A method, device, equipment and storage medium for identifying stromatolite reservoirs

Abstract

The present invention discloses a method, apparatus, device and storage medium for identifying stromatolite reservoirs. The method includes: obtaining well logging data of the stromatolite reservoir to be identified; inputting the well logging data into a pre-trained reservoir identification model to obtain an identification result of the stromatolite reservoir to be identified output by the reservoir identification model; wherein, the reservoir identification model is built based on a neural network; the training function and activation function of the reservoir identification model are determined based on mean square error constraints. This technical solution solves the problem of low accuracy in identifying stromatolite reservoirs, and can improve the identification accuracy of stromatolite reservoirs while reducing the identification cost of stromatolite reservoirs.

Description

Technical Field

[0001] The present invention relates to the field of geophysical technologies, and particularly to a method, device, equipment and storage medium for identifying stromatolite reservoirs. Background Art

[0002] Stromatolite is a kind of microbial rock composed of various laminated structures and is an important deep hydrocarbon reservoir. Due to the characteristics of strong overall heterogeneity, uneven hydrocarbon content, and small difference in logging responses between effective reservoirs and ineffective reservoirs in stromatolite reservoirs, it is difficult to identify stromatolite reservoirs from conventional logging curves. The porosity of stromatolite reflects the ability of the reservoir to store fluids, and accurate porosity is an important parameter for estimating reserves and establishing geological models, which can effectively reduce the risks in exploration, development, and engineering. Currently, the methods for obtaining the porosity of stromatolite mainly include experimental measurement methods and logging fitting methods.

[0003] The experimental measurement method is mainly obtained through experiments such as mercury injection and nitrogen adsorption. The overall experimental process is complex, costly, and severely limited by the sampling location and core preservation conditions. Therefore, the relevant data samples are relatively single, and it is impossible to have a clear and intuitive understanding of the relevant parameters of the reservoir. Therefore, how to accurately identify stromatolite reservoirs has become an urgent problem to be solved. Summary of the Invention

[0004] The present invention provides a method, device, equipment and storage medium for identifying stromatolite reservoirs to solve the problem of low accuracy in identifying stromatolite reservoirs, and can improve the accuracy of identifying stromatolite reservoirs while reducing the cost of identifying stromatolite reservoirs.

[0005] According to one aspect of the present invention, a method for identifying stromatolite reservoirs is provided, and the method includes:

[0006] Obtaining logging data of the stromatolite reservoir to be identified;

[0007] Inputting the logging data into a pre-trained reservoir identification model to obtain an identification result of the stromatolite reservoir to be identified output by the reservoir identification model; wherein, the reservoir identification model is built based on a neural network; the training function and activation function of the reservoir identification model are determined based on mean square error constraints.

[0008] According to another aspect of the present invention, a device for identifying stromatolite reservoirs is provided, and the device includes:

[0009] A data acquisition module for obtaining logging data of the stromatolite reservoir to be identified;

[0010] An identification result determination module, configured to input the logging data into a pre-trained reservoir identification model to obtain an identification result of the stromatolite reservoir to be identified output by the reservoir identification model; wherein, the reservoir identification model is built based on a neural network; the training function and activation function of the reservoir identification model are determined based on mean square error constraints.

[0011] According to another aspect of the present invention, there is provided an electronic device, which includes:

[0012] At least one processor; and

[0013] A memory communicatively connected to the at least one processor; wherein,

[0014] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the stromatolite reservoir identification method according to any embodiment of the present invention.

[0015] According to another aspect of the present invention, there is provided a computer-readable storage medium, which stores computer instructions for causing a processor to implement the stromatolite reservoir identification method according to any embodiment of the present invention when executed.

[0016] The technical solution of the embodiment of the present invention identifies the logging data of the stromatolite reservoir to be identified through a pre-trained reservoir identification model to determine the identification result of the stromatolite reservoir to be identified. This solution solves the problem of low accuracy in identifying stromatolite reservoirs, and can improve the accuracy of stromatolite reservoir identification while reducing the cost of stromatolite reservoir identification.

[0017] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0019] Figure 1 is a flowchart of a method for identifying a stromatolite reservoir according to Embodiment 1 of the present invention;

[0020] Figure 2It is a flowchart of a stromatolite reservoir identification method provided by Embodiment 2 of the present invention;

[0021] Figure 3 It is a schematic structural diagram of a stromatolite reservoir identification device provided by Embodiment 3 of the present invention;

[0022] Figure 4 It is a schematic structural diagram of an electronic device for implementing the stromatolite reservoir identification method of the embodiments of the present invention. Detailed implementation manners

[0023] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data used can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of this application all comply with the relevant regulations of national laws and regulations.

[0025] Embodiment 1

[0026] Figure 1 This is a flowchart of a stromatolite reservoir identification method provided by Embodiment 1 of the present invention. This embodiment is applicable to the stromatolite reservoir identification scenario. This method can be executed by a stromatolite reservoir identification device, and this device can be implemented in the form of hardware and / or software, and this device can be configured in an electronic device. As Figure 1 shown, this method includes:

[0027] S110. Obtain the logging data of the stromatolite reservoir to be identified.

[0028] This solution can be executed by electronic devices such as computers and servers, which can obtain well logging data related to the stromatolite reservoir to be identified. Among them, the well logging data may include well logging curves such as natural gamma, spontaneous potential, shallow lateral resistivity, deep lateral resistivity, acoustic wave, and density. The well logging data can be input by the user into the electronic device or collected by the electronic device through the network.

[0029] S120. Input the well logging data into a pre-trained reservoir identification model to obtain the identification result of the stromatolite reservoir to be identified output by the reservoir identification model.

[0030] The electronic device can input the well logging data into the reservoir identification model, and the reservoir identification model can output the identification result of the stromatolite reservoir. Among them, the reservoir identification model is built based on a neural network. The reservoir identification model may include an input layer, an output layer, and at least one hidden layer. Each hidden layer may include multiple neuron nodes, and the output layer may include one or more neuron nodes. Activation functions are set for each node in the hidden layer and the output layer. The activation functions may include functions such as Sigmoid, Tanh, ReLU, Leaky Relu, P-Relu, ELU, and Gelu.

[0031] A training function is configured in the reservoir identification model, and the training function is used to update the weights during the backpropagation process. The training functions may include functions such as sarprop, quickprop, rprop, batch, and incremental. The training function and activation function of the reservoir identification model can be determined based on the mean square error constraint during the training stage. Specifically, the electronic device can train the reservoir identification model based on different reservoir identification model configurations to determine the training results of each configuration. Among them, the reservoir identification model configuration may include settings in aspects such as the number of hidden layers, the number of nodes in the hidden layer, the activation function, and the training function. The electronic device can determine the mean square error statistical result based on the mean square error model according to the training results of each configuration. According to the mean square error statistical result, the electronic device can determine the best reservoir identification model configuration. For example, the electronic device can use the reservoir identification model configuration corresponding to the minimum mean square error as the optimal configuration.

[0032] Determining the training function and activation function based on the mean square error constraint is beneficial to obtaining the best reservoir identification model, and thus achieving good reservoir identification effects during the application process.

[0033] This technical solution uses a pre-trained reservoir identification model to identify the log data of the stromatolite reservoir to be identified, and determines the identification result of the stromatolite reservoir to be identified. This solution solves the problem of low accuracy in stromatolite reservoir identification, and can improve the accuracy of stromatolite reservoir identification while reducing the cost of stromatolite reservoir identification.

[0034] Embodiment 2

[0035] Figure 2 FIG. is a flowchart of a method for identifying a stromatolite reservoir provided in Embodiment 2 of the present invention. This embodiment is refined based on the above embodiment. As Figure 2 shown, the method includes:

[0036] S210. Obtain the log data to be trained and the label data matching the log data to be trained.

[0037] After completing the construction of the structure of the reservoir identification model, the electronic device can use the pre-acquired training data to train the reservoir identification model to obtain a reservoir identification model that has learned the quality characteristics of the stromatolite reservoir. The electronic device can use the log data with the determined labels as the training data set. Among them, the training data set includes the log data to be trained and the label data matching the log data to be trained. The electronic device can use the log data to be trained as the input of the reservoir identification model, and use the corresponding label data as the supervision of the reservoir identification model to train the reservoir identification model.

[0038] In a feasible solution, the label data is the quality of the stromatolite reservoir determined based on the pore face ratio of the core sample.

[0039] In this solution, the label data can be used to identify the quality of the stromatolite reservoir of the core sample corresponding to the log data to be trained. The quality of the stromatolite reservoir can be determined according to the pore face ratio of the core sample. Using the quality of the stromatolite reservoir as the label data of the log data is beneficial to realizing the positioning of high-quality reservoirs and improving the accuracy of stromatolite reservoir identification.

[0040] Based on the above solution, optionally, the determination process of the quality of the stromatolite reservoir includes:

[0041] If the pore face ratio of the core sample is greater than a preset first ratio threshold, it is determined that the quality of the stromatolite reservoir is an excellent stromatolite reservoir;

[0042] If the pore face ratio of the core sample is less than or equal to the preset first ratio threshold and greater than the preset second ratio threshold, it is determined that the quality of the stromatolite reservoir is a good stromatolite reservoir;

[0043] If the pore face ratio of the core sample is less than or equal to the preset second ratio threshold and greater than the preset third ratio threshold, it is determined that the quality of the stromatolite reservoir is a medium stromatolite reservoir;

[0044] If the pore space ratio of the core sample is less than or equal to a preset third ratio threshold, it is determined that the stromatolite reservoir quality is a poor stromatolite reservoir;

[0045] Among them, the first ratio threshold, the second ratio threshold, and the third ratio threshold decrease in sequence.

[0046] Specifically, the user can select one or more wells, select core samples according to a preset sampling principle, macroscopically identify the cores with stromatolite structures, and microscopically determine the pore space ratio of the core samples by using cast thin sections. Among them, the preset sampling principle can be sampling at equal intervals according to a preset length, or non-interval sampling according to the reservoir distribution.

[0047] The electronic device can identify stromatolites with a pore space ratio greater than the first ratio threshold as excellent stromatolite reservoirs, stromatolites with a pore space ratio between the first ratio threshold and the second ratio threshold as good stromatolite reservoirs, stromatolites with a pore space ratio between the second ratio threshold and the third ratio threshold as medium stromatolite reservoirs, and stromatolites with a pore space ratio less than or equal to the preset third ratio threshold as poor stromatolite reservoirs. Among them, the first ratio threshold, the second ratio threshold, and the third ratio threshold can decrease in equal intervals in sequence. For example, the first ratio threshold can be 5%, the second ratio threshold can be 3%, and the third ratio threshold can be 1%. The first ratio threshold, the second ratio threshold, and the third ratio threshold can also decrease in non-equal intervals in sequence. For example, the first ratio threshold can be 5%, the second ratio threshold can be 2%, and the third ratio threshold can be 1%.

[0048] S220: Use the logging data to be trained as input, and perform at least one iterative training on the reservoir identification model according to the output result of the reservoir identification model and the label data matching the logging data to be trained until a preset iterative termination condition is met, and output the reservoir identification model.

[0049] The electronic device can input the logging data to be trained into the reservoir identification model, compare the output result of the reservoir identification model with the corresponding label data, and calculate the loss error. According to the loss error, the electronic device can perform at least one iterative training on the reservoir identification model until the iterative termination condition is met, and output the reservoir identification model obtained from the last iterative training. Specifically, the iterative termination condition can be that the number of iterations reaches a preset number, or the performance evaluation index of the reservoir identification model meets a preset index threshold. For example, the verification loss error of the reservoir identification model is lower than a preset loss threshold.

[0050] In a preferred solution, taking the logging data to be trained as the input, and based on the output result of the reservoir identification model and the label data matching the image data to be trained, performing at least one iterative training on the reservoir identification model until a preset iterative termination condition is met, and outputting the reservoir identification model, including:

[0051] Determine a candidate training function in the set of training functions, and use the candidate training function as the training function of the candidate reservoir identification model; wherein, the set of training functions includes at least one of the sarprop function, the quickprop function, the rprop function, the batch function, and the incremental function;

[0052] Taking the logging data to be trained as the input, and based on the output result of the candidate reservoir identification model and the label data matching the image data to be trained, performing at least one iterative training on the candidate reservoir identification model until a preset iterative termination condition is met, and outputting the candidate reservoir identification model;

[0053] Determine the target reservoir identification model according to each candidate reservoir identification model.

[0054] In order to determine a reservoir identification model with stronger applicability to the stromatolite reservoir identification scenario, the electronic device can sequentially select a training function in the set of training functions as the training function of the reservoir identification model to generate each candidate reservoir identification model. Taking the logging data to be trained as the input of each candidate reservoir identification model, and based on the output result of the candidate reservoir identification model and the label data matching the image data to be trained, perform iterative training on each candidate reservoir identification model until the iterative termination condition is met to obtain each candidate reservoir identification model. It should be noted that the iterative termination conditions for the training of each candidate reservoir identification model can be the same. The electronic device can select the target reservoir identification model from each candidate reservoir identification model according to the performance evaluation index of each candidate reservoir identification model.

[0055] In a specific example, the performance indicators of each candidate reservoir identification model can be as shown in Table 1 below. The electronic device can select the candidate reservoir identification model corresponding to the sarprop function with the smallest mean square error and the smallest loss error as the target identification model.

[0056] Table 1:

[0057] Training function Mean squared error Number of iterations Loss error sarprop <![CDATA[3.624×10 -6 > 500000 <![CDATA[2.385×10 -7 > quickprop 0.008 500000 <![CDATA[4.369×10 -5 > rprop <![CDATA[4.624×10 -4 > 500000 <![CDATA[7.441×10 -6 > batch <![CDATA[3.217×10 -3 > 500000 <![CDATA[7.005×10 -7 > incremental <![CDATA[9.483×10 -4 > 500000 <![CDATA[3.296×10 -6 >

[0058] In addition, the electronic device can also set model configuration parameters such as the number of hidden layer nodes and activation functions of different candidates to obtain each candidate reservoir identification model. According to the performance evaluation indicators of each candidate reservoir identification model, the electronic device can select the candidate reservoir identification model corresponding to the target model configuration parameters as the target reservoir identification model to achieve a good reservoir identification effect.

[0059] Exemplarily, if there is only one hidden layer in the reservoir identification model, the electronic device can set different numbers of hidden layer nodes and perform iterative training on each candidate reservoir identification model respectively to select the best candidate reservoir identification model. The performance evaluation indicators of each candidate reservoir identification model can be shown in Table 2 below. The electronic device can select the candidate reservoir identification model corresponding to the node number 3 with the smallest mean square error and loss error as the target reservoir identification model.

[0060] Table 2:

[0061] Number of nodes Mean squared error Number of iterations Loss error 1 <![CDATA[9.624×10 -3 > 500000 <![CDATA[6.624×10 -5 > 2 0.008 500000 <![CDATA[9.173×10 -5 > 3 <![CDATA[4.624×10 -4 > 500000 <![CDATA[1.486×10 -6 > 4 <![CDATA[3.217×10 -3 > 500000 <![CDATA[8.549×10 -6 > 5 <![CDATA[9.483×10 -4 > 500000 <![CDATA[8.779×10 -6 >

[0062] Similarly, the electronic device can also set different activation functions for the hidden layer and the output layer, perform iterative training on each candidate reservoir identification model respectively, and select the best candidate reservoir identification model. The performance evaluation indicators of each candidate reservoir identification model can be shown in Table 3 below. The electronic device can select the candidate reservoir identification model with the sigmoid symmetricstepwise activation function for the hidden layer and the ell tot symmetric activation function for the output layer as the target reservoir identification model.

[0063] Table 3:

[0064]

[0065] The above solution can select the optimal model configuration for the reservoir identification model, which is beneficial to achieving the best training effect and improving the accuracy of reservoir identification.

[0066] S230. Obtain the logging data of the stromatolite reservoir to be identified.

[0067] S240. Input the logging data into the pre-trained reservoir identification model to obtain the identification result of the stromatolite reservoir to be identified output by the reservoir identification model.

[0068] Through the pre-trained reservoir identification model, this technical solution performs reservoir identification on the logging data of the stromatolite reservoir to be identified and determines the identification result of the stromatolite reservoir to be identified. This solution solves the problem of low accuracy in stromatolite reservoir identification and can improve the identification accuracy of stromatolite reservoirs while reducing the identification cost of stromatolite reservoirs.

[0069] Embodiment III

[0070] Figure 3 This is a schematic structural diagram of a stromatolite reservoir identification device provided in Embodiment 3 of the present invention. As Figure 3 shown, the device includes:

[0071] A data acquisition module 310, configured to acquire well logging data of the stromatolite reservoir to be identified;

[0072] An identification result determination module 320, configured to input the well logging data into a pre-trained reservoir identification model to obtain an identification result of the stromatolite reservoir to be identified output by the reservoir identification model; wherein, the reservoir identification model is built based on a neural network; the training function and activation function of the reservoir identification model are determined based on mean square error constraints.

[0073] In this solution, optionally, the reservoir identification model includes an input layer, an output layer, and at least one hidden layer; activation functions are set for each node of the hidden layer and the output layer; the training function is used to update weights during the backpropagation process.

[0074] In a feasible solution, the device further includes a model training module, including:

[0075] A data to be trained acquisition unit, configured to acquire well logging data to be trained and label data matching the well logging data to be trained;

[0076] A model output unit, configured to use the well logging data to be trained as input, and perform at least one iterative training on the reservoir identification model according to the output result of the reservoir identification model and the label data matching the well logging image data to be trained until a preset iterative termination condition is met, and output the reservoir identification model.

[0077] Optionally, the label data is the quality of the stromatolite reservoir determined based on the pore ratio of the core sample.

[0078] Based on the above solution, the device further includes a reservoir quality determination module, configured to:

[0079] If the pore ratio of the core sample is greater than a preset first ratio threshold, determine that the quality of the stromatolite reservoir is an excellent stromatolite reservoir;

[0080] If the pore ratio of the core sample is less than or equal to the preset first ratio threshold and greater than a preset second ratio threshold, determine that the quality of the stromatolite reservoir is a good stromatolite reservoir;

[0081] If the pore ratio of the core sample is less than or equal to the preset second ratio threshold and greater than a preset third ratio threshold, determine that the quality of the stromatolite reservoir is a medium stromatolite reservoir;

[0082] If the pore space ratio of the core sample is less than or equal to a preset third ratio threshold, it is determined that the stromatolite reservoir quality is a poor stromatolite reservoir;

[0083] Among them, the first ratio threshold, the second ratio threshold, and the third ratio threshold decrease in sequence.

[0084] In a preferred solution, the model output unit is specifically configured to:

[0085] Determine a candidate training function in the set of training functions, and use the candidate training function as the training function of the candidate reservoir identification model; wherein, the set of training functions includes at least one of the sarprop function, the quickprop function, the rprop function, the batch function, and the incremental function;

[0086] Use the logging data to be trained as the input, and perform at least one iterative training on the candidate reservoir identification model according to the output result of the candidate reservoir identification model and the label data matching the image data to be trained until a preset iteration termination condition is met, and output the candidate reservoir identification model;

[0087] Determine the target reservoir identification model according to each candidate reservoir identification model.

[0088] In a feasible solution, the logging data includes natural gamma, spontaneous potential, shallow lateral resistivity, deep lateral resistivity, acoustic wave, and density.

[0089] The stromatolite reservoir identification device provided by the embodiments of the present invention can execute the stromatolite reservoir identification method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0090] Embodiment 4

[0091] Figure 4 FIG. shows a schematic structural diagram of an electronic device 410 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0092] Such as Figure 4As shown, the electronic device 410 includes at least one processor 411 and a memory communicatively connected to the at least one processor 411, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc. The memory stores a computer program executable by the at least one processor. The processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or the computer program loaded from the storage unit 418 into the random access memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other via a bus 414. The input / output (I / O) interface 415 is also connected to the bus 414.

[0093] Multiple components in the electronic device 410 are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, a mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a magnetic disk, an optical disc, etc.; and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 419 allows the electronic device 410 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0094] The processor 411 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 411 executes the various methods and processes described above, such as the stromatolite reservoir identification method.

[0095] In some embodiments, the stromatolite reservoir identification method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 418. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded into the RAM 413 and executed by the processor 411, one or more steps of the stromatolite reservoir identification method described above can be executed. Alternatively, in other embodiments, the processor 411 can be configured to execute the stromatolite reservoir identification method by any other suitable means (e.g., by means of firmware).

[0096] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0097] The computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0098] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0099] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0100] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0101] The computing system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0102] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0103] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for identifying stromatolite reservoirs, characterized in that, The method includes: Obtaining well logging data of the stromatolite reservoir to be identified; Inputting the well logging data into a pre-trained reservoir identification model to obtain the identification result of the stromatolite reservoir to be identified output by the reservoir identification model; wherein, the reservoir identification model is built based on a neural network; the training function and activation function of the reservoir identification model are determined based on the mean square error constraint; Among them, the training process of the reservoir identification model includes: Obtaining well logging data to be trained and label data matching the well logging data to be trained; the label data is the quality of the stromatolite reservoir determined based on the pore face rate of the core sample; Taking the well logging data to be trained as the input, and performing at least one iterative training on the reservoir identification model according to the output result of the reservoir identification model and the label data matching the well logging data to be trained until a preset iterative termination condition is met, and outputting the reservoir identification model; The determination process of the quality of the stromatolite reservoir includes: If the pore face rate of the core sample is greater than a preset first proportion threshold, it is determined that the quality of the stromatolite reservoir is an excellent stromatolite reservoir; If the pore face rate of the core sample is less than or equal to the preset first proportion threshold and greater than the preset second proportion threshold, it is determined that the quality of the stromatolite reservoir is a good stromatolite reservoir; If the pore face rate of the core sample is less than or equal to the preset second proportion threshold and greater than the preset third proportion threshold, it is determined that the quality of the stromatolite reservoir is a medium stromatolite reservoir; If the pore face rate of the core sample is less than or equal to the preset third proportion threshold, it is determined that the quality of the stromatolite reservoir is a poor stromatolite reservoir; Among them, the first proportion threshold, the second proportion threshold, and the third proportion threshold decrease in sequence.

2. The method according to claim 1, wherein The reservoir identification model includes an input layer, an output layer, and at least one hidden layer; activation functions are set for each node of the hidden layer and the output layer; the training function is used for weight update during the backpropagation process.

3. The method according to claim 1, characterized in that, The step of taking the well logging data to be trained as the input, and performing at least one iterative training on the reservoir identification model according to the output result of the reservoir identification model and the label data matching the well logging data to be trained until a preset iterative termination condition is met, and outputting the reservoir identification model includes: Determining a candidate training function in the set of training functions, and using the candidate training function as the training function of the candidate reservoir identification model; wherein, the set of training functions includes at least one of the sarprop function, the quickprop function, the rprop function, the batch function, and the incremental function; Taking the well logging data to be trained as the input, and performing at least one iterative training on the candidate reservoir identification model according to the output result of the candidate reservoir identification model and the label data matching the well logging data to be trained until a preset iterative termination condition is met, and outputting the candidate reservoir identification model; Determining the target reservoir identification model according to each candidate reservoir identification model.

4. The method according to claim 1, wherein The well logging data includes natural gamma, natural potential, shallow lateral resistivity, deep lateral resistivity, acoustic wave, and density.

5. A stromatolite reservoir identification device, characterized in that, The device includes: A data acquisition module for obtaining well logging data of the stromatolite reservoir to be identified; An identification result determination module, configured to input the logging data into a pre-trained reservoir identification model to obtain an identification result of the stromatolite reservoir to be identified output by the reservoir identification model; wherein, the reservoir identification model is built based on a neural network; the training function and activation function of the reservoir identification model are determined based on mean square error constraints; Wherein, the training process of the reservoir identification model includes: Obtaining logging data to be trained and label data matching the logging data to be trained; the label data is the stromatolite reservoir quality determined based on the pore surface rate of core samples; Taking the logging data to be trained as input, and performing at least one iteration training on the reservoir identification model according to the output result of the reservoir identification model and the label data matching the logging data to be trained until a preset iteration termination condition is met, and outputting the reservoir identification model; The determination process of the stromatolite reservoir quality includes: If the pore surface rate of the core sample is greater than a preset first ratio threshold, it is determined that the stromatolite reservoir quality is an excellent stromatolite reservoir; If the pore surface rate of the core sample is less than or equal to the preset first ratio threshold and greater than a preset second ratio threshold, it is determined that the stromatolite reservoir quality is a good stromatolite reservoir; If the pore surface rate of the core sample is less than or equal to the preset second ratio threshold and greater than a preset third ratio threshold, it is determined that the stromatolite reservoir quality is a medium stromatolite reservoir; If the pore surface rate of the core sample is less than or equal to the preset third ratio threshold, it is determined that the stromatolite reservoir quality is a poor stromatolite reservoir; Wherein, the first ratio threshold, the second ratio threshold, and the third ratio threshold decrease in sequence.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the stromatolite reservoir identification method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a processor to implement the stromatolite reservoir identification method according to any one of claims 1-4 when executed.

Images