Shale oil productivity prediction method and device, medium and equipment

Abstract

The invention discloses a shale oil productivity prediction method and device, a medium and equipment, and relates to the technical field of deep learning. Comprising the following steps: acquiring shale oil productivity data of a horizontal well in a geological layer containing shale oil; seismic attributes in a specified time window are extracted from a geological horizon containing shale oil, and initial seismic attribute data are obtained; by taking the geodetic coordinate of the target horizontal well as an index, constructing a mapping relation between the initial seismic attribute data and shale oil productivity according to the initial seismic attribute data and the shale oil productivity data; constructing a shale oil productivity prediction model, and training the shale oil productivity prediction model by using the mapping relation to obtain a trained shale oil productivity prediction model; and inputting the whole-region seismic attribute data of the target region into the trained shale oil productivity prediction model to obtain shale oil productivity data of the target region.

Description

Technical Field

[0001] This application relates to the field of deep learning technology, and particularly to a shale oil production capacity prediction method, device, medium, and equipment. Background Art

[0002] Shale oil sweet spots refer to shale oil enrichment areas with superior source rocks, reservoir properties, oil-bearing properties, brittleness, and in-situ stress characteristics, etc., and at the same time, with relatively low engineering transformation costs and good development benefits under the current economic and technical conditions. Establishing a shale oil sweet spot evaluation system is the key to achieving shale oil target optimization and efficient development. Shale oil sweet spot evaluation usually includes geological sweet spots, engineering sweet spots, and economic sweet spots (Sun et al., 2021). Geological sweet spots mainly focus on the comprehensive evaluation of geological characteristics such as source rocks, reservoirs, natural fractures, formation energy, and local structures (Qian et al., 2018; ); Engineering sweet spots mainly include comprehensive evaluations of rock fracturability, in-situ stress anisotropy, etc. (Hou et al., 2021; Lu et al., 2022), and economic sweet spots usually cover comprehensive evaluations of economic influencing factors such as resource abundance, surface conditions, and development difficulty (Wu et al., 2023; Zeng et al., 2024). The parameter indicators selected for shale oil sweet spots vary in different regions, and the numerical ranges of the evaluation indicators are also different, resulting in different predictions of shale oil production.

[0003] In the prior art, the prediction of shale oil production includes multi-parameter plane superposition method, geophysical response prediction method, logging modeling evaluation method, etc.

[0004] Among the above prediction methods, the multi-parameter plane superposition method can quickly select favorable areas, but considering the large thickness and strong heterogeneity of continental shale formations, the prediction accuracy after multi-parameter plane superposition is reduced. In the geophysical response prediction method, the seismic inversion scale and the currently established geophysical response characteristics are limited, resulting in inaccurate prediction results. In the logging modeling evaluation method, due to the large variety of shale oil sweet spot evaluation parameters, not all shale oil sweet spot evaluation parameters can be included, resulting in inaccurate prediction results. In summary, in the prior art, the prediction results of shale oil production capacity are inaccurate due to various factors. Summary of the Invention

[0005] Based on this, it is necessary to provide a shale oil production capacity prediction method, device, medium, and equipment for the above technical problems.

[0006] This specification adopts the following technical solutions: This specification provides a shale oil production capacity prediction method, including: Obtain shale oil production capacity data for horizontal wells in geological formations containing shale oil; Extracting seismic attributes within a specified time window in a geological layer containing shale oil to obtain initial seismic attribute data; Taking the geodetic coordinates of the target horizontal well as an index, a mapping relationship between the initial seismic attribute data and the shale oil production capacity is constructed according to the initial seismic attribute data and the shale oil production capacity data; Constructing a shale oil production capacity prediction model, and using the mapping relationship to train the shale oil production capacity prediction model to obtain a trained shale oil production capacity prediction model; The seismic attribute data of the entire target area is input into the trained shale oil production capacity prediction model to obtain the shale oil production capacity data of the target area.

[0007] Optionally, the model architecture of the shale oil production capacity prediction model includes an input layer, a hidden layer, a BN layer, and an output layer; The number of hidden layers is at least two, and every two adjacent hidden layers are connected through a BN layer; The shale oil production capacity prediction model uses the grid search method to determine the number of hidden layers and the number of neurons in the hidden layers; The shale oil production capacity prediction model determines the target hyperparameter combination from the preset hyperparameter combinations through the three-fold cross-validation method.

[0008] Optionally, before building a mapping relationship between the initial seismic attribute data and the shale oil production capacity according to the initial seismic attribute data and the shale oil production capacity data with the geodetic coordinates of the target horizontal well as an index, the method further includes: Performing data preprocessing on the initial seismic attribute data to obtain preprocessed seismic attribute data; According to the correlation between each seismic attribute data in the preprocessed seismic attribute data and the shale oil production capacity, the preprocessed seismic attribute data are screened to obtain seismic attribute data; A mapping relationship between the initial seismic attribute data and the shale oil production capacity data is constructed based on the initial seismic attribute data and the shale oil production capacity data, specifically including: A mapping relationship between initial seismic attribute data and shale oil production capacity is constructed based on seismic attribute data and shale oil production capacity data.

[0009] Optionally, according to the correlation between each seismic attribute data in the preprocessed seismic attribute data and the shale oil production capacity, the preprocessed seismic attribute data is screened to obtain seismic attribute data, specifically including: The hierarchical clustering method is used to calculate the correlation between each seismic attribute data and shale oil production capacity in the preprocessed seismic attribute data to obtain the similarity calculation result; Determine earthquake attribute data based on similarity calculation results; The seismic attribute data includes the average negative polarity amplitude, average amplitude, average positive polarity amplitude, average energy, asymmetry, root mean square amplitude, kurtosis, and maximum amplitude.

[0010] Optionally, obtain the shale oil production capacity data of horizontal wells in the geological formation containing shale oil, including: Obtain the shale oil production volume, contribution rate at the fracturing stage, and oil-phase tracer concentration at the fracturing stage for each single well in each fracturing stage; Based on the shale oil production volume, contribution rate at the fracturing stage, and oil-phase tracer concentration at the fracturing stage for each single well in each fracturing stage, use the preset shale oil fracturing stage production capacity calculation formula to calculate the shale oil production capacity data.

[0011] Optionally, the preset shale oil fracturing stage production capacity calculation formula is: ; Wherein, represents the shale oil production volume of the th day and the th fracturing stage, represents the shale oil production volume of a single well on the th day, represents the contribution rate at the th day and the th fracturing stage, represents the oil-phase tracer concentration at the th day and the th fracturing stage, the sum of the oil-phase tracer concentrations in all fracturing stages within the th day.

[0012] Optionally, the method further includes: Calculate the cumulative oil production based on the shale oil production capacity data; Calculate the cumulative probability of oil production based on the cumulative oil production; Draw a relationship diagram based on the cumulative oil production and the cumulative probability of oil production, and classify according to the Lorenz cumulative probability curve relationship diagram to determine the type of oil-producing layer in the target area.

[0013] This specification provides a shale oil production capacity prediction device, including: A data acquisition module, specifically used to obtain the shale oil production capacity data of horizontal wells in the geological formation containing shale oil; extract seismic attributes within a specified time window in the geological formation containing shale oil to obtain initial seismic attribute data; construct a mapping relationship between the initial seismic attribute data and the shale oil production capacity with the geodetic coordinates of the target horizontal well as the index; The model training module is specifically used to construct a shale oil production capacity prediction model, and train the shale oil production capacity prediction model using the mapping relationship to obtain a trained shale oil production capacity prediction model; The production capacity calculation module is specifically used to input the seismic attribute data of the entire region of the target area into the trained shale oil production capacity prediction model to obtain the shale oil production capacity data of the target area.

[0014] This specification provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above-mentioned shale oil production capacity prediction method is implemented.

[0015] This specification provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the above-mentioned shale oil production capacity prediction method is implemented.

[0016] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects: In the shale oil production capacity prediction method provided in this specification, first, seismic attributes within a specified time window are extracted from the geological horizons containing shale oil as initial data, and the shale oil production capacity of horizontal wells is calculated in combination with a preset formula; subsequently, based on the geographical coordinates of the horizontal wells as the association basis, a mapping relationship between seismic attributes and production capacity is established, and a machine learning model is trained based on this; finally, using the trained model, the shale oil production capacity distribution of the target area is predicted according to the seismic attribute data of the entire region of the target area, realizing a quantitative intelligent prediction from seismic characteristics to production capacity.

[0017] The present invention uses a data-driven method to establish the relationship between the production capacity of favorable areas and seismic attributes, realizing the transformation from the traditional method of qualitatively identifying favorable areas based on geological characteristics to the method of identifying favorable areas through deep learning non-linear big data, fully excavating the implicit relationships between seismic attributes, solving the problems of high uncertainty and strong subjectivity in traditional methods, and improving the accuracy of shale oil production capacity prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application, form a part of the present application, and the schematic embodiments and descriptions thereof are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings: Figure 1 is a schematic flowchart of a shale oil production capacity prediction method provided in this specification; Figure 2 is a schematic diagram of the oil production contribution rate of a fracturing stage; Figure 3 is a schematic diagram of the average daily oil production distribution of a fracturing stage; Figure 4 is a schematic diagram of the shale oil production capacity - seismic attribute link; Figure 5 It is a model architecture diagram of a shale oil production capacity prediction model; Figure 6 It is a schematic diagram of the model accuracy of the training result of the shale oil production capacity prediction model; Figure 7 It is a schematic diagram of the shale oil production capacity distribution in the target area; Figure 8 It is a relationship diagram between the daily oil production and the cumulative probability of the daily oil production; Figure 9 It is a schematic diagram of the favorable area after classification of the target area; Figure 10 It is a schematic diagram of a shale oil production capacity prediction device provided in this specification; Figure 11 It is a schematic diagram of a computer device for implementing a shale oil production capacity prediction method provided in this specification. Detailed implementation manners

[0019] To make the purpose, technical solutions and advantages of this specification clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. Based on the embodiments in the specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

[0020] The following will detail the technical solutions provided in each embodiment of this application in conjunction with the drawings.

[0021] Figure 1 It is a schematic diagram of the flow of a shale oil production capacity prediction method in this specification, which specifically includes the following steps: S101: Obtain the shale oil production capacity data of horizontal wells in the geological layer containing shale oil.

[0022] Exemplarily, in this embodiment, the prediction of shale oil production capacity is the main goal. And since in the geological characteristics, the G9 layer is mainly composed of organic-rich shale, intercalated with thin layers of siltstone or calcareous layers, having typical shale oil reservoir characteristics, therefore, the geological layer containing shale oil in this embodiment can refer to the G9 layer.

[0023] Based on this, in one or more embodiments of this specification, the execution subject can be a hardware device or system with multi-modal data acquisition, processing and analysis capabilities, including servers, edge computing devices, etc.

[0024] The server mentioned in this specification can be a server set up on the business platform, or a device such as a desktop computer or a laptop computer that can execute the solution of this specification. For the convenience of description, only the server will be used as the execution subject for description below.

[0025] In this embodiment, obtaining the shale oil production capacity data of horizontal wells in the geological formation containing shale oil includes: Obtaining the shale oil production volume, contribution rate at the fracturing stage, and oil-phase tracer concentration at the fracturing stage for each individual well in each fracturing stage; Based on the shale oil production volume, contribution rate at the fracturing stage, and oil-phase tracer concentration at the fracturing stage for each individual well in each fracturing stage, using a preset calculation formula for the shale oil production capacity of the fracturing stage, calculate the shale oil production capacity data.

[0026] The preset calculation formula for the shale oil production capacity of the fracturing stage is: ; Wherein, represents the shale oil production volume of the th day and the th fracturing stage, represents the shale oil production volume of an individual well on the th day, represents the contribution rate at the th day and the th fracturing stage, represents the oil-phase tracer concentration at the th day and the th fracturing stage, the sum of the oil-phase tracer concentrations in all fracturing stages within the th day.

[0027] Exemplarily, taking QH2202Y-G9 as an example, as shown in Figure 2, Figure 2 is a schematic diagram of the oil production contribution rate of the fracturing stage. As Figure 3 shown, Figure 3 is a schematic diagram of the average daily oil production distribution of the fracturing stage.

[0028] S102: Extract seismic attributes within a specified time window in the geological formation containing shale oil to obtain initial seismic attribute data.

[0029] In seismic data interpretation, a specified time window (Time Window) refers to a fixed time range selected around the geological formation containing shale oil (such as the top and bottom interfaces of the G9 layer) for extracting seismic attribute values within this range. The length of the time window can be determined according to the thickness of the target layer and the seismic resolution, and the position of the time window can be a fixed time window or a sliding time window.

[0030] Optionally, before step S102, a method of calibrating seismic data with well logging data can be adopted. Based on shale oil seismic data and a small amount of horizon interpretation annotation data, seismic horizons are interpreted, and the geological horizon containing shale oil is determined to be horizon G9. And seismic attributes within the specified time window are extracted along horizon G9. In this embodiment, 36 seismic attributes such as amplitude, frequency, phase, and energy for lithology interpretation and reservoir physical property prediction are extracted, as shown in Table 1. Table 1 is an example of some seismic attributes. Among them, Ant average envelope represents the Ant average envelope value, Average energy represents the average energy which are 3.9912e+05 and 1.3089e+06 respectively, Average magnitude represents the average amplitude which are 732.9124 (the first group) and 1355.3828 (the second group), Average negative amplitude represents the average value of the negative polarity amplitude which is 0, indicating that no negative fluctuations are detected, Median represents the median which are 557.5268 and 731.1199 respectively, and there are differences from the average values, suggesting that the data distribution is asymmetric.

[0031] Table 1 Example of Some Seismic Attributes

[0032] S103: Using the geodetic coordinates of the target horizontal well as an index, a mapping relationship between the initial seismic attribute data and shale oil production capacity is constructed based on the initial seismic attribute data and shale oil production capacity data.

[0033] Exemplarily, as shown in Table 2, Table 2 is an example table of the mapping relationship between shale oil production capacity and seismic attributes.

[0034] Table 2 Example Table of the Mapping Relationship between Shale Oil Production Capacity and Seismic Attributes

[0035] In Table 2, (X, Y) represents the geodetic coordinates of the target horizontal well, Oil Production (t / d) represents the oil production (tons per day), Ant average envelope represents the Ant average envelope value, Average energy represents the average energy, Average magnitude represents the average amplitude, Average negative amplitude represents the average value of the negative polarity amplitude, Average positive amplitude represents the average value of the positive polarity amplitude, and Median represents the median. And, as Figure 4 shown, Figure 4 is a schematic diagram of the link between shale oil production capacity and seismic attributes.

[0036] In this embodiment, before constructing the mapping relationship between the initial seismic attribute data and the shale oil production capacity with the geodetic coordinates of the target horizontal well as the index, the method further includes: performing data preprocessing on the initial seismic attribute data to obtain the preprocessed seismic attribute data; screening the preprocessed seismic attribute data according to the correlation between each seismic attribute data and the shale oil production capacity in the preprocessed seismic attribute data to obtain the seismic attribute data; Constructing the mapping relationship between the initial seismic attribute data and the shale oil production capacity according to the initial seismic attribute data and the shale oil production capacity data specifically includes: constructing the mapping relationship between the initial seismic attribute data and the shale oil production capacity according to the seismic attribute data and the shale oil production capacity data.

[0037] Optionally, the steps of performing data preprocessing on the initial seismic attribute data and screening the preprocessed seismic attribute data may also be executed after S103, and no specific limitation is made here.

[0038] Taking the steps of performing data preprocessing on the initial seismic attribute data and screening the preprocessed seismic attribute data can also be executed after S103 as an example. Due to the large difference in the order of magnitude of seismic attributes, directly using the original data to input into the neural network for training may cause repeated oscillations during the gradient update process, affecting the convergence of the network, and even causing numerical out-of-bounds problems. Therefore, the zero-mean normalization method is used to standardize the data (that is, data preprocessing), mapping the original data to a distribution with a mean of 0 and a standard deviation of 1, and the calculation formula is: ; wherein, represents the initial seismic attribute data, and respectively represent the average value and the standard deviation of the initial seismic attribute data, represents the preprocessed seismic attribute data.

[0039] Exemplarily, as shown in Table 3, Table 3 is an example table of shale oil production capacity - seismic attribute data after standardization. Among them, (X, Y) represents the geodetic coordinates of the target horizontal well, Oil Production (t / d) represents the oil production (tons per day), Antaverage envelope represents the Ant average envelope value, Average energy represents the average energy, average envelope represents the average envelope value, Average magnitude represents the average amplitude, Average negative amplitude represents the average value of the negative polarity amplitude, and Median represents the median.

[0040] Table 3 Example Table of Shale Oil Production Capacity - Seismic Attribute Data after Standardization

[0041] In this embodiment, according to the correlation between each seismic attribute data and shale oil production capacity in the preprocessed seismic attribute data, the preprocessed seismic attribute data is screened to obtain seismic attribute data, which specifically includes: using the hierarchical clustering method to calculate the correlation between each seismic attribute data and shale oil production capacity in the preprocessed seismic attribute data to obtain the similarity calculation result; determining the seismic attribute data according to the similarity calculation result; the seismic attribute data includes the average negative polarity amplitude, average amplitude, average positive polarity amplitude, average energy, asymmetry, root mean square amplitude, kurtosis, and maximum amplitude.

[0042] S104: Construct a shale oil production capacity prediction model, and use the mapping relationship to train the shale oil production capacity prediction model to obtain a trained shale oil production capacity prediction model.

[0043] In this embodiment, the model architecture of the shale oil production capacity prediction model includes an input layer, a hidden layer, a BN layer, and an output layer; among them, the number of hidden layers is at least two, and every two adjacent hidden layers are connected by a BN layer; the shale oil production capacity prediction model determines the number of hidden layers and the number of neurons in the hidden layer through the grid search method; the shale oil production capacity prediction model determines the target hyperparameter combination from the preset hyperparameter combinations through the three-fold cross-validation method.

[0044] Exemplarily, the shale oil production capacity prediction model can be obtained by adding a BN layer to a fully connected neural network. A fully connected neural network is a classic feedforward neural network structure, usually composed of multiple neuron layers stacked together. Each neuron in a layer is connected to all neurons in the previous layer and the next layer. Data propagates unidirectionally from the input layer through a series of hidden layers to the output layer without feedback connections. Each neuron can be regarded as a computing unit that receives inputs from all neurons in the previous layer, performs a weighted sum operation, adds a bias term, and outputs the final result through an activation function.

[0045] Optionally, to avoid overfitting problems, the Dropout layer is used to randomly deactivate the outputs of some neurons, reduce the correlation between neurons, reduce the dependence of the model on certain specific neurons, and improve the generalization ability of the model.

[0046] During the training process of a deep neural network, due to the high degree of correlation and coupling between layers in the network, the update of parameters will cause changes in the distribution of input data for subsequent layers. This phenomenon is called ("Internal Covariate Shift"), which increases the difficulty of training and reduces the convergence speed of the model. Therefore, the BN layer is introduced into the fully connected neural network. The basic idea of BN is to insert a normalization layer at the input of each layer of the network. By normalizing the output of the activation layer, the distribution of the input data of each layer of the neural network is transformed into a standard normal distribution with a mean of 0 and a standard deviation of 1. The input training data passes through the fully connected layer and then enters the BN layer for batch normalization. The data distribution is transformed back into a standard normal distribution and then passed to the next layer for training, which speeds up the convergence speed of the model and helps prevent problems such as gradient disappearance and gradient explosion. As Figure 5 shown, Figure 5 is the model architecture diagram of the shale oil production capacity prediction model.

[0047] In this embodiment, the hyperparameters (such as the number of intermediate hidden layers and the number of neurons in the hidden layer) of the fully connected neural network are optimized by the grid search method (Gird Search), and the preset parameter combinations are cross-validated and evaluated by the 3-fold cross-validation method, so as to select the combination of hyperparameters with the best performance indicators (that is, the target hyperparameter combination) to establish the network model. As shown in Table 4, Table 4 is an example of preset parameter combinations. Among them, layers represents the number of network layers, neurons represents the number of neurons, batch represents the batch size, epochs represents the number of training rounds, and dropout represents the dropout rate.

[0048] Table 4 Preset Parameter Combinations

[0049] Optionally, four evaluation indicators, namely Mean Squared Error (MSE), Root Squared Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R²), can be used to evaluate the performance of the model, and the optimal model is selected to determine the shale oil production capacity prediction model. Through grid search, the optimal grid parameters and the training results of the shale oil production capacity prediction model are obtained, as shown in Table 5. Table 5 is the optimal grid parameters and the training results of the shale oil production capacity prediction model. And, as Figure 6 shown, Figure 6Schematic diagram of the model accuracy of the shale oil production capacity prediction model. Among them, "layers" represents the number of network layers, "neurons" represents the number of neurons, "batch" represents the batch size, "epochs" represents the number of training rounds, and "dropout" represents the dropout rate.

[0050] Table 5 Optimal grid parameters and training results of the shale oil production capacity prediction model

[0051] S105: Input the seismic attribute data of the entire target area into the trained shale oil production capacity prediction model to obtain the shale oil production capacity data of the target area.

[0052] In this embodiment, the method further includes: Calculate the cumulative oil production based on the shale oil production capacity data; Calculate the cumulative probability of oil production based on the cumulative oil production; Draw a relationship diagram based on the cumulative oil production and the cumulative probability of oil production, and classify according to the Lorenz cumulative probability curve relationship diagram to determine the type of oil-producing layer in the target area.

[0053] Exemplarily, as Figure 7 shown, Figure 7 is the schematic diagram of the shale oil production capacity distribution in the target area.

[0054] Optionally, the calculation formula for calculating the cumulative oil production based on the shale oil production capacity data is: ; where represents the cumulative oil production corresponding to each data, represents the daily oil production corresponding to each shale oil production capacity data.

[0055] The calculation formula used to calculate the cumulative probability of oil production based on the cumulative oil production is: ; where represents the cumulative probability of oil production corresponding to each shale oil production capacity data, represents the sample size of the shale oil production capacity data.

[0056] As Figure 8 shown, Figure 8 is the relationship diagram between the daily oil production and the cumulative probability of daily oil production. As Figure 9 shown, Figure 9 is the schematic diagram of the favorable area after classification of the target area.

[0057] Optionally, according to the classification based on the Lorenz cumulative probability curve relationship diagram, the type of oil-producing layer can be divided into three types of reservoirs if the daily oil production is <0.17t / d; 0.17t / d<daily oil production<0.61t / d, which is a second-class reservoir; daily oil production>0.61t / d, which is a first-class reservoir.

[0058] based on Figure 1 The shale oil production capacity prediction method shown in the figure uses a data-driven approach to establish the relationship between the production capacity of favorable areas and seismic attributes, realizing the transition from the traditional method of qualitatively identifying favorable areas based on geological characteristics to the method of identifying favorable areas based on deep learning nonlinear big data, fully exploring the implicit relationship between seismic attributes, solving the problems of high uncertainty and subjectivity in traditional methods, and improving the accuracy of shale oil production capacity prediction.

[0059] When applying the shale oil production capacity prediction method provided in this manual, it is not necessary to Figure 1 The steps are executed in the order shown. The specific execution order of the steps can be determined according to needs, and this manual does not limit this.

[0060] The above is a shale oil production capacity prediction method provided by one or more embodiments of this specification. Based on the same idea, this specification also provides a corresponding shale oil production capacity prediction device, such as Figure 10 shown.

[0061] Figure 10 A schematic diagram of a shale oil production capacity prediction device provided for this specification includes: The data acquisition module is specifically used to obtain shale oil production capacity data of horizontal wells in geological layers containing shale oil; extract seismic attributes within a specified time window in the geological layers containing shale oil to obtain initial seismic attribute data; use the geodetic coordinates of the target horizontal well as an index, and construct a mapping relationship between the initial seismic attribute data and the shale oil production capacity according to the initial seismic attribute data and the shale oil production capacity data; The model training module is specifically used to construct a shale oil capacity prediction model, and use the mapping relationship to train the shale oil capacity prediction model to obtain a trained shale oil capacity prediction model; The production capacity calculation module is specifically used to input the seismic attribute data of the entire target area into the trained shale oil production capacity prediction model to obtain the shale oil production capacity data of the target area.

[0062] For the specific limitations of the shale oil production capacity prediction device, reference can be made to the limitations of the shale oil production capacity prediction method in the above text, which will not be elaborated here. Each module in the above shale oil production capacity prediction device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in the form of hardware or be independent of it, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0063] This specification also provides a computer-readable storage medium, which stores a computer program that can be used to execute the above Figure 1 provided shale oil production capacity prediction method.

[0064] This specification also provides Figure 11 the structural schematic diagram of the computer device shown, as Figure 11 , at the hardware level, this computer device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory. Of course, it may also include other hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to implement the above Figure 1 provided shale oil production capacity prediction method.

[0065] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to the memory, storage, database, or other media used in the various embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0066] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

Claims

1. A method for predicting shale oil production capacity, characterized in that include: Obtain shale oil production capacity data for horizontal wells in geological formations containing shale oil; Extracting seismic attributes within a specified time window in a geological layer containing shale oil to obtain initial seismic attribute data; Taking the geodetic coordinates of the target horizontal well as an index, a mapping relationship between the initial seismic attribute data and the shale oil production capacity is established according to the initial seismic attribute data and the shale oil production capacity data; Constructing a shale oil production capacity prediction model, and using the mapping relationship to train the shale oil production capacity prediction model to obtain a trained shale oil production capacity prediction model; The whole-area seismic attribute data of the target area is input into the trained shale oil production capacity prediction model to obtain the shale oil production capacity data of the target area.

2. The shale oil production capacity prediction method according to claim 1, characterized in that The model architecture of the shale oil production capacity prediction model includes an input layer, a hidden layer, a BN layer and an output layer; The number of hidden layers is at least two, and every two adjacent hidden layers are connected through a BN layer; The shale oil production capacity prediction model determines the number of hidden layers and the number of neurons in the hidden layers by a grid search method; The shale oil production capacity prediction model determines the target hyperparameter combination from the preset hyperparameter combinations through a three-fold cross validation method.

3. The shale oil production capacity prediction method according to claim 1, wherein Before constructing a mapping relationship between the initial seismic attribute data and the shale oil production capacity according to the initial seismic attribute data and the shale oil production capacity data by taking the geodetic coordinates of the target horizontal well as an index, the method further comprises: Performing data preprocessing on the initial seismic attribute data to obtain preprocessed seismic attribute data; According to the correlation between each seismic attribute data in the preprocessed seismic attribute data and the shale oil production capacity, the preprocessed seismic attribute data are screened to obtain seismic attribute data; The step of constructing a mapping relationship between the initial seismic attribute data and the shale oil production capacity data according to the initial seismic attribute data and the shale oil production capacity data specifically includes: A mapping relationship between the initial seismic attribute data and the shale oil production capacity data is constructed based on the seismic attribute data and the shale oil production capacity data.

4. The shale oil production capacity prediction method according to claim 3, characterized in that The step of screening the preprocessed seismic attribute data according to the correlation between each seismic attribute data in the preprocessed seismic attribute data and the shale oil production capacity to obtain the seismic attribute data specifically includes: Using a hierarchical clustering method, calculating the correlation between each seismic attribute data in the preprocessed seismic attribute data and the shale oil production capacity, and obtaining a similarity calculation result; Determining the earthquake attribute data according to the similarity calculation result; The seismic attribute data include negative polarity amplitude average, average amplitude, positive polarity amplitude average, average energy, asymmetry, root mean square amplitude, kurtosis and maximum amplitude.

5. The shale oil production capacity prediction method according to claim 1, wherein The step of obtaining shale oil production capacity data of a horizontal well in a geological layer containing shale oil includes: Obtaining the shale oil production of each single well in each fracturing stage, the contribution rate at the fracturing stage, and the oil phase tracer concentration at the fracturing stage; Based on the shale oil production of each single well in each fracturing stage, the contribution rate at the fracturing stage and the oil phase tracer concentration at the fracturing stage, the shale oil production capacity data is calculated using a preset shale oil fracturing stage production capacity calculation formula.

6. The shale oil production capacity prediction method according to claim 5, wherein The preset shale oil fracturing stage capacity calculation formula is: ； Among them, represents the shale oil production of the th day and the th fracturing stage, represents the shale oil production of a single well on the th day, represents the contribution rate at the th day and the th fracturing stage, represents the concentration of oil-phase tracer at the th day and the th fracturing stage, The sum of the concentrations of oil-phase tracers in all fracturing stages within the th day.

7. The shale oil production capacity prediction method according to claim 1, wherein, The method further comprises: Calculate the cumulative oil production based on the shale oil production capacity data; Calculating the cumulative probability of oil production according to the cumulative oil production; A relationship diagram is drawn according to the cumulative oil production and the cumulative probability of oil production, and the relationship diagram is classified according to the Lorenz cumulative probability curve relationship diagram to determine the type of oil-producing layer in the target area.

8. A shale oil production capacity prediction device, characterized in that, include: The data acquisition module is specifically used to acquire shale oil production capacity data of horizontal wells in geological layers containing shale oil; extract seismic attributes within a specified time window in the geological layers containing shale oil to obtain initial seismic attribute data; and use the geodetic coordinates of the target horizontal well as an index to construct a mapping relationship between the initial seismic attribute data and the shale oil production capacity data according to the initial seismic attribute data and the shale oil production capacity data; A model training module is specifically used to construct a shale oil production capacity prediction model, and use the mapping relationship to train the shale oil production capacity prediction model to obtain a trained shale oil production capacity prediction model; The production capacity calculation module is specifically used to input the seismic attribute data of the entire target area into the trained shale oil production capacity prediction model to obtain the shale oil production capacity data of the target area.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer device, characterized in that, The method comprises 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 described in any one of claims 1 to 7 is implemented.

Images