Well seismic data matching method and device

Abstract

The present invention discloses a method and device for matching well-seismic data, which includes: obtaining a reservoir parameter time-shift curve of a target well target layer; determining a porosity time-shift curve of the target well target layer using a trained probabilistic neural network model based on the reservoir parameter time-shift curve of the target well target layer; determining a well velocity time-shift curve of the target well target layer using a constructed rock physics model based on the predicted porosity time-shift curve of the target well target layer; and correcting an original velocity curve of the target well target layer using the well velocity time-shift curve of the target well target layer to obtain a corrected well velocity curve of the target well target layer. The present invention predicts the porosity time-shift curve using a probabilistic neural network, determines the well velocity time-shift curve using a rock physics model, and eliminates the time variation of the original velocity data through the well velocity time-shift curve correction, thereby improving the matching accuracy of well-seismic data in the time dimension.

Description

Technical Field

[0001] The present invention relates to the field of geological exploration technology, and in particular to a well-seismic data matching method and device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. No statement herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] The combination of well logging and seismic data is a primary tool for reservoir characterization, and logging velocity serves as a bridge to establish relationships between well and seismic data. However, in the development of clastic oil fields, the long-term development environment can lead to fluid displacement and passive reservoir transformation, causing changes in physical parameters such as target layer saturation, porosity, and shale content, which in turn alters formation velocity. When well logging and seismic data are acquired over a long time span, the two data reflect different subsurface reservoir and fluid states, resulting in incomplete matching between annual logging and seismic data, making it difficult to fully utilize the advantages of both.

[0004] Previous research has examined the impact of the long-term oilfield development environment on formation elasticity and physical properties. Li Cungui et al. (2003) used waterflooding tests and core analysis to first propose how reservoir pore structure changes with waterflooding. Ling Dongming et al. (2018) used forward modeling of rock physics models to summarize the effects of changes in formation porosity, shale content, and saturation on formation velocity. Zhao Qiping et al. (2019) conducted rock physics experiments and summarized the patterns of changes in physical parameters such as porosity with reservoir parameters such as pressure and injection rate. Current research has only analyzed the mechanisms of changes in reservoir physical properties and hydrocarbon content during reservoir development, and the main reasons for the reduced matching of well-seismic data, but has failed to propose a reasonable well-seismic data matching method.

[0005] In summary, it is urgent to propose a matching correction method for well logging and seismic data in the time dimension to improve the accuracy of well-seismic matching. Summary of the Invention

[0006] An embodiment of the present invention provides a well seismic data matching method for improving the well seismic data matching accuracy. The well seismic data matching method includes:

[0007] Obtain the time-lapse curve of reservoir parameters of the target well and target layer;

[0008] Based on the reservoir parameter time-shift curve of the target well's target layer, the porosity time-shift curve of the target well's target layer is determined using a trained probabilistic neural network model; the trained probabilistic neural network model can establish a strong nonlinear relationship between the porosity time-shift and the reservoir parameter time-shift;

[0009] Based on the predicted porosity time-lapse curve of the target well's target layer, the well velocity time-lapse curve of the target well's target layer is determined using the constructed rock physics model; the rock physics model reflects the relationship between well velocity and porosity;

[0010] The original velocity curve of the target well target layer is corrected by using the well velocity time shift curve of the target well target layer to obtain a corrected well velocity curve of the target well target layer.

[0011] An embodiment of the present invention further provides a well seismic data matching device for improving the well seismic data matching accuracy. The well seismic data matching device includes:

[0012] Target well reservoir acquisition module, used to obtain the reservoir parameter time-lapse curve of the target well target layer;

[0013] The target well porosity prediction module is used to determine the porosity time-shift curve of the target well's target layer based on the reservoir parameter time-shift curve of the target well's target layer using a trained probabilistic neural network model. The trained probabilistic neural network model can establish a strong nonlinear relationship between the porosity time-shift and the reservoir parameter time-shift.

[0014] The target well velocity time shift determination module is used to determine the target well velocity time shift curve of the target layer based on the predicted porosity time shift curve of the target well using the constructed rock physics model; the rock physics model reflects the relationship between well velocity and porosity;

[0015] The target well velocity correction module is used to correct the original velocity curve of the target well target layer using the well velocity time-shift curve of the target well target layer to obtain the corrected well velocity curve of the target well target layer.

[0016] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned well-seismic data matching method when executing the computer program.

[0017] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program for executing the well-seismic data matching method.

[0018] In an embodiment of the present invention, a reservoir parameter time-shift curve of a target well target layer is obtained; a porosity time-shift curve of the target well target layer is determined using a trained probabilistic neural network model; a well velocity time-shift curve of the target well target layer is determined using a constructed rock physics model; and finally, the original velocity curve is corrected using the well velocity time-shift curve of the target well target layer to obtain a corrected well velocity curve of the target well target layer. This embodiment of the present invention can predict the porosity time-shift curve using a probabilistic neural network, determine the well velocity time-shift curve using a rock physics model, and finally, eliminate the temporal variation of the well velocity data through well velocity correction, thereby improving the matching accuracy of well logging and seismic data in the time dimension. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0020] Figure 1 A flowchart of the well-seismic data matching method provided in an embodiment of the present invention;

[0021] Figure 1-1 A schematic diagram of a time-lapse curve of the porosity of a certain well predicted by a probabilistic neural network according to an embodiment of the present invention;

[0022] Figure 2 A flowchart for implementing step 101 in the well-seismic data matching method provided in an embodiment of the present invention;

[0023] Figure 2-1 A schematic diagram of the time shift of reservoir parameters of a target layer of a well provided by an embodiment of the present invention;

[0024] Figure 3 A flowchart for implementing the training of a probabilistic neural network model in the well-seismic data matching method provided in an embodiment of the present invention;

[0025] Figure 4 A flowchart for implementing step 301 in the well-seismic data matching method provided in an embodiment of the present invention;

[0026] Figure 4-1 A schematic diagram illustrating the principle of the point set difference method provided by an embodiment of the present invention;

[0027] Figure 5 A flowchart for implementing step 302 in the well-seismic data matching method provided in an embodiment of the present invention;

[0028] Figure 6A flowchart for implementing step 103 in the well-seismic data matching method provided in an embodiment of the present invention;

[0029] Figure 7 A flowchart for implementing step 104 in the well-seismic data matching method provided in an embodiment of the present invention;

[0030] Figure 8 Another implementation flow chart of the well-seismic data matching method provided in an embodiment of the present invention;

[0031] Figure 9 A flowchart for implementing step 801 in the well-seismic data matching method provided in an embodiment of the present invention;

[0032] Figure 9-1 A schematic diagram of a synthetic seismic record (i.e., synthetic seismic trace) of a well before correction provided by an embodiment of the present invention;

[0033] Figure 9-2 A schematic diagram of a corrected synthetic seismic record (i.e., synthetic seismic trace) of a well provided in an embodiment of the present invention;

[0034] Figure 10 A functional module diagram of a well-seismic data matching device provided by an embodiment of the present invention;

[0035] Figure 11 This is a structural block diagram of the target well reservoir acquisition module 1001 in the well seismic data matching device provided in an embodiment of the present invention;

[0036] Figure 12 This is a structural block diagram of the target well porosity prediction module 1002 in the well seismic data matching device provided in an embodiment of the present invention;

[0037] Figure 13 This is a structural block diagram of the basic well porosity acquisition unit 1201 in the well-seismic data matching device provided in an embodiment of the present invention;

[0038] Figure 14 This is a structural block diagram of the basic well reservoir acquisition unit 1202 in the well seismic data matching device provided in an embodiment of the present invention;

[0039] Figure 15 This is a structural block diagram of the target well velocity time shift determination module 1003 in the well seismic data matching device provided by an embodiment of the present invention;

[0040] Figure 16 This is a structural block diagram of the target well velocity correction module 1004 in the well seismic data matching device provided in an embodiment of the present invention;

[0041] Figure 17 Another functional module diagram of the well-seismic data matching device provided by an embodiment of the present invention;

[0042] Figure 18 This is a structural block diagram of the verification module 1701 in the well-seismic data matching device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0044] Figure 1 The implementation process of the well-seismic data matching method provided by an embodiment of the present invention is shown. For ease of description, only the part related to the embodiment of the present invention is shown, which is detailed as follows:

[0045] like Figure 1 As shown, the well-seismic data matching method includes:

[0046] Step 101, obtaining a time-lapse curve of reservoir parameters of a target layer of a target well;

[0047] Step 102: Determine the porosity time-shift curve of the target layer of the target well using a trained probabilistic neural network model based on the reservoir parameter time-shift curve of the target layer of the target well. The trained probabilistic neural network model can establish a strong nonlinear relationship between the porosity time-shift and the reservoir parameter time-shift.

[0048] Step 103: Determine the well velocity time-lapse curve of the target layer of the target well based on the predicted porosity time-lapse curve of the target layer of the target well using the constructed rock physics model; the rock physics model reflects the relationship between well velocity and porosity;

[0049] Step 104 , using the well velocity time-shift curve of the target well target layer, correct the original velocity curve of the target well target layer to obtain a corrected well velocity curve of the target well target layer.

[0050] When matching well-seismic data, the target well is the well being studied. Reservoir parameters include one or more of the following: water cut, liquid production, and pressure. Those skilled in the art will appreciate that reservoir parameters may also include other parameters besides the aforementioned water cut, liquid production, pressure, and temperature, such as temperature, and this is not particularly limited in the present embodiment. Therefore, a reservoir parameter time-shift curve may include a water cut square wave curve, a liquid production square wave curve, a pressure square wave curve, and a temperature square wave curve. A reservoir parameter time-shift curve is a continuous square wave line formed by the time-shifted values ​​of multiple reservoir parameters.

[0051] After obtaining the reservoir parameter time-shift curve for the target well's target layer, the porosity time-shift curve is predicted using a trained probabilistic neural network (PNN) using the reservoir parameter time-shift curve as input, thereby determining the porosity time-shift curve for the target well's target layer. The trained PNN can establish a strong nonlinear relationship between the porosity time-shift and the reservoir parameter time-shift. Figure 1-1 Schematic diagram of a time-lapse curve of the porosity of a certain well predicted by a probabilistic neural network provided in an embodiment of the present invention.

[0052] After using the trained probabilistic neural network to predict and determine the porosity time-lapse curve of the target well's target layer, a rock physics model encompassing the target well region is constructed. This rock physics model reflects the relationship between well velocity and porosity. Based on the predicted porosity time-lapse curve of the target well's target layer, the constructed rock physics model is then used to calculate the well velocity time-lapse curve of the target well's target layer. Finally, after determining the well velocity time-lapse curve of the target layer, the well velocity time-lapse curve of the target well's target layer is used to correct the original velocity curve of the target well's target layer, thereby obtaining the corrected well velocity curve of the target well's target layer.

[0053] In an embodiment of the present invention, a reservoir parameter time-shift curve of a target well's target layer is obtained; a porosity time-shift curve of the target well's target layer is determined using a trained probabilistic neural network model; a well velocity time-shift curve of the target well's target layer is determined using a constructed rock physics model; and finally, the original velocity curve is corrected using the well velocity time-shift curve of the target well's target layer to obtain a corrected well velocity curve of the target well's target layer. This embodiment of the present invention can predict the porosity time-shift curve using a probabilistic neural network, determine the well velocity time-shift curve using a rock physics model, and ultimately, eliminate the temporal variation of the well velocity data through well velocity correction, thereby improving the matching accuracy of well logging and seismic data in the time dimension.

[0054] Figure 2 The implementation process of step 101 in the well-seismic data matching method provided by an embodiment of the present invention is shown. For ease of description, only the part related to the embodiment of the present invention is shown, which is detailed as follows:

[0055] In one embodiment of the present invention, in order to improve the efficiency of obtaining the time-shift curve of reservoir parameters, as shown in FIG. Figure 2 As shown, step 101, obtaining a time-shift curve of reservoir parameters of a target layer of a target well, includes:

[0056] Step 201, obtaining the time shift of reservoir parameters of the target layer of the target well;

[0057] Step 202 : Repeat the time-shift of the reservoir parameters of the target layer of the target well for multiple times, and use the repeated time-shift of the reservoir parameters of the target layer of the target well to form a time-shift curve of the reservoir parameters of the target layer of the target well.

[0058] Figure 2-1 The following is a schematic diagram showing the time shift of reservoir parameters of a target layer in a well provided by an embodiment of the present invention. For ease of explanation, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0059] Specifically, when obtaining the reservoir parameter time-shift curve of the target well's target layer, the reservoir parameter time-shift of the target layer from the target well's production year to the acquisition year that matches the seismic data is counted. The reservoir parameter time-shift includes the water cut time-shift, the liquid production time-shift, the pressure time-shift, and the temperature time-shift. Then, the reservoir parameter time-shift data of each target well is repeated multiple times, for example, 10 times, and sorted vertically according to the well number. The reservoir parameter time-shift data after the repeat is used to form the reservoir parameter time-shift curve of the target well's target layer. The reservoir parameter time-shift curve mainly includes the water cut time-shift curve (water cut change), the liquid production time-shift curve (initial liquid production change), the pressure time-shift curve (pressure change), and the temperature time-shift curve (temperature change).

[0060] In an embodiment of the present invention, by obtaining the time-shift of the reservoir parameters of the target well target layer, and then repeating the time-shift of the reservoir parameters of the target well target layer multiple times, the reservoir parameter time-shift curve of the target well target layer is formed using the repeated time-shift of the reservoir parameters of the target well target layer, the efficiency of obtaining the reservoir parameter time-shift curve can be improved.

[0061] Figure 3 The implementation process of training a probabilistic neural network model in the well-seismic data matching method provided by an embodiment of the present invention is shown. For ease of description, only the part related to the embodiment of the present invention is shown, which is detailed as follows:

[0062] In one embodiment of the present invention, in order to improve the accuracy of predicting the porosity time-shift curve, as shown in FIG. Figure 3 As shown in Figure 2, the probabilistic neural network model training process is as follows:

[0063] Step 301, obtaining a porosity time-lapse curve of a target layer of a base well;

[0064] Step 302, obtaining a reservoir parameter time-shift curve corresponding to a porosity time-shift curve of a target layer of a base well;

[0065] Step 303: Using the reservoir parameter time-shift curve as a training curve and the porosity time-shift curve as a target curve, train the network parameters of the probabilistic neural network.

[0066] Step 304: Repeat the iterative training until the training convergence condition is met to obtain a trained probabilistic neural network.

[0067] Based on deep learning technology, this invention establishes the relationship between the logging velocity curve and reservoir parameters, counts the dynamic data changes from drilling commissioning to seismic data acquisition, and uses the time shift of reservoir parameters based on deep learning technology to predict the time shift of logging velocity, and then corrects the logging velocity to improve the matching accuracy of logging and seismic data.

[0068] In order to improve the accuracy of predicting porosity time-shift curves, it is necessary to first train a probabilistic neural network. The main purpose of training the probabilistic neural network is to establish a strong nonlinear relationship between the time-shift of porosity and the time-shift of reservoir parameters.

[0069] Well logging velocity is the bridge between well and seismic data. Research has shown that porosity differences are the primary factor influencing velocity changes, and that porosity time shifts are correlated with changes in reservoir dynamic parameters such as water cut, liquid production, pressure, and temperature. To this end, using porosity time shifts as target data and reservoir parameter time shifts as training data, we obtain porosity time shift curves for the target layer of the base well, as well as reservoir parameter time shift curves corresponding to the porosity time shift curves for the target layer of the base well.

[0070] After obtaining the porosity time-shift curves and corresponding reservoir parameter time-shift curves for the target layer of the base well, the probabilistic neural network is trained using the reservoir parameter time-shift curves as training curves and the porosity time-shift curves as target curves. Specifically, through forward data calculation and reverse error correction, repeated iterations are performed until convergence conditions are reached. This continuously trains and ultimately determines the network parameters, such as the weights and thresholds of each node in the neural network. This training establishes a strong nonlinear relationship between the reservoir parameter time-shift and the porosity time-shift, ultimately yielding the trained probabilistic neural network.

[0071] In this embodiment of the present invention, a porosity time-shift curve of the target layer of a base well and its corresponding reservoir parameter time-shift curve are obtained. The reservoir parameter time-shift curve is then used as a training curve and the porosity time-shift curve as a target curve to train the network parameters of a probabilistic neural network. Training is iterated repeatedly until convergence conditions are met, resulting in a trained probabilistic neural network. The trained probabilistic neural network is capable of accurately predicting the porosity time-shift curve.

[0072] Figure 4 The implementation process of step 301 in the well-seismic data matching method provided by an embodiment of the present invention is shown. For ease of description, only the part related to the embodiment of the present invention is shown, which is detailed as follows:

[0073] In one embodiment of the present invention, in order to improve the efficiency of obtaining the porosity time-lapse curve, as shown in FIG. Figure 4 As shown, step 301, obtaining a porosity time-lapse curve of a target layer of a base well, includes:

[0074] Step 401: Determine the porosity time shift of the target layer of the base well using the point set difference method; the porosity time shift of the target layer of the base well is the difference between the mean porosity of the target layer of the wells within a preset range centered on the base well and the mean porosity of the target layer of the base well;

[0075] Step 402: Repeat the porosity time shift of the target layer of the base well for multiple times, and use the repeated porosity time shift of the target layer of the base well to form a porosity time shift curve.

[0076] Specifically, to generate a porosity time-shift curve, the point set difference method can be used to first obtain the porosity time-shift of the target layer of the base well. The porosity time-shift of the target layer of the base well is calculated as the difference between the mean porosity of the target layer of the wells within a preset range centered on the base well and the mean porosity of the target layer of the base well.

[0077] Figure 4-1 The principle of the point set difference method provided by an embodiment of the present invention is shown. For ease of explanation, only the part related to the embodiment of the present invention is shown, which is detailed as follows:

[0078] Statistical target data (porosity time shift that constitutes the porosity time shift curve) and training data (reservoir parameter time shift that constitutes the reservoir parameter time shift curve): Porosity change data is based on porosity logging data and is statistically analyzed using the "point set difference method". Figure 4-1 As shown in the figure, a circle with a radius of 500 meters is drawn with the foundation well (Well 1, logged in 1990) from the early stages of oilfield development as the center. For weakly heterogeneous clastic reservoirs, the primary pores are assumed to be essentially uniform within a 500-meter radius, meaning that porosity differences between different wells are attributed to the influence of the development environment. To this end, the mean porosity difference between the target layer of Well 1 and the wells from different periods within the set range (e.g., Well 2, logged in 1995) is calculated. This difference is approximated as the porosity change at Well 1 from 1990 to 1995. Using this as a porosity sample point, the porosity changes up to 2000, 2005, and 2010 can be calculated analogously (the time intervals between the different point sets are inconsistent) and serve as the target data.

[0079] Based on this, in order to improve the stability of learning and training, the porosity time-shift of the target layer of the basic well is repeated multiple times, and then the porosity change after repetition (i.e., porosity time-shift) is used to form a porosity time-shift curve as the target data.

[0080] In an embodiment of the present invention, the porosity time shift of the target layer of the base well is determined by using the point set difference method, and then the porosity time shift is formed by copying the porosity time shift, which can improve the efficiency of obtaining the porosity time shift curve.

[0081] Figure 5The implementation process of step 302 in the well-seismic data matching method provided by an embodiment of the present invention is shown. For ease of description, only the part related to the embodiment of the present invention is shown, which is detailed as follows:

[0082] In one embodiment of the present invention, in order to improve the efficiency of obtaining the time-shift curve of reservoir parameters, as shown in FIG. Figure 5 As shown, step 302, obtaining a reservoir parameter time-shift curve corresponding to a porosity time-shift curve of a target layer of a base well, includes:

[0083] Step 501: Determine the reservoir parameter time shift corresponding to the porosity time shift of the target layer of the base well using the point set difference method; the reservoir parameter time shift is the difference between the mean reservoir parameter of the target layer of the wells within a preset range centered on the base well and the mean reservoir parameter of the target layer of the base well;

[0084] Step 502 : Repeat the time-shift of the reservoir parameters of the target layer of the basic well for multiple times, and use the repeated time-shift of the reservoir parameters of the target layer of the basic well to form a time-shift curve of the reservoir parameters.

[0085] When determining the reservoir parameter time-shift curve for the target layer of the base well, the point set difference method is also used to determine the reservoir parameter time-shift corresponding to the porosity time-shift of the target layer of the base well. The reservoir parameter time-shift is the difference between the mean reservoir parameter of the target layer of the base well and the mean reservoir parameter of the target layer of the base well within a preset range centered on the base well.

[0086] Continue to refer to Figure 4-1 , with the foundation well (well 1, logged in 1990) at the beginning of oilfield development as the center and a circle with a radius of 500 meters. For weakly heterogeneous clastic reservoirs, it is assumed that the primary pores within a 500-meter range are basically the same, that is, the porosity differences between different wells are attributed to the influence of the development environment. To this end, the mean differences in reservoir parameters between wells in different periods within the set range (such as well 2, logged in 1995) and the target layer of well 1 are statistically analyzed. The change in reservoir parameters (i.e., the time shift of reservoir parameters) is based on the production dynamic data of the single well of the foundation well well 1. Corresponding to the porosity statistical time interval, the changes in water cut, liquid production, pressure, and temperature in 1995, 2000, 2005, and 2010 are counted as training data.

[0087] Based on this, in order to improve the stability of learning and training, the statistical reservoir parameter time shift of the target layer of the basic well is repeated many times, and then the reservoir parameter change after the repetition (i.e., reservoir parameter time shift) is used to form a reservoir parameter time shift curve as training data.

[0088] In an embodiment of the present invention, the point set difference method is used to determine the time shift of the reservoir parameters of the target layer of the base well, and then the reservoir parameter time shift curve is formed by copying the reservoir parameter time shift, which can improve the efficiency of obtaining the reservoir parameter time shift curve.

[0089] Figure 6 The implementation process of step 103 in the well-seismic data matching method provided by an embodiment of the present invention is shown. For ease of description, only the part related to the embodiment of the present invention is shown, which is detailed as follows:

[0090] In one embodiment of the present invention, in order to improve the accuracy of determining the time-shift curve of the well velocity, as shown in FIG. Figure 6 As shown, step 103, based on the predicted porosity time-lapse curve of the target well target layer, uses the constructed rock physics model to determine the well velocity time-lapse curve of the target well target layer, including:

[0091] Step 601, determining basic rock physical parameters of a rock physical model to be constructed; the basic rock physical parameters include at least pore aspect ratio;

[0092] Step 602 , by adjusting the pore aspect ratio, the forward P- and S-wave velocities of the fitted rock physics model are matched with the measured P- and S-wave velocities to obtain a constructed rock physics model;

[0093] Step 603 : Based on the predicted porosity time-lapse curve of the target layer of the target well, the well velocity time-lapse curve of the target layer of the target well is calculated using the constructed rock physics model.

[0094] When determining the well velocity time-lapse curve for the target well's target layer, first select an applicable rock physics model for the study area containing the target well's target layer and conduct modeling to determine the relationship between well velocity and porosity in the study area. Specifically, based on well logging statistics and experimental data, the basic rock physics parameters of each component of the saturated rock are given, that is, the basic rock physics parameters of the rock physics model to be constructed are determined. These basic rock physics parameters include at least the pore aspect ratio. The rock physics model is then fitted by adjusting the pore aspect ratio so that the forward P- and S-wave velocities of the rock physics model match the measured P- and S-wave velocities, thereby obtaining a constructed rock physics model. The constructed rock physics model reflects the relationship between porosity and well velocity. Based on this, the well velocity time-lapse curve for the target well's target layer can be calculated using the constructed rock physics model based on the predicted porosity time-lapse curve for the target well's target layer.

[0095] In an embodiment of the present invention, by constructing a rock physics model and then calculating the well velocity time-shift curve of the target well target layer based on the porosity time-shift curve using the rock physics model, the accuracy of determining the well velocity time-shift curve can be improved.

[0096] Figure 7 The implementation process of step 104 in the well-seismic data matching method provided by an embodiment of the present invention is shown. For ease of description, only the part related to the embodiment of the present invention is shown, which is detailed as follows:

[0097] In one embodiment of the present invention, in order to improve the accuracy of well-seismic matching, Figure 7 As shown, step 104, using the well velocity time-shift curve of the target well target layer, correcting the original velocity curve of the target well target layer to obtain a corrected well velocity curve of the target well target layer, includes:

[0098] Step 701 : Superimpose the original velocity curve of the target well target layer and the well velocity time-shift curve of the target well target layer to obtain a corrected well velocity curve of the target well target layer.

[0099] When performing well-seismic matching, the original velocity curve of the target well's target layer is superimposed with the well velocity time-shift curve of the target well's target layer to correct the original velocity curve, thereby obtaining the corrected well velocity curve of the target well's target layer to improve the accuracy of well-seismic matching.

[0100] In the embodiment of the present invention, the original velocity curve of the target well target layer is superimposed with the well velocity time-shift curve of the target well target layer to obtain the corrected well velocity curve of the target well target layer, which can improve the accuracy of well-seismic matching.

[0101] Figure 8 Another implementation process of the well-seismic data matching method provided by an embodiment of the present invention is shown. For ease of description, only the part related to the embodiment of the present invention is shown, which is detailed as follows:

[0102] In one embodiment of the present invention, in order to verify the accuracy of the calibration result, Figure 8 As shown, based on the above method steps, the well-seismic data matching method further includes:

[0103] Step 801 : Using the original velocity curve of the target well and the corrected velocity curve of the target well, the accuracy of the correction result is verified.

[0104] After the well velocity curve of the target well target layer is corrected, the accuracy of the correction result can be verified using the original velocity curve of the target well target layer and the corrected well velocity curve of the target well target layer.

[0105] In the embodiment of the present invention, the accuracy of the correction result can be verified by using the original velocity curve of the target layer of the target well and the corrected well velocity curve of the target layer of the target well.

[0106] Figure 9 The implementation process of step 801 in the well-seismic data matching method provided by an embodiment of the present invention is shown. For ease of description, only the part related to the embodiment of the present invention is shown, which is detailed as follows:

[0107] In one embodiment of the present invention, in order to verify the accuracy of the calibration result, Figure 9 As shown, step 801 uses the original velocity curve of the target well target layer and the well velocity curve of the target well target layer after correction to verify the accuracy of the correction result, including:

[0108] Step 901, performing well seismic calibration using the original velocity curve of the target layer of the target well and the corrected well velocity curve of the target layer of the target well to determine the synthetic seismic records of the target layer of the target well before and after correction;

[0109] Step 902, verifying the accuracy of the correction result by comparing the correlation coefficient before correction with the correlation coefficient after correction; wherein the correlation coefficient before correction is the correlation coefficient between the synthetic seismic record and the actual seismic record of the target well target layer before correction, and the correlation coefficient after correction is the correlation coefficient between the synthetic seismic record and the actual seismic record of the target well target layer after correction.

[0110] Among them, when correcting the accuracy of the verification results, the original velocity curve of the target well target layer is first used to perform well seismic calibration to determine the synthetic seismic record of the target well target layer before correction; then the well velocity curve of the target well target layer after correction is used to perform well seismic calibration to determine the synthetic seismic records of the target well target layer before and after correction. Figure 9-1 Schematic diagram of a synthetic seismic record (i.e., synthetic seismic trace) of a well before correction provided by an embodiment of the present invention. Figure 9-2 Schematic diagram of a synthetic seismic record (i.e., synthetic seismic trace) of a well before correction provided by an embodiment of the present invention.

[0111] After determining the synthetic seismic record of the target well's target layer before correction, a pre-correction correlation coefficient is determined based on the synthetic seismic record and actual seismic record of the target well's target layer before correction. A post-correction correlation coefficient is determined based on the synthetic seismic record and actual seismic record of the target well's target layer after correction. The accuracy of the correction result is then verified by comparing the pre-correction correlation coefficient with the post-correction correlation coefficient. The verification criteria may be: the pre-correction correlation coefficient > the post-correction correlation coefficient, and the post-correction correlation coefficient ≥ 0.9.

[0112] In an embodiment of the present invention, well seismic calibration is performed using the original velocity curve of the target well target layer and the well velocity curve of the target well target layer after correction to determine the synthetic seismic records of the target well target layer before and after correction. The accuracy of the correction result is verified by comparing the correlation coefficient before correction with the correlation coefficient after correction.

[0113] The present invention also provides a well-seismic data matching device, as described in the following embodiments. Since the principles of these devices are similar to those of the well-seismic data matching method, the implementation of these devices can refer to the implementation of the method, and the repeated parts will not be repeated.

[0114] Figure 10The functional modules of the well seismic data matching device provided by an embodiment of the present invention are shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0115] refer to Figure 10 The modules included in the well-seismic data matching device are used to perform Figure 1 For details of each step in the corresponding embodiment, please refer to Figure 1 as well as Figure 1 In the embodiment of the present invention, the well seismic data matching device includes a target well reservoir acquisition module 1001, a target well porosity prediction module 1002, a target well velocity time shift determination module 1003, and a target well velocity correction module 1004.

[0116] The target well reservoir acquisition module 1001 is used to obtain a time-lapse curve of reservoir parameters of a target layer of a target well.

[0117] The target well porosity prediction module 1002 is used to determine the porosity time-shift curve of the target well target layer based on the reservoir parameter time-shift curve of the target well target layer using a trained probabilistic neural network model; the trained probabilistic neural network model can establish a strong nonlinear relationship between the porosity time-shift amount and the reservoir parameter time-shift amount.

[0118] The target well velocity time shift determination module 1003 is used to determine the well velocity time shift curve of the target well target layer based on the predicted porosity time shift curve of the target well target layer using the constructed rock physics model; the rock physics model reflects the relationship between well velocity and porosity.

[0119] The target well velocity correction module 1004 is used to correct the original velocity curve of the target well target layer using the well velocity time-shift curve of the target well target layer to obtain a corrected well velocity curve of the target well target layer.

[0120] In an embodiment of the present invention, the target well reservoir acquisition module 1001 obtains a time-shift curve of reservoir parameters for the target well's target layer; the target well porosity prediction module 1002 uses a trained probabilistic neural network model to determine the porosity time-shift curve for the target well's target layer; the target well velocity time-shift determination module 1003 uses a constructed rock physics model to determine the well velocity time-shift curve for the target well's target layer; and finally, the target well velocity correction module 1004 uses the well velocity time-shift curve for the target well's target layer to correct the original velocity curve to obtain a corrected well velocity curve for the target well's target layer. This embodiment of the present invention can predict the porosity time-shift curve using a probabilistic neural network, determine the well velocity time-shift curve using a rock physics model, and ultimately eliminate the temporal variation of the well velocity data through well velocity correction, thereby improving the matching accuracy of well logging and seismic data in the time dimension.

[0121] Figure 11 The structure of the target well reservoir acquisition module 1001 in the well seismic data matching device provided by an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0122] In one embodiment of the present invention, in order to improve the efficiency of obtaining the time-shift curve of reservoir parameters, reference is made to Figure 11 The target well reservoir acquisition module 1001 includes various units for executing Figure 2 For details of each step in the corresponding embodiment, please refer to Figure 2 as well as Figure 2 In the embodiment of the present invention, the target well reservoir acquisition module 1001 includes a target well reservoir acquisition unit 1101 and a target well reservoir curve formation unit 1102 .

[0123] The target well reservoir acquisition unit 1101 is used to obtain the time shift of the reservoir parameters of the target layer of the target well.

[0124] The target well reservoir curve forming unit 1102 is used to repeatedly perform the reservoir parameter time shift of the target well target layer multiple times and form a reservoir parameter time shift curve of the target well target layer using the repeated reservoir parameter time shift of the target well target layer.

[0125] In an embodiment of the present invention, the target well reservoir acquisition unit 1101 obtains the time-shift of the reservoir parameters of the target well target layer, and then repeats the time-shift of the reservoir parameters of the target well target layer multiple times. The target well reservoir curve forming unit 1102 uses the repeated time-shift of the reservoir parameters of the target well target layer to form the reservoir parameter time-shift curve of the target well target layer, which can improve the efficiency of obtaining the reservoir parameter time-shift curve.

[0126] Figure 12 The structure of the target well porosity prediction module 1002 in the well seismic data matching device provided by an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0127] In one embodiment of the present invention, in order to improve the accuracy of predicting the porosity time-shift curve, reference is made to Figure 12 The target well porosity prediction module 1002 includes various units for executing Figure 3 For details of each step in the corresponding embodiment, please refer to Figure 3 as well as Figure 3In the embodiment of the present invention, the target well porosity prediction module 1002 includes a basic well porosity acquisition unit 1201 , a basic well reservoir acquisition unit 1202 , a training unit 1203 and an iterative convergence unit 1204 .

[0128] The basic well porosity acquisition unit 1201 is used to obtain the porosity time-lapse curve of the target layer of the basic well.

[0129] The basic well reservoir acquisition unit 1202 is used to obtain a reservoir parameter time-shift curve corresponding to the porosity time-shift curve of the target layer of the basic well.

[0130] The training unit 1203 is used to train the network parameters of the probabilistic neural network by using the reservoir parameter time-shift curve as the training curve and the porosity time-shift curve as the target curve.

[0131] The iterative convergence unit 1204 is used to repeatedly iterate the training until the training convergence condition is met to obtain the trained probabilistic neural network.

[0132] In this embodiment of the present invention, the base well porosity acquisition unit 1201 and the base well reservoir acquisition unit 1202 acquire a porosity time-shift curve of the base well target layer and its corresponding reservoir parameter time-shift curve. The training unit 1203 then uses the reservoir parameter time-shift curve as a training curve and the porosity time-shift curve as a target curve to train the network parameters of the probabilistic neural network. The iterative convergence unit 1204 repeatedly iteratively trains until the training convergence condition is met, thereby obtaining a trained probabilistic neural network. The trained probabilistic neural network can predict the accuracy of the porosity time-shift curve.

[0133] Figure 13 The structure of the basic well porosity acquisition unit 1201 in the well-seismic data matching device provided by an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0134] In one embodiment of the present invention, in order to improve the efficiency of obtaining the porosity time-lapse curve, reference is made to Figure 13 The various units included in the basic well porosity acquisition unit 1201 are used to perform Figure 4 For details of each step in the corresponding embodiment, please refer to Figure 4 as well as Figure 4 In the embodiment of the present invention, the basic well porosity acquisition unit 1201 includes a basic well porosity time shift determination subunit 1301 and a basic well porosity curve formation subunit 1302 .

[0135] The basic well porosity time shift determination subunit 1301 is used to determine the porosity time shift of the basic well target layer using the point set difference method; the porosity time shift of the basic well target layer is the difference between the target layer porosity mean of the period wells within a preset range centered on the basic well and the target layer porosity mean of the basic well.

[0136] The basic well porosity curve forming subunit 1302 is used to repeat the porosity time shift of the basic well target layer multiple times and form a porosity time shift curve using the repeated porosity time shift of the basic well target layer.

[0137] In an embodiment of the present invention, the basic well porosity time-shift determination subunit 1301 uses the point set difference method to determine the porosity time-shift of the basic well target layer, and then the basic well porosity curve formation subunit 1302 forms a porosity time-shift curve by copying the porosity time-shift, which can improve the efficiency of obtaining the porosity time-shift curve.

[0138] Figure 14 The structure of the basic well reservoir acquisition unit 1202 in the well seismic data matching device provided by an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0139] In one embodiment of the present invention, in order to improve the efficiency of obtaining the time-shift curve of reservoir parameters, reference is made to Figure 14 The various units included in the basic well reservoir acquisition unit 1202 are used to execute Figure 5 For details of each step in the corresponding embodiment, please refer to Figure 5 as well as Figure 5 In the embodiment of the present invention, the basic well reservoir acquisition unit 1202 includes a basic well reservoir time shift determination subunit 1401 and a basic well reservoir curve formation subunit 1402 .

[0140] The basic well reservoir time-shift determination subunit 1401 is used to determine the reservoir parameter time-shift corresponding to the porosity time-shift of the target layer of the basic well using the point set difference method; the reservoir parameter time-shift is the difference between the mean reservoir parameter of the target layer of the wells within a preset range centered on the basic well and the mean reservoir parameter of the target layer of the basic well.

[0141] The basic well reservoir curve forming subunit 1402 is used to repeatedly perform the reservoir parameter time shift of the basic well target layer multiple times and form a reservoir parameter time shift curve using the repeated reservoir parameter time shift of the basic well target layer.

[0142] In an embodiment of the present invention, the basic well reservoir time-shift determination subunit 1401 uses the point set difference method to determine the reservoir parameter time-shift of the basic well target layer, and then the basic well reservoir curve formation subunit 1402 forms a reservoir parameter time-shift curve by copying the reservoir parameter time-shift, which can improve the efficiency of obtaining the reservoir parameter time-shift curve.

[0143] Figure 15 The structure of the target well velocity time shift determination module 1003 in the well seismic data matching device provided by an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0144] In one embodiment of the present invention, in order to improve the accuracy of determining the time-shift curve of the well velocity, reference is made to Figure 15 The target well velocity time shift determination module 1003 includes various units for executing Figure 6 For details of each step in the corresponding embodiment, please refer to Figure 6 as well as Figure 6 In the embodiment of the present invention, the target well velocity time shift determination module 1003 includes a petrophysical parameter determination unit 1501 , a fitting construction unit 1502 and a target well velocity time shift determination unit 1503 .

[0145] The rock physical parameter determination unit 1501 is used to determine the basic rock physical parameters of the rock physical model to be constructed; the basic rock physical parameters at least include the pore aspect ratio.

[0146] The fitting construction unit 1502 is used to adjust the pore aspect ratio to match the forward P- and S-wave velocities of the fitted rock physics model with the measured P- and S-wave velocities to obtain a constructed rock physics model.

[0147] The target well velocity time shift determining unit 1503 is configured to calculate the target well velocity time shift curve of the target layer according to the predicted porosity time shift curve of the target well using the constructed rock physics model.

[0148] In an embodiment of the present invention, the fitting construction unit 150 constructs a rock physics model, and then the target well velocity time-shift determination unit 1503 calculates the well velocity time-shift curve of the target well target layer based on the porosity time-shift curve using the rock physics model, which can improve the accuracy of determining the well velocity time-shift curve.

[0149] Figure 16 The structure of the target well velocity correction module 1004 in the well seismic data matching device provided by an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0150] In one embodiment of the present invention, in order to improve the accuracy of well-seismic matching, reference is made to Figure 16 The target well velocity correction module 1004 includes various units for executing Figure 7 For details of each step in the corresponding embodiment, please refer to Figure 7 as well as Figure 7 In the embodiment of the present invention, the target well velocity correction module 1004 includes a superposition correction unit 1601 .

[0151] The superposition correction unit 1601 is used to superpose the original velocity curve of the target well target layer with the well velocity time-shift curve of the target well target layer to obtain a corrected well velocity curve of the target well target layer.

[0152] In the embodiment of the present invention, the superposition correction unit 1601 superimposes the original velocity curve of the target well target layer with the well velocity time-shift curve of the target well target layer to obtain the corrected well velocity curve of the target well target layer, which can improve the accuracy of well-seismic matching.

[0153] Figure 17 Another functional module of the well seismic data matching device provided by an embodiment of the present invention is shown. For ease of description, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0154] In one embodiment of the present invention, in order to verify the accuracy of the calibration result, reference is made to Figure 17 The modules included in the well-seismic data matching device are used to perform Figure 8 For details of each step in the corresponding embodiment, please refer to Figure 8 as well as Figure 8 The relevant descriptions in the corresponding embodiments are not repeated here. Figure 1 Based on the module structure shown, the well-seismic data matching device further includes a verification module 1701.

[0155] The verification module 1701 is used to verify the accuracy of the correction result by using the original velocity curve of the target layer of the target well and the well velocity curve of the target layer of the target well after correction.

[0156] In the embodiment of the present invention, the verification module 1701 can verify the accuracy of the correction result by using the original velocity curve of the target well target layer and the corrected well velocity curve of the target well target layer.

[0157] Figure 18 The structure of the verification module 1701 in the well seismic data matching device provided by the embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0158] In one embodiment of the present invention, in order to verify the accuracy of the calibration result, reference is made to Figure 18 The various units included in the verification module 1701 are used to perform Figure 9 For details of each step in the corresponding embodiment, please refer to Figure 9 as well as Figure 9 In the embodiment of the present invention, the verification module 1701 includes a well seismic calibration unit 1801 and an accuracy verification unit 1802 .

[0159] The well seismic calibration unit 1801 is used to perform well seismic calibration using the original velocity curve of the target well target layer and the corrected well velocity curve of the target well target layer to determine the synthetic seismic records of the target well target layer before and after correction.

[0160] The accuracy verification unit 1802 is used to verify the accuracy of the correction result by comparing the correlation coefficient before correction with the correlation coefficient after correction; wherein the correlation coefficient before correction is the correlation coefficient between the synthetic seismic record and the actual seismic record of the target well target layer before correction, and the correlation coefficient after correction is the correlation coefficient between the synthetic seismic record and the actual seismic record of the target well target layer after correction.

[0161] In an embodiment of the present invention, the well seismic calibration unit 1801 uses the original velocity curve of the target well target layer and the well velocity curve of the target well target layer after correction to perform well seismic calibration to determine the synthetic seismic records of the target well target layer before and after correction. The accuracy verification unit 1802 verifies the accuracy of the correction result by comparing the correlation coefficient before correction with the correlation coefficient after correction.

[0162] An embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned well-seismic data matching method when executing the computer program.

[0163] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program for executing the well-seismic data matching method.

[0164] In summary, in an embodiment of the present invention, a reservoir parameter time-shift curve of the target well target layer is obtained; a porosity time-shift curve of the target well target layer is determined using a trained probabilistic neural network model; a well velocity time-shift curve of the target well target layer is determined using a constructed rock physics model; and finally, the original velocity curve is corrected using the well velocity time-shift curve of the target well target layer to obtain a corrected well velocity curve of the target well target layer. This embodiment of the present invention can predict the porosity time-shift curve using a probabilistic neural network, determine the well velocity time-shift curve using a rock physics model, and finally eliminate the variation of the well velocity data over time through well velocity correction, thereby improving the matching accuracy of well logging and seismic data in the time dimension.

[0165] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0166] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0167] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0168] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0169] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A well-seismic data matching method, characterized in that: include: Obtain the time-lapse curve of reservoir parameters of the target well and target layer; Based on the reservoir parameter time-shift curve of the target well's target layer, the porosity time-shift curve of the target well's target layer is determined using a trained probabilistic neural network model; the trained probabilistic neural network model can establish a strong nonlinear relationship between the porosity time-shift and the reservoir parameter time-shift; Based on the predicted porosity time-lapse curve of the target well's target layer, the well velocity time-lapse curve of the target well's target layer is determined using the constructed rock physics model; the rock physics model reflects the relationship between well velocity and porosity; Using the well velocity time-shift curve of the target well target layer, the original velocity curve of the target well target layer is corrected to obtain a corrected well velocity curve of the target well target layer; Obtaining a time-shift curve of a reservoir parameter of a target layer of a target well, including: obtaining a time-shift amount of the reservoir parameter of the target layer of the target well; repeating the time-shift amount of the reservoir parameter of the target layer of the target well for multiple times, and forming a time-shift curve of the reservoir parameter of the target layer of the target well using the repeated time-shift amounts of the reservoir parameter of the target layer of the target well; The probabilistic neural network model training process is as follows: obtain the porosity time-shift curve of the target layer of the base well; obtain the reservoir parameter time-shift curve corresponding to the porosity time-shift curve of the target layer of the base well; use the reservoir parameter time-shift curve as the training curve and the porosity time-shift curve as the target curve to train the network parameters of the probabilistic neural network; repeatedly iterate the training until the training convergence condition is met, and obtain the trained probabilistic neural network; Determining a well velocity time-shift curve of the target layer of the target well using a constructed rock physics model based on a predicted porosity time-shift curve of the target layer of the target well, including: determining basic rock physics parameters of the rock physics model to be constructed, wherein the basic rock physics parameters include at least a pore aspect ratio; adjusting the pore aspect ratio to match the forward P- and S-wave velocities of the rock physics model with the measured P- and S-wave velocities to obtain a constructed rock physics model; and calculating a well velocity time-shift curve of the target layer of the target well using the constructed rock physics model based on the predicted porosity time-shift curve of the target layer of the target well; The original velocity curve of the target well target layer is corrected by using the well velocity time-shift curve of the target well target layer to obtain the corrected well velocity curve of the target well target layer, including: superimposing the original velocity curve of the target well target layer with the well velocity time-shift curve of the target well target layer to obtain the corrected well velocity curve of the target well target layer.

2. The well-seismic data matching method according to claim 1, wherein: Obtain the porosity time-lapse curve of the target layer of the base well, including: The porosity time shift of the target layer of the basic well is determined by using the point set difference method; the porosity time shift of the target layer of the basic well is the difference between the mean porosity of the target layer of the period wells within a preset range centered on the basic well and the mean porosity of the target layer of the basic well; The porosity time shift of the target layer of the base well is repeated multiple times, and the porosity time shift curve is formed using the repeated porosity time shift of the target layer of the base well.

3. The well-seismic data matching method according to claim 1, wherein: Obtain the reservoir parameter time-shift curve corresponding to the porosity time-shift curve of the target layer of the base well, including: The time shift of the reservoir parameters corresponding to the porosity time shift of the target layer of the base well is determined using the point set difference method. The time shift of the reservoir parameters is the difference between the mean reservoir parameters of the target layer of the wells within a preset range centered on the base well and the mean reservoir parameters of the target layer of the base well. The time shift of the reservoir parameters of the target layer of the basic well is repeated multiple times, and the time shift of the reservoir parameters of the target layer of the basic well after the repeat is used to form a time shift curve of the reservoir parameters.

4. The well-seismic data matching method according to claim 1, wherein: Also includes: The accuracy of the correction result is verified by using the original velocity curve of the target well target layer and the well velocity curve of the target well target layer after correction.

5. The well-seismic data matching method according to claim 4, characterized in that: The accuracy of the correction results is verified using the original velocity curve of the target well's target layer and the corrected velocity curve of the target well's target layer, including: Well seismic calibration is performed using the original velocity curve of the target well target layer and the well velocity curve of the target well target layer after correction to determine the synthetic seismic records of the target well target layer before and after correction; The accuracy of the correction result is verified by comparing the correlation coefficient before correction with the correlation coefficient after correction; among them, the correlation coefficient before correction is the correlation coefficient between the synthetic seismic record and the actual seismic record of the target well target layer before correction, and the correlation coefficient after correction is the correlation coefficient between the synthetic seismic record and the actual seismic record of the target well target layer after correction.

6. A well seismic data matching device, characterized in that: include: Target well reservoir acquisition module, used to obtain the reservoir parameter time-lapse curve of the target well target layer; The target well porosity prediction module is used to determine the porosity time-shift curve of the target well's target layer based on the reservoir parameter time-shift curve of the target well's target layer using a trained probabilistic neural network model. The trained probabilistic neural network model can establish a strong nonlinear relationship between the porosity time-shift and the reservoir parameter time-shift. The target well velocity time shift determination module is used to determine the target well velocity time shift curve of the target layer based on the predicted porosity time shift curve of the target well using the constructed rock physics model; the rock physics model reflects the relationship between well velocity and porosity; A target well velocity correction module is used to correct the original velocity curve of the target well target layer using the well velocity time-shift curve of the target well target layer to obtain a corrected well velocity curve of the target well target layer; The target well reservoir acquisition module includes: a target well reservoir acquisition unit, which is used to obtain the time-shifted amount of the reservoir parameters of the target well target layer; a target well reservoir curve formation unit, which is used to repeat the time-shifted amount of the reservoir parameters of the target well target layer multiple times and form a reservoir parameter time-shift curve of the target well target layer using the repeated time-shifted amount of the reservoir parameters of the target well target layer; The target well porosity prediction module includes: a base well porosity acquisition unit, used to obtain the porosity time-shift curve of the base well target layer; a base well reservoir acquisition unit, used to obtain the reservoir parameter time-shift curve corresponding to the porosity time-shift curve of the base well target layer; a training unit, used to train the network parameters of the probabilistic neural network using the reservoir parameter time-shift curve as the training curve and the porosity time-shift curve as the target curve; an iterative convergence unit, used to repeatedly iteratively train until the training convergence condition is met to obtain the trained probabilistic neural network; The target well velocity time-shift determination module includes: a rock physical parameter determination unit, used to determine the basic rock physical parameters of the rock physical model to be constructed; the basic rock physical parameters include at least the pore aspect ratio; a fitting construction unit, used to match the forward P- and S-wave velocities of the fitted rock physical model with the measured P- and S-wave velocities by adjusting the pore aspect ratio to obtain a constructed rock physical model; a target well velocity time-shift determination unit, used to calculate the well velocity time-shift curve of the target well target layer using the constructed rock physical model based on the predicted porosity time-shift curve of the target well target layer; The target well velocity correction module includes: a superposition correction unit for superimposing the original velocity curve of the target well target layer with the well velocity time-shift curve of the target well target layer to obtain a corrected well velocity curve of the target well target layer.

7. The well seismic data matching device according to claim 6, characterized in that: The basic well porosity acquisition unit includes: The base well porosity time shift determination subunit is used to determine the porosity time shift of the base well target layer using the point set difference method; the porosity time shift of the base well target layer is the difference between the mean porosity of the target layer of the period wells within a preset range centered on the base well and the mean porosity of the target layer of the base well; The basic well porosity curve forming subunit is used to repeat the porosity time shift of the basic well target layer multiple times and form a porosity time shift curve using the repeated porosity time shift of the basic well target layer.

8. The well seismic data matching device according to claim 6, characterized in that: The basic well reservoir acquisition unit includes: The basic well reservoir time shift determination subunit is used to determine the reservoir parameter time shift corresponding to the porosity time shift of the target layer of the basic well using the point set difference method; the reservoir parameter time shift is the difference between the mean reservoir parameter of the target layer of the well within a preset range centered on the basic well and the mean reservoir parameter of the target layer of the basic well; The basic well reservoir curve forming subunit is used to repeat the reservoir parameter time shift of the basic well target layer multiple times and form a reservoir parameter time shift curve using the repeated reservoir parameter time shift of the basic well target layer.

9. The well seismic data matching device according to claim 6, characterized in that: Also includes: The verification module is used to verify the accuracy of the correction result by using the original velocity curve of the target well target layer and the well velocity curve of the target well target layer after correction.

10. The well seismic data matching device according to claim 9, characterized in that: The verification module includes: A well seismic calibration unit is used to perform well seismic calibration using the original velocity curve of the target well target layer and the well velocity curve of the target well target layer after correction, so as to determine the synthetic seismic records of the target well target layer before and after correction; The accuracy verification unit is used to verify the accuracy of the correction result by comparing the correlation coefficient before correction with the correlation coefficient after correction; wherein the correlation coefficient before correction is the correlation coefficient between the synthetic seismic record and the actual seismic record of the target well target layer before correction, and the correlation coefficient after correction is the correlation coefficient between the synthetic seismic record and the actual seismic record of the target well target layer after correction.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the well-seismic data matching method according to any one of claims 1 to 5 is implemented.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the well-seismic data matching method according to any one of claims 1 to 5 is implemented.

Images