolecular organic matter during in-situ pyrolysis. Its metal center is atomically anchored to a flexible carbon framework through M-N-C and M-O-C coordination bonds, maintaining high dispersibility and structural stability even at formation temperatures of 500℃. Simultaneously, this catalyst is easily and uniformly injected into oil shale reservoirs using fracturing fluid and disperses well in complex pore networks, significantly improving solid-solid catalytic interface efficiency. This catalyst lacks strong acid centers and primarily promotes selective breaking of C-C / C-H bonds through metal electron transfer, reducing the risk of formation blockage. Therefore, it has promising application prospects in in-situ pyrolysis of oil shale.

An effective identification method of continental interbedded shale oil and gas reservoir sandstone relates to the field of unconventional oil and gas exploration, and solves the problem that the existing interbedded shale oil sandstone target layer has no conventional logging curve exploration and development needs a large number of drilling investment and high risk. The method comprises the following steps: S1: extracting the full well section gamma and resistivity curves of Fuyu oil layer wells; for the Fuyu oil layer straight and inclined wells in the evaluation or development wells, extracting the full well section casing behind amplitude gamma and casing before standard 2.5 meter gradient electrode curves; fitting the casing behind amplitude gamma and the casing before conventional gamma and doing linear regression to obtain the fitted gamma curve; for the Fuyu oil layer horizontal wells, combining the gamma curve in the logging while drilling with the dual lateral curve in the resistivity curve to form a graph; S2: identifying and interpreting the interbedded shale oil and gas reservoir sandstone of the Fuyu oil layer well; determining the effective oil-bearing sandstone potential layer. The effective identification method realizes the interpretation data from nothing to something, greatly reduces the investment and investment risk.

The application relates to a wetting reversal agent and a preparation method and application thereof, and belongs to the technical field of unconventional oil and gas exploitation. Raw materials of the wetting reversal agent include strong hydrophobic modified nano silicon dioxide and a synergist; the strong hydrophobic modified nano silicon dioxide is obtained by modifying and treating nano silicon dioxide with heptadecafluorodecyltrimethoxysilane; and the synergist includes polydimethylsiloxane, glycerol trioleate and 2-ethylhexanol polyoxyethylene ether. According to the embodiment of the application, the excellent water-repellent performance provided by the strong hydrophobic modified nano silicon dioxide and the surface tension reduction effect brought by the synergist are synergized, a more effective water lock inhibition system is formed, and the system jointly acts on the key link of the water lock problem possibly occurring in the fracturing process of deep tight gas reservoirs, so that the water lock inhibition capacity of the wetting reversal agent is improved in all directions.

The application discloses a modeling method for identifying natural fractures by using hierarchical classification quantitative discriminators, and comprises the following steps: step S1, constructing a wellbore natural fracture hierarchical classification quantitative discriminator by relying on static and dynamic and macroscopic and microscopic multi-element information fusion; step S2, constructing a spatial natural fracture hierarchical classification quantitative discriminator by relying on multi-level nested time window optimization of seismic attributes; and step S3, using the above identification results, adopting a natural fracture hierarchical classification three-dimensional modeling method to accurately, reliably and quickly construct a natural fracture hierarchical classification three-dimensional network model. The method can not only accurately and finely depict the horizontal and longitudinal distribution characteristics and laws of natural fractures, but also can solve the problems of accurately and reliably identifying induced fractures near faults and natural fractures in stable areas far from fault structures, and provides reliable geological models and technical support for scientifically and efficiently developing conventional fractured reservoirs, dense sandstone, dense carbonate rock and shale oil and gas and other unconventional oil and gas reservoirs.

The application discloses a kind of robust prestack seismic inversion methods and devices based on coherence constraint algorithm, belong to unconventional oil and gas exploration and development field, comprising: through the extraction of seismic coherence attribute of centrifugal window of space transformation;Based on the approximate formula of azimuthal anisotropy reflection coefficient, the forward operator of fracture reservoir is deduced and constructed, and the positive problem of prestack seismic inversion prediction is clear;Based on the prestack seismic inversion prediction positive problem, under the Bayesian framework, the coherence attribute is added to the objective function of inverse problem as the prior information of seismic inversion prediction, and stable prestack and poststack joint seismic inversion prediction is carried out.The application not only considers the influence of large-scale fracture in post-stack, but also considers the azimuthal anisotropy characteristics caused by small-scale fracture, which can greatly improve the stability of anisotropy parameter inversion of fracture reservoir, and has better predictability for small-scale fracture associated with large-scale fracture.

This invention belongs to the field of petrochemical new materials technology, specifically relating to a novel micro-fracture network oil displacement agent and its preparation method. The novel micro-fracture network oil displacement agent comprises the following raw materials in parts by weight: 2-6 parts of one of acrylic acid or methacrylic acid, 30-40 parts of acrylamide, 2-4.3 parts of octadecyl acrylate, 10-30 parts of polymeric oil, 2-5 parts of emulsifier, 0.06-0.09 parts of initiator, and 1.7-2.4 parts of phase inverting agent. The micro-fracture network oil displacement agent provided by this invention possesses nanoscale penetration, low residue, low damage, and high drag reduction characteristics. It can efficiently construct fracture networks in unconventional oil and gas reservoirs, improve oil washing and recovery rates, and features a simple process and stable performance. It is suitable for fracture network fracturing and efficient oil and gas displacement in continental sedimentary unconventional oil and gas reservoirs.

This invention discloses a method for evaluating the quality of deep oil shale based on segmented well logging inversion, belonging to the technical field of geophysical well logging interpretation and unconventional oil and gas resource evaluation. The steps are as follows: (1) data input; (2) data preprocessing; (3) joint segmentation of stratigraphy and depth; (4) segmented modeling; (5) inversion calculation; (6) dual-parameter threshold discrimination; (7) quality classification; (8) result output. By including multiple sedimentary segments in the evaluation object of deep oil shale, oil content and TOC inversion models are established for different target stratigraphic positions and different model selection depth ranges. The model can be used to supplement the oil content inversion of the 1000–2500m depth segment and improve the inversion accuracy of deep oil shale in the 1000–2500m depth segment. At the same time, it retains the advantages of continuous, economical and high-resolution well logging data, and can realize continuous evaluation of deep oil shale in the 1000–2500m depth segment, providing a more reliable technical means for accurate identification, quality classification and resource evaluation of deep oil shale.

This invention discloses a glycosyl carbon quantum dot oil displacement agent for unconventional oil reservoirs, its preparation method, and its application, belonging to the field of oilfield chemical technology. The preparation of the glycosyl carbon quantum dot oil displacement agent for unconventional oil reservoirs of this invention includes: adding a carbon source and a modifier to an alcohol solution, stirring to dissolve, and then carrying out a hydrothermal reaction to obtain the product; wherein the modifier is a ketoxime modifier; this method is simple, low-cost, has controllable particle size, and high yield, making it suitable for industrial application; the obtained carbon quantum dots have a high specific surface area and functional groups such as carboxyl and hydroxyl groups, which can penetrate nanopores and synergistically reduce the oil-water interfacial tension to below 5.0 mN / m; this product has outstanding high-temperature resistance and penetration ability, and can effectively penetrate into the nanopore throat structure of tight reservoirs, significantly improving oil displacement efficiency through interfacial modification, and is particularly suitable for the exploitation of unconventional nano-oil and gas resources.

The invention relates to a method for extracting unconventional oil and to a complex for the implementation thereof. The method comprises injecting oxygen into an oil-bearing formation through injection-production wells, igniting the oil in the vicinity of an injection well, and displacing the oil toward production wells in an injection-production well cluster. Water is injected into the injection wells along with the oxygen, creating within the formation a pressure of the medium which is higher than that supercritical for water. A movable cloud of water in a supercritical state is formed at the well bottom. The combustion zone and the supercritical water cloud are induced to move through the oil-bearing formation from a depleted well to the next well. As the supercritical water cloud moves, it carries out thermochemical reactions, extracting hydrocarbons into itself and directing these hydrocarbons into the production wells to be brought to the surface. Oil recovery and the movement of the cloud are effectuated from the deepest wells. Having a cluster of injection-production wells that are hydrodynamically connected to one another makes it possible to sweep oil-bearing formations that extend over a large area, since the supercritical water cloud can be made to move from one injection-production well to another by changing the ratio of the flow rates of the water and the oil products in individual injection-production wells.

The application provides a composite oil well cement and a preparation method thereof. By introducing carbon nanotubes and nano magnesium oxide, and compounding the carbon nanotubes and the nano magnesium oxide with oil well cement, water and an oil well cement dispersant, and by limiting the calcination treatment of the nano magnesium oxide at 300 DEG C to 1000 DEG C and the content of the above components, the compressive strength and the tensile strength of the cement stone formed by the composite oil well cement are effectively improved, the elastic modulus of the cement stone is significantly reduced, and the occurrence of self-shrinkage is inhibited. The cement stone formed by the composite oil well cement meets the cementing construction requirements, has good construction performance, can be used for high-performance cementing cement system design, research and application of high-temperature and high-pressure gas wells, unconventional oil and gas wells, gas storage wells and the like, meets the long-term sealing requirement of the cement sheath under a complex stress environment, and has good application prospect.

This invention provides a method for efficient proppant delivery and placement in tight sandstone and conglomerate reservoirs, belonging to the field of unconventional oil and gas exploration and development technology. The invention includes the following steps: determining the surface roughness of the hydraulic fracture in the sandstone and conglomerate reservoir; determining the effective width of the hydraulic fracture based on the surface roughness; determining the sand transport index of the hydraulic fracture based on the effective fracture width; determining the hydraulic fracturing sand transport capacity index; and optimizing the sand transport parameters using dimensionless sand transport capacity. This invention can rapidly optimize proppant delivery and placement by utilizing hydraulic fracture parameters and hydraulic fracturing construction parameters, combining the sand transport capacity of the fracture itself with the sand transport capacity of the construction conditions. This provides a basis for optimizing fracturing schemes in tight sandstone and conglomerate oil and gas reservoirs, and is beneficial for improving the fracturing effect in tight sandstone and conglomerate oil and gas reservoirs.

This invention relates to the field of unconventional oil and gas reservoir development and artificial intelligence inversion technology. It discloses a method for inverting fracture network parameters by integrating well testing and microseismic data, addressing the problems of high computational cost and severe non-uniqueness in traditional numerical well testing inversion. This method constructs a well testing forward model and inversion sample library, completes data preprocessing, builds a training attention-enhanced operator learning surrogate model, and efficiently solves for pressure transient responses. It inverts global reservoir seepage parameters through multi-starting-point gradient descent, and constructs a probabilistic inversion model combined with microseismic constraints to accurately determine the half-length of segmented fractures. It relies on latent variable neighborhood search to screen effective solutions, quantifies parameter uncertainty, and outputs the results. This invention integrates well testing dynamics and microseismic monitoring data, improving inversion accuracy and rationality, enabling rapid well testing interpretation and parameter probabilistic evaluation, and is suitable for field development applications in shale oil fractured horizontal wells.