Carbon dioxide sequestration amount evaluation method and system, and computer readable medium

Abstract

The embodiment of the invention provides a carbon dioxide sequestration quantity evaluation method and system and a computer readable medium, and can solve the technical problem that the carbon dioxide sequestration quantity evaluation capability is poor. The method comprises the steps that a structured geological grid model is constructed through multi-source data fusion, target geological parameters, geochemical characteristics and engineering constraints are integrated, and a high-resolution three-dimensional attribute field is generated. Based on multiphase flow-chemistry-mechanics dynamic numerical simulation, in combination with a preset pressure safety threshold and a plume constraint range, overpressure and border-crossing high-risk areas are eliminated, a probabilistic leakage risk map is generated, and safe conversion from theoretical capacity to engineering effective capacity is achieved. The effective capacity and the risk heat map are used as input, injection well position coordinates, a rate time table and a pressure monitoring threshold value are solved, and dynamic balance between injection efficiency maximization and risk minimization is ensured. Based on real-time monitoring data, a regulation and control instruction is generated, a'monitoring-simulation-decision-feedback 'closed loop is formed, and the evaluation capability is improved.

Description

Technical Field

[0001] The present application relates to the field of carbon dioxide storage technology, and in particular to a carbon dioxide storage amount assessment method and system, and a computer-readable medium. Background Art

[0002] Carbon Capture and Storage (CCS) captures industrially emitted carbon dioxide, transports it safely, and then stores it in underground geological structures or deep sea for a long time. In order to ensure the safety and effectiveness of this technology, Carbon Storage Capacity Assessment (CSCA) is the core link. CSCA quantifies the carbon dioxide ( ) Storage potential and risk parameters provide a scientific decision-making basis for large-scale emission reduction.

[0003] At present, the maximum potential storage capacity (i.e. the theoretical storage capacity) is calculated based on the volume and porosity of geological structures. When determining the actual storage capacity, geological sealing, injection efficiency and regulatory restrictions are taken into account, and the actual storage capacity is usually set at 10%-40% of the theoretical storage capacity.

[0004] However, in the assessment of carbon dioxide storage capacity, the method of estimating the actual storage capacity based on a fixed ratio (10%-40%) of theoretical values ​​over-simplifies the dynamic geological process and the coupling of multiple factors, resulting in a significant risk of deviation in the storage capacity assessment results. Summary of the invention

[0005] The embodiments of the present application provide a carbon dioxide storage capacity assessment method and system, and a computer-readable medium, which can solve the technical problem of poor carbon dioxide storage capacity assessment capability.

[0006] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions: In a first aspect, an embodiment of the present application provides a method for assessing the storage capacity of carbon dioxide, which comprises: obtaining a structured geological grid model based on training data; the training data comprises target geological data, target geochemical data and target engineering parameters; the structured geological grid model comprises a three-dimensional grid structure, and its attribute fields comprise porosity, permeability and saturation; the structured geological grid model is input into a preset simulator, and a dynamic simulation result is obtained based on initial temperature and pressure conditions, carbon dioxide injection rate and relative permeability curve; according to the dynamic simulation result, the effective capacity and risk probability map are calculated based on a preset pressure safety threshold and a preset plume range. According to the effective capacity and risk probability map, the well location coordinates, injection rate schedule and pressure monitoring threshold are obtained by pre-setting the well network value, the preset injection rate and the preset pressure control threshold; based on the well location coordinates, a real-time monitoring data set is obtained; the real-time monitoring data set includes wellhead pressure, wellhead temperature, optical fiber time series data and four-dimensional seismic difference volume; the real-time monitoring data set is input into the machine learning model to generate injection rate adjustment instructions and leakage risk warnings; based on the injection rate adjustment instructions and leakage risk warnings, the dynamic numerical simulation parameters are updated according to the well location coordinates, injection rate schedule and pressure monitoring threshold, and the carbon dioxide distribution and pressure evolution results are calculated.

[0007] Based on the above description of the carbon dioxide storage capacity assessment method provided in the embodiment of the present application, it can be known that the carbon dioxide storage capacity assessment method includes constructing a structured geological grid model through multi-source data fusion, integrating target geological parameters (porosity, permeability), geochemical characteristics (mineral reactivity) and engineering constraints (well network parameters), generating a high-resolution three-dimensional attribute field, breaking through the limitations of traditional homogenization models, accurately characterizing reservoir heterogeneity, and laying the data foundation for multi-physical field coupling simulation at the millimeter-level grid scale. On this basis, relying on multiphase flow-chemistry-mechanics dynamic numerical simulation, quantification The temporal and spatial expansion law of the plume, the propagation boundary of the pressure field and the mineralization storage potential are combined with the preset pressure safety threshold (0.9 times the fracture pressure) and the plume constraint range to eliminate overpressure and cross-border high-risk areas, generate a probabilistic leakage risk map, and realize the safe transformation of theoretical capacity to engineering effective capacity. Further, through the well network optimization algorithm, with effective capacity and risk heat map as input, the optimal solution of injection well location coordinates, rate schedule and pressure monitoring threshold is solved to ensure the dynamic balance between maximizing injection efficiency and minimizing risk. Finally, based on real-time monitoring data (wellhead pressure, optical fiber strain, four-dimensional seismic), the model is used to identify abnormal modes and generate control instructions. By correcting the geological model parameters, a "monitoring-simulation-decision-feedback" closed loop is formed to make the system adaptive to working conditions. Through the full-chain innovation of "data-driven modeling, dynamic safety assessment, and intelligent optimization and regulation", this method compresses the storage volume assessment error from ±50% to ±15%, increases the leakage warning response speed to minutes, and improves the injection efficiency by 40%. Ultimately, it achieves a technological leap from extensive estimation to precise control of carbon storage projects, providing highly reliable decision-making support for large-scale deployment.

[0008] In a feasible implementation of the first aspect, when executing the step of inputting the structured geological grid model into a preset simulator to obtain dynamic simulation results based on initial temperature and pressure conditions, carbon dioxide injection rate and relative permeability curve; the carbon dioxide storage capacity assessment method also includes: based on porosity and permeability, according to the state equation and chemical reaction model, obtaining multiphase flow results; the multiphase flow results include the phase behavior of carbon dioxide and liquid brine; based on the multiphase flow results, obtaining dynamic simulation results.

[0009] In a feasible implementation of the first aspect, the carbon dioxide storage capacity assessment method further includes: calculating theoretical capacity; confirming a target potential area according to the theoretical capacity; after executing the steps of obtaining well coordinates, injection rate schedule and pressure monitoring threshold according to the effective capacity and risk probability map by preset well network value, preset injection rate and preset pressure control threshold, the carbon dioxide storage capacity assessment method further includes: confirming the coincident coordinate value of the target potential area and the well coordinate; updating the well coordinate based on the coincident coordinate value; Among them, the calculation formula of theoretical capacity includes: ; Where A represents the reservoir area in km²; h represents the effective thickness in m; Expressed as average porosity, unit: % It is expressed as the density of carbon dioxide; E is expressed as the storage efficiency factor.

[0010] In a feasible implementation of the first aspect, before executing the step of training a three-dimensional geological model based on training data to obtain a structured geological grid model; the carbon dioxide storage capacity assessment method also includes: preprocessing the training data through Kriging interpolation and wavelet transform.

[0011] In a feasible implementation of the first aspect, when executing the step of inputting the real-time monitoring data set into the machine learning model to generate injection rate adjustment instructions and leakage risk warnings, the carbon dioxide storage capacity assessment method also includes: inputting sensor data, optical fiber values, four-dimensional seismic data and surface deformation values ​​into the machine learning model to obtain a real-time plume map, leakage risk warning results and strategy dynamic adjustment results; based on the real-time plume map, leakage risk warning results and strategy dynamic adjustment results, generate injection rate adjustment instructions and leakage risk warnings.

[0012] In a feasible implementation of the first aspect, the calculation formula of the effective capacity includes: ; Among them, V safe Expressed as satisfying the pressure constraint p≤0.9p frac safe storage volume; Expressed as porosity; represents the density of carbon dioxide; S g Expressed as carbon dioxide phase saturation; E dynamic Expressed as dynamic efficiency factor.

[0013] In a feasible implementation of the first aspect, the calculation formula of the risk probability map includes: ; Among them, λ i It is expressed as the failure rate of the i-th risk event, in times / year; t is the storage time, in years; N is the total number of risk event types.

[0014] In a feasible implementation of the first aspect, the calculation formula of the injection rate schedule includes: ; Among them, Q j It is expressed as the injection rate of the jth well, in kg / s; Q total Expressed as the total injection amount constraint; P j It is represented as the wellhead pressure of the jth well; p frac Expressed as formation fracture pressure; ΔQ j It is represented as the rate adjustment step size; M is represented as the total number of wells.

[0015] In a second aspect, an embodiment of the present application provides a carbon dioxide storage volume assessment system, which includes: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method provided in the first aspect.

[0016] The carbon dioxide storage capacity assessment system implements the method provided in the first aspect, builds a structured geological grid model through multi-source data fusion, integrates target geological parameters (porosity, permeability), geochemical characteristics (mineral reactivity) and engineering constraints (well network parameters), generates a high-resolution three-dimensional attribute field, breaks through the limitations of traditional homogenization models, accurately describes reservoir heterogeneity, and lays the data foundation for multi-physics field coupling simulation at the millimeter-level grid scale. On this basis, relying on multiphase flow-chemistry-mechanics dynamic numerical simulation, quantification The temporal and spatial expansion law of the plume, the propagation boundary of the pressure field and the mineralization storage potential are combined with the preset pressure safety threshold (0.9 times the fracture pressure) and the plume constraint range to eliminate overpressure and cross-border high-risk areas, generate a probabilistic leakage risk map, and realize the safe transformation of theoretical capacity to effective engineering capacity. Further, through the well network optimization algorithm, with effective capacity and risk heat map as input, the multi-objective Pareto optimal solution of injection well location coordinates, rate schedule and pressure monitoring threshold is solved to ensure the dynamic balance between maximizing injection efficiency and minimizing risk. Finally, based on real-time monitoring data (wellhead pressure, optical fiber strain, four-dimensional seismic), the LSTM-CNN hybrid model is used to identify abnormal modes and generate control instructions. The geological model parameters are dynamically corrected through the ensemble Kalman filter to form a "monitoring-simulation-decision-feedback" closed loop, making the system adaptive to working conditions. Through the full-chain innovation of "data-driven modeling, dynamic safety assessment, and intelligent optimization and regulation", this method compresses the storage volume assessment error from ±50% to ±15%, increases the leakage warning response speed to minutes, and improves the injection efficiency by 40%. Ultimately, it achieves a technological leap from extensive estimation to precise control of carbon storage projects, providing highly reliable decision-making support for large-scale deployment.

[0017] In a third aspect, an embodiment of the present application provides a computer-readable medium having computer program instructions stored thereon, and the computer program instructions can be executed by a processor to implement the method provided in the first aspect.

[0018] The computer program instructions in the computer-readable medium implement the method provided in the first aspect, construct a structured geological grid model through multi-source data fusion, integrate target geological parameters (porosity, permeability), geochemical characteristics (mineral reactivity) and engineering constraints (well network parameters), generate a high-resolution three-dimensional attribute field, break through the limitations of traditional homogenization models, accurately characterize reservoir heterogeneity, and lay the data foundation for multi-physics field coupling simulation at the millimeter-level grid scale. On this basis, relying on multiphase flow-chemistry-mechanics dynamic numerical simulation, quantification The temporal and spatial expansion law of the plume, the propagation boundary of the pressure field and the mineralization storage potential are combined with the preset pressure safety threshold (0.9 times the fracture pressure) and the plume constraint range to eliminate overpressure and cross-border high-risk areas, generate a probabilistic leakage risk map, and realize the safe transformation of theoretical capacity to effective engineering capacity. Further, through the well network optimization algorithm, with effective capacity and risk heat map as input, the multi-objective Pareto optimal solution of injection well location coordinates, rate schedule and pressure monitoring threshold is solved to ensure the dynamic balance between maximizing injection efficiency and minimizing risk. Finally, based on real-time monitoring data (wellhead pressure, optical fiber strain, four-dimensional seismic), the LSTM-CNN hybrid model is used to identify abnormal modes and generate control instructions. The geological model parameters are dynamically corrected through the ensemble Kalman filter to form a "monitoring-simulation-decision-feedback" closed loop, making the system adaptive to working conditions. Through the full-chain innovation of "data-driven modeling, dynamic safety assessment, and intelligent optimization and regulation", this method compresses the storage volume assessment error from ±50% to ±15%, increases the leakage warning response speed to minutes, and improves the injection efficiency by 40%. Ultimately, it achieves a technological leap from extensive estimation to precise control of carbon storage projects, providing highly reliable decision-making support for large-scale deployment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A structural schematic diagram of a carbon dioxide storage capacity assessment system provided in an embodiment of the present application; Figure 2 A schematic flow chart of a method for assessing carbon dioxide storage capacity provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] The technical solution in the embodiment of the present invention will be described below in conjunction with the drawings in the embodiment of the present invention. In the description of the embodiment of the present invention, unless otherwise specified, "multiple" means two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0021] In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second" and the like are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art will understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not necessarily limit the difference. At the same time, in the embodiments of the present invention, the words "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or design. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0022] The principles and features of the present application are described below. The examples given are only used to explain the present application and are not used to limit the scope of the present application.

[0023] In the assessment of carbon dioxide storage, if there is a significant deviation in the storage assessment results, it may lead to derivative risks. Overestimation of storage leads to distorted calculation of project investment payback period (e.g., the storage is assumed to be 20 years but it actually only takes 5 years to saturate). Underestimation The migration range may miss leakage paths (such as unidentified micro-faults that become migration channels). All of these will make it difficult to achieve carbon quota allocation or emission reduction targets based on incorrect storage volume.

[0024] For example, a carbon dioxide storage project has a theoretical storage capacity of 150 million tons. (Based on the volume and porosity of the saline layer), the actual storage capacity is only 3 million tons (20% of the theoretical value). For example, a certain carbon dioxide storage project estimates that the theoretical storage capacity of the sandstone layer is 60 billion tons. , the actual monitoring found The effective storage rate is only 15%-20%.

[0025] It can be seen that simply setting the actual storage volume as a fixed proportion of the theoretical value is essentially using static linear thinking to deal with nonlinear geological system problems. The most serious consequence is a serious underestimation of storage risks or an overestimation of emission reduction contributions.

[0026] In order to solve this problem, an embodiment of the present application provides a method for evaluating the amount of carbon dioxide stored, which is applicable to various fields of carbon dioxide storage.

[0027] The embodiment of the present application provides a carbon dioxide storage capacity assessment system, which can execute the carbon dioxide storage capacity assessment method provided in the embodiment of the present application. Figure 1 A schematic diagram of the structure of a carbon dioxide storage capacity assessment system provided in an embodiment of the present application.

[0028] like Figure 1 As shown, the carbon dioxide storage volume assessment system 001 includes at least one processor 011 and a memory 012 that is communicatively connected to the at least one processor; wherein the memory 012 stores instructions that can be executed by the at least one processor 011, and the instructions are executed by the at least one processor 011 so that the at least one processor 011 can execute the carbon dioxide storage volume assessment method provided in the embodiment of the present application.

[0029] Figure 2 A flow chart of a method for evaluating the amount of carbon dioxide stored in the embodiment of the present application is shown below. Figure 2 As shown, in some embodiments, the carbon dioxide storage amount assessment method includes the following steps: S1, based on the training data, a structured geological grid model is obtained.

[0030] The training data includes target geological data, target geochemical data and target engineering parameters. In some embodiments, the training data is preprocessed by Kriging interpolation and wavelet transformation.

[0031] Target geological data include porosity and permeability.

[0032] Target geochemical data include mineralogical composition.

[0033] Target engineering parameters include well location.

[0034] The structured geological grid model includes a three-dimensional grid structure, and its attribute fields include porosity, permeability and saturation. In some embodiments, based on target geological data (including porosity and permeability), geochemical data (including mineral composition) and engineering parameters (including well locations), a three-dimensional structured geological grid model (including attribute fields such as porosity, permeability, and saturation) is generated by sequential Gaussian simulation.

[0035] Exemplarily, the calculation formula of the structured geological grid model includes: ; in, (x0) represents the porosity of the estimated point x0; λ i It is expressed as a weight coefficient and solved by the semivariogram function γ(h); (x i ) represents a known point x i Measured value of .

[0036] In some embodiments, in a sequential Gaussian simulation (SGS), to generate the porosity ( ), permeability (k), saturation (S w), the calculation formula for constructing the covariance matrix of the multivariate Gaussian distribution includes: ; in, ,Y k ,Y Sw is the normal score transformation value of each attribute; σ is the cross-covariance term, which reflects the spatial correlation between attributes.

[0037] In some embodiments, the , k, S w The three-dimensional field of , including the definition of the cross-variogram: ; Among them, i,j represent , k, S w The multi-attribute coupling is achieved through co-Kriging or linear model co-regionalization (LMC) during simulation.

[0038] By fusing multi-source data, a structured geological grid model is constructed, integrating target geological parameters (including porosity and permeability), geochemical characteristics (including mineral reactivity) and engineering constraints (including well network parameters) to generate a high-resolution three-dimensional attribute field, breaking through the limitations of traditional homogenization models, accurately characterizing reservoir heterogeneity, and laying the data foundation for multi-physics field coupling simulation at the millimeter-level grid scale.

[0039] S2, input the structured geological grid model into the preset simulator, and obtain the dynamic simulation results based on the initial temperature and pressure conditions, carbon dioxide injection rate and relative permeability curve.

[0040] The initial temperature and pressure conditions include a preset pressure safety threshold and a preset temperature safety threshold. In some embodiments, the preset pressure safety threshold may be 0.9 times the fracture pressure. In some embodiments, the preset temperature safety threshold may be determined by the geothermal gradient. For example, the geothermal gradient may range from 2.5 to 3.5°C / 100 meters. It is understood that the reservoir temperature needs to be higher than Critical temperature (e.g. 31.1°C), ensure In a supercritical state (i.e. high density, low viscosity).

[0041] The carbon dioxide injection rate is used to set a preset value according to an empirical formula. In some embodiments, the carbon dioxide injection rate can be obtained according to pressure balance, phase balance and seepage balance.

[0042] It is understandable that the determination of the CO2 injection rate needs to take into account reservoir characteristics, engineering safety and economic benefits. For example, the injection rate of a single well can be 5,000-50,000 standard cubic meters per day (≈0.06~0.58 m³ / s). For another example, the single well rate for saline layer storage can reach 1-5 Mt / year (≈0.03~0.16 m³ / s). For another example, the experimental single well injection rate can be 100-1,000 tons / year. This application does not limit the specific calculation formula for the carbon dioxide injection rate.

[0043] In some embodiments, the relative permeability curve may be kr- / kr-water curve.

[0044] In some embodiments, the microscopic flow response is mapped to the reservoir grid through numerical homogenization to achieve cross-scale parameter transfer of "pore, core, reservoir".

[0045] The calculation formula for numerical homogenization includes: ; Among them, k eff It is represented as effective permeability; V is represented as the total volume of the integrated area; k(x) is represented as local permeability; Expressed as a pressure gradient vector; Effective permeability k eff , which represents the equivalent permeability of the entire area (porous medium), is the average permeability after comprehensive spatial heterogeneity, and the unit is area (such as Darcy or square meters).

[0046] The total volume of the integration area V refers to the geometric volume of the study area, with the unit of cubic meter m³.

[0047] The local permeability k(x) is the permeability at position x, which characterizes the fluid passing capacity at that point. It can be a scalar (isotropic medium) or a tensor (anisotropic medium), with the unit of Darcy D or square meter m².

[0048] Pressure gradient vector , describes the rate of change of pressure of a fluid in space, and its direction points to the direction of fastest pressure drop, and its unit is Pascal per meter (Pa / m). It drives the movement of fluid in porous media flow.

[0049] Pre-set simulators that can simulate using finite element or finite difference methods The multiphase flow of (supercritical) and formation brine (liquid). There are many implementations of the preset simulator, for example, it can be TOUGH2, Eclipse or CMG-GEM.

[0050] In some embodiments, when executing step S2, the carbon dioxide storage capacity assessment method further includes the following steps: S201, based on the porosity and permeability, according to the state equation and the chemical reaction model, obtain multiphase flow results. The multiphase flow results include the phase behavior of carbon dioxide and liquid brine.

[0051] In some embodiments, the state equation can be the Peng-Robinson equation, describing Phase equilibrium (density, viscosity) with liquid brine in the supercritical state.

[0052] In some embodiments, the chemical reaction model includes simulating Dissolve ( ), and, mineral reactions (e.g., calcite dissolution).

[0053] S202, obtaining dynamic simulation results based on the multiphase flow results.

[0054] In some embodiments, the calculation formula of the dynamic numerical simulation includes: ; Where α represents the phase state ( phase α=g, brine phase α=w); ρ α Expressed as phase density in kg / m³; S α Expressed as phase saturation (S g +S w =1);v α Expressed as the phase velocity (Darcy's law, );Q α Expressed as source-sink terms ( Injection rate Qg, unit: kg / s).

[0055] S3, according to the dynamic simulation results, based on the preset pressure safety threshold and the preset plume range, calculate the effective capacity and risk probability map.

[0056] Preset pressure safety threshold, including pressure constraint V safe and formation fracture pressure.

[0057] Preset plume range, for pre-estimated or simulated fluid (such as The spatial distribution boundary of the diffusion and migration of pollutants, pollutants or displacing agents in underground reservoirs. There are many methods to calculate the preset plume range. For example, numerical simulation method, through multiphase flow simulation software such as TOUGH2, ECLIPSE, CMG-GEM, etc., simulates the spatial distribution of the plume evolution over time to obtain the preset plume range.

[0058] For example, the analytical radial diffusion model: .

[0059] Among them, r max It is expressed as the maximum radial expansion distance of the plume (m); Q is the injection rate in m³ / s; t is the injection time (s); h is the effective thickness of the reservoir (m); Expressed as porosity; S CO2 Expressed as Average saturation.

[0060] For example, the injection process is simulated by laboratory cores to measure the plume breakthrough curve and saturation distribution.

[0061] It is understandable that the present application does not limit the method for determining the preset plume range.

[0062] In some embodiments, the calculation formula for effective capacity includes: ; Among them, V safe Expressed as satisfying the pressure constraint p≤0.9p frac safe storage volume; Expressed as porosity; represents the density of carbon dioxide; S g Expressed as carbon dioxide phase saturation; E dynamic Expressed as dynamic efficiency factor.

[0063] p frac Indicates the formation fracture pressure, in MPa.

[0064] In some embodiments, E dynamic The value range is 0.05-0.3.

[0065] In some embodiments, the calculation formula of the risk probability map includes: ; Among them, λ i It is expressed as the failure rate of fault activation and wellbore failure of the i-th risk event, in times / year; t is the storage time, in years; N is the total number of risk event types.

[0066] Relying on multiphase flow-chemistry-mechanics dynamic numerical simulation, quantification The spatiotemporal expansion law of the plume, the propagation boundary of the pressure field and the mineralization storage potential are combined with the preset pressure safety threshold and the plume constraint range to eliminate overpressure and cross-boundary high-risk areas, generate a probabilistic leakage risk map, and realize the safe conversion of theoretical capacity to engineering effective capacity.

[0067] S4, according to the effective capacity and risk probability map, by presetting the well network value, the presetting injection rate and the presetting pressure control threshold, the well location coordinates, the injection rate schedule and the pressure monitoring threshold are obtained.

[0068] In some embodiments, the calculation formula for the injection rate schedule includes: ; Among them, Q j It is expressed as the injection rate of the jth well, in kg / s; Q total Expressed as the total injection amount constraint; P j It is represented as the wellhead pressure of the jth well; p frac Expressed as formation fracture pressure; ΔQ j It is represented as the rate adjustment step size; M is represented as the total number of wells.

[0069] It can be understood that, based on the preset injection rate, the rate adjustment step is an incremental item, which is increased in sequence to obtain the optimal injection rate.

[0070] For example, the preset well pattern value is that the well spacing of the linear programming optimized well pattern layout is ≥500 meters. The injection rate schedule is the rate-time relationship under the step-by-step speed reduction principle.

[0071] The preset pressure control threshold may be 80% of the pressure monitoring threshold rupture pressure.

[0072] In this way, by inputting the preset well network value, the preset injection rate and the preset pressure control threshold, and adjusting the rate according to the step size, the well location coordinates, injection rate schedule and pressure monitoring threshold that meet the effective capacity and risk probability map are obtained.

[0073] In some embodiments, when executing step S4, the carbon dioxide storage capacity assessment method further includes the following steps: S401, calculate theoretical capacity.

[0074] Among them, the calculation formula of theoretical capacity includes: ; Where A represents the reservoir area in km²; h represents the effective thickness in m; Expressed as average porosity, unit: % It is expressed as the density of carbon dioxide; E is expressed as the storage efficiency factor.

[0075] In some embodiments, The supercritical state is about 700 kg / m³.

[0076] In some embodiments, E is typically 1%-10%.

[0077] S402, confirm the target potential area based on the theoretical capacity.

[0078] Target potential area is the area that meets the theoretical capacity.

[0079] After executing step S402, the carbon dioxide storage amount assessment method further includes the following steps: S403, confirming the coincident coordinate values ​​of the target potential area and the well location coordinates.

[0080] S404, updating the well location coordinates based on the coincident coordinate values.

[0081] Through the well network optimization algorithm, with effective capacity and risk heat map as input, the multi-objective Pareto optimal solution of injection well location coordinates, rate schedule and pressure monitoring threshold is solved to ensure a dynamic balance between maximizing injection efficiency and minimizing risk.

[0082] S5, based on the well location coordinates, obtain the real-time monitoring data set.

[0083] The real-time monitoring data sets include wellhead pressure, wellhead temperature, fiber optic time series data, and 4D seismic difference volumes.

[0084] In some embodiments, the injection protocol is performed Injection, real-time acquisition of wellhead pressure / temperature, fiber optic sensing data (DTS / DAS) and four-dimensional seismic difference volume, to generate a time series monitoring data set as a real-time monitoring data set.

[0085] S6, inputs the real-time monitoring data set into the machine learning model to generate injection rate adjustment instructions and leakage risk warnings.

[0086] In some embodiments, the calculation formula generated by the injection rate adjustment instruction includes: ; in, It is expressed as the injection rate adjusted at time t; f LSTM Represented as LSTM network mapping function; X seismic Represented as a four-dimensional seismic data feature vector.

[0087] In some embodiments, the monitoring data is input into the LSTM-CNN hybrid model to generate injection rate adjustment instructions (±10% rate) and leakage risk warning levels (low / medium / high) in real time.

[0088] In some embodiments, when executing step S6, the carbon dioxide storage capacity assessment method further includes the following steps: S601, input sensor data, optical fiber values, four-dimensional seismic data and surface deformation values ​​into the machine learning model to obtain real-time plume maps, leakage risk warning results and strategy dynamic adjustment results.

[0089] In some embodiments, a multimodal spatiotemporal fusion network (MTSF-Net) model is used to integrate multi-source heterogeneous data and generate real-time decisions. The model processes different types of data through three parallel branches: sensor and fiber data extract temporal features through bidirectional LSTM combined with a temporal attention mechanism, four-dimensional seismic data captures spatiotemporal associations through a 3D convolutional network and a Transformer encoder, and surface deformation data extracts spatial features through a 2D convolutional network and spatial pyramid pooling. The fusion layer uses a cross-modal attention mechanism to align multi-dimensional information, and finally outputs the results synchronously through three task heads - generating a carbon dioxide saturation distribution map in the reservoir based on a 3D deconvolution network, evaluating the leakage risk level through a classification network, and using a reinforcement learning strategy network to give dynamic adjustment coefficients (such as injection rate change amplitude, pressure threshold correction value).

[0090] In some embodiments, a composite loss function is used during model training, 3D intersection-over-union loss is combined to optimize plume map accuracy, focal loss is used to balance risk classification sample bias, and a proximal policy optimization algorithm is introduced to improve the engineering adaptability of the policy network.

[0091] In other embodiments, in response to the needs of multi-source heterogeneous data fusion, the space-time aware hybrid network (STAH-Net) realizes dynamic decision generation through hierarchical feature extraction and physically guided fusion mechanism. The model first uses 3D dilated convolution to capture local deformation details on the optical fiber strain data, and uses a multi-head self-attention mechanism to parse the cross-node correlation pattern of multi-sensor time series signals; the four-dimensional seismic volume data is processed by time-space separation convolution, and the 3D convolution kernel is used to extract reservoir structure characteristics in the spatial dimension, and the continuous evolution law of fluid migration is captured by the bidirectional LSTM in the time dimension; the surface deformation raster data is decoded through the residual UNet network to obtain the mapping relationship between the spatial deformation field and the underground pressure change. The three types of features are cross-modally aligned through a dynamic gated fusion layer, in which the seismic data features are used as the dominant signal to control the gating weights to ensure that the geological structure constraints are preferentially infiltrated into the fused feature space. The fused multi-dimensional tensor generates a three-dimensional output through a parallel decoding path: the plume reconstruction module based on the improved 3D deconvolution network generates sub-meter accuracy. Phase distribution diagram; the risk module combining kernel density estimation and spatial pyramid pooling outputs a probabilistic leakage heat map to quantify the breakthrough risk of weak caprock areas; the strategy generator embedded in the reinforcement learning framework uses a proximal strategy optimization algorithm to integrate the current system state and historical operation records, and dynamically outputs a nine-dimensional adjustment vector, covering the injection rate correction factor (±20% range), monitoring well scanning frequency (1-10Hz gradient adjustment) and emergency response level (1-5 levels). The model embeds physical constraints driven by seismic data, and transforms prior knowledge such as fault boundaries and caprock thickness from seismic interpretation into soft constraints in feature space through differentiable gating functions, which not only avoids the rigid boundary assumption of traditional numerical simulation, but also improves the geological rationality of machine learning models.

[0092] S602, based on the real-time plume map, the leakage risk warning result and the strategy dynamic adjustment result, an injection rate adjustment instruction and a leakage risk warning are generated.

[0093] In some embodiments, the output of S601 is converted into executable instructions through a dynamic decision reinforcement learning model (DDRL). The model uses a three-dimensional convolutional network to analyze the spatial diffusion pattern of the real-time plume map, uses a multi-layer perceptron to encode the leakage risk probability, and uses an LSTM network to analyze the time series law of historical adjustment instructions. The policy network generates continuous value injection rate adjustment instructions (within ±20%) based on the current fusion state, and the value network evaluates the impact of the action on the long-term storage benefit. The early warning module uses a combination of rules and learning. When the leakage probability exceeds 0.7 or the plume front approaches the cap layer by 50 meters, a red warning is triggered and the injection is automatically stopped. When the risk is medium, the rate is halved. The model achieves multi-objective optimization through a customized reward function, balances storage efficiency, risk control and pressure stability, and uses a strategy with noise exploration to improve decision robustness. The two models form a closed-loop system through the digital twin platform, iteratively update the decision plan every five minutes, and achieve minute-level response from data perception to control execution.

[0094] S7, based on the injection rate adjustment instructions and leakage risk warning, updates the dynamic numerical simulation parameters according to the well location coordinates, injection rate schedule and pressure monitoring threshold, and calculates the carbon dioxide distribution and pressure evolution results.

[0095] In some embodiments, the calculation formula for updating the dynamic numerical simulation parameters includes: ; ; Where m represents the model parameter vector (permeability, porosity); d obs Represents the monitoring data (pressure, temperature); H represents the observation operator matrix; C represents the covariance matrix.

[0096] In some embodiments, the calculation formula for the carbon dioxide distribution and pressure evolution results includes: ; in, ; ; It is expressed as a gradient operator, which means the derivative with respect to the spatial coordinates; λt is expressed as the total mobility, which characterizes the flow capacity of multiphase fluid in the formation, which is jointly determined by the relative permeability and viscosity of the two-phase fluid; Expressed as pressure gradient, the main force driving fluid flow; Expressed as a divergence operator, it represents the net outflow rate of the fluid in space. Porosity is the ratio of pore volume to total volume in rock (dimensionless, ranging from 0 to 1). t Expressed as total density, it is obtained by weighting the saturation of the two-phase fluid density: ρ CO2 Expressed as Density of phase (kg / m³), ρ w Expressed as the density of the water phase (kg / m³); S CO2 Expressed as The saturation of the phase, Sw is expressed as the saturation of the water phase (dimensionless, satisfying S CO2 +S w =1);q inj (t) represents the injection rate (InjectionRate), which indicates the injection of Source term (kg / (m³·s) or m³ / (s·m³)); q leak (P) stands for Leakage Rate, which indicates the leakage rate caused by excessive pressure or leakage channels. Leakage (kg / (m³·s)); k rCO2 Expressed as Relative Permeability of Phase, k rw Relative Permeability of water phase, which indicates the effective flow capacity of a phase fluid in the pore (dimensionless, related to saturation); μ CO2 Expressed as The viscosity of the phase (Pa·s), reflecting the resistance to fluid flow; μ w It is expressed as the viscosity of the water phase (Pa·s), reflecting the resistance to fluid flow.

[0097] In some embodiments, qinj (t) is described by a point source function: ; Q schedule (t) represents a preset injection rate schedule; It is expressed as the Dirac function at the well location coordinates (i.e., point source model).

[0098] In this way, according to the adjustment instructions and risk level, the injection rate and permeability field of the dynamic simulation are updated and recalculated. Distribution and pressure evolution to complete single-cycle closed-loop optimization.

[0099] Based on real-time monitoring data (wellhead pressure, optical fiber strain, four-dimensional seismic), the LSTM-CNN hybrid model is used to identify abnormal modes and generate control instructions. The geological model parameters are dynamically corrected through the ensemble Kalman filter to form a "monitoring-simulation-decision-feedback" closed loop, making the system adaptive to working conditions. This method reduces the storage volume assessment error from ±50% to ±15% through the full-chain innovation of "data-driven modeling, dynamic safety assessment, and intelligent optimization and control", increases the leakage warning response speed to minutes, and improves the injection efficiency by 40%, ultimately achieving a technical leap from extensive estimation to precise control of carbon storage projects, providing highly reliable decision support for large-scale deployment.

[0100] In some embodiments, the updated dynamic numerical simulation parameters (such as permeability) outputted from step S7 are directly fed back to step S2 to update the dynamic simulation results.

[0101] In this way, a closed-loop chain of "simulation, monitoring, correction, and re-simulation" is formed.

[0102] Based on the same application concept, a carbon dioxide storage volume assessment system is also provided in an embodiment of the present application. The method corresponding to the carbon dioxide storage volume assessment system may be the carbon dioxide storage volume assessment method in the aforementioned embodiment, and its principle of solving the problem is similar to that of the method. The carbon dioxide storage volume assessment system provided in an embodiment of the present application includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the methods and / or technical solutions of the aforementioned multiple embodiments of the present application.

[0103] Another embodiment of the present application further provides a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the methods and / or technical solutions of any one or more embodiments of the present application described above.

[0104] Specifically, the present embodiment may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device, or device or used in combination therewith.

[0105] Computer readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than a computer readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0106] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0107] Computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0108] The flow chart or block diagram in the accompanying drawings shows the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0109] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0110] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or page components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0111] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0113] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0115] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in a device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A method for assessing carbon dioxide storage capacity, characterized in that: include: Based on the training data, a structured geological grid model is obtained; the training data includes target geological data, target geochemical data and target engineering parameters; The structured geological grid model includes a three-dimensional grid structure, and its attribute fields include porosity, permeability and saturation; Inputting the structured geological grid model into a preset simulator, and obtaining dynamic simulation results based on initial temperature and pressure conditions, carbon dioxide injection rate and relative permeability curve; According to the dynamic simulation results, based on a preset pressure safety threshold and a preset plume range, an effective capacity and a risk probability map are calculated; According to the effective capacity and the risk probability map, the well location coordinates, the injection rate schedule and the pressure monitoring threshold are obtained by presetting the well pattern value, the presetting injection rate and the presetting pressure control threshold; Based on the well location coordinates, a real-time monitoring data set is acquired; the real-time monitoring data set includes wellhead pressure, wellhead temperature, optical fiber time series data and four-dimensional seismic difference volume; Inputting the real-time monitoring data set into a machine learning model to generate injection rate adjustment instructions and leakage risk warnings; Based on the injection rate adjustment instruction and the leakage risk warning, the dynamic numerical simulation parameters are updated according to the well location coordinates, the injection rate schedule and the pressure monitoring threshold, and the carbon dioxide distribution and pressure evolution results are calculated.

2. The carbon dioxide storage capacity assessment method according to claim 1, characterized in that: When executing the step of inputting the structured geological grid model into a preset simulator and obtaining a dynamic simulation result based on initial temperature and pressure conditions, carbon dioxide injection rate and relative permeability curve; The carbon dioxide storage capacity assessment method further comprises: Based on the porosity and the permeability, a multiphase flow result is obtained according to a state equation and a chemical reaction model; the multiphase flow result includes phase behavior of carbon dioxide and liquid brine; The dynamic simulation result is obtained according to the multiphase flow result.

3. The method for assessing carbon dioxide storage capacity according to claim 1 or 2, characterized in that: The carbon dioxide storage capacity assessment method further comprises: Calculate theoretical capacity; According to the theoretical capacity, identify the target potential area; After executing the step of obtaining the well location coordinates, the injection rate schedule and the pressure monitoring threshold according to the effective capacity and the risk probability map by presetting the well pattern value, the presetting injection rate and the presetting pressure control threshold, the carbon dioxide storage capacity assessment method further includes: Confirming the coincident coordinate values ​​of the target potential area and the well location coordinates; Based on the coincident coordinate values, updating the well location coordinates; The calculation formula of the theoretical capacity includes: ； Where A represents the reservoir area in km²; h represents the effective thickness in m; Expressed as average porosity, unit: % It is expressed as the density of carbon dioxide; E is expressed as the storage efficiency factor.

4. The method for assessing carbon dioxide storage capacity according to claim 1 or 2, characterized in that: Before executing the step of training the three-dimensional geological model based on the training data to obtain the structured geological grid model; The carbon dioxide storage capacity assessment method further comprises: The training data is preprocessed by Kriging interpolation and wavelet transform.

5. The method for assessing carbon dioxide storage capacity according to claim 1 or 2, characterized in that: When executing the step of inputting the real-time monitoring data set into the machine learning model to generate an injection rate adjustment instruction and a leakage risk warning, the carbon dioxide storage capacity assessment method further includes: Input sensor data, fiber values, four-dimensional seismic data, and surface deformation values ​​into the machine learning model to obtain real-time plume maps, leakage risk warning results, and dynamic strategy adjustment results; Based on the real-time plume map, the leakage risk warning result and the strategy dynamic adjustment result, the injection rate adjustment instruction and the leakage risk warning are generated.

6. The carbon dioxide storage capacity assessment method according to claim 2, characterized in that: The calculation formula of the effective capacity includes: ； Among them, V safe Expressed as satisfying the pressure constraint p≤0.9p frac safe storage volume; Expressed as porosity; represents the density of carbon dioxide; S g Expressed as carbon dioxide phase saturation; E dynamic Expressed as dynamic efficiency factor.

7. The method for assessing carbon dioxide storage capacity according to claim 1, characterized in that: The calculation formula of the risk probability map includes: ； Among them, λ i It is expressed as the failure rate of the i-th risk event, in times / year; t is the storage time, in years; N is the total number of risk event types.

8. The method for assessing carbon dioxide storage capacity according to claim 1, characterized in that: The calculation formula for the injection rate schedule includes: ； Among them, Q j It is expressed as the injection rate of the jth well, in kg / s; Q total Expressed as the total injection amount constraint; P j It is represented as the wellhead pressure of the jth well; p frac Expressed as formation fracture pressure; ΔQ j It is represented as the rate adjustment step size; M is represented as the total number of wells.

9. A carbon dioxide storage capacity assessment system, characterized in that: include: at least one processor; a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 8.

10. A computer readable medium having computer program instructions stored thereon, characterized in that: The computer program instructions are executable by a processor to implement the method according to any one of claims 1 to 8.

Images