Method and device for predicting shale porosity and matrix permeability based on neural network

Abstract

The invention discloses a method and device for predicting shale porosity and matrix permeability based on a neural network. The method comprises the steps of obtaining a speed curve, a porosity curve and a permeability curve of a drilled well in a shale reservoir, and obtaining a three-dimensional speed body of a target layer through interpolation based on the speed curve; taking the three-dimensional velocity body and the viscosity attenuation coefficient of the shale in the target layer as known conditions, taking the porosity curve and the permeability curve as constraints, and solving a tight reservoir wave control equation by utilizing a neural network to obtain a three-dimensional porosity data body and a matrix permeability data body of the target layer. According to the method, the tight reservoir wave control equation is solved through the neural network, and the shale porosity and the matrix permeability are reasonably predicted.

Description

Technical Field

[0001] The present invention relates to the technical field of shale oil and gas exploration and development, and in particular to a method and device for predicting shale porosity and matrix permeability based on a neural network. Background Art

[0002] Rocks are composed of rock skeletons, pores, and fluids in the pores. The ratio of the rock pore volume to the total rock volume is the rock's porosity, which reflects the ability to store fluids. Most of the pores in a rock sample are interconnected, and it not only has the ability to store oil and gas, but also the ability for fluids to flow through it. Under a certain pressure difference, the property of rock that allows fluids to pass through is called rock permeability, and the quantitative measurement of rock permeability parameters is called rock permeability. When formulating a shale reservoir development plan, it is necessary to master the reservoir's porosity and permeability distribution data. Existing methods for determining reservoir porosity and permeability, including laboratory measurements and logging curve calculations, cannot obtain comprehensive three-dimensional porosity and permeability distribution data. Conventional seismic inversion methods can obtain three-dimensional data on physical property distribution, but the inversion has strong multi-solutions and insufficient inversion accuracy.

[0003] Shale porosity and permeability are key parameters for evaluating the optimal sweet spot and predicting single well production and EUR. It is urgent to develop new methods that can improve the three-dimensional prediction accuracy of shale reservoir porosity and permeability. Summary of the invention

[0004] In order to enrich the process routes and increase the selection space, the embodiment of the present invention provides a method and device for predicting shale porosity and matrix permeability based on neural network. The tight reservoir wave control equation is solved by neural network to achieve reasonable three-dimensional prediction of shale porosity and matrix permeability.

[0005] In a first aspect, an embodiment of the present invention provides a method for predicting shale porosity and matrix permeability based on a neural network, comprising:

[0006] Obtaining velocity, porosity and permeability curves of the wells drilled in the shale reservoir, and obtaining a three-dimensional velocity body of the target layer of the reservoir by interpolation based on the velocity curves;

[0007] With the three-dimensional velocity body and the viscous attenuation coefficient of the shale in the target layer as known conditions, and with the porosity curve and the permeability curve as constraints, a neural network is used to solve the tight reservoir wave control equation to obtain the three-dimensional porosity data body and matrix permeability data body of the target layer.

[0008] In some embodiments, the method of solving the tight reservoir wave control equation using a neural network includes:

[0009] The neural 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 value of the current network loss function is determined by the following method:

[0010] Taking the porosity curve and the permeability curve as physical property label data, determining a first error between the current porosity prediction result and the matrix permeability prediction result and the physical property label data;

[0011] Taking the velocity curve as the velocity label data, based on the current matrix permeability prediction result, using the velocity and permeability mapping relationship of the target layer, a predicted velocity is obtained, and a second error between the predicted velocity and the velocity label data is determined;

[0012] According to the predicted velocity, seismic forward modeling data is obtained by convolution operation, and a third error between the seismic forward modeling data and actual seismic data is determined;

[0013] The sum of the first error, the second error and the third error is determined as the value of the current network loss function.

[0014] In some embodiments, the velocity and permeability mapping relationship is pre-established in the following manner:

[0015] Based on the velocity and permeability experimental test data of multiple shale samples in the target layer, a velocity and permeability mapping relationship is established.

[0016] In some embodiments, the velocity and permeability mapping relationship is pre-established in the following manner:

[0017] Based on the velocity and permeability experimental test data of multiple shale samples in the target layer at multiple temperature points in a first temperature interval, a velocity and permeability mapping relationship in the first temperature interval is established, and the first temperature interval is a temperature interval corresponding to the low-maturity thermal evolution stage of shale organic matter;

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

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

[0020] In some embodiments, the using the velocity and permeability mapping relationship of the target layer to obtain the predicted velocity includes:

[0021] The temperature range is determined according to the temperature conditions corresponding to the porosity and matrix permeability to be solved, and the predicted velocity is obtained by using the velocity and permeability mapping relationship corresponding to the temperature range of the target layer.

[0022] In some embodiments, before solving the tight reservoir wave control equation using a neural network, the method further includes:

[0023] The three-dimensional velocity body, porosity curve and permeability curve are respectively decomposed into a background component and a disturbance component.

[0024] In some embodiments, the tight reservoir wave governing equation is:

[0025]

[0026] Where P is the seismic wave field, t is time, v is the seismic wave velocity, φ is the porosity, γ is the permeability coefficient, μ f is the fluid viscosity, ρ f is the fluid density, k is the reservoir permeability, b f is the viscous attenuation coefficient.

[0027] In some embodiments, the method of using a neural network to solve the tight reservoir wave governing equation to obtain a three-dimensional porosity data volume and a matrix permeability data volume of the target layer includes:

[0028] The neural network is used to solve the tight reservoir wave control equation to obtain the three-dimensional porosity data volume and permeability coefficient data volume;

[0029] According to the density and viscosity of the fluid in the target layer, a three-dimensional matrix permeability data volume is obtained from the permeability coefficient data volume.

[0030] In a second aspect, an embodiment of the present invention provides a device for predicting shale porosity and matrix permeability based on a neural network, comprising:

[0031] A basic data processing module is used to obtain velocity, porosity and permeability curves of the wells drilled in the shale reservoir, and obtain a three-dimensional velocity body of the target layer of the reservoir by interpolation based on the velocity curve;

[0032] The three-dimensional physical property data prediction module is used to solve the tight reservoir wave control equation using a neural network with the three-dimensional velocity body and the viscous attenuation coefficient of the shale in the target layer as known conditions, and with the porosity curve and the permeability curve as constraints, to obtain the three-dimensional porosity data body and matrix permeability data body of the target layer.

[0033] In a third aspect, an embodiment of the present invention provides a computer storage medium, wherein the computer storage medium stores computer executable instructions, and when the computer executable instructions are executed by a processor, the above-mentioned method for predicting shale porosity and matrix permeability based on a neural network is implemented.

[0034] In a fourth aspect, an embodiment of the present disclosure provides a server, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for predicting shale porosity and matrix permeability based on a neural network is implemented.

[0035] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:

[0036] (1) The wave control equations of tight reservoirs are difficult to solve. The method for predicting shale porosity and matrix permeability based on a neural network provided in the embodiment of the present invention uses a three-dimensional velocity body and the viscous attenuation coefficient of shale in the target layer as known conditions, and a porosity curve and a permeability curve as constraints. The neural network is used to solve the wave control equations of tight reservoirs to obtain a three-dimensional porosity data body and a matrix permeability data body of the target layer. The three-dimensional prediction of shale porosity and matrix permeability is achieved, and the prediction is highly reasonable and accurate.

[0037] (2) The method for predicting shale porosity and matrix permeability based on a neural network provided in an embodiment of the present invention ensures the accuracy of the prediction results by limiting the triple error; and in the process, only the total error is considered regardless of the single error, thereby avoiding falling into the local optimum.

[0038] (3) In the method for predicting shale porosity and matrix permeability based on a neural network provided in an embodiment of the present invention, the velocity and permeability mapping relationship is established in different temperature intervals, so that the predicted porosity and permeability are closer to the actual geological conditions and have higher usability.

[0039] (4) The method for predicting shale porosity and matrix permeability based on a neural network provided in an embodiment of the present invention decomposes velocity, porosity and permeability into background components and disturbance components, thereby reducing the time of network inversion and avoiding falling into a local optimal solution.

[0040] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0041] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0043] Figure 1 It is a flow chart of a method for predicting shale porosity and matrix permeability based on a neural network in an embodiment of the present invention;

[0044] Figure 2 A schematic diagram of constructing a network loss function in an embodiment of the present invention;

[0045] Figure 3 It is a schematic diagram of the structure of a device for predicting shale porosity and matrix permeability based on a neural network in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0047] It should be understood that the terms described in the present invention are only for describing special embodiments and are not intended to limit the present invention. In addition, for the numerical range in the present invention, it should be understood that each intermediate value between the upper and lower limits of the scope is also specifically disclosed. Each smaller range between the intermediate value in any stated value or stated range and any other stated value or intermediate value in the described range is also included in the present invention. The upper and lower limits of these smaller ranges can be independently included or excluded in the scope.

[0048] Unless otherwise indicated, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which the invention belongs. Although the present invention describes only preferred methods and materials, any methods and materials similar or equivalent to those described herein may also be used in the implementation or testing of the present invention. All documents mentioned in this specification are incorporated by reference to disclose and describe the methods and / or materials related to the documents. In the event of a conflict with any incorporated document, the content of this specification shall prevail.

[0049] The embodiment of the present invention provides a method and device for predicting shale porosity and matrix permeability based on a neural network, and solves the tight reservoir wave control equation through the neural network, thereby achieving a reasonable prediction of shale porosity and matrix permeability.

[0050] Example

[0051] The present invention provides a method for predicting shale porosity and matrix permeability based on a neural network. Figure 1 As shown, the following steps are included:

[0052] Step S11: Obtain velocity, porosity and permeability curves of wells drilled in the shale reservoir, and obtain a three-dimensional velocity body of the target layer of the reservoir through interpolation based on the velocity curves.

[0053] The acquisition of velocity, porosity and permeability curves of a drilled well may include the following steps:

[0054] (1) Combined with rock physics experimental data, the existing logging data in the reservoir is corrected to obtain velocity, porosity and permeability curves at the well location;

[0055] (2) Based on the mineral volume content (obtained through coring and well log interpretation), velocity curves are constructed using the Xu-White rock physics model;

[0056] (3) Since the logging curve obtained in step (1) is affected by diameter expansion, diameter contraction, etc., the logging curve of some well sections with abnormal well diameters is prone to certain errors. In this case, the curves obtained in steps (1) and (2) can be combined to obtain a velocity curve with higher credibility.

[0057] (4) Perform well-seismic matching correction on velocity, porosity and permeability curves.

[0058] The velocity in this embodiment is specifically the longitudinal wave velocity V P .

[0059] Based on the velocity curve, the stratigraphic structure along the reservoir target layer is analytically interpolated to obtain the three-dimensional velocity body of the reservoir target layer.

[0060] Furthermore, the seismic data volume can be used as a constraint in the interpolation process.

[0061] Step S12: With the three-dimensional velocity body and the viscous attenuation coefficient of the shale in the target layer as known conditions, and with the porosity curve and the permeability curve as constraints, a neural network is used to solve the tight reservoir wave control equation to obtain the three-dimensional porosity data body and matrix permeability data body of the target layer.

[0062] The governing equation of tight reservoir waves, that is, the tight oil and gas seismic wave equation is:

[0063]

[0064] Where P is the seismic wave field, t is time, v is the seismic wave velocity, φ is the porosity, γ is the permeability coefficient, μ f is the fluid viscosity, ρ f is the fluid density, k is the reservoir permeability, bf is the viscous attenuation coefficient.

[0065] Substituting the velocity and viscous attenuation coefficient into the above equation, the tight reservoir wave control equation is solved iteratively using a neural network to obtain a three-dimensional porosity data volume and a permeability coefficient data volume; according to the density and viscosity of the fluid in the target layer, a three-dimensional matrix permeability data volume is obtained from the permeability coefficient data volume.

[0066] In some embodiments, the three-dimensional velocity volume, porosity curve and permeability curve can be decomposed into background components and disturbance components respectively by low-pass filtering, and the decomposed data are used to solve the three-dimensional matrix permeability data volume.

[0067] Decomposing velocity, porosity and permeability into background component and disturbance component can reduce the network inversion time and avoid falling into local optimal solution.

[0068] In some embodiments, the above-mentioned neural 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, see Figure 2 As shown, during the iteration process, the value of the current network loss function is determined in the following way:

[0069] Taking the porosity curve and the permeability curve as the physical property label data, determining the first error between the current porosity prediction result and the matrix permeability prediction result and the physical property label data;

[0070] Taking the velocity curve as the velocity label data, based on the current matrix permeability prediction result, using the velocity and permeability mapping relationship of the target layer, the predicted velocity is obtained, and the second error between the predicted velocity and the velocity label data is determined;

[0071] According to 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;

[0072] The sum of the first error, the second error and the third error is determined as the value of the current network loss function.

[0073] The wave control equations of tight reservoirs are difficult to solve. The method for predicting shale porosity and matrix permeability based on a neural network provided in the embodiment of the present invention uses a three-dimensional velocity body and the viscous attenuation coefficient of shale in the target layer as known conditions, and a porosity curve and a permeability curve as constraints. The neural network is used to solve the wave control equations of tight reservoirs to obtain a three-dimensional porosity data body and a matrix permeability data body of the target layer. The three-dimensional prediction of shale porosity and matrix permeability is achieved, and the prediction is highly reasonable and accurate.

[0074] The method for predicting shale porosity and matrix permeability based on a neural network provided in an embodiment of the present invention ensures the accuracy of the prediction results by limiting the triple error; and in the process, only the total error is considered regardless of the single error, thereby avoiding falling into the local optimum.

[0075] The above velocity and permeability mapping relationship is pre-established in the following way:

[0076] Based on the velocity and permeability experimental test data of multiple shale samples in the target layer, a velocity-permeability mapping relationship is established.

[0077] Since the matrix permeability is greatly affected by the shale temperature, we can further establish different mapping relationships between velocity and permeability in different temperature intervals:

[0078] (1) The first temperature range corresponding to the low-maturity thermal evolution stage of shale organic matter

[0079] Based on velocity and permeability experimental test data of multiple shale samples in the target layer at multiple temperature points in the first temperature interval, a velocity and permeability mapping relationship in the first temperature interval is established.

[0080] The low-maturity thermal evolution stage of organic matter is the stage where Ro < 0.8%.

[0081] (2) The second temperature range corresponding to the thermal evolution stage of shale organic matter maturity

[0082] Based on the velocity and permeability experimental test data of multiple shale samples in the target layer at multiple temperature points in the second temperature interval, a velocity and permeability mapping relationship in the second temperature interval is established.

[0083] The thermal evolution stage of organic matter maturity is 0.8%≤Ro≤1.5%.

[0084] (3) The third temperature range corresponding to the thermal evolution stage of shale organic matter overmaturity

[0085] Based on velocity and permeability experimental test data of multiple shale samples in the target layer at multiple temperature points in the third temperature interval, a velocity and permeability mapping relationship in the third temperature interval is established.

[0086] The overmature thermal evolution stage of organic matter is Ro>1.5%.

[0087] Correspondingly, the second error can be determined by determining the temperature range according to the temperature conditions corresponding to the porosity and matrix permeability to be solved, using the velocity curve as the velocity label data, based on the current matrix permeability prediction result, and using the velocity and permeability mapping relationship of the target layer corresponding to the temperature range to obtain the predicted velocity.

[0088] In the method for predicting shale porosity and matrix permeability based on a neural network provided in an embodiment of the present invention, the velocity and permeability mapping relationship is established in different temperature intervals, so that the predicted porosity and permeability bodies are closer to the actual geological conditions and have higher availability.

[0089] Based on the inventive concept of the present invention, an embodiment of the present invention further provides a device for predicting shale porosity and matrix permeability based on a neural network. The structure of the device is as follows: Figure 3 As shown, including:

[0090] The basic data processing module 31 is used to obtain the velocity, porosity and permeability curves of the wells drilled in the shale reservoir, and obtain the three-dimensional velocity body of the target layer of the reservoir by interpolation based on the velocity curve;

[0091] The three-dimensional physical property data prediction module 32 is used to solve the tight reservoir wave control equation using a neural network with the three-dimensional velocity body and the viscous attenuation coefficient of the shale in the target layer as known conditions and the porosity curve and permeability curve as constraints to obtain the three-dimensional porosity data body and matrix permeability data body of the target layer.

[0092] In some embodiments, the three-dimensional physical property data prediction module 32 uses a neural network to solve the tight reservoir wave control equation for:

[0093] A neural 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, the value of the current network loss function is determined in the following manner: using the porosity curve and the permeability curve as physical property label data, determining the first error between the current porosity prediction result and the matrix permeability prediction result and the physical property label data; using the velocity curve as the velocity label data, based on the current matrix permeability prediction result, using the velocity and permeability mapping relationship of the target layer, the predicted velocity is obtained, and the second error between the predicted velocity and the velocity label data is determined; according to the predicted velocity, seismic forward modeling data is obtained through a convolution operation, and the third error between the seismic forward modeling data and the actual seismic data is determined; and the sum of the first error, the second error and the third error is determined as the value of the current network loss function.

[0094] In some embodiments, the above-mentioned device further comprises a velocity and permeability mapping relationship establishing module 33, which is used to establish a velocity and permeability mapping relationship based on velocity and permeability experimental test data of a plurality of shale samples in the target layer.

[0095] In some embodiments, the velocity and permeability mapping relationship establishing module 33 is further used to:

[0096] Based on the experimental test data of velocity and permeability of multiple shale samples in the target layer at multiple temperature points in a first temperature interval, a velocity-permeability mapping relationship in the first temperature interval is established, and the first temperature interval is a temperature interval 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 a second temperature interval, a velocity-permeability mapping relationship in the second temperature interval is established, and the second temperature interval is a temperature interval corresponding to the mature 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 a third temperature interval, a velocity-permeability mapping relationship in the third temperature interval is established, and the third temperature interval is a temperature interval corresponding to the over-maturity thermal evolution stage of shale organic matter.

[0097] In some embodiments, the three-dimensional physical property data prediction module 32 uses the velocity and permeability mapping relationship of the target layer to obtain the predicted velocity, which is used to:

[0098] The temperature range is determined according to the temperature conditions corresponding to the porosity and matrix permeability to be solved, and the predicted velocity is obtained by using the velocity and permeability mapping relationship corresponding to the temperature range of the target layer.

[0099] In some embodiments, the three-dimensional physical property data prediction module 32, before using a neural network to solve the tight reservoir wave control equation, is further used to:

[0100] The three-dimensional velocity body, porosity curve and permeability curve are respectively decomposed into a background component and a disturbance component.

[0101] In some embodiments, the three-dimensional physical property data prediction module 32 uses a neural network to solve the tight reservoir wave control equation to obtain a three-dimensional porosity data volume and a matrix permeability data volume of the target layer, which is used to:

[0102] A neural network is used to solve the tight reservoir wave control equation to obtain a three-dimensional porosity data volume and a permeability coefficient data volume; and a three-dimensional matrix permeability data volume is obtained from the permeability coefficient data volume according to the density and viscosity of the fluid in the target layer.

[0103] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0104] Based on the inventive concept of the present invention, an embodiment of the present invention further provides a computer storage medium, in which computer executable instructions are stored. When the computer executable instructions are executed by a processor, the above-mentioned method for predicting shale porosity and matrix permeability based on a neural network is implemented.

[0105] Based on the inventive concept of the present invention, an embodiment of the present invention also provides a server, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for predicting shale porosity and matrix permeability based on a neural network is implemented.

[0106] Unless otherwise specifically stated, terms such as processing, computing, calculating, determining, displaying, etc. may refer to the actions and / or processes of one or more processing or computing systems, or similar devices, which operate and convert data represented as physical (e.g., electronic) quantities within registers or memories of a processing system into other data similarly represented as physical quantities within memories, registers, or other such information storage, transmission, or display devices of the processing system. Information and signals may 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 may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, light fields or particles, or any combination thereof.

[0107] 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 can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.

[0108] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that an embodiment of the claimed subject matter requires more features than those set forth in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0109] Those skilled in the art will also appreciate that the various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the embodiments herein can all be implemented as electronic hardware, computer software, or a combination thereof. In order to clearly illustrate the interchangeability between hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above around their functions. Whether such functions are implemented as hardware or software depends on specific applications and the design constraints imposed on the entire system. A skilled person can implement the described functions in an alternative manner for each specific application, but such implementation decisions should not be interpreted as departing from the scope of protection of the present disclosure.

[0110] The steps of the method or algorithm described in conjunction with the embodiments herein may be directly embodied as hardware, a software module executed by a processor, or a combination thereof. The software module may be located in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium may also be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The ASIC may be located in a user terminal. Of course, the processor and the storage medium may also be present in a user terminal as discrete components.

[0111] For software implementation, the techniques described in this application can be implemented with modules (e.g., procedures, functions, etc.) that perform the functions described in this application. These software codes can be stored in a memory unit and executed by a processor. The memory unit can be implemented within the processor or outside the processor. In the latter case, it is coupled to the processor in a communication manner via various means, which are well known in the art.

[0112] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments can be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to represent "non-exclusive or". The terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance.

Claims

1. A method for predicting shale porosity and matrix permeability based on neural network, characterized in that: include: Obtaining velocity, porosity and permeability curves of the wells drilled in the shale reservoir, and obtaining a three-dimensional velocity body of the target layer of the reservoir by interpolation based on the velocity curves; With the three-dimensional velocity body and the viscous attenuation coefficient of the shale in the target layer as known conditions, and with the porosity curve and the permeability curve as constraints, a neural network is used to solve the tight reservoir wave control equation to obtain the three-dimensional porosity data body and matrix permeability data body of the target layer.

2. The method according to claim 1, characterized in that The method of solving the tight reservoir wave control equation by using a neural network includes: The neural 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 value of the current network loss function is determined by the following method: Taking the porosity curve and the permeability curve as physical property label data, determining a first error between the current porosity prediction result and the matrix permeability prediction result and the physical property label data; Taking the velocity curve as the velocity label data, based on the current matrix permeability prediction result, using the velocity and permeability mapping relationship of the target layer, a predicted velocity is obtained, and a second error between the predicted velocity and the velocity label data is determined; According to the predicted velocity, seismic forward modeling data is obtained by convolution operation, and a third error between the seismic forward modeling data and 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.

3. The method according to claim 2, characterized in that The velocity and permeability mapping relationship is pre-established in the following manner: Based on the velocity and permeability experimental test data of multiple shale samples in the target layer, a velocity and permeability mapping relationship is established.

4. The method according to claim 3, characterized in that The velocity and permeability mapping relationship is pre-established in the following manner: Based on the velocity and permeability experimental test data of multiple shale samples in the target layer at multiple temperature points in a first temperature interval, a velocity and permeability mapping relationship in the first temperature interval is established, and the first temperature interval is a temperature interval corresponding to the low-maturity thermal evolution stage of shale organic matter; Based on the velocity and permeability experimental test data of multiple shale samples in the target layer at multiple temperature points in a second temperature interval, a velocity and permeability mapping relationship in the second temperature interval is established, and the second temperature interval is a temperature interval corresponding to the thermal evolution stage of shale organic matter maturity; Based on the velocity and permeability experimental test data of multiple shale samples in the target layer at multiple temperature points in the third temperature interval, a velocity and permeability mapping relationship in the third temperature interval is established, and the third temperature interval is the temperature interval corresponding to the overmature thermal evolution stage of shale organic matter.

5. The method according to claim 4, characterized in that The method of obtaining the predicted velocity by using the velocity and permeability mapping relationship of the target layer includes: The temperature range is determined according to the temperature conditions corresponding to the porosity and matrix permeability to be solved, and the predicted velocity is obtained by using the velocity and permeability mapping relationship corresponding to the temperature range of the target layer.

6. The method according to claim 1, characterized in that Before using neural networks to solve the tight reservoir wave control equations, it also includes: The three-dimensional velocity body, porosity curve and permeability curve are respectively decomposed into a background component and a disturbance component.

7. The method according to claim 1, characterized in that The tight reservoir wave control equation is: Where P is the seismic wave field, t is time, v is the seismic wave velocity, φ is the porosity, γ is the permeability coefficient, μ f is the fluid viscosity, ρ f is the fluid density, k is the reservoir permeability, b f is the viscous attenuation coefficient.

8. The method according to claim 7, characterized in that The method of using a neural network to solve the tight reservoir wave control equation to obtain a three-dimensional porosity data volume and a matrix permeability data volume of the target layer includes: The neural network is used to solve the tight reservoir wave control equation to obtain the three-dimensional porosity data volume and permeability coefficient data volume; According to the density and viscosity of the fluid in the target layer, a three-dimensional matrix permeability data volume is obtained from the permeability coefficient data volume.

9. A device for predicting shale porosity and matrix permeability based on neural network, characterized in that: include: A basic data processing module is used to obtain velocity, porosity and permeability curves of the wells drilled in the shale reservoir, and obtain a three-dimensional velocity body of the target layer of the reservoir by interpolation based on the velocity curve; The three-dimensional physical property data prediction module is used to solve the tight reservoir wave control equation using a neural network with the three-dimensional velocity body and the viscous attenuation coefficient of the shale in the target layer as known conditions, and with the porosity curve and the permeability curve as constraints, to obtain the three-dimensional porosity data body and matrix permeability data body of the target layer.

10. A computer storage medium, characterized in that: The computer storage medium stores computer executable instructions, and when the computer executable instructions are executed by a processor, the method for predicting shale porosity and matrix permeability based on a neural network as described in any one of claims 1 to 8 is implemented.

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 when the processor executes the program, the method for predicting shale porosity and matrix permeability based on a neural network as claimed in any one of claims 1 to 8 is implemented.

Images