CO based on deep learning parameterized strategy 2 Inverse simulation method for geological storage

Abstract

The present invention discloses a CO2 geological sequestration inversion simulation method based on a deep learning parameterization strategy. The deep learning method is used to parametrically reduce the dimensionality and characterize the complex permeability field of the CO2 geological sequestration reservoir. The distribution characteristics of the heterogeneous permeability field are characterized by a set of low-dimensional normal distribution latent vectors, reducing the number of parameters to be estimated in the CO2 geological sequestration numerical simulation. By combining the parameterization method based on deep learning with the multiple data assimilation iterative ensemble smoothing algorithm, only the low-dimensional latent vectors need to be cyclically updated during inversion, so as to efficiently estimate the heterogeneous permeability field of the complex reservoir, and further improve the simulation and prediction accuracy of the numerical model for the CO2 geological sequestration process. By effectively estimating the complex permeability distribution of the CO2 geological sequestration reservoir, the invention improves the simulation and characterization accuracy of the CO2 migration and transformation process, and can provide technical support for the optimized operation and risk management of CO2 geological sequestration projects.

Description

Technical Field

[0001] The present invention relates to the cross-technical field of hydrogeological numerical simulation, carbon emission reduction and deep learning, and specifically to a CO2 emission reduction method based on deep learning parameterization strategy. 2 Inverse simulation methods for geological storage. Background Art

[0002] CO 2 Geological storage (GCS) is a method of storing CO 2 The technical means of injecting CO2 into deep aquifers for permanent storage can effectively reduce greenhouse gas emissions and achieve the goal of "carbon neutrality". 2 It exists in the supercritical phase in the reservoir, forming CO 2 -Water multiphase flow system. Due to CO 2 The geological storage process usually involves a spatial scale of hundreds of kilometers and a time scale of hundreds of years. The deep geological environment is often invisible, so numerical simulation methods have become an important method for studying CO 2 An important tool for tracking the migration and return of CO2 in the formation after injection. A reliable numerical model needs to accurately characterize the hydrogeological parameters of the reservoir (such as permeability, etc.), but due to the heterogeneity of the medium itself and the lack of observation data, it is usually not feasible to directly measure the hydrogeological parameters of the reservoir. Therefore, the unknown parameter field is often estimated by solving the inversion problem, that is, given the historical observation data of the relevant state variables, the hydrogeological parameter values ​​are continuously adjusted through the inversion algorithm to reduce the fitting error between the numerical model simulation value and the historical observation data, and reproduce the actual CO2. 2 Therefore, the inversion simulation provides an important decision-making reference for the optimization of GCS project operations and risk management.

[0003] However, commonly used set-based inversion algorithms usually assume that the hydrogeological parameter field to be estimated (such as the permeability field) is Gaussian distributed. However, many actual reservoirs usually contain multiple sedimentary facies with different properties, and their hydrogeological parameters show significant non-Gaussian distribution characteristics, which makes the commonly used set-based inversion algorithms difficult to apply. In addition, a large number of parameters to be estimated will bring a huge computational burden to the inversion calculation. These challenges still have many limitations in the practical application of set-based inversion algorithms. In recent years, the deep learning parameterization (DLP) method has received increasing attention in dealing with non-Gaussian parameter inversion. Combining it with the traditional set-based inversion algorithm is a solution worth exploring. It is also worth noting that due to limited training data, the output results of the deep learning parameterization method itself also have certain uncertainties, and the commonly used set-based inversion algorithm often ignores this uncertainty, which leads to unreliable inversion simulation results. Summary of the invention

[0004] The purpose of the present invention is to provide a CO based on deep learning parameterization strategy 2 The geological storage inversion simulation method first constructs a deep learning parameterized model to characterize the non-Gaussian distribution characteristics of the reservoir permeability field with a set of low-dimensional normally distributed latent vectors, while greatly reducing the number of parameters to be estimated. Then, it is combined with a multiple data assimilation iterative ensemble smoothing algorithm to construct a CO 2 The geological storage coupled inversion simulation framework only needs to cyclically update the low-dimensional latent vector during inversion to efficiently estimate the complex heterogeneous permeability field of the reservoir, thus improving the numerical model's accuracy for CO 2 The simulation prediction accuracy of the migration and transformation process. The error term of the standard deviation of the output results of the deep learning parameterized model is also incorporated into the multiple data assimilation iterative ensemble smoothing algorithm, which further improves the accuracy of the inversion simulation.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] CO based on deep learning parameterized strategy 2 The geological storage inversion simulation method comprises the following steps:

[0007] Obtain geological lithology drilling data and hydrogeological data of the storage target reservoir in the study area, and collect CO2 during the storage process at the drilling site. 2 Historical observations of saturation and reservoir pressure;

[0008] Generate a heterogeneous reservoir permeability field sample using geostatistical software based on the geological lithology drilling data and the hydrogeological data;

[0009] The CO2-based lithology drilling data and the hydrogeology data were constructed using multiphase flow numerical simulation software. 2 Storage forward numerical model;

[0010] Training a deep learning parameterized model based on the heterogeneous reservoir permeability field samples, and randomly generating an initial sample set of low-dimensional standard normal distribution latent vectors;

[0011] The deep learning parameterized model, the CO 2 The forward numerical model for storage and the multiple data assimilation iterative ensemble smoothing algorithm jointly construct the CO 2 A coupled inversion modeling framework for geology and storage;

[0012] Based on the initial sample set of low-dimensional standard normal distribution latent vectors, CO 2 The geological storage coupled inversion simulation framework obtains the final low-dimensional latent vector sample set;

[0013] The final low-dimensional latent vector sample set is input into the trained deep learning parameterized model to obtain the corresponding heterogeneous reservoir permeability field posterior sample data set; the heterogeneous reservoir permeability field posterior sample data set is input into the CO 2 Storage forward numerical model to obtain the corresponding CO 2 A dataset of a posteriori samples of simulated values ​​of saturation and reservoir pressure.

[0014] Among them, the geostatistical software can be TProGS software. TProGS (Transition Probability Geostatistical Software) is a set of FORTRAN computer programs. It uses the transition probability / Markov chain method to perform geostatistical analysis and simulation on the spatial distribution of geological parameters such as geological units and lithofacies based on known geological drilling data.

[0015] The multiphase flow numerical simulation software can be selected from TOUGH2 (Transport Of Unsaturated Groundwater and Heat) / ECO2N software. TOUGH2 / ECO2N software is the fluid property module of TOUGH2 simulator, which is specially designed for CO2 in saline aquifers. 2 Designed for geological storage projects, it can 2 O-NaCl-CO 2 The thermodynamic and thermophysical properties of the mixture can be fully and accurately described.

[0016] Preferably, the deep learning parameterized model construction step includes:

[0017] Randomly dividing the heterogeneous reservoir permeability field samples into training samples and test samples;

[0018] During model training, the deep learning parameterized model uses the training samples as input and generates a reconstructed heterogeneous reservoir permeability field from a decoder of the deep learning parameterized model;

[0019] During model testing, the coefficient of determination between the reconstructed heterogeneous reservoir permeability field generated by the decoder of the deep learning parameterized model trained with the test sample and the training sample is compared. R 2 Precision, judging the coefficient of determination R 2 Whether the preset accuracy requirements are met, if so, it indicates that the deep learning parameterized model training is completed, otherwise continue to use the training samples to optimize and adjust the model parameters until the trained deep learning parameterized model meets the preset accuracy requirements.

[0020] The heterogeneous permeability field is a set of permeability values ​​that change with the spatial coordinates in the geological statistical sense at various locations in the reservoir. According to literature research, the heterogeneous permeability field is found to be the factor that affects CO 2 The most important influencing factor indicator of plume migration and transformation.

[0021] The coefficient of determination R 2 The preset accuracy requirement is the coefficient of determination of the deep learning parameterized model based on the test sample R 2 ≥ α , α is the default value.

[0022] Preferably, the coefficient of determination R 2 :

[0023] ;

[0024] In the formula, N is the number of test samples, Represents the test sample, The reconstructed heterogeneous reservoir permeability field generated by the decoder representing the deep learning parameterized model, and represent N The average value of the test samples.

[0025] Preferably, the deep learning parameterized model includes an encoder, a decoder and a discriminator;

[0026] The encoder is used to extract geostatistical features from the input heterogeneous reservoir permeability field x, and map the geostatistical features to and output a low-dimensional latent vector z;

[0027] The decoder is used to generate a reconstructed heterogeneous reservoir permeability field from the input low-dimensional latent vector z as well as Standard Deviation As output;

[0028] The discriminator is used to identify whether the low-dimensional latent vector z obtained by the encoder obeys the standard normal distribution.

[0029] Preferably, the network parameters of the decoder of the deep learning parameterized model are θ As an uncertain parameter, the decoder of the deep learning parameterized model is trained using the SVGD Bayesian inference algorithm to obtain N S Set different network parameters θ The decoder of the deep learning parameterized model of NS Set different network parameters θ The decoder of the deep learning parameterized model is obtained N S Different sets of heterogeneous reservoir permeability fields will be N S The mean value of the permeability field of different heterogeneous reservoirs is used as the output of the decoder of the deep learning parameterized model. ,Will N S The standard deviation of the permeability field of different heterogeneous reservoirs is used as the standard deviation of the permeability field of heterogeneous reservoirs output by the deep learning parameterized model decoder .

[0030] Preferably, the encoder and decoder of the deep learning parameterized model use multi-layer residual dense blocks as basic modules, each of which is composed of 3 residual dense blocks, each of which contains 5 internal convolutional layers, and each of which includes batch normalization, ReLU nonlinear activation function and convolution operation; the multi-layer residual dense block makes full use of its dense connection and residual learning characteristics, which can increase the propagation of information flow within the network, alleviate the burden of training complex networks, and thus improve the deep learning parameterized model's characterization of the geological statistical characteristics of complex heterogeneous permeability fields.

[0031] The discriminator of the deep learning parameterized model includes a first convolutional layer, a second convolutional layer, a first fully connected layer, and a second fully connected layer. The first convolutional layer, the second convolutional layer, the first fully connected layer, and the second fully connected layer are connected in sequence, and the second fully connected layer uses a Sigmoid function as a nonlinear activation function to ensure that a value between 0 and 1 is output, indicating the probability that the low-dimensional latent vector z obtained by the encoder of the deep learning parameterized model follows a standard normal distribution.

[0032] Preferably, the loss function used by the encoder and decoder of the deep learning parameterized model is for:

[0033] ;

[0034] In the formula, Represents the encoder i Input fields, Represents the first i Output fields, represents the encoder, represents the discriminator, N is the number of samples, w is the weight factor;

[0035] The loss function used by the discriminator of the deep learning parameterized model is for:

[0036] ;

[0037] In the formula, Representative i A low-dimensional normally distributed latent vector.

[0038] Among them, training the encoder, decoder and discriminator of the deep learning parameterized model is an adversarial training process: the encoder constantly deceives the discriminator so that the encoding vector output by the encoder The probability of following the standard normal distribution is higher, and the discriminator constantly distinguishes whether the input vector is a real sample from the standard normal distribution or a "fake" sample generated by the encoder. After this adversarial training, when the input arbitrary low-dimensional latent vector z is a normal distribution, the decoder is able to generate a reconstructed sample with similar geostatistical characteristics to the input field x. as well as Standard Deviation .

[0039] Preferably, the CO 2 The coupled inversion simulation framework for geological storage includes:

[0040] A decoder of a deep learning parameterized model, wherein the decoder of the deep learning parameterized model takes a low-dimensional standard normal distribution latent vector sample set as input and outputs a heterogeneous reservoir permeability field sample set and a heterogeneous reservoir permeability field standard deviation sample set;

[0041] CO 2 Storage forward numerical model, the CO 2 The storage forward numerical model takes the heterogeneous reservoir permeability field sample set output by the decoder of the deep learning parameterized model as input and outputs CO 2 A sample set of simulated values ​​of saturation and reservoir pressure;

[0042] A multiple data assimilation iterative set smoothing algorithm, wherein the multiple data assimilation iterative set smoothing algorithm uses the low-dimensional standard normal distribution latent vector sample set, the CO 2 The output of the storage forward numerical model, the CO 2 The historical observation data of saturation and reservoir pressure and the standard deviation sample set of the heterogeneous reservoir permeability field are used as input data of the multiple data assimilation iterative set smoothing algorithm, and an updated low-dimensional standard normal distribution latent vector sample set is output.

[0043] Preferably, the CO 2 The steps of the geological storage coupled inversion simulation framework include:

[0044] S1, randomly generate a series of low-dimensional standard normal distribution latent vector initial sample sets;

[0045] S2, inputting a series of randomly generated low-dimensional standard normal distribution latent vector initial sample sets into the decoder of the trained deep learning parameterized model to obtain the corresponding heterogeneous reservoir permeability field initial sample set and heterogeneous reservoir permeability field standard deviation initial sample set;

[0046] S3, inputting the initial sample set of the heterogeneous reservoir permeability field into the CO 2 In the storage forward numerical model, the corresponding CO 2 An initial sample set of simulated values ​​of saturation and reservoir pressure;

[0047] S4. Based on the collected CO 2 Saturation and reservoir pressure historical observation data, the initial sample set of the standard deviation of the heterogeneous reservoir permeability field and the CO 2 An initial sample set of saturation and reservoir pressure simulation values, and an update of a low-dimensional latent vector sample set using the multiple data assimilation iterative set smoothing algorithm;

[0048] S5. Determine whether the preset maximum number of cycles has been reached. If the preset maximum number of cycles has not been reached, input the low-dimensional latent vector sample set updated by the multiple data assimilation iterative set smoothing algorithm into the decoder of the trained deep learning parameterized model to obtain the corresponding heterogeneous reservoir permeability field sample set and the heterogeneous reservoir permeability field standard deviation sample set, and jump to step S3 to continue executing until the preset maximum number of cycles has been reached to obtain the final low-dimensional latent vector sample set.

[0049] Preferably, the multiple data assimilation iterative ensemble smoothing algorithm:

[0050] ;

[0051] In the formula, represents the set of low-dimensional latent vector samples before updating, represents the updated low-dimensional latent vector sample set, It is CO 2 A sample set of simulated values ​​of saturation and reservoir pressure, is a low-dimensional latent vector sample set and CO 2 The cross-covariance matrix between the sample sets of simulated saturation and reservoir pressure values, Indicates CO 2 The autocovariance matrix of the sample set of simulated values ​​of saturation and reservoir pressure, is the historical observation data, is the autocovariance matrix of the standard deviation of the historical observation data error, E is the autocovariance matrix of the standard deviation of the heterogeneous reservoir permeability field output by the deep learning parameterized model decoder; ; ;in, is the set size of the low-dimensional latent vector sample set, The preset maximum number of cycles for the multiple data assimilation iterative ensemble smoothing algorithm; is the coefficient of expansion and α = N iter .

[0052] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0053] 1. The present invention effectively maps the non-Gaussian distribution characteristics of the reservoir permeability field to the latent vector space of low-dimensional normal distribution, greatly reducing the CO 2 The number of parameters to be estimated in the geological storage inversion simulation can be increased, and the parameter field with non-Gaussian distribution can be estimated.

[0054] 2. By constructing the encoder, decoder and discriminator components in the deep learning parameterized model, and using multi-layer residual dense blocks with dense connections and residual learning characteristics as basic modules, the model can enhance the characterization of the geological statistical characteristics of complex heterogeneous permeability fields.

[0055] 3. The decoder of the trained deep learning parameterized model takes any low-dimensional standard normal distribution latent vector as input and can output the corresponding heterogeneous reservoir permeability field and the standard deviation field of the heterogeneous reservoir permeability field, and the heterogeneous reservoir permeability field retains its non-Gaussian distribution geological statistical characteristics.

[0056] 4. Decoder and CO of the deep learning parameterized model 2 The forward numerical model for storage and the multiple data assimilation iterative ensemble smoothing algorithm jointly construct the CO 2 A coupled inversion simulation framework for geological storage can effectively reproduce CO in reservoirs 2 The historical process of plume migration. During inversion, only the low-dimensional latent vector needs to be updated cyclically to efficiently estimate the heterogeneous permeability field of complex reservoirs, thereby improving the numerical model’s accuracy for CO 2 The simulation prediction accuracy of the geological storage process can be used to predict CO 2 Possible migration patterns in the future.

[0057] 5. In the multiple data assimilation iterative ensemble smoothing algorithm, the standard deviation of the heterogeneous reservoir permeability field output by the deep learning parameterized model decoder is also incorporated into the algorithm formula as an error term, thereby further improving the accuracy of the inversion simulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0059] Figure 1 The present invention utilizes CO 2 Flowchart of steps for obtaining the final low-dimensional standard normal distribution latent vector sample set in the geological storage coupled inversion simulation framework;

[0060] Figure 2 It is a schematic diagram of the deep learning parameterization (DLP) model structure;

[0061] Figure 3 It is a schematic diagram of the structure of the multi-layer residual dense block (MLRDB), which is the basic component module of the encoder and decoder of the deep learning parameterized model;

[0062] Figure 4 It is a sample comparison diagram of three groups of real permeability fields, the reconstructed permeability fields generated by the decoder of the deep learning parameterized model, and the standard deviation field of the reconstructed permeability fields;

[0063] Figure 5 It is CO 2 Heterogeneous permeability (log 10 k ) Reference field diagram and permeability histogram;

[0064] Figure 6 This is the inversion result diagram of the heterogeneous permeability field;

[0065] Figure 7 It is the CO of 4 moments 2 Saturation field inversion result diagram;

[0066] Figure 8 It is the inversion result diagram of reservoir pressure increment field at four moments. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] The CO selected by the present invention 2The geological storage site is the Frio carbon storage site in the southwestern United States. It is a typical fluvial sedimentary reservoir with a high degree of channelization. The lithology is mainly composed of high-permeability sandstone and low-permeability shale. The present invention is further described, in which the deep learning parameterized model can be referred to as the DLP model.

[0069] The present invention provides a technical solution based on the CO 2 The geological storage inversion simulation method includes the following specific steps:

[0070] L1. The study area is determined to be the Frio storage site in the southwestern United States. The target reservoir is a fluvial sedimentary reservoir with a highly channelized lithofacies composition. Geological drilling shows that sandstone accounts for about 75% of the target reservoir with an average permeability of 4×10 -13 m 2 , porosity 0.30, capillary pressure 20 kPa, pore distribution index 0.457; shale accounts for about 25%, with an average permeability of 1×10 -18 m 2 , porosity 0.10, capillary pressure 20000kPa, pore distribution index 0.457; reservoir depth 1500m, initial average pressure 15MPa, temperature 60℃ (isothermal), salinity 0.03, rock anisotropy ratio 0.5. CO is collected at the drilling site 2 The historical observation data of saturation and reservoir pressure are used, and Gaussian noise with a standard deviation of 2% is added as the observation error of the historical observation data.

[0071] L2. Generate 40,000 sets of heterogeneous reservoir permeability field samples that conform to drilling and hydrogeological data through the geological statistics software TProGS, of which 35,000 sets are used as training samples to optimize the training DLP model, and 5,000 sets are used as test samples to evaluate the test accuracy of the DLP model.

[0072] Among them, the DLP model is as follows Figure 2 As shown in Figure 1, it consists of an encoder, a decoder, and a discriminator. The basic building block of the encoder and decoder is the multi-layer residual dense block (MLRDB), whose structure is as follows: Figure 3 As shown in the figure, each MLRDB consists of 3 residual dense blocks (RDBs), each RDB contains 5 internal convolutional layers, and each convolutional layer includes batch normalization (BN), ReLU nonlinear activation function and convolution (Conv) operation. N f Represents the number of feature maps, and the residual scaling factor is set to β = 0.2, ⊕ represents the addition operation.

[0073] Figure 2The encoder of the DLP model also involves a downsampling operation to fully extract features from the heterogeneous permeability field x and map it to a low-dimensional latent vector z. The decoder also involves an upsampling operation to restore and reconstruct the heterogeneous permeability field from the low-dimensional latent vector z. The reshape operation is used in the discriminator, and the last two layers are fully connected (FC) layers with 128 and 1 neurons respectively. The last fully connected layer uses a Sigmoid activation function to output a value between 0 and 1, indicating the probability that the low-dimensional latent vector z obtained by the encoder follows the standard normal distribution.

[0074] L3, 35000 sets of training samples were used to train the DLP model. The decoder was trained using the SVGD Bayesian inference algorithm with an initial learning rate of 0.0025, and the encoder and discriminator were trained using the Adam optimizer with an initial learning rate of 0.0002. The sample batch size was set to 16, the number of training rounds was set to 50, and the loss function weight factor used by the encoder and decoder was w =0.01.

[0075] When training the decoder, the SVGD Bayesian inference algorithm uses the decoder's network parameters θ As an uncertain parameter, we get N S = 20 different network parameters θ The low-dimensional latent vector z is input to N S = 20 different network parameters θ The corresponding decoder obtains N S = 20 sets of different heterogeneous reservoir permeability field data, N S = The average value of 20 sets of heterogeneous reservoir permeability field data is used as the heterogeneous reservoir permeability field output by the decoder ,Will N S = The standard deviation of 20 sets of heterogeneous reservoir permeability field data as the standard deviation of the heterogeneous reservoir permeability field output by the decoder .

[0076] The test accuracy of the DLP model is evaluated based on 5000 test samples, and the determination coefficient ( R 2 ) precision, and R 2 Optimize and adjust the trained DLP model for the discrimination criteria until R2 Meet the preset accuracy requirements (determination coefficient R 2 ≥ α , α is the preset value), and the final trained DLP model is obtained.

[0077] The final calculated coefficient of determination R 2 It is 0.961, indicating that the DLP model has met the accuracy requirements and can effectively explore the geostatistical characteristics of the heterogeneous permeability field, map it to a low-dimensional latent vector space, and reconstruct the permeability field.

[0078] Figure 4 The three groups of real permeability fields (randomly selected from 5000 test samples) were compared with the reconstructed permeability fields and the standard deviation fields of the reconstructed permeability fields generated by the decoders of the corresponding DLP models. As shown in the figure, the real fields and reconstructed fields of the three groups of samples are very close, indicating that the DLP model can accurately approximate complex heterogeneous permeability fields. The standard deviation of the reconstructed permeability field is also basically below 0.5, indicating that the uncertainty of the output results of the DLP model decoder is small, and the inversion simulation results obtained by incorporating this error term into the multiple data assimilation iterative ensemble smoothing algorithm are more reliable.

[0079] At this time, the decoder of the DLP model is incorporated into the CO 2 The geological storage coupled inversion simulation framework can output the corresponding heterogeneous reservoir permeability field and heterogeneous reservoir permeability standard deviation field given any low-dimensional standard normal distribution latent vector as input.

[0080] L4, using multiphase flow simulation software TOUGH2 / ECO2N to establish CO 2 The storage forward numerical model simulates a storage area of ​​7200 m×1000 m×100 m, and the reservoir is discretized into 35×25×10 grids. 2 The injection well (Well 5) is located in the center of the reservoir and is injected into the CO 2 The grid around the injection well is appropriately denser. 2 With an injection rate of 2.0 kg / s for 10 years, CO 2 Heterogeneous permeability (log 10 k ) Reference field and 9 well locations are as follows Figure 5 As shown in a, Figure 5 The b in FIG. 5 is a histogram of permeability, and its distribution shows obvious non-Gaussian characteristics.

[0081] L5, decoder in the trained DLP model, CO 2The CO storage forward numerical model and the ESMDA algorithm are used to construct a CO 2 A coupled inversion modeling framework for geology and storage;

[0082] Among them, CO 2 The geological storage coupled inversion simulation framework includes: an encoder of a deep learning parameterized model, which takes a low-dimensional standard normal distribution latent vector sample set as input and outputs a heterogeneous reservoir permeability field sample set and a heterogeneous reservoir permeability field standard deviation sample set;

[0083] CO 2 The forward numerical model for storage takes the heterogeneous reservoir permeability field sample set output by the decoder of the deep learning parameterized model as input and outputs CO 2 A sample set of simulated values ​​of saturation and reservoir pressure;

[0084] Multiple data assimilation iterative ensemble smoothing algorithm, based on low-dimensional standard normal distribution latent vector sample set, CO 2 Saturation and reservoir pressure simulation value sample set, CO 2 The historical observation data of saturation and reservoir pressure and the standard deviation sample set of the heterogeneous reservoir permeability field are taken as input, and the updated low-dimensional standard normal distribution latent vector sample set is output.

[0085] L6, randomly generate 500 sets of low-dimensional latent vector initial sample sets, and use CO 2 The geological storage coupled inversion simulation framework obtains the final low-dimensional latent vector sample set. The specific steps are:

[0086] The 500 sets of initial sample sets of low-dimensional latent vectors are input into the decoder of the DLP model trained in L3 to obtain 500 sets of initial sample sets of heterogeneous reservoir permeability fields and initial sample sets of standard deviations of heterogeneous reservoir permeability fields.

[0087] An initial set of 500 samples of heterogeneous reservoir permeability fields were input into the CO 2 In the storage forward numerical model, 500 groups of CO 2 An initial sample set of simulated values ​​for saturation and reservoir pressure.

[0088] Based on CO collected in L1 2 Saturation and reservoir pressure historical observation data, 500 sets of initial sample sets of heterogeneous reservoir permeability field standard deviations, and 500 sets of CO 2 The initial sample set of saturation and reservoir pressure simulation values ​​is updated by the ESMDA algorithm with 500 sets of low-dimensional latent vector initial sample sets. The above process is repeated until the cycle is repeated 30 times to obtain the final low-dimensional latent vector sample set. The set size of the low-dimensional latent vector sample set in the ESMDA algorithm is The preset maximum number of cycles is 500. is 30.

[0089] L7, the low-dimensional latent vector sample set obtained in the final (30th update) is input into the decoder of the DLP model trained in L3 to obtain the corresponding heterogeneous permeability field posterior sample data set. The results are as follows Figure 6 shown.

[0090] in, Figure 6 The inversion result diagram of the heterogeneous permeability field is shown, including the true permeability field, the posterior permeability mean field and the posterior permeability standard deviation field. The locations of the 9 wells are still marked in the figure.

[0091] The inversion results of the heterogeneous permeability field show that the proposed CO 2 The geological storage coupled inversion simulation framework successfully estimated and inverted the general distribution characteristics of the true permeability field, and the values ​​of the posterior standard deviation field were relatively small in areas with observation wells, indicating that the accuracy and stability of the inversion simulation were relatively high.

[0092] L8. Input the heterogeneous permeability field posterior sample dataset into the CO 2 Storage forward numerical model to obtain CO 2 The posterior sample data set of saturation and reservoir pressure simulation values, the results are as follows Figure 7 and 8 shown.

[0093] in, Figure 7 The CO2 at four time points (2.5 years, 5 years, 7.5 years, and 10 years) is shown. 2 Saturation field inversion results, including CO 2 Saturation real field, CO 2 Saturation posterior mean field and CO 2 Saturation posterior standard deviation field. The locations of the 9 wells are still marked in the figure.

[0094] Figure 8 The inversion results of the reservoir pressure increment field at four moments (2.5 years, 5 years, 7.5 years, and 10 years) are shown, including the true field of reservoir pressure increment, the posterior mean field of reservoir pressure increment, and the posterior standard deviation field of reservoir pressure increment. The locations of the nine wells are still marked in the figure.

[0095] Depend on Figure 7 and Figure 8 It can be seen that the CO based on deep learning parameterization strategy proposed in this invention 2The geological storage inversion simulation method can achieve good inversion simulation results. At any time, the posterior mean value field obtained by inversion is very close to the real field in the area covered by the observation well in the middle of the reservoir. In the area without observation wells, the similarity between the two decreases with the increase of the distance from the observation well. The values ​​of the posterior standard deviation field are relatively small, indicating that the obtained posterior sample data set is highly stable and can effectively characterize the CO2 in complex reservoirs. 2 The historical process of plume migration can also be used to describe the CO 2 Provide technical support for optimized operation and risk management of geological storage projects.

[0096] It is worth mentioning that in this implementation case, the deep learning parameterized model reduced the dimension of a complex heterogeneous permeability field of 8750 dimensions to a low-dimensional latent vector of 378 dimensions, which increased the efficiency of parameter estimation by the multiple data assimilation iterative ensemble smoothing algorithm by about 23 times, successfully accelerating the CO 2 The calculation process of geological storage inversion simulation. And the present invention is not limited to CO 2 The dimensionality reduction of high-dimensional heterogeneous permeability fields in geological storage numerical simulation still has broad application prospects for parameter field dimensionality reduction in other similar multiphase flow numerical simulations (such as DNAPL solute transport simulation, etc.).

[0097] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0098] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A CO2 geological storage inversion simulation method based on deep learning parameterization strategy, characterized in that: The steps include: Obtain geological lithology drilling data and hydrogeological data of the target reservoir in the study area, and collect historical observation data of CO2 saturation and reservoir pressure during the storage process at the drilling site; Generate a heterogeneous reservoir permeability field sample using geostatistical software based on the geological lithology drilling data and the hydrogeological data; Constructing a CO2 storage forward numerical model using multiphase flow numerical simulation software based on the geological lithology drilling data and the hydrogeological data; Training a deep learning parameterized model based on the heterogeneous reservoir permeability field samples, and randomly generating an initial sample set of low-dimensional standard normal distribution latent vectors; The deep learning parameterized model, the CO2 storage forward numerical model and the multiple data assimilation iterative ensemble smoothing algorithm jointly construct a CO2 geological storage coupled inversion simulation framework; the CO2 geological storage coupled inversion simulation framework includes: A decoder of a deep learning parameterized model, wherein the decoder of the deep learning parameterized model takes a low-dimensional standard normal distribution latent vector sample set as input and outputs a heterogeneous reservoir permeability field sample set and a heterogeneous reservoir permeability field standard deviation sample set; A CO2 storage forward numerical model, wherein the CO2 storage forward numerical model takes a heterogeneous reservoir permeability field sample set output by a decoder of a deep learning parameterized model as an input, and outputs a CO2 saturation and reservoir pressure simulation value sample set; A multiple data assimilation iterative ensemble smoothing algorithm, wherein the multiple data assimilation iterative ensemble smoothing algorithm uses the low-dimensional standard normal distribution latent vector sample set, the output of the CO2 storage forward numerical model, the historical observation data of CO2 saturation and reservoir pressure, and the standard deviation sample set of the heterogeneous reservoir permeability field as input data of the multiple data assimilation iterative ensemble smoothing algorithm, and outputs an updated low-dimensional standard normal distribution latent vector sample set; Based on the initial sample set of low-dimensional standard normal distribution latent vectors, the final low-dimensional latent vector sample set is obtained by using the CO2 geological storage coupled inversion simulation framework; The final low-dimensional latent vector sample set is input into the trained deep learning parameterized model to obtain the corresponding heterogeneous reservoir permeability field posterior sample data set; the heterogeneous reservoir permeability field posterior sample data set is input into the CO2 storage forward numerical model to obtain the corresponding CO2 saturation and reservoir pressure simulation value posterior sample data set.

2. The CO2 geological storage inversion simulation method based on deep learning parameterization strategy according to claim 1 is characterized in that: The deep learning parameterized model construction step includes: Randomly dividing the heterogeneous reservoir permeability field samples into training samples and test samples; During model training, the deep learning parameterized model uses the training samples as input and generates a reconstructed heterogeneous reservoir permeability field from a decoder of the deep learning parameterized model; During model testing, the coefficient of determination between the reconstructed heterogeneous reservoir permeability field generated by the decoder of the deep learning parameterized model trained with the test sample and the training sample is compared. R 2 Precision, judging the coefficient of determination R 2 Whether the preset accuracy requirements are met, if so, it indicates that the deep learning parameterized model training is completed, otherwise continue to use the training samples to optimize and adjust the model parameters until the trained deep learning parameterized model meets the preset accuracy requirements.

3. The CO2 geological storage inversion simulation method based on deep learning parameterization strategy according to claim 2 is characterized in that: The coefficient of determination R 2 : ； In the formula, N is the number of test samples, Represents the test sample, The reconstructed heterogeneous reservoir permeability field generated by the decoder representing the deep learning parameterized model, and represent N The average value of the test samples.

4. The CO2 geological storage inversion simulation method based on deep learning parameterization strategy according to claim 1 is characterized in that: The deep learning parameterized model includes an encoder, a decoder, and a discriminator; The encoder is used to extract geostatistical features from the input heterogeneous reservoir permeability field x, and map the geostatistical features to and output a low-dimensional latent vector z; The decoder is used to generate a reconstructed heterogeneous reservoir permeability field from the input low-dimensional latent vector z as well as Standard Deviation As output; The discriminator is used to identify whether the low-dimensional latent vector z obtained by the encoder obeys the standard normal distribution.

5. The CO2 geological storage inversion simulation method based on deep learning parameterization strategy according to claim 4 is characterized in that: The network parameters of the decoder of the deep learning parameterized model θ As an uncertain parameter, the decoder of the deep learning parameterized model is trained using the SVGD Bayesian inference algorithm to obtain N S Set different network parameters θ The decoder of the deep learning parameterized model of N S Set different network parameters θ The decoder of the deep learning parameterized model is obtained N S Different sets of heterogeneous reservoir permeability fields will be N S The mean value of the permeability field of different heterogeneous reservoirs is used as the output of the decoder of the deep learning parameterized model. ,Will N S The standard deviation of the permeability field of different heterogeneous reservoirs is used as the standard deviation of the permeability field of heterogeneous reservoirs output by the deep learning parameterized model decoder .

6. The CO2 geological storage inversion simulation method based on deep learning parameterization strategy according to claim 4 is characterized in that: The encoder and decoder of the deep learning parameterized model use multi-layer residual dense blocks as basic modules, each of which is composed of 3 residual dense blocks, each of which contains 5 internal convolutional layers, and each of which includes batch normalization, ReLU nonlinear activation function and convolution operation; The discriminator of the deep learning parameterized model includes a first convolutional layer, a second convolutional layer, a first fully connected layer, and a second fully connected layer; the first convolutional layer, the second convolutional layer, the first fully connected layer, and the second fully connected layer are connected in sequence, and the second fully connected layer uses a Sigmoid function as a nonlinear activation function to ensure that a value between 0 and 1 is output, indicating the probability that the low-dimensional latent vector z obtained by the encoder of the deep learning parameterized model follows a standard normal distribution.

7. The CO2 geological storage inversion simulation method based on deep learning parameterization strategy according to claim 4 is characterized in that: The loss function used by the encoder and decoder of the deep learning parameterized model for: ； In the formula, Represents the encoder i Input fields, Represents the first i Output fields, represents the encoder, represents the discriminator, N is the number of samples, w is the weight factor; The loss function used by the discriminator of the deep learning parameterized model is for: ； In the formula, Representative i A low-dimensional normally distributed latent vector.

8. The CO2 geological storage inversion simulation method based on deep learning parameterization strategy according to claim 1, characterized in that: The steps of executing the CO2 geological storage coupled inversion simulation framework include: S1, randomly generate a series of low-dimensional standard normal distribution latent vector initial sample sets; S2, inputting a series of randomly generated low-dimensional standard normal distribution latent vector initial sample sets into the decoder of the trained deep learning parameterized model to obtain the corresponding heterogeneous reservoir permeability field initial sample set and heterogeneous reservoir permeability field standard deviation initial sample set; S3, inputting the initial sample set of the heterogeneous reservoir permeability field into the CO2 storage forward numerical model to obtain the corresponding initial sample set of CO2 saturation and reservoir pressure simulation values; S4, based on the collected historical observation data of CO2 saturation and reservoir pressure, the initial sample set of standard deviation of the heterogeneous reservoir permeability field and the initial sample set of simulated values ​​of CO2 saturation and reservoir pressure, using the multiple data assimilation iterative set smoothing algorithm to update the low-dimensional latent vector sample set; S5. Determine whether the preset maximum number of cycles has been reached. If the preset maximum number of cycles has not been reached, input the low-dimensional latent vector sample set updated by the multiple data assimilation iterative set smoothing algorithm into the decoder of the trained deep learning parameterized model to obtain the corresponding heterogeneous reservoir permeability field sample set and the heterogeneous reservoir permeability field standard deviation sample set, and jump to step S3 to continue executing until the preset maximum number of cycles has been reached to obtain the final low-dimensional latent vector sample set.

9. The CO2 geological storage inversion simulation method based on deep learning parameterization strategy according to claim 1, characterized in that: The multiple data assimilation iterative ensemble smoothing algorithm: ； In the formula, represents the set of low-dimensional latent vector samples before updating, represents the updated low-dimensional latent vector sample set, is a sample set of simulated values ​​of CO2 saturation and reservoir pressure, The cross-covariance matrix between the low-dimensional latent vector sample set and the CO2 saturation and reservoir pressure simulation value sample set, represents the autocovariance matrix of the sample set of simulated values ​​of CO2 saturation and reservoir pressure, is the historical observation data, is the autocovariance matrix of the standard deviation of the historical observation data error, E is the autocovariance matrix of the standard deviation of the heterogeneous reservoir permeability field output by the deep learning parameterized model decoder ; ;in, The set size of the low-dimensional latent vector sample set, The preset maximum number of cycles for the multiple data assimilation iterative ensemble smoothing algorithm; is the coefficient of expansion and α = N iter。

Images