A method and apparatus for predicting shale matrix permeability based on residual depth networks

Abstract

This invention discloses a method and apparatus for predicting shale matrix permeability based on a residual depth network. The method includes: acquiring the velocity, porosity, and permeability curves of drilled wells within a shale reservoir; obtaining a three-dimensional velocity volume of the target layer through interpolation based on the velocity curves; obtaining a three-dimensional porosity data volume based on the three-dimensional velocity volume, constrained by the porosity curves, and utilizing the velocity-permeability mapping relationship of the target layer; and solving the tight reservoir wave control equations using a residual depth network, with the three-dimensional velocity volume, the three-dimensional porosity data volume, and the viscosity attenuation coefficient of the shale within the target layer as known conditions, and constrained by the permeability curves, to obtain the three-dimensional matrix permeability data volume of the target layer. This method achieves reasonable prediction of shale matrix permeability by solving the tight reservoir wave control equations using a residual depth network.

Description

Technical Field

[0001] This invention relates to the field of shale oil and gas exploration and development technology, and in particular to a method and apparatus for predicting shale matrix permeability based on residual depth networks. Background Technology

[0002] Most pores in rocks are interconnected, giving them not only the ability to store oil and gas but also the ability for fluids to seep through. The property of a rock to allow fluids to pass through under a given pressure difference is called its permeability. The permeability parameter of a rock is quantitatively measured by its permeability rate.

[0003] Permeability is an extremely important parameter in the exploration and development of oil and gas reservoirs. Existing methods for determining reservoir permeability mainly include laboratory measurements and well logging curve calculations, but none of them can obtain comprehensive three-dimensional permeability distribution data. Conventional seismic inversion methods can obtain three-dimensional permeability distribution data, but the inversion is highly ambiguous and the inversion accuracy is insufficient. Summary of the Invention

[0004] To enrich process routes and increase the options, this invention provides a method and apparatus for predicting shale matrix permeability based on residual depth networks. By solving the wave control equation of tight reservoirs through residual depth networks, reasonable prediction of shale matrix permeability is achieved.

[0005] In a first aspect, embodiments of the present invention provide a method for predicting shale matrix permeability based on residual depth networks, comprising:

[0006] Obtain the velocity, porosity, and permeability curves of drilled wells within the shale reservoir. Based on the velocity curves, interpolate to obtain the three-dimensional velocity volume of the target layer in the reservoir.

[0007] Based on the three-dimensional velocity volume, and constrained by the porosity curve, the three-dimensional porosity data volume is obtained by utilizing the velocity-porosity mapping relationship of the target layer.

[0008] Using the three-dimensional velocity volume, the three-dimensional porosity data volume, and the viscosity attenuation coefficient of the shale in the target layer as known conditions, and with the permeability curve as a constraint, the tight reservoir wave control equation is solved using a residual depth network to obtain the three-dimensional matrix permeability data volume of the target layer.

[0009] In some embodiments, solving the tight reservoir wave governing equations using a residual depth network includes:

[0010] The wave control equations of tight reservoirs are solved iteratively using a residual depth network until the value of the network loss function reaches the iteration termination condition. During the iteration process, the current value of the network loss function is determined in the following way:

[0011] Using the permeability curve as permeability label data, determine the first error between the current matrix permeability prediction result and the permeability label data;

[0012] Using the velocity curve as velocity label data, and based on the current matrix permeability prediction results, the second error between the predicted velocity and the velocity label data is determined by utilizing the velocity-permeability mapping relationship of the target layer.

[0013] Based on the predicted velocity, earthquake forward modeling data is obtained through convolution operation, and a third error between the earthquake forward modeling data and the actual earthquake data is determined.

[0014] The sum of the first error, the second error, and the third error is determined as the value of the current network loss function.

[0015] In some embodiments, the velocity-permeability mapping relationship is pre-established in the following manner:

[0016] Based on experimental test data of velocity and permeability of multiple shale samples within the target layer, a mapping relationship between velocity and permeability is established.

[0017] In some embodiments, the velocity-permeability mapping relationship is pre-established in the following manner:

[0018] Based on the experimental test data of velocity and permeability of multiple shale samples in the target layer at multiple temperature points in the first temperature range, a velocity-permeability mapping relationship is established in the first temperature range, which is the temperature range corresponding to the low-maturity thermal evolution stage of shale organic matter.

[0019] Based on the experimental test data of velocity and permeability of multiple shale samples in the target layer at multiple temperature points in the second temperature range, a velocity-permeability mapping relationship is established in the second temperature range, which is the temperature range corresponding to the thermal evolution stage of shale organic matter maturity.

[0020] Based on experimental test data of velocity and permeability of multiple shale samples in the target layer at multiple temperature points within the third temperature range, a velocity-permeability mapping relationship is established within the third temperature range, which is the temperature range corresponding to the over-maturation thermal evolution stage of shale organic matter.

[0021] In some embodiments, obtaining the predicted velocity using the velocity-permeability mapping relationship of the target layer includes:

[0022] The temperature range to which the target layer belongs is determined based on the temperature conditions corresponding to the permeability of the matrix to be solved. The predicted velocity is obtained by using the velocity-permeability mapping relationship between the target layer and the temperature range.

[0023] In some embodiments, obtaining the three-dimensional velocity volume of the reservoir target layer by interpolation based on the velocity curve includes:

[0024] Based on the velocity curve, analytical interpolation is performed along the formation structure of the target reservoir layer to obtain the three-dimensional velocity volume of the target reservoir layer.

[0025] In some embodiments, before solving the tight reservoir wave governing equations using a residual depth network, the method further includes:

[0026] The three-dimensional velocity volume, the three-dimensional porosity data volume, and the permeability curve are decomposed into background components and disturbance components, respectively.

[0027] In some embodiments, the tight reservoir wave control equation is:

[0028]

[0029] Where P represents the seismic wave field and t represents time. For seismic wave velocity, Porosity Permeability coefficient, For fluid viscosity, For fluid density, For reservoir permeability, This is the viscous decay coefficient.

[0030] In some embodiments, the step of solving the tight reservoir wave control equation using a residual depth network to obtain the three-dimensional matrix permeability data volume of the target layer includes:

[0031] The wave control equation of tight reservoirs is solved using residual depth networks to obtain the predicted permeability coefficient.

[0032] Based on the density and viscosity of the fluid within the target layer, a three-dimensional matrix permeability data volume is obtained from the permeability coefficient prediction results.

[0033] Secondly, embodiments of the present invention provide an apparatus for predicting shale matrix permeability based on a residual depth network, comprising:

[0034] The basic data processing module is used to obtain the velocity, porosity and permeability curves of drilled wells in shale reservoirs. Based on the velocity curves, the three-dimensional velocity volume of the target layer of the reservoir is obtained by interpolation.

[0035] The three-dimensional porosity data volume prediction module is used to obtain the three-dimensional porosity data volume based on the three-dimensional velocity volume, with the porosity curve as a constraint, and by utilizing the velocity-porosity mapping relationship of the target layer.

[0036] The three-dimensional matrix permeability data volume prediction module is used to obtain the three-dimensional matrix permeability data volume of the target layer by solving the tight reservoir wave control equation using the residual depth network, with the three-dimensional velocity volume, the three-dimensional porosity data volume and the viscosity attenuation coefficient of the shale in the target layer as known conditions and the permeability curve as a constraint.

[0037] Thirdly, embodiments of the present invention provide a computer storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method for predicting shale matrix permeability based on residual depth networks.

[0038] Fourthly, embodiments of this disclosure provide a server, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described method for predicting shale matrix permeability based on residual depth networks.

[0039] The beneficial effects of the above-described technical solutions provided in the embodiments of the present invention include at least the following:

[0040] (1) The velocity-permeability coefficient characteristic equation, i.e., the wave control equation of tight reservoirs, is difficult to solve. The method for predicting shale matrix permeability based on residual depth network provided in this embodiment of the invention first obtains the porosity data volume from the velocity volume using the velocity-porosity mapping relationship. Then, using the three-dimensional velocity volume, the three-dimensional porosity data volume, and the viscosity attenuation coefficient of shale in the target layer as known conditions, and the permeability curve as a constraint, the wave control equation of tight reservoirs is solved using residual depth network to obtain the three-dimensional matrix permeability data volume of the target layer. This achieves three-dimensional prediction of shale matrix permeability, and the prediction is reasonable and accurate.

[0041] (2) The method for predicting shale matrix permeability based on residual depth network provided in this embodiment of the invention ensures the accuracy of the prediction results by limiting the triple error; and in the process, no single error is considered, only the total error is considered, so as to avoid getting trapped in local optima.

[0042] (3) The method for predicting shale matrix permeability based on residual depth network provided in the embodiments of the present invention establishes the mapping relationship between velocity and permeability in different temperature ranges, making the predicted permeability volume closer to the actual geological situation and more usable.

[0043] (4) The method for predicting shale matrix permeability based on residual depth network provided in this embodiment of the invention decomposes velocity, porosity and permeability into background components and disturbance components, reducing the network inversion time and avoiding getting trapped in local optima.

[0044] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0045] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0046] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0047] Figure 1 This is a flowchart of the method for predicting shale matrix permeability based on residual depth networks in an embodiment of the present invention;

[0048] Figure 2 This is a schematic diagram illustrating the construction of the network loss function in an embodiment of the present invention;

[0049] Figure 3 This is a schematic diagram of the device for predicting shale matrix permeability based on residual depth network in an embodiment of the present invention. Detailed Implementation

[0050] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0051] It should be understood that the terminology used in this invention is merely for describing particular embodiments and is not intended to limit the invention. Furthermore, with respect to numerical ranges in this invention, it should be understood that each intermediate value between the upper and lower limits of the range is also specifically disclosed. Every smaller range between any stated value or intermediate value within a stated range, and any other stated value or intermediate value within said range, is also included in this invention. The upper and lower limits of these smaller ranges may be independently included or excluded from the range.

[0052] Unless otherwise stated, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. While only preferred methods and materials have been described herein, any methods and materials similar or equivalent to those described herein may be used in the implementation or testing of this invention. All references to this specification are incorporated by way of citation to disclose and describe methods and / or materials associated with those references. In the event of any conflict with any incorporated reference, the content of this specification shall prevail.

[0053] This invention provides a method and apparatus for predicting shale matrix permeability based on residual depth networks. By solving the wave control equations of tight reservoirs using residual depth networks, reasonable prediction of shale matrix permeability is achieved.

[0054] Example

[0055] This invention provides a method for predicting shale matrix permeability based on residual depth networks, the process of which is as follows: Figure 1 As shown, it includes the following steps:

[0056] Step S11: Obtain the velocity, porosity, and permeability curves of the drilled wells in the shale reservoir. Based on the velocity curves, interpolate to obtain the three-dimensional velocity volume of the target layer in the reservoir.

[0057] Obtaining the velocity, porosity, and permeability profiles of drilled wells can include the following steps:

[0058] (1) Combine rock physics experimental data to correct the existing well logging data in the reservoir and obtain the velocity, porosity and permeability curves at the well location;

[0059] (2) Based on the mineral volume content (obtained through coring and logging curves), velocity curves were constructed using the Xu-White rock physics model;

[0060] (3) Since the logging curves obtained in step (1) are affected by the expansion and contraction of the diameter, the logging curves of some well sections with abnormal diameters are prone to certain errors. At this time, the curves obtained in steps (1) and (2) can be combined to obtain a more reliable velocity curve.

[0061] (4) Perform well-sound matching correction on velocity, porosity and permeability curves.

[0062] In this embodiment, the velocity is specifically the longitudinal wave velocity V. P .

[0063] Based on the velocity curve, analytical interpolation is performed along the formation structure of the target reservoir layer to obtain the three-dimensional velocity volume of the target reservoir layer.

[0064] Furthermore, the seismic data volume can be used as a constraint during the interpolation process.

[0065] Step S12: Based on the three-dimensional velocity volume and constrained by the porosity curve, the three-dimensional porosity data volume is obtained by utilizing the velocity-porosity mapping relationship of the target layer.

[0066] The mapping relationship between velocity and porosity can be established in advance in the following way:

[0067] Based on experimental test data of velocity and porosity from multiple shale samples within the target layer, a mapping relationship between velocity and porosity was established through mathematical fitting.

[0068] Step S13: Using the three-dimensional velocity volume, the three-dimensional porosity data volume, and the viscosity attenuation coefficient of the shale in the target layer as known conditions, and the permeability curve as a constraint, the residual depth network is used to solve the tight reservoir wave control equation to obtain the three-dimensional matrix permeability data volume of the target layer.

[0069] The governing equations for tight reservoir waves, i.e., the seismic wave equations for tight oil and gas, are as follows:

[0070]

[0071] Where P represents the seismic wave field and t represents time. For seismic wave velocity, Porosity Permeability coefficient, For fluid viscosity, For fluid density, For reservoir permeability, This is the viscous decay coefficient.

[0072] Substituting velocity, porosity, and viscosity attenuation coefficient into the above equations, the wave control equations of the tight reservoir are solved iteratively using a residual depth network to obtain the permeability coefficient prediction results. Based on the density and viscosity of the fluid within the target layer, the three-dimensional matrix permeability data volume is obtained from the permeability coefficient prediction results.

[0073] In some embodiments, low-pass filtering can be used to decompose the three-dimensional velocity volume, the three-dimensional porosity data volume, and the permeability curve into background and disturbance components, respectively. The decomposed data is then used to solve for the three-dimensional matrix permeability data volume.

[0074] Decomposing velocity, porosity, and permeability into background and disturbance components reduces the time required for network inversion and avoids getting trapped in local optima.

[0075] In some embodiments, the above-described method utilizes a residual depth network to iteratively solve the wave control equations of tight reservoirs until the value of the network loss function reaches the iteration termination condition. (See [link to previous text]). Figure 2 As shown, the current value of the network loss function is determined during the iteration process in the following way:

[0076] Using the permeability curve as permeability label data, determine the first error between the current matrix permeability prediction result and the permeability label data;

[0077] Using the velocity curve as velocity label data, based on the current matrix permeability prediction results, the predicted velocity is obtained by utilizing the velocity-permeability mapping relationship of the target layer, and the second error between the predicted velocity and the velocity label data is determined.

[0078] Based on the predicted velocity, earthquake forward modeling data is obtained through convolution operation, and the third error between the earthquake forward modeling data and the actual earthquake data is determined.

[0079] The sum of the first error, the second error, and the third error is determined as the value of the current network loss function.

[0080] The velocity-permeability coefficient characteristic equation, also known as the wave control equation for tight reservoirs, is difficult to solve. This invention provides a method for predicting shale matrix permeability based on a residual depth network. First, it uses the velocity-porosity mapping relationship to obtain a porosity data volume from the velocity volume. Then, using the three-dimensional velocity volume, the three-dimensional porosity data volume, and the viscosity attenuation coefficient of the shale within the target layer as known conditions, and the permeability curve as a constraint, it uses a residual depth network to solve the tight reservoir wave control equation, obtaining a three-dimensional matrix permeability data volume for the target layer. This achieves three-dimensional prediction of shale matrix permeability with strong predictive rationality and high accuracy.

[0081] The method for predicting shale matrix permeability based on residual depth network provided in this invention ensures the accuracy of the prediction results through triple error limitation; and in the process, it does not consider individual errors, but only the total error, thus avoiding getting trapped in local optima.

[0082] The above-mentioned mapping relationship between velocity and permeability is established in advance in the following manner:

[0083] Based on experimental test data of velocity and permeability of multiple shale samples within the target layer, a mapping relationship between velocity and permeability is established.

[0084] Since matrix permeability is significantly affected by shale temperature, we can further establish different mapping relationships between velocity and permeability for different temperature ranges:

[0085] (1) The first temperature range corresponding to the low-maturity thermal evolution stage of shale organic matter

[0086] Based on experimental test data of velocity and permeability of multiple shale samples within the target layer at multiple temperature points in the first temperature range, a mapping relationship between velocity and permeability in the first temperature range is established.

[0087] The low-maturity thermal evolution stage of organic matter is the stage where Ro < 0.8%.

[0088] (2) The second temperature range corresponding to the thermal evolution stage of shale organic matter maturation

[0089] Based on experimental test data of velocity and permeability of multiple shale samples within the target layer at multiple temperature points in the second temperature range, a mapping relationship between velocity and permeability in the second temperature range is established.

[0090] The organic matter maturation thermal evolution stage is the 0.8%≤Ro≤1.5% stage.

[0091] (3) The third temperature range corresponding to the over-maturation thermal evolution stage of shale organic matter

[0092] Based on experimental test data of velocity and permeability of multiple shale samples within the target layer at multiple temperature points in the third temperature range, a velocity-permeability mapping relationship is established in the third temperature range.

[0093] The over-maturation thermal evolution stage of organic matter is the stage where Ro>1.5%.

[0094] Accordingly, the determination of the second error may include determining the temperature range corresponding to the temperature conditions of the matrix permeability to be solved, using the velocity curve as velocity label data, and based on the current matrix permeability prediction results, using the velocity-permeability mapping relationship of the target layer with the temperature range to obtain the predicted velocity.

[0095] The method for predicting shale matrix permeability based on residual depth networks provided in this invention establishes the mapping relationship between velocity and permeability in different temperature ranges, making the predicted permeability volume closer to the actual geological situation and thus more usable.

[0096] Based on the inventive concept of this invention, embodiments of this invention also provide a device for predicting shale matrix permeability based on residual depth networks, the structure of which is as follows: Figure 3 As shown, it includes:

[0097] The basic data processing module 31 is used to obtain the velocity, porosity and permeability curves of the drilled wells in the shale reservoir, and to obtain the three-dimensional velocity volume of the target layer of the reservoir by interpolation based on the velocity curves.

[0098] The three-dimensional porosity data volume prediction module 32 is used to obtain the three-dimensional porosity data volume based on the three-dimensional velocity volume, with the porosity curve as a constraint, and by utilizing the velocity-porosity mapping relationship of the target layer.

[0099] The three-dimensional matrix permeability data volume prediction module 33 is used to obtain the three-dimensional matrix permeability data volume of the target layer by using the three-dimensional velocity volume, the three-dimensional porosity data volume and the viscosity attenuation coefficient of the shale in the target layer as known conditions, the permeability curve as a constraint, and the residual depth network to solve the tight reservoir wave control equation.

[0100] In some embodiments, the three-dimensional matrix permeability data volume prediction module 33, which utilizes a residual depth network to solve the tight reservoir wave control equation, is used for:

[0101] The residual depth network iteratively solves the wave control equations of tight reservoirs until the value of the network loss function reaches the iteration termination condition. During the iteration process, the current value of the network loss function is determined in the following ways: using the permeability curve as permeability label data, the first error between the current matrix permeability prediction result and the permeability label data is determined; using the velocity curve as velocity label data, based on the current matrix permeability prediction result, the predicted velocity is obtained using the velocity-permeability mapping relationship of the target layer, and the second error between the predicted velocity and the velocity label data is determined; based on the predicted velocity, seismic forward modeling data is obtained through convolution operation, and the third error between the seismic forward modeling data and the actual seismic data is determined; the sum of the first error, the second error, and the third error is determined as the value of the current network loss function.

[0102] In some embodiments, the above-described apparatus further includes a velocity-permeability mapping relationship establishment module 34, used to: establish a velocity-permeability mapping relationship based on experimental test data of velocity and permeability of multiple shale samples within the target layer.

[0103] In some embodiments, the velocity-permeability mapping module 34 is further configured to:

[0104] Based on experimental test data of velocity and permeability of multiple shale samples within the target layer at multiple temperature points within a first temperature range, a velocity-permeability mapping relationship is established within the first temperature range, which corresponds to the low-maturity thermal evolution stage of shale organic matter. Based on experimental test data of velocity and permeability of multiple shale samples within the target layer at multiple temperature points within a second temperature range, a velocity-permeability mapping relationship is established within the second temperature range, which corresponds to the mature thermal evolution stage of shale organic matter. Based on experimental test data of velocity and permeability of multiple shale samples within the target layer at multiple temperature points within a third temperature range, a velocity-permeability mapping relationship is established within the third temperature range, which corresponds to the over-maturity thermal evolution stage of shale organic matter.

[0105] In some embodiments, the three-dimensional matrix permeability data volume prediction module 33, which uses the velocity-permeability mapping relationship of the target layer to obtain the predicted velocity, is used for:

[0106] The temperature range to which the target layer belongs is determined based on the temperature conditions corresponding to the permeability of the matrix to be solved. The predicted velocity is obtained by using the velocity-permeability mapping relationship between the target layer and the temperature range.

[0107] In some embodiments, the basic data processing module 31, which obtains the three-dimensional velocity volume of the reservoir target layer by interpolation based on the velocity curve, is used for:

[0108] Based on the velocity curve, analytical interpolation is performed along the formation structure of the target reservoir layer to obtain the three-dimensional velocity volume of the target reservoir layer.

[0109] In some embodiments, before the three-dimensional matrix permeability data volume prediction module 33 solves the tight reservoir wave governing equation using the residual depth network, it is also used for:

[0110] The three-dimensional velocity volume, the three-dimensional porosity data volume, and the permeability curve are decomposed into background components and disturbance components, respectively.

[0111] In some embodiments, the three-dimensional matrix permeability data volume prediction module 33, which uses a residual depth network to solve the tight reservoir wave control equation to obtain the three-dimensional matrix permeability data volume of the target layer, is used for:

[0112] The wave control equation of the tight reservoir is solved using a residual depth network to obtain the permeability coefficient prediction result; based on the density and viscosity of the fluid in the target layer, a three-dimensional matrix permeability data volume is obtained from the permeability coefficient prediction result.

[0113] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0114] Based on the inventive concept of this invention, embodiments of this invention also provide a computer storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method for predicting shale matrix permeability based on residual depth networks.

[0115] Based on the inventive concept of this invention, embodiments of this invention also provide a server, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described method for predicting shale matrix permeability based on residual depth networks.

[0116] Unless otherwise specifically stated, terms such as processing, calculation, operation, determination, display, etc., may refer to the actions and / or processes of one or more processing or computing systems or similar devices that represent the manipulation and conversion of data representing physical (e.g., electronic) quantities within the registers or memory of the processing system into other data similarly representing physical quantities within the memory, registers, or other such information storage, transmission, or display devices of the processing system. Information and signals can be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the above description can be represented by voltage, current, electromagnetic waves, magnetic fields or particles, light fields or particles, or any combination thereof.

[0117] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process may be rearranged without departing from the scope of this disclosure. The appended method claims provide elements of various steps in an exemplary order and are not intended to limit the scope to the specific order or hierarchy described.

[0118] In the detailed description above, various features are combined together in a single embodiment to simplify this disclosure. This approach to disclosure should not be construed as reflecting an intention that embodiments of the claimed subject matter require more features than those stated in each claim. Rather, as reflected in the appended claims, the invention is presented with fewer features than all of the features in a single disclosed embodiment. Therefore, the appended claims are hereby clearly incorporated into the detailed description, wherein each claim stands alone as a preferred embodiment of the invention.

[0119] Those skilled in the art will also understand that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments herein can be implemented as electronic hardware, computer software, or a combination thereof. To clearly illustrate the interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps described above are generally described in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art can implement the described functionality in alternative ways for each specific application; however, such implementation decisions should not be construed as departing from the scope of this disclosure.

[0120] The steps of the methods or algorithms described in conjunction with the embodiments herein can be directly embodied in hardware, software modules executed by a processor, or a combination thereof. The software modules can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in a user terminal. Alternatively, the processor and storage medium can exist as discrete components in the user terminal.

[0121] For software implementation, the techniques described in this application can be implemented using modules (e.g., procedures, functions, etc.) that perform the functions described in this application. This software code can be stored in memory units and executed by a processor. The memory units can be implemented within the processor or outside the processor; in the latter case, they are communicatively coupled to the processor via various means, as is well known in the art.

[0122] The foregoing description includes examples of one or more embodiments. It is certainly impossible to describe all possible combinations of components or methods in order to describe the above embodiments, but those skilled in the art will recognize that further combinations and arrangements of the various embodiments are possible. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. Furthermore, the term “comprising” as used in the specification or claims is interpreted in a manner similar to the term “including,” as it is understood when used as a conjunction in the claims. Additionally, the use of any term “or” in the specification of the claims is intended to mean “non-exclusive or.” The terms “first” and “second” are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

Claims

1. A method for predicting shale matrix permeability based on residual depth networks, characterized in that, include: Obtain the velocity, porosity, and permeability curves of drilled wells within the shale reservoir. Based on the velocity curves, interpolate to obtain the three-dimensional velocity volume of the target layer in the reservoir. Based on the three-dimensional velocity volume, and constrained by the porosity curve, the three-dimensional porosity data volume is obtained by utilizing the velocity-porosity mapping relationship of the target layer. Using the three-dimensional velocity volume, the three-dimensional porosity data volume, and the viscosity attenuation coefficient of the shale in the target layer as known conditions, and the permeability curve as a constraint, the tight reservoir wave control equation is solved using a residual depth network to obtain the three-dimensional matrix permeability data volume of the target layer. The method of solving the wave governing equations of tight reservoirs using residual depth networks includes: The wave control equations of tight reservoirs are solved iteratively using a residual depth network until the value of the network loss function reaches the iteration termination condition. During the iteration process, the current value of the network loss function is determined in the following way: Using the permeability curve as permeability label data, determine the first error between the current matrix permeability prediction result and the permeability label data; Using the velocity curve as velocity label data, based on the current matrix permeability prediction results, the velocity-permeability mapping relationship of the target layer is used to obtain the predicted velocity, and the second error between the predicted velocity and the velocity label data is determined. Based on the predicted velocity, earthquake forward modeling data is obtained through convolution operation, and a third error between the earthquake forward modeling data and the actual earthquake data is determined. The sum of the first error, the second error, and the third error is determined as the value of the current network loss function.

2. The method as described in claim 1, characterized in that, The mapping relationship between velocity and permeability is established in advance in the following manner: Based on experimental test data of velocity and permeability of multiple shale samples within the target layer, a mapping relationship between velocity and permeability is established.

3. The method as described in claim 2, characterized in that, The mapping relationship between velocity and permeability is established in advance in the following manner: Based on the experimental test data of velocity and permeability of multiple shale samples in the target layer at multiple temperature points in the first temperature range, a velocity-permeability mapping relationship is established in the first temperature range, which is the temperature range corresponding to the low-maturity thermal evolution stage of shale organic matter. Based on the experimental test data of velocity and permeability of multiple shale samples in the target layer at multiple temperature points in the second temperature range, a velocity-permeability mapping relationship is established in the second temperature range, which is the temperature range corresponding to the thermal evolution stage of shale organic matter maturity. Based on experimental test data of velocity and permeability of multiple shale samples in the target layer at multiple temperature points within the third temperature range, a velocity-permeability mapping relationship is established within the third temperature range, which is the temperature range corresponding to the over-maturation thermal evolution stage of shale organic matter.

4. The method as described in claim 3, characterized in that, The process of obtaining the predicted velocity by utilizing the velocity-permeability mapping relationship of the target layer includes: The temperature range to which the target layer belongs is determined based on the temperature conditions corresponding to the permeability of the matrix to be solved. The predicted velocity is obtained by using the velocity-permeability mapping relationship between the target layer and the temperature range.

5. The method as described in claim 1, characterized in that, The method of obtaining the three-dimensional velocity volume of the target reservoir layer by interpolation based on the velocity curve includes: Based on the velocity curve, analytical interpolation is performed along the formation structure of the target reservoir layer to obtain the three-dimensional velocity volume of the target reservoir layer.

6. The method as described in claim 1, characterized in that, Before solving the wave governing equations of tight reservoirs using residual depth networks, the following steps are also included: The three-dimensional velocity volume, the three-dimensional porosity data volume, and the permeability curve are decomposed into background components and disturbance components, respectively.

7. The method as described in claim 1, characterized in that, The wave control equation for the tight reservoir is: ； Where P represents the seismic wave field and t represents time. For seismic wave velocity, Porosity Permeability coefficient, For fluid viscosity, For fluid density, For reservoir permeability, This is the viscous decay coefficient.

8. The method as described in claim 7, characterized in that, The method of solving the tight reservoir wave control equation using a residual depth network to obtain the three-dimensional matrix permeability data volume of the target layer includes: The wave control equation of tight reservoirs is solved using residual depth networks to obtain the predicted permeability coefficient. Based on the density and viscosity of the fluid within the target layer, a three-dimensional matrix permeability data volume is obtained from the permeability coefficient prediction results.

9. A device for predicting shale matrix permeability based on residual depth networks, characterized in that, include: The basic data processing module is used to obtain the velocity, porosity and permeability curves of drilled wells in shale reservoirs. Based on the velocity curves, the three-dimensional velocity volume of the target layer of the reservoir is obtained by interpolation. A three-dimensional porosity data volume prediction module is used to obtain a three-dimensional porosity data volume based on the three-dimensional velocity volume, with the porosity curve as a constraint, and by utilizing the velocity-porosity mapping relationship of the target layer. The three-dimensional matrix permeability data volume prediction module is used to obtain the three-dimensional matrix permeability data volume of the target layer by using the three-dimensional velocity volume, the three-dimensional porosity data volume, and the viscosity attenuation coefficient of the shale in the target layer as known conditions, and the permeability curve as a constraint, and solving the tight reservoir wave control equation using a residual depth network. Specifically, the solution of the tight reservoir wave control equation using the residual depth network is used to iteratively solve the tight reservoir wave control equation until the value of the network loss function reaches the iteration termination condition. During the iteration process, the current value of the network loss function is determined in the following way: using permeability... The rate curve is used as permeability label data. A first error is determined between the current matrix permeability prediction result and the permeability label data. Using the velocity curve as velocity label data, based on the current matrix permeability prediction result, the predicted velocity is obtained using the velocity-permeability mapping relationship of the target layer. A second error is determined between the predicted velocity and the velocity label data. Based on the predicted velocity, seismic forward modeling data is obtained through convolution operation. A third error is determined between the seismic forward modeling data and the actual seismic data. The sum of the first error, the second error, and the third error is determined as the value of the current network loss function.

10. A computer storage medium, characterized in that, The computer storage medium stores computer-executable instructions, which, when executed by a processor, implement the method for predicting shale matrix permeability based on residual depth networks as described in any one of claims 1 to 8.

11. A server, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method for predicting shale matrix permeability based on residual depth networks as described in any one of claims 1 to 8.

Images