CO2 injection parameter selection and escape monitoring method and device in geological storage

Abstract

The invention belongs to the technical field of CO2 geological sequestration, and particularly relates to a CO2 injection parameter selection and escape monitoring method and device in geological sequestration, and the CO2 injection parameter selection method comprises the steps: obtaining CO2 simulation injection data and stratum parameter data of a target work area; the obtained data are input into a pre-trained CO2 injection parameter analysis model, CO2 injection parameters are obtained, and the CO2 injection parameters comprise CO2 injection points. The CO2 escape monitoring method comprises the following steps: in the process of injecting CO2 into a target work area, acquiring CO2 real-time injection data and stratum parameter data of the target work area; and inputting the obtained data into a pre-trained CO2 injection parameter analysis model to obtain an escape monitoring result in the CO2 injection process. The problems that in geological storage, CO2 injection parameter selection is low in efficiency and high in cost, and escape monitoring in the CO2 injection process is lacked are solved.

Description

Technical Field

[0001] This invention belongs to the field of CO2 geological storage technology, and particularly relates to a method and device for selecting CO2 injection parameters and monitoring escape in geological storage. Background Technology

[0002] Carbon Dioxide Geological Sequestration (CCS) is a technology for reducing atmospheric carbon dioxide concentration. It involves capturing carbon dioxide emitted from industrial processes and injecting it into deep underground rock layers for long-term storage, thereby reducing carbon emissions. However, if CO2 escapes during the capture and injection process, the efficiency of carbon sequestration in reducing carbon emissions will be significantly reduced, and it will also cause varying degrees of damage to soil and vegetation, negatively impacting the global environment and socio-economic development. Therefore, it is necessary to select appropriate CO2 injection parameters for CCS and to monitor and provide early warning of CO2 escape during the injection process. This will provide the necessary foundation for optimizing subsequent sequestration technologies and mitigating escape risks.

[0003] Currently, when selecting CO2 injection parameters for CCS (Chemical Sequestration System), it is mainly based on a comprehensive consideration of the geological structure, stratigraphic permeability, connectivity, and safety of the target work area. This relies on human judgment, resulting in low efficiency and high cost. For monitoring and early warning of CO2 escape from geological sequestration, existing technologies primarily monitor the sequestered CO2. However, CO2 may escape during the injection process, which can also damage the environment and the economy. Therefore, monitoring the CO2 injection process is essential. However, using existing technologies for monitoring sequestered CO2 to monitor escape during injection also presents some problems. For example, existing technologies use online analysis of the correlation between oxygen and carbon dioxide in the air to monitor CO2 leakage flux, or use colorimetric analysis of the absorbent to monitor leakage. However, these methods struggle to achieve comprehensive coverage of the monitoring area and face challenges in monitoring accuracy. Furthermore, the cost of long-term monitoring combined with instruments is also high. Summary of the Invention

[0004] This invention provides a method and apparatus for selecting CO2 injection parameters and monitoring escape in geological storage, which solves the problems of low efficiency and high cost in selecting CO2 injection parameters and lack of monitoring of escape during the CO2 injection process in geological storage.

[0005] To address the aforementioned technical problems, the first aspect of this paper provides a method for selecting CO2 injection parameters in geological storage, the method comprising:

[0006] Obtain CO2 simulation injection data and formation parameter data for the target work area;

[0007] The CO2 simulation injection data and formation parameter data of the target work area are input into the pre-trained CO2 injection parameter analysis model to obtain CO2 injection parameters, which include CO2 injection points.

[0008] In a further embodiment of this paper, the CO2 simulated injection data includes the CO2 simulated injection rate and the CO2 simulated injection concentration;

[0009] The formation parameter data includes data on porosity, permeability, Poisson's ratio, formation temperature, and formation pressure variations in different formations.

[0010] As a further embodiment of this paper, the process of establishing the CO2 injection parameter analysis model includes:

[0011] Obtain historical CO2 injection data for the target work area;

[0012] A dataset is generated based on the historical CO2 injection data and the corresponding formation parameter data.

[0013] The dataset is divided into a training set and a test set;

[0014] The elastic regression model is trained using the training set.

[0015] The test set is used to test whether the current elastic regression model meets the preset conditions;

[0016] If the current elastic regression model meets the preset conditions, then training is stopped, and the current elastic regression model is determined as the CO2 injection parameter analysis model.

[0017] As a further embodiment of this paper, the step of generating a dataset based on the historical CO2 injection data and the corresponding formation parameter data includes:

[0018] The formation parameter data corresponding to the historical CO2 injection data are preprocessed to obtain the overall formation parameter data.

[0019] Characteristic data of the overall stratigraphic parameter data were extracted using principal component analysis.

[0020] A data sample is obtained based on the characteristic data and the historical CO2 injection data;

[0021] Data labels are obtained based on the CO2 injection analysis results corresponding to the data samples;

[0022] A dataset is generated based on the data sample and the data label.

[0023] As a further embodiment of this article, the CO2 injection point includes:

[0024] The target work area is a stratum with a CO2 escape probability lower than a first predetermined probability.

[0025] As a further embodiment of this article, the CO2 injection parameters also include:

[0026] Simulated injection data corresponding to the minimum escape probability at each of the CO2 injection points.

[0027] As a further embodiment of this article, the CO2 injection parameters also include:

[0028] The range of simulated CO2 injection concentrations corresponding to injection points with an escape probability less than the second predetermined probability in each of the aforementioned CO2 injection points;

[0029] The range of CO2 simulated injection rates corresponding to each CO2 simulated injection concentration within each of the aforementioned CO2 simulated injection concentration ranges;

[0030] Wherein, the value of the second predetermined probability is less than the value of the first predetermined probability.

[0031] The second aspect of this paper provides a method for monitoring CO2 escape in geological storage, the method comprising:

[0032] During the process of injecting CO2 into the target work area, real-time CO2 injection data and formation parameter data of the target work area are obtained;

[0033] The real-time CO2 injection data and formation parameter data of the target work area are input into a pre-trained CO2 injection parameter analysis model to obtain the escape monitoring results during the CO2 injection process.

[0034] In a further embodiment of this article, the real-time CO2 injection data includes the real-time CO2 injection rate and the real-time CO2 injection concentration;

[0035] The formation parameter data includes variations in porosity, permeability, Poisson's ratio, formation temperature, and formation pressure in different formations.

[0036] As a further embodiment of this paper, the process of establishing the CO2 injection parameter analysis model includes:

[0037] Obtain historical CO2 injection data for the target work area;

[0038] A dataset is generated based on the historical CO2 injection data and the corresponding formation parameter data.

[0039] The dataset is divided into a training set and a test set;

[0040] The elastic regression model is trained using the training set.

[0041] The test set is used to test whether the current elastic regression model meets the preset conditions;

[0042] If the current elastic regression model meets the preset conditions, then training is stopped, and the current elastic regression model is determined as the CO2 injection parameter analysis model.

[0043] As a further embodiment of this paper, the step of generating a dataset based on the historical CO2 injection data and the corresponding formation parameter data includes:

[0044] The formation parameter data corresponding to the historical CO2 injection data are preprocessed to obtain the overall formation parameter data.

[0045] Characteristic data of the overall stratigraphic parameter data were extracted using principal component analysis.

[0046] A data sample is obtained based on the characteristic data and the historical CO2 injection data;

[0047] Data labels are obtained based on the CO2 injection analysis results corresponding to the data samples;

[0048] A dataset is generated based on the data sample and the data label.

[0049] As a further embodiment of this paper, the escape monitoring results during the CO2 injection process include:

[0050] The probability of CO2 escape during the CO2 injection process.

[0051] The third aspect of this paper provides a device for selecting CO2 injection parameters in geological storage, the device comprising:

[0052] The first data acquisition module is used to acquire CO2 simulation injection data and formation parameter data of the target work area;

[0053] The first analysis module is used to input the CO2 simulation injection data and formation parameter data of the target work area into a pre-trained CO2 injection parameter analysis model to obtain CO2 injection parameters, which include CO2 injection points.

[0054] The fourth aspect of this article provides a CO2 escape monitoring device in geological storage, the device comprising:

[0055] The second data acquisition module is used to acquire real-time CO2 injection data and formation parameter data of the target work area;

[0056] The second analysis module is used to input the real-time CO2 injection data and formation parameter data of the target work area into a pre-trained CO2 injection parameter analysis model to obtain the escape monitoring results during the CO2 injection process.

[0057] The fifth aspect of this document provides a computer device including a memory, a processor, and a computer program stored on the memory, wherein the computer program, when executed by the processor, performs instructions for the CO2 injection parameter selection and escape monitoring method in geological storage as described in any of the foregoing embodiments.

[0058] The sixth aspect of this document provides a computer storage medium storing a computer program, which, when run by a processor of a computer device, executes instructions for the CO2 injection parameter selection and escape monitoring method in geological sealing as described in any of the foregoing embodiments.

[0059] The CO2 injection parameter selection and escape monitoring methods and devices provided in this paper for geological storage can be used to select injection points and guide the selection of optimal injection data by analyzing simulated CO2 injection data and formation parameter data of the target area. By analyzing the optimal range of CO2 injection concentration and the corresponding optimal range of CO2 injection rate in the formation of the target area, analysis and reference are provided for the selection of CO2 injection data, reducing the risk of CO2 escape in geological storage. By analyzing real-time CO2 injection data and formation parameter data of the target area, escape monitoring of CO2 during the injection process can be achieved, reducing monitoring costs and improving monitoring accuracy.

[0060] To make the above and other objects, features and advantages of this document more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0061] To more clearly illustrate the technical solutions in the embodiments or prior art described herein, the accompanying drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this article. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 A flowchart illustrating the method for selecting CO2 injection parameters in geological storage as described in this embodiment is shown.

[0063] Figure 2 This document shows a flowchart illustrating the process of establishing the CO2 injection parameter analysis model in the CO2 injection parameter selection method of this embodiment.

[0064] Figure 3This paper shows a graph illustrating the variation of formation porosity with formation depth in the target work area of ​​the embodiment.

[0065] Figure 4 This paper shows a graph illustrating the variation of formation permeability with formation depth in the target work area of ​​the embodiment.

[0066] Figure 5 This paper shows a graph illustrating the variation of Poisson's ratio with formation depth in the target work area of ​​this embodiment.

[0067] Figure 6 This paper shows a graph illustrating the variation of formation temperature with formation depth in the target work area of ​​the embodiment.

[0068] Figure 7 This paper shows a graph illustrating the variation of formation pressure with formation depth in the target work area of ​​the embodiment.

[0069] Figure 8 This document illustrates a flowchart of the process for generating a CO2 injection parameter analysis model dataset in the CO2 injection parameter selection method described in this embodiment.

[0070] Figure 9 A flowchart of the CO2 escape monitoring method in geological storage as described in this embodiment is shown;

[0071] Figure 10 This document shows a flowchart illustrating the process of establishing the CO2 injection parameter analysis model in the CO2 escape monitoring method described in this embodiment.

[0072] Figure 11 This document illustrates a flowchart of the process for generating a CO2 injection parameter analysis model dataset in the CO2 escape monitoring method described in this embodiment.

[0073] Figure 12 This paper shows a structural diagram of the CO2 injection parameter selection device in the geological storage embodiment.

[0074] Figure 13 The structural diagram of the CO2 escape monitoring device in geological storage as described in this embodiment is shown.

[0075] Figure 14 A structural diagram of the computer device described in this embodiment is shown.

[0076] Explanation of symbols in the attached drawings:

[0077] 1210. First data acquisition module;

[0078] 1220. First Analysis Module;

[0079] 1310. Second data acquisition module;

[0080] 1320. Second Analysis Module;

[0081] 1402. Computer equipment;

[0082] 1404, Processor;

[0083] 1406. Memory;

[0084] 1408. Drive mechanism;

[0085] 1410. Input / Output Module;

[0086] 1412. Input devices;

[0087] 1414. Output devices;

[0088] 1416. Presentation equipment;

[0089] 1418. Graphical User Interface;

[0090] 1420. Network interface;

[0091] 1422. Communication link;

[0092] 1424. Communication bus. Detailed Implementation

[0093] The technical solutions in the embodiments described below will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments described herein, and not all of the embodiments. Based on the embodiments described herein, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this document.

[0094] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings herein are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0095] This specification provides the operational steps of the methods described in the embodiments or flowcharts, but based on conventional or non-inventive labor, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual system or device products, the methods shown in the embodiments or drawings can be executed sequentially or in parallel.

[0096] It should be noted that the acquisition, storage, use, and processing of data in the technical solutions of the embodiments of this specification all comply with the relevant provisions of national laws and regulations.

[0097] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0098] In one embodiment of this paper, a method for selecting CO2 injection parameters in geological storage is provided to solve the problem of intelligent selection of CO2 injection parameters in geological storage.

[0099] Specifically, such as Figure 1 As shown, the methods for selecting CO2 injection parameters in geological storage include:

[0100] Step 110: Obtain CO2 simulation injection data and formation parameter data for the target work area;

[0101] Step 120: Input the CO2 simulation injection data and formation parameter data of the target work area into the pre-trained CO2 injection parameter analysis model to obtain CO2 injection parameters, which include CO2 injection points.

[0102] Specifically, in step 110 above, the simulated injection data includes the simulated CO2 injection rate and the simulated CO2 injection concentration; the formation parameter data includes porosity, permeability, Poisson's ratio, formation temperature, and formation pressure variation data for different formations.

[0103] The target work area is the work area where the strata to be injected with CO2 are located. The target work area can be a work area with similar geology to the work area from which the dataset of the CO2 injection parameter analysis model is derived. The simulated injection data is the simulation data generated that is similar to the actual injection data. The simulated CO2 injection rate is the simulated injection rate generated that is similar to the actual CO2 injection rate. The simulated CO2 injection concentration is the simulated injection concentration generated that is similar to the actual CO2 injection concentration.

[0104] In step 120 above, the CO2 injection point in the CO2 injection parameters is the stratum in the target work area where the CO2 escape probability is less than the first predetermined probability. The first predetermined probability can be 10%, 5%, 3%, etc., and can be set by the user according to the actual situation. This article does not limit it. By setting the first predetermined probability, the stratum with a probability less than the first predetermined probability is taken as a reasonable stratum that can be selected during CO2 injection. The simulated injection data corresponding to this stratum is the optional reference injection data.

[0105] CO2 injection parameters can also include simulated injection data corresponding to the minimum escape probability at each CO2 injection point. By finding the simulated injection data corresponding to the minimum escape probability at each CO2 injection point, we can guide the selection of injection data during actual injection.

[0106] The CO2 injection parameters may also include the simulated CO2 injection concentrations corresponding to the strata in the target work area where the CO2 escape probability is less than the second predetermined probability. The second predetermined probability can be 5%, 3%, 2%, etc., and the second predetermined probability must be less than the first predetermined probability. It is set by the user according to the actual situation. This article does not limit it. By setting the second predetermined probability, the preferred simulated CO2 injection concentration in the CO2 injection point is found, and the actual CO2 injection concentration is guided by the preferred simulated CO2 injection concentration.

[0107] CO2 injection parameters may also include a range of simulated CO2 injection concentrations at each injection point, comprising preferred simulated CO2 injection concentrations. This range is defined as the optimal interval for simulated CO2 injection concentrations. For example, the preferred simulated CO2 injection concentrations for formation A are a1, a2, ..., a n (This is the result after sorting the simulated CO2 injection concentrations from smallest to largest), therefore the optimal range for the simulated CO2 injection concentration in formation A is (a1, a...). n If n=1, then formation A only has the optimal concentration reference; if n=0, then formation A has no preferred concentration reference. Other special cases are to be handled by the user and are not limited in this article. By providing the optimal range of CO2 simulated injection concentration, this article provides users with more reference space when implementing CO2 concentration injection selection.

[0108] CO2 injection parameters may also include a range of CO2 injection rates consisting of the CO2 injection rates corresponding to each CO2 simulated injection concentration within the range of CO2 simulated injection concentrations. This range of CO2 simulated injection rates is defined as the optimal interval for CO2 simulated injection rates. For example, the preferred CO2 simulated injection concentration a1 in formation A corresponds to CO2 simulated injection rates b1, b2, ..., b... m (This is the result after sorting the simulated CO2 injection concentrations from smallest to largest), then the optimal range of simulated CO2 injection rates corresponding to the preferred simulated CO2 injection concentration a1 in formation A is (b1, b...).m If m=1, then formation A only has the optimal rate reference. Other special cases are to be handled by the user and are not limited in this article. By providing the optimal range of CO2 injection rate, more reference space is provided for users when implementing CO2 rate injection selection.

[0109] This embodiment analyzes the CO2 simulation injection data and formation parameter data of the target work area, enabling the selection of injection points, guidance on optimal injection data, and identification of the optimal range of CO2 injection concentration and the corresponding optimal range of CO2 injection rate in the formation of the target work area. This provides users with analysis and reference of CO2 injection data, reducing the risk of CO2 escape during geological storage.

[0110] In one embodiment of this article, such as Figure 2 As shown, the process of establishing the CO2 injection parameter analysis model in the CO2 injection parameter selection method includes:

[0111] Step 210: Obtain historical CO2 injection data for the target work area;

[0112] Step 220: Generate a dataset based on the historical CO2 injection data and the formation parameter data corresponding to the historical CO2 injection data;

[0113] Step 230: Divide the dataset into a training set and a test set;

[0114] Step 240: Train the elastic regression model using the training set;

[0115] Step 250: Use the test set to test whether the current elastic regression model meets the preset conditions;

[0116] Step 260: If the current elastic regression model meets the preset conditions, then stop training and determine the current elastic regression model as the CO2 injection parameter analysis model.

[0117] Specifically, in step 210 above, the target work area is the work area where historical CO2 injection data and corresponding formation parameter data are to be collected. The historical CO2 injection data are the CO2 injection concentration and CO2 injection rate recorded during the historical CO2 injection process in the target work area. The non-dispersive infrared (NDIR) technology is used to detect whether CO2 escape occurs on the surface of the target work area. Two narrow-band filters are used to filter the light before the detector. One detector is used as the sensor and the other as a comparison. By comparing the two detection signals, the amount of infrared light absorbed by the gas being measured is obtained, thus obtaining the CO2 concentration. Generally, the ground CO2 concentration is around 400 ppm, while in large cities it is around 500 ppm. When CO2 is injected into the target work area, if the detector detects that the CO2 concentration exceeds 500 ppm, the infrared alarm will be triggered. After confirmation by the staff, it is recorded that CO2 escape has occurred in this CO2 geological storage experiment. At the same time, the CO2 injection concentration and CO2 injection rate are recorded. If the infrared alarm is not triggered in the CO2 geological storage experiment, it is recorded that no CO2 escape has occurred in this CO2 geological storage experiment after confirmation by the staff.

[0118] In step 220 above, the formation parameter data corresponding to the historical CO2 injection data includes porosity, permeability, Poisson's ratio, formation temperature, and formation pressure variation data of different strata in the target area. This data is acquired by installing distributed temperature and acoustic sensors in the formation, or by manual measurement. The measured formation parameter data of different strata are saved and imported into a table for display. The results are shown below. Figures 3-7 As shown, Figure 3 This shows the variation of formation porosity with formation depth in the target work area. Figure 4 The data shows the variation of formation permeability with formation depth in the target work area. Figure 5 The data shows the variation of Poisson's ratio with formation depth in the target work area. Figure 6 The data shows the variation of formation temperature with formation depth in the target work area. Figure 7 This shows the variation of formation pressure in the target work area with formation depth.

[0119] In step 230 above, the dataset is divided into 80% training set and 20% test set. The division method can also be 90% training set and 10% test set, etc., which is not limited in this paper.

[0120] In step 240 above, the pre-defined training set is used to train the elastic regression model. The parameter selection process for the elastic regression model is as follows:

[0121] First, solve for the optimal parameter regression coefficients:

[0122]

[0123] θ is the optimal parameter regression coefficient to be solved, l(θ) is the loss function of the elastic regression model, and x i y is the feature vector of the i-th sample. i α is the target quantity of the i-th sample, α1 is the regularization strength parameter that controls the overall weight of the regularization term, γ is the mixing ratio parameter of L1 and L2 regularization, when γ = 0 it is ridge regression (L2 regularization), when γ = 1 it is Lasso regression (L1 regularization), and the median value is elastic net regression.

[0124] Secondly, find the optimal combination of hyperparameters:

[0125] Define a set of candidate hyperparameter values ​​(such as different combinations of α1 and γ), evaluate the performance of each set of hyperparameters using K-fold cross-validation, and select the best-performing parameter combination. The calculation method is as follows:

[0126] Let the dataset be D, containing N samples, D = {(x1,y1),(x2,y2),…,(x... N ,y N Divide D into K mutually exclusive subsets, denoted as D1, D2, D3, D4, D5, D6, D7, D8, D9, D1, D2 ...9, D1, D2, D9, D1, D2, D9, D1, D2, D9, D1, D K ,Right now and

[0127] For each fold K, the training set test set The model is trained on the training set to obtain model parameters.

[0128] Calculating average performance: This model uses the mean squared error for performance evaluation, i.e.

[0129] in,

[0130] In K-fold cross-validation, multiple hyperparameter combinations are evaluated using the method described above, and the best-performing hyperparameter combination λ is selected. * =argmin λ∈Λ AverageMSE(λ),

[0131] Where Λ represents that the hyperparameter combination contains multiple sets of candidate hyperparameter values, and for each set of hyperparameters λ∈Λ;

[0132] The training set data and the optimal hyperparameter combination are input into the elastic regression model for training.

[0133] In step 250 above, the preset conditions can be evaluation metrics for classification models such as accuracy threshold, recall threshold, and precision threshold. This paper does not limit these parameters. When the elastic regression model meets the preset conditions, training will stop.

[0134] This implementation generates diverse datasets by acquiring historical CO2 injection data and corresponding formation parameter data from different strata in the target work area. These datasets serve as the training basis for the elastic regression model. The elastic regression model under training is evaluated using classification model evaluation metrics, ultimately generating the CO2 injection parameter analysis model required in this paper.

[0135] In one embodiment of this article, such as Figure 8 As shown, the CO2 injection parameter selection method generates a dataset based on the historical CO2 injection data and the corresponding formation parameter data, including:

[0136] Step 810: Preprocess the formation parameter data corresponding to the historical CO2 injection data to obtain the overall formation parameter data;

[0137] Step 820: Extract feature data from the overall stratigraphic parameter data through principal component analysis;

[0138] Step 830: Obtain a data sample based on the feature data and the historical CO2 injection data;

[0139] Step 840: Obtain data labels based on the CO2 injection analysis results corresponding to the data samples;

[0140] Step 850: Generate a dataset based on the data sample and the data label.

[0141] Specifically, in step 810 above, the process of processing the formation parameter data includes:

[0142] First, the standard deviation of the overall formation parameter data (all acquired formation parameter data) is calculated using the Bessel formula. The formula is as follows:

[0143]

[0144] Where, σ s The standard deviation of the overall stratigraphic parameter data, x i This represents formation parameter data, where n represents the number of sample data.

[0145] Secondly, the Laida criterion is used to clean and remove outliers from the overall stratigraphic parameter data. i >3σ s If the data is considered outlier, it should be removed.

[0146] Then, the Kriging space interpolation method is used to predict the overall stratigraphic parameter data after outlier removal. Interpolation is performed on the five stratigraphic parameter data categories to obtain the overall stratigraphic parameter data.

[0147] In step 820 above, feature data of the overall stratigraphic parameter data is extracted through principal component analysis. The overall stratigraphic parameter data is then dimensionality-reduced, retaining principal components with high contribution, thereby reducing the amount of data required for model training and identification. The process of extracting feature data through principal component analysis is as follows:

[0148] Taking 20 samples as an example, there are 5 indicators for the formation parameter data, thus a 20×5 sample matrix can be formed.

[0149] First, standardize the sample matrix x and calculate the mean column by column: Obtain the standard deviation: Standardized data:

[0150] The original sample matrix has been standardized.

[0151]

[0152] Next, calculate the covariance matrix of the standardized sample differences:

[0153] in

[0154] Finally, the eigenvalues ​​and eigenvectors of the covariance matrix R are solved to obtain the principal components of the overall stratigraphic parameter data, and the contribution rate and cumulative contribution rate of each principal component are calculated. The contribution rate of the i-th principal component is... The first, second, ..., m-th (m≤5) principal components corresponding to the feature values ​​with a cumulative contribution rate exceeding 80% are taken as stratigraphic feature data, where the i-th principal component is:

[0155] F i =a 1i X1+a 2i X2+a 3i X3+a 4i X4+a 5i X5

[0156] The larger the coefficient in front of the principal component index, the greater the influence of the index on the principal component.

[0157] In step 830 above, the feature data of each stratum and the historical CO2 injection data corresponding to the feature data of each stratum are merged to form a data sample for the elastic regression model dataset.

[0158] In step 840 above, the CO2 injection analysis result corresponding to the data sample is the CO2 escape situation recorded during the CO2 injection process after confirmation by the staff in step 210. If escape occurs, the data label is 1, otherwise it is 0.

[0159] This implementation processes the overall stratigraphic parameter data to obtain the overall stratigraphic parameter data, saving measurement costs. Principal component analysis is used to reduce the dimensionality of the overall stratigraphic parameter data, retaining the principal components with high contribution, thus obtaining the characteristic data of the overall stratigraphic parameter data. This improves the accuracy and computational efficiency of the elastic regression model and reduces the operating cost of the elastic regression model.

[0160] In some embodiments of this paper, a method for monitoring CO2 escape in geological storage is also provided to solve the problem of monitoring CO2 escape during the CO2 injection process in geological storage.

[0161] Specifically, such as Figure 9 As shown, CO2 escape monitoring methods in geological storage include:

[0162] Step 910: During the process of injecting CO2 into the target work area, acquire real-time CO2 injection data and formation parameter data of the target work area;

[0163] Step 920: Input the real-time CO2 injection data and formation parameter data of the target work area into the pre-trained CO2 injection parameter analysis model to obtain the escape monitoring results during the CO2 injection process.

[0164] Specifically, in step 910 above, the real-time CO2 injection data includes the real-time CO2 injection rate and the real-time CO2 injection concentration; the formation parameter data includes porosity, permeability, Poisson's ratio, formation temperature, and formation pressure variation data for different formations.

[0165] The target work area is the work area where the strata to be injected with CO2 are located. The target work area can be a work area with similar geology to the work area from which the dataset of the CO2 injection parameter analysis model is generated. The real-time injection data is the data during the injection process. The real-time CO2 injection rate is the rate at which CO2 is being injected. The real-time CO2 injection concentration is the concentration at which CO2 is being injected.

[0166] In step 920 above, the escape monitoring results during the CO2 injection process include:

[0167] The probability of CO2 escape during CO2 injection.

[0168] Users can determine whether CO2 has escaped during the injection process based on the CO2 escape probability in the escape monitoring results. Multiple escape monitoring results can be combined to reduce the probability of incorrect judgment. When it is confirmed that CO2 is suspected to be escaping during the injection process, actual measurement is performed to finally confirm the CO2 escape result.

[0169] This embodiment analyzes real-time CO2 injection data and formation parameter data of the target work area, enabling escape monitoring during the CO2 injection process. At the same time, it eliminates the need to deploy a large number of monitoring instruments, thus reducing monitoring costs.

[0170] In one embodiment of this article, such as Figure 10 As shown, the process of establishing the CO2 injection parameter analysis model in the CO2 escape monitoring method includes:

[0171] Step 1010: Obtain historical CO2 injection data for the target work area;

[0172] Step 1020: Generate a dataset based on the historical CO2 injection data and the formation parameter data corresponding to the historical CO2 injection data;

[0173] Step 1030: Divide the dataset into a training set and a test set;

[0174] Step 1040: Train the elastic regression model using the training set;

[0175] Step 1050: Use the test set to test whether the current elastic regression model meets the preset conditions;

[0176] Step 1060: If the current elastic regression model meets the preset conditions, then stop training and determine the current elastic regression model as the CO2 injection parameter analysis model.

[0177] Specifically, in step 1010 above, the target work area is the work area where historical CO2 injection data and corresponding formation parameter data are to be collected. The historical CO2 injection data are the CO2 injection concentration and CO2 injection rate recorded during the historical CO2 injection process in the target work area. The non-dispersive infrared (NDIR) technology is used to detect whether CO2 escape occurs on the surface of the target work area. Two narrow-band filters are used to filter the light before the detector. One detector is used as the sensor and the other as the comparison. By comparing the two detection signals, the amount of infrared light absorbed by the gas being measured is obtained, thus obtaining the CO2 concentration. Generally, the ground CO2 concentration is around 400 ppm, while in large cities it is around 500 ppm. When CO2 is injected into the target work area, if the detector detects that the CO2 concentration exceeds 500 ppm, the infrared alarm will be triggered. After confirmation by the staff, it is recorded that CO2 escape has occurred in this CO2 geological storage experiment. At the same time, the CO2 injection concentration and CO2 injection rate are recorded. If the infrared alarm is not triggered in the CO2 geological storage experiment, it is recorded that no CO2 escape has occurred in this CO2 geological storage experiment after confirmation by the staff.

[0178] In step 1020 above, the formation parameter data corresponding to the historical CO2 injection data includes porosity, permeability, Poisson's ratio, formation temperature, and formation pressure variation data of different strata in the target area. This data is acquired by installing distributed temperature and acoustic sensors in the formation, or by manual measurement. The measured formation parameter data of different strata are saved and imported into a table for display. The results are shown below. Figures 3-7 As shown, Figure 3 This shows the variation of formation porosity with formation depth in the target work area. Figure 4 The data shows the variation of formation permeability with formation depth in the target work area. Figure 5 The data shows the variation of Poisson's ratio with formation depth in the target work area. Figure 6 The data shows the variation of formation temperature with formation depth in the target work area. Figure 7 This shows the variation of formation pressure in the target work area with formation depth.

[0179] In step 1030 above, the dataset is divided into 80% training set and 20% test set. The division method can also be 90% training set and 10% test set, etc., which is not limited in this paper.

[0180] In step 1040 above, the pre-defined training set is used to train the elastic regression model. The parameter selection process for the elastic regression model is as follows:

[0181] First, solve for the optimal parameter regression coefficients:

[0182]

[0183] θ is the optimal parameter regression coefficient to be solved, l(θ) is the loss function of the elastic regression model, and x i y is the feature vector of the i-th sample. i α is the target quantity of the i-th sample, α1 is the regularization strength parameter that controls the overall weight of the regularization term, γ is the mixing ratio parameter of L1 and L2 regularization, when γ = 0 it is ridge regression (L2 regularization), when γ = 1 it is Lasso regression (L1 regularization), and the median value is elastic net regression.

[0184] Secondly, find the optimal combination of hyperparameters:

[0185] Define a set of candidate hyperparameter values ​​(such as different combinations of α1 and γ), evaluate the performance of each set of hyperparameters using K-fold cross-validation, and select the best-performing parameter combination. The calculation method is as follows:

[0186] Let the dataset be D, containing N samples, D = {(x1,y1),(x2,y2),…,(x... N ,y N Divide D into K mutually exclusive subsets, denoted as D1, D2, D3, D4, D5, D6, D7, D8, D9, D1, D2 ...9, D1, D2, D9, D1, D2, D9, D1, D2, D9, D1, D K ,Right now and

[0187] For each fold K, the training set test set The model is trained on the training set to obtain model parameters.

[0188] Calculating average performance: This model uses the mean squared error for performance evaluation, i.e.

[0189] in,

[0190] In K-fold cross-validation, multiple hyperparameter combinations are evaluated using the method described above, and the best-performing hyperparameter combination λ is selected. * =argmin λ∈Λ AverageMSE(λ),

[0191] Where Λ represents that the hyperparameter combination contains multiple sets of candidate hyperparameter values, and for each set of hyperparameters λ∈Λ;

[0192] The training set data and the optimal hyperparameter combination are input into the elastic regression model for training.

[0193] In step 1050 above, the preset conditions can be evaluation metrics for classification models such as accuracy threshold, recall threshold, and precision threshold. This paper does not limit these parameters. When the elastic regression model meets the preset conditions, training will stop.

[0194] This implementation generates diverse datasets by acquiring historical CO2 injection data and corresponding formation parameter data from different strata in the target work area. These datasets serve as the training basis for the elastic regression model. The elastic regression model under training is evaluated using classification model evaluation metrics, ultimately generating the CO2 injection parameter analysis model required in this paper.

[0195] In one embodiment of this article, such as Figure 11 As shown, the CO2 escape monitoring method generates a dataset based on the historical CO2 injection data and the corresponding formation parameter data, including:

[0196] Step 1110: Preprocess the formation parameter data corresponding to the historical CO2 injection data to obtain the overall formation parameter data;

[0197] Step 1120: Extract feature data from the overall stratigraphic parameter data through principal component analysis;

[0198] Step 1130: Obtain a data sample based on the feature data and the historical CO2 injection data;

[0199] Step 1140: Obtain data labels based on the CO2 injection analysis results corresponding to the data samples;

[0200] Step 1150: Generate a dataset based on the data sample and the data label.

[0201] Specifically, in step 1110 above, the process of processing the formation parameter data includes:

[0202] First, the standard deviation of the overall formation parameter data (all acquired formation parameter data) is calculated using the Bessel formula. The formula is as follows:

[0203]

[0204] Where, σ s The standard deviation of the overall stratigraphic parameter data, x i This represents formation parameter data, where n represents the number of sample data.

[0205] Secondly, the Laida criterion is used to clean and remove outliers from the overall stratigraphic parameter data. i >3σ s If the data is considered outlier, it should be removed.

[0206] Then, the Kriging space interpolation method is used to predict the overall stratigraphic parameter data after outlier removal. Interpolation is performed on the five stratigraphic parameter data categories to obtain the overall stratigraphic parameter data.

[0207] In step 1120 above, feature data of the overall stratigraphic parameter data is extracted through principal component analysis. The overall stratigraphic parameter data is then dimensionality-reduced, retaining principal components with high contribution, thereby reducing the amount of data required for model training and identification. The process of extracting feature data through principal component analysis is as follows:

[0208] Taking 20 stratigraphic parameter data samples as an example, there are 5 indices in the stratigraphic parameter data, therefore, a 20×5 sample matrix can be formed.

[0209] First, standardize the sample matrix x and calculate the mean column by column: Obtain the standard deviation: Standardized data:

[0210] The original sample matrix has been standardized.

[0211]

[0212] Next, calculate the covariance matrix of the standardized sample differences:

[0213] in

[0214] Finally, the eigenvalues ​​and eigenvectors of the covariance matrix R are solved to obtain the principal components of the overall stratigraphic parameter data, and the contribution rate and cumulative contribution rate of each principal component are calculated. The contribution rate of the i-th principal component is... The first, second, ..., m-th (m≤5) principal components corresponding to the feature values ​​with a cumulative contribution rate exceeding 80% are taken as stratigraphic feature data, where the i-th principal component is:

[0215] F i =a 1i X1+a 2i X2+a 3i X3+a 4i X4+a 5i X5

[0216] The larger the coefficient in front of the principal component index, the greater the influence of the index on the principal component.

[0217] In step 1130 above, the feature data of each stratum and the historical CO2 injection data corresponding to the feature data of each stratum are merged to form a data sample for the elastic regression model dataset.

[0218] In step 1140 above, the CO2 injection analysis result corresponding to the data sample is the CO2 escape situation recorded during the CO2 injection process after confirmation by the staff in step 910. If escape occurs, the data label is 1, otherwise it is 0.

[0219] This implementation processes the overall stratigraphic parameter data to obtain the overall stratigraphic parameter data, saving measurement costs. Principal component analysis is used to reduce the dimensionality of the overall stratigraphic parameter data, retaining the principal components with high contribution, thus obtaining the characteristic data of the overall stratigraphic parameter data. This improves the accuracy and computational efficiency of the elastic regression model and reduces the operating cost of the elastic regression model.

[0220] Based on the same inventive concept, this paper also provides a CO2 injection parameter selection device for geological storage, as described in the following embodiments. Since the principle of the CO2 injection parameter selection device for geological storage is similar to the method for selecting CO2 injection parameters in geological storage, the implementation of the CO2 injection parameter selection device for geological storage can refer to the method for selecting CO2 injection parameters in geological storage; repeated details will not be elaborated further.

[0221] Specifically, such as Figure 12 As shown, the CO2 injection parameter selection device in geological storage includes:

[0222] The first data acquisition module 1210 is used to acquire CO2 simulation injection data and formation parameter data of the target work area;

[0223] The first analysis module 1220 is used to input the CO2 simulation injection data and formation parameter data of the target work area into a pre-trained CO2 injection parameter analysis model to obtain CO2 injection parameters, the CO2 injection parameters including CO2 injection points.

[0224] This embodiment analyzes the CO2 simulation injection data and formation parameter data of the target work area, enabling intelligent selection of injection points, guidance on optimal injection data, and identification of the optimal range of CO2 injection concentration and the corresponding optimal range of CO2 injection rate in the formation of the target work area. This provides users with more options and reduces the risk of CO2 escape during geological storage.

[0225] Based on the same inventive concept, this paper also provides a CO2 escape monitoring device in geological storage, as described in the following embodiments. Since the principle of the CO2 escape monitoring device in geological storage is similar to that of the CO2 escape monitoring method in geological storage, the implementation of the CO2 escape monitoring device in geological storage can refer to the CO2 escape monitoring method in geological storage; repeated details will not be elaborated further.

[0226] Specifically, such asFigure 13 As shown, the CO2 escape monitoring device in geological storage includes:

[0227] The second data acquisition module 1310 is used to acquire real-time CO2 injection data and formation parameter data of the target work area;

[0228] The second analysis module 1320 is used to input the real-time CO2 injection data and formation parameter data of the target work area into a pre-trained CO2 injection parameter analysis model to obtain the escape monitoring results during the CO2 injection process.

[0229] This embodiment analyzes real-time CO2 injection data and formation parameter data of the target work area, enabling escape monitoring during the CO2 injection process. At the same time, it eliminates the need to deploy a large number of monitoring instruments, thus reducing monitoring costs.

[0230] This paper presents a method for selecting CO2 injection parameters, a method for monitoring CO2 escape, and a device for geological sealing. By analyzing simulated CO2 injection data and formation parameter data of the target work area, it determines whether the strata meet predetermined conditions. If so, the stratum is the CO2 injection point for the target work area. The paper further analyzes the simulated CO2 injection data and formation parameter data of the target work area to determine the optimal simulated injection data for each CO2 injection point, and selects the actual injection data based on the guidance of the optimal simulated injection data. Finally, the paper analyzes the simulated CO2 injection data and formation parameter data of the target work area to determine the optimal CO2 injection concentration range and the corresponding CO2 concentration range in each stratum that meets the conditions. The optimal range for O2 injection rate; by analyzing real-time CO2 injection data and formation parameter data of the target work area, this paper determines whether CO2 escapes during the injection process; by analyzing simulated CO2 injection data and formation parameter data of the target work area, this paper can achieve intelligent selection of injection points, guidance of optimal injection data, and identification of the optimal range of CO2 injection concentration and the corresponding optimal range of CO2 injection rate in the formation of the target work area, thereby reducing the risk of CO2 escape in geological storage; by analyzing real-time CO2 injection data and formation parameter data of the target work area, this paper can achieve monitoring of CO2 escape during the injection process, reducing monitoring costs and improving monitoring accuracy.

[0231] In one embodiment of this document, a computer device is also provided for implementing the methods described in any of the above embodiments, such as... Figure 14The diagram illustrates the structure of a node in an embodiment of this paper. This embodiment describes the structure of nodes in the sidechain network and the main chain network, which may include relay nodes, decision-maker nodes, or other functional nodes. In this embodiment, the node is referred to as a computer device. The computer device 1402 may include one or more processors 1404, such as one or more central processing units (CPUs), each of which can implement one or more hardware threads. The computer device 1402 may also include any type of memory 1406 for storing information of any kind, such as code, settings, data, etc. Without limitation, for example, the memory 1406 may include any combination of one or more of the following: any type of RAM, any type of ROM, flash memory, hard disk, optical disk, etc. More generally, any memory can use any technology to store information. Furthermore, any memory can provide volatile or non-volatile retention of information. Furthermore, any memory can represent a fixed or removable component of the computer device 1402. In one case, when the processor 1404 executes associated instructions stored in any memory or combination of memories, the computer device 1402 can perform any operation of the associated instructions. The computer device 1402 also includes one or more drive mechanisms 1408 for interacting with any memory, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.

[0232] Computer device 1402 may also include an input / output module 1410 (I / O) for receiving various inputs (via input device 1412) and providing various outputs (via output device 1414). A specific output mechanism may include a presentation device 1416 and an associated graphical user interface (GUI) 1418. In other embodiments, the input / output module 1410 (I / O), input device 1412, and output device 1414 may be omitted, and the device may function solely as a computer device within a network. Computer device 1402 may also include one or more network interfaces 1420 for exchanging data with other devices via one or more communication links 1422. One or more communication buses 1424 couple the components described above together.

[0233] Communication link 1422 can be implemented in any way, such as via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, or any combination thereof. Communication link 1422 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0234] Corresponding to Figure 1 , Figure 2 , Figures 8-11In addition to the methods described above, this embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the above-described methods.

[0235] This embodiment also provides a computer-readable instruction, wherein when a processor executes the instruction, the program therein causes the processor to perform the following: Figure 1 , Figure 2 , Figures 8-11 The method shown.

[0236] It should be understood that in the various embodiments of this document, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this document.

[0237] It should also be understood that, in the embodiments herein, the term "and / or" is merely a description of the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following associated objects have an "or" relationship.

[0238] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this document.

[0239] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0240] In the embodiments provided herein, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.

[0241] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described herein, depending on actual needs.

[0242] Furthermore, the functional units in the various embodiments of this document can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0243] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this paper, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this paper. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0244] This document uses specific embodiments to illustrate the principles and implementation methods of this document. The descriptions of the embodiments above are only for the purpose of helping to understand the methods and core ideas of this document. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this document. Therefore, the content of this specification should not be construed as a limitation of this document.

Claims

1. A method for selecting CO2 injection parameters in geological storage, characterized in that, The method includes: Obtain CO2 simulation injection data and formation parameter data for the target work area; The CO2 simulation injection data and formation parameter data of the target work area are input into the pre-trained CO2 injection parameter analysis model to obtain CO2 injection parameters, which include CO2 injection points.

2. The method as described in claim 1, characterized in that, The CO2 simulated injection data includes the CO2 simulated injection rate and the CO2 simulated injection concentration; The formation parameter data includes data on porosity, permeability, Poisson's ratio, formation temperature, and formation pressure variations in different formations.

3. The method as described in claim 1, characterized in that, The process of establishing the CO2 injection parameter analysis model includes: Obtain historical CO2 injection data for the target work area; A dataset is generated based on the historical CO2 injection data and the corresponding formation parameter data. The dataset is divided into a training set and a test set; The elastic regression model is trained using the training set. The test set is used to test whether the current elastic regression model meets the preset conditions; If the current elastic regression model meets the preset conditions, then training is stopped, and the current elastic regression model is determined as the CO2 injection parameter analysis model.

4. The method as described in claim 3, characterized in that, The process of generating a dataset based on the historical CO2 injection data and the corresponding formation parameter data includes: The formation parameter data corresponding to the historical CO2 injection data are preprocessed to obtain the overall formation parameter data. Characteristic data of the overall stratigraphic parameter data were extracted using principal component analysis. A data sample is obtained based on the characteristic data and the historical CO2 injection data; Data labels are obtained based on the CO2 injection analysis results corresponding to the data samples; A dataset is generated based on the data sample and the data label.

5. The method as described in claim 1, characterized in that, The CO2 injection point includes: The target work area is a stratum with a CO2 escape probability lower than a first predetermined probability.

6. The method as described in claim 5, characterized in that, The CO2 injection parameters also include: Simulated injection data corresponding to the minimum escape probability at each of the CO2 injection points.

7. The method as described in claim 5, characterized in that, The CO2 injection parameters also include: The range of simulated CO2 injection concentrations corresponding to injection points with an escape probability less than the second predetermined probability in each of the aforementioned CO2 injection points; The range of CO2 simulated injection rates corresponding to each CO2 simulated injection concentration within each of the aforementioned CO2 simulated injection concentration ranges; Wherein, the value of the second predetermined probability is less than the value of the first predetermined probability.

8. A method for monitoring CO2 escape in geological storage, characterized in that, The method includes: During the process of injecting CO2 into the target work area, real-time CO2 injection data and formation parameter data of the target work area are obtained; The real-time CO2 injection data and formation parameter data of the target work area are input into a pre-trained CO2 injection parameter analysis model to obtain the escape monitoring results during the CO2 injection process.

9. The method as described in claim 8, characterized in that, The real-time CO2 injection data includes the real-time CO2 injection rate and the real-time CO2 injection concentration. The formation parameter data includes variations in porosity, permeability, Poisson's ratio, formation temperature, and formation pressure in different formations.

10. The method as described in claim 8, characterized in that, The process of establishing the CO2 injection parameter analysis model includes: Obtain historical CO2 injection data for the target work area; A dataset is generated based on the historical CO2 injection data and the corresponding formation parameter data. The dataset is divided into a training set and a test set; The elastic regression model is trained using the training set. The test set is used to test whether the current elastic regression model meets the preset conditions; If the current elastic regression model meets the preset conditions, then training is stopped, and the current elastic regression model is determined as the CO2 injection parameter analysis model.

11. The method as described in claim 10, characterized in that, The process of generating a dataset based on the historical CO2 injection data and the corresponding formation parameter data includes: The formation parameter data corresponding to the historical CO2 injection data are preprocessed to obtain the overall formation parameter data. Characteristic data of the overall stratigraphic parameter data were extracted using principal component analysis. A data sample is obtained based on the characteristic data and the historical CO2 injection data; Data labels are obtained based on the CO2 injection analysis results corresponding to the data samples; A dataset is generated based on the data sample and the data label.

12. The method as described in claim 8, characterized in that, The escape monitoring results during the CO2 injection process include: The probability of CO2 escape during the CO2 injection process.

13. A device for selecting CO2 injection parameters in geological storage, characterized in that, The device includes: The first data acquisition module is used to acquire CO2 simulation injection data and formation parameter data of the target work area; The first analysis module is used to input the CO2 simulation injection data and formation parameter data of the target work area into a pre-trained CO2 injection parameter analysis model to obtain CO2 injection parameters, which include CO2 injection points.

14. A CO2 escape monitoring device in geological storage, characterized in that, The device includes: The second data acquisition module is used to acquire real-time CO2 injection data and formation parameter data of the target work area; The second analysis module is used to input the real-time CO2 injection data and formation parameter data of the target work area into a pre-trained CO2 injection parameter analysis model to obtain the escape monitoring results during the CO2 injection process.

15. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 12.

16. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor of a computer device, it implements the method according to any one of claims 1 to 12.

Images