A method and device for predicting reservoir distribution and a storage medium

Abstract

The embodiment of the present application provides a kind of reservoir distribution prediction method, device and storage medium, belong to petroleum technical field.The prediction method includes: obtaining the logging data of reservoir at different logging depths, wherein the logging data includes the permeability, porosity, water saturation and shale content of the reservoir;Determine reservoir quality factor based on the logging data;And reservoir quality factor curve is formed based on the reservoir quality factor at different logging depths, and reservoir distribution prediction is carried out.The embodiment of the present application obtains reservoir quality factor based on permeability, porosity, water saturation and shale content, and the reservoir quality factor can accurately identify reservoir, so as to accurately predict reservoir distribution, which is beneficial to higher reservoir drilling rate for well deployment.

Description

Technical Field

[0001] This invention relates to the field of petroleum development technology, and more specifically to a method, apparatus, and storage medium for predicting reservoir distribution. Background Technology

[0002] Current reservoir quality evaluation requires a comprehensive assessment using multiple logging curves, including porosity, permeability, and saturation, making it difficult to clearly distinguish different reservoir types using a single curve. Existing technologies construct reservoir quality indices using functions of porosity and permeability to characterize reservoir quality. However, these indices are merely optimal macroscopic physical properties that quantitatively characterize the microscopic pore structure of the reservoir, reflecting only the quality of the pore structure. This results in insufficient precision in reservoir type evaluation and difficulty in accurately predicting reservoir distribution. For example, in practical applications, using existing reservoir quality indices, the calculated results for dry reservoirs and gas-bearing reservoirs are quite similar, making it difficult to distinguish between them and leading to unclear differentiation between different reservoir types. Furthermore, reservoir spatial distribution is generally predicted based on the established relationship between the reservoir quality index and elastic parameters (such as P-wave velocity, S-wave velocity, and density). However, due to the difficulty in establishing the relationship between reservoir quality factors and coelastic parameters, accurate predictions of reservoir spatial distribution are challenging. Summary of the Invention

[0003] The purpose of this invention is to provide a method, apparatus, and storage medium for predicting reservoir distribution, in order to at least solve the aforementioned technical problems.

[0004] To achieve the above objectives, in a first aspect, embodiments of the present invention provide a method for predicting reservoir distribution. The method includes: acquiring well logging data of a reservoir at different logging depths, wherein the well logging data includes the reservoir's permeability, porosity, water saturation, and clay content; determining a reservoir quality factor based on the well logging data; and predicting reservoir distribution based on a reservoir quality factor curve formed by the reservoir quality factors at different logging depths.

[0005] Optionally, the reservoir quality factor is determined by the following formula:

[0006]

[0007] Where RQIstr is the reservoir quality factor, and K is the permeability at the specified logging depth. SW is the porosity at a specified logging depth, SH is the water saturation at a specified logging depth, and SH is the clay content at a specified logging depth.

[0008] Optionally, the reservoir distribution prediction based on the reservoir quality factor curves formed by the reservoir quality factors at different logging depths includes: analyzing the curve characteristics of the reservoir quality factor curves at different logging depths, wherein the curve characteristics include the peak points of the reservoir quality factor curves; determining the reservoir types corresponding to different curve characteristics based on the curve characteristics of the reservoir quality factors; wherein the reservoir types include at least one of the following: gas layer, poor gas layer, gas-bearing layer, dry layer, and water layer.

[0009] Optionally, the reservoir distribution prediction based on the reservoir quality factor curves formed by reservoir quality factors at different logging depths further includes: matching the reservoir depth location corresponding to the reservoir quality factor curve with the seismic calibration location of the reservoir to determine the reservoir type at the seismic calibration location matched with the reservoir depth location; analyzing the seismic reflection waveform characteristics of the reservoir at the seismic calibration location, and predicting the spatial distribution range of different types of reservoirs based on the spatial distribution pattern of the seismic reflection waveform.

[0010] Optionally, based on the reservoir quality factor and the porosity, a relationship diagram between the reservoir quality factor and the porosity is obtained; the distribution of the reservoir quality factor on the relationship diagram is obtained, and the prediction results of the reservoir distribution based on the reservoir quality factor are verified according to the well logging data.

[0011] Secondly, embodiments of the present invention provide a reservoir distribution prediction device, the prediction device comprising: an acquisition unit for acquiring well logging data of a reservoir at different logging depths, wherein the well logging data includes the reservoir's permeability, porosity, water saturation, and clay content; a determination unit for determining a reservoir quality factor based on the well logging data; and a prediction unit for predicting the reservoir distribution based on a reservoir quality factor curve formed by the reservoir quality factors at different logging depths.

[0012] Optionally, the preset association relationship is configured to be represented by the following formula:

[0013]

[0014] Where RQIstr is the reservoir quality factor, and K is the permeability at the specified logging depth. SW is the porosity at a specified logging depth, SH is the water saturation at a specified logging depth, and SH is the clay content at a specified logging depth.

[0015] Optionally, the prediction unit is used to predict reservoir distribution in the following manner: analyze the curve characteristics of reservoir quality factor curves at different logging depths, wherein the curve characteristics include the peak points of the reservoir quality factor curves; based on the curve characteristics of the reservoir quality factor, predict the reservoir types corresponding to different curve characteristics; wherein the reservoir types include at least one of the following: gas layer, poor gas layer, gas-bearing layer, dry layer, and water layer.

[0016] Optionally, the step of predicting the reservoir distribution based on the reservoir quality factor further includes: matching the reservoir depth location corresponding to the reservoir quality factor curve with the seismic calibration location of the reservoir to determine the reservoir type of the seismic calibration location that matches the reservoir depth location; analyzing the seismic reflection waveform characteristics of the reservoir at the seismic calibration location, and predicting the spatial distribution range of different types of reservoirs based on the spatial distribution pattern of the seismic reflection waveform.

[0017] Thirdly, embodiments of the present invention provide a machine-readable storage medium storing instructions that cause a machine to execute the reservoir distribution prediction method described in any of the first aspects of this application.

[0018] Through the above technical solution, this invention obtains a reservoir quality factor based on a comprehensive analysis of permeability, porosity, water saturation, and clay content. This reservoir quality factor enables accurate reservoir identification and precise prediction of reservoir distribution, which is beneficial for achieving a higher reservoir encounter rate during drilling deployment.

[0019] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0020] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0021] Figure 1 This is a flowchart illustrating a method for predicting reservoir distribution according to an exemplary embodiment;

[0022] Figure 2 This is a schematic diagram of a reservoir quality factor according to an exemplary embodiment;

[0023] Figure 3 This is a schematic diagram illustrating the relationship between reservoir quality factor and porosity according to an exemplary embodiment;

[0024] Figure 4This is a schematic diagram illustrating another relationship between reservoir quality factor and porosity according to an exemplary embodiment;

[0025] Figure 5 This is a flowchart illustrating a method for predicting reservoir spatial distribution according to an exemplary embodiment;

[0026] Figure 6 This is a schematic diagram of a reservoir spatial distribution according to an exemplary embodiment;

[0027] Figure 7 This is a schematic diagram illustrating another reservoir spatial distribution according to an exemplary embodiment;

[0028] Figure 8 This is a schematic block diagram of a reservoir distribution prediction device according to an exemplary embodiment. Detailed Implementation

[0029] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0030] Figure 1 This is a method for predicting reservoir distribution according to an exemplary embodiment, such as... Figure 1 The prediction method described includes:

[0031] Step S11: Obtain logging data of the reservoir at different logging depths, wherein the logging data includes the reservoir's permeability, porosity, water saturation, and clay content.

[0032] For example, in oil drilling, to gain a preliminary understanding of the rock formation characteristics of the explored area, well logging is typically performed at the designed well depth to obtain reservoir parameters at different depths. This can be achieved through methods such as geophysical testing, exploration logging, and sonic logging.

[0033] Step S12: Determine the reservoir quality factor based on the well logging data.

[0034] For example, the embodiments of this application comprehensively consider the influence of reservoir permeability, porosity, water saturation and clay content on reservoir quality, and determine the reservoir quality factor based on the preset correlation between them and the reservoir quality factor.

[0035] In a preferred embodiment, the reservoir quality factor is determined by the following formula:

[0036]

[0037] Where RQIstr is the reservoir quality factor, and K is the permeability at the specified logging depth. SW is the porosity at a specified logging depth, SH is the water saturation at a specified logging depth, and SH is the clay content at a specified logging depth. It should be noted that the embodiments of this application are not limited to the above formulas. This application can also configure different calculation formulas according to the weight of each logging data according to actual application needs, so as to effectively predict the distribution of different types of reservoirs.

[0038] Step S13: Based on the reservoir quality factor curves formed by the reservoir quality factors at different logging depths, reservoir distribution is predicted.

[0039] In a preferred embodiment, the reservoir distribution prediction based on the reservoir quality factor curves formed by reservoir quality factors at different logging depths includes: analyzing the curve characteristics of the reservoir quality factor curves at different logging depths, wherein the curve characteristics include the peak points of the reservoir quality factor curves; determining the reservoir types corresponding to different curve characteristics based on the curve characteristics of the reservoir quality factors; wherein the reservoir types include at least one of the following: gas layer, poor gas layer, gas-bearing layer, dry layer, and water layer.

[0040] For example, such as Figure 2 As shown, Figure 2 The first column represents the logging depth, the second column represents the logging interpretation conclusions obtained from the analysis of logging data, the third column represents the reservoir quality index curves corresponding to different logging depths obtained using existing technologies, and the fourth column represents the reservoir quality factor curves corresponding to different logging depths obtained using the method implemented in this application. First, the curve characteristics of the reservoir quality factor curves formed based on the reservoir quality factors are analyzed. From... Figure 2 The fourth column shows that, for example, the peak points of curves a and b correspond to higher calculated results, while the peak point of curve c corresponds to a lower calculated result. For well logging depths between 3380 and 3390 mm, the reservoir quality factor curve approaches a straight line, meaning its calculated result is 0. Furthermore, based on the characteristics of different curves and the corresponding well logging data, reservoir types are predicted. From the above formula for calculating the reservoir quality factor, it can be seen that water saturation (SW) has a significant impact on the calculated result. Therefore, if the calculated result of the peak point of the curve is high, it indicates that the water saturation of the reservoir at that logging depth is low. Combining this with other well logging data at that depth and the basic characteristics of different reservoir types, the reservoir type at that logging depth can be comprehensively predicted. Therefore, the reservoir distribution predicted by the above method shows that for gas-bearing reservoirs, the calculated result of the peak point of the reservoir quality factor curve is much lower than that of gas-bearing and poor-gas-bearing reservoirs, while for dry reservoirs, the calculated result of the reservoir quality factor curve approaches 0. And for… Figure 2 In the conventionally calculated reservoir quality index curves, although the peak values ​​of the curves for gas-bearing and poorly gas-bearing reservoirs are higher, while those for dry and gas-bearing reservoirs are lower, the calculated results for dry and gas-bearing reservoirs are quite similar, making it difficult to effectively distinguish between them. Clearly, through the embodiments of this application, the differences in the calculated reservoir quality factors for various reservoir categories are more pronounced. The reservoir quality factors of this application can effectively identify reservoir distribution, especially making the distinction between gas-bearing and dry reservoirs more obvious.

[0041] In a preferred embodiment, in order to further verify the accuracy of the reservoir quality factor calculation results of this application, this embodiment can also obtain the distribution state of the reservoir quality factor based on the relationship between the reservoir quality factor and the porosity, so as to verify the prediction results of the reservoir distribution based on the reservoir quality factor.

[0042] For example, based on the relationship between the reservoir quality factor and porosity, a cross-plot of the reservoir quality factor and porosity is established. (Refer to...) Figure 3 and Figure 4 As shown, where, Figure 3 and Figure 4 Different shapes of markers represent different types of reservoirs. Figure 3 The horizontal axis represents porosity, and the vertical axis represents the reservoir quality index. Figure 4 The horizontal axis represents porosity, and the vertical axis represents the reservoir quality factor. For example... Figure 3 As shown, before the improvement, both the gas layer (circles) and the water layer (squares) were at high values, making them difficult to distinguish effectively. However, as... Figure 4 As shown, the improved water layer (square dot) is at a low value position, making the difference between the gas layer (circle dot) and the water layer (square dot) more obvious.

[0043] In a more preferred embodiment, the embodiments of this application can also predict the spatial distribution of reservoirs based on the reservoir type predicted by the reservoir quality factor curve. For example... Figure 5 As shown, the prediction of reservoir distribution based on the reservoir quality factor further includes:

[0044] Step S21: Match the reservoir depth location corresponding to the reservoir quality factor curve with the seismic calibration location of the reservoir to determine the reservoir type of the seismic calibration location that matches the reservoir depth location.

[0045] For example, the accurate time-depth relationship between well logging data and seismic calibration can be obtained in this application, allowing for the matching of reservoir depth locations of reservoir quality factors with seismic calibration locations. Specifically, firstly, based on well logging curves of reservoir quality factors from multiple wells as samples, an initial low-frequency three-dimensional data model of reservoir quality factors is established. Secondly, the correlation between this three-dimensional data model and the lateral variation of seismic waveforms is analyzed, and the high-frequency components of reservoir quality factors are simulated within a Bayesian framework, ensuring that the simulation results conform to the structural characteristics of both seismic logging curves and well logging curves. Furthermore, the probability is calculated using the lateral transformation relationship of seismic waveforms and the reservoir quality factor model, and the result of the reservoir quality factor data volume is output when the probability is maximized, thereby obtaining the reservoir type distribution at different depths. After location matching, the reservoir type at the matched seismic calibration location can be obtained.

[0046] Step S22: Analyze the seismic reflection waveform characteristics of the reservoir at the seismic calibration location, and predict the spatial distribution range of different types of reservoirs based on the spatial distribution pattern of the seismic reflection waveform.

[0047] For example, in the above embodiments, the reservoir quality factor curve can only analyze the reservoir distribution vertically. However, due to factors such as the number of wells logged and measurement costs, it is impossible to effectively predict the lateral distribution of the reservoir during actual well logging. Therefore, this embodiment uses seismic waveform indication inversion to predict the spatial distribution of the reservoir. By analyzing the seismic reflection waveform characteristics of the reservoir at seismically calibrated locations, and based on the spatial distribution pattern of the seismic reflection waveform, the spatial distribution range of different types of reservoirs is predicted. Specifically, this embodiment establishes a three-dimensional seismic inversion model using well logging data, seismic data, and geological data. The reservoir quality factor data volume obtained after seismic calibration of the reservoir quality factor curve and the three-dimensional seismic data volume characterizing the seismic waveform are used as inputs. The three-dimensional seismic inversion model obtains the three-dimensional data volume of the reservoir quality factor, thereby obtaining the spatial distribution range of the reservoir. This embodiment utilizes the similarity of seismic waveform characteristics and spatial distance to establish a correlation between the reservoir quality factor curve calculated on-site and the three-dimensional seismic data, analyzing the lateral changes in reservoir distribution, and thus accurately predicting the spatial distribution of the reservoir.

[0048] Further reference Figure 6 and Figure 7 As shown, Figure 6 This is the seismic prediction profile of the reservoir quality index before improvement. Figure 6 Curve 1 and Curve 2 are the calculated reservoir quality index curves. Figure 7 This is a seismic prediction profile of the improved reservoir quality factor. Figure 7 Curves 3 and 4 are the calculated reservoir quality factor curves on the well. Figure 7 Compared to Figure 6In comparison, its reservoir distribution curve has a clearer lateral distribution, which can clearly identify the spatial distribution range of the reservoir.

[0049] Therefore, the calculation method of this application can make the differences between gas layers, water-bearing gas layers, poor gas layers, dry layers, etc. more obvious. Thus, the reservoir quality factor calculated by this application can effectively distinguish various types of reservoirs, especially the gas layer identification is more accurate.

[0050] As can be seen from the above embodiments, reservoir quality factors are established based on logging data at different logging depths to predict reservoir distribution at different logging depths. Clearly, this primarily analyzes reservoir distribution from a vertical perspective, making it difficult to intuitively analyze the spatial distribution of reservoirs from a horizontal perspective.

[0051] In summary, the reservoir distribution prediction method of this application has the following advantages: 1) It can combine the influence of water saturation on reservoir quality, adding clay content and water saturation to the existing reservoir permeability and porosity, making the factors considered more comprehensive and the reservoir analysis more accurate. 2) Based on the relationship between permeability, porosity, water saturation, clay content and reservoir quality factors, the reservoir quality factor is calculated, and a single curve is used to quickly identify different types of reservoirs, making the differences between different types of reservoirs more obvious, especially in quickly identifying gas layers. 3) It can combine well logging data, starting from the reservoir quality factor analysis that characterizes reservoir quality, and based on the seismic waveform characteristic indication inversion method, effectively combine well logging data and seismic data, predicting the lateral changes in reservoir distribution on the basis of vertical reservoir distribution prediction, and thus predicting the spatial distribution of reservoirs, improving the accuracy of reservoir distribution prediction, which is conducive to obtaining a higher drilling encounter rate in subsequent drilling deployment.

[0052] Based on the same concept as the above-mentioned reservoir distribution prediction method, such as Figure 8 As shown in the figure, this application provides a reservoir distribution prediction device 10, characterized in that the prediction device 100 includes: an acquisition unit 110, used to acquire well logging data of the reservoir at different logging depths, wherein the well logging data includes the permeability, porosity, water saturation and clay content of the reservoir; a determination unit 120, used to determine the reservoir quality factor based on the well logging data; and a prediction unit 130, used to predict the reservoir distribution based on the reservoir quality factor curve formed by the reservoir quality factors at different logging depths.

[0053] In the determining unit 120, the preset association relationship is configured to be represented by the following formula:

[0054]

[0055] Where RQIstr is the reservoir quality factor, and K is the permeability at the specified logging depth. SW is the porosity at a specified logging depth, SH is the water saturation at a specified logging depth, and SH is the clay content at a specified logging depth.

[0056] The prediction unit 130 predicts reservoir distribution in the following manner: it analyzes the curve characteristics of reservoir quality factor curves at different logging depths, wherein the curve characteristics include the peak points of the reservoir quality factor curves; based on the curve characteristics of the reservoir quality factors, it predicts the reservoir types corresponding to different curve characteristics; wherein the reservoir types include at least one of the following: gas layer, poor gas layer, gas-bearing layer, dry layer, and water layer.

[0057] The prediction unit 130 predicts the reservoir distribution, and further includes: matching the reservoir depth location corresponding to the reservoir quality factor curve with the seismic calibration location of the reservoir to determine the reservoir type of the seismic calibration location that matches the reservoir depth location; analyzing the seismic reflection waveform characteristics of the reservoir at the seismic calibration location, and predicting the spatial distribution range of different types of reservoirs based on the spatial distribution pattern of the seismic reflection waveform.

[0058] Accordingly, embodiments of this application also provide a machine-readable storage medium storing instructions that cause a machine to execute the reservoir distribution prediction method described in the above embodiments of this application.

[0059] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0060] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0061] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0062] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0063] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0064] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0065] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0066] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0067] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for predicting reservoir distribution, characterized in that, The prediction method includes: Acquire logging data of the reservoir at different logging depths, wherein the logging data includes the reservoir's permeability, porosity, water saturation, and clay content; Based on the well logging data, reservoir quality factors are determined; and Reservoir distribution is predicted based on reservoir quality factor curves generated at different logging depths. The reservoir quality factor is determined by the following formula: in, It is the reservoir quality factor, It is the permeability at a specified logging depth. It refers to the porosity at a specified logging depth. It is the water saturation at a specified logging depth. It refers to the mud content at a specified logging depth.

2. The prediction method according to claim 1, characterized in that, The reservoir quality factor curves formed based on reservoir quality factors at different logging depths are used to predict reservoir distribution, including: Analyze the curve characteristics of reservoir quality factor curves at different logging depths, wherein the curve characteristics include the peak points of the reservoir quality factor curves. Based on the curve characteristics of the reservoir quality factor, the reservoir types corresponding to different curve characteristics are determined. The reservoir type includes at least one of the following: gas reservoir, gas-deficient reservoir, gas-bearing reservoir, dry reservoir, and water reservoir.

3. The prediction method according to claim 2, characterized in that, The reservoir distribution prediction based on reservoir quality factor curves formed at different logging depths also includes: Match the reservoir depth location corresponding to the reservoir quality factor curve with the seismic calibration location of the reservoir to determine the reservoir type of the seismic calibration location that matches the reservoir depth location; The seismic reflection waveform characteristics of the reservoir at the seismic calibration location are analyzed, and the spatial distribution range of different types of reservoirs is predicted based on the spatial distribution pattern of the seismic reflection waveform.

4. The prediction method according to claim 1, characterized in that, The prediction method further includes: Based on the reservoir quality factor and the porosity, a relationship diagram between the reservoir quality factor and the porosity is obtained; The distribution of the reservoir quality factor on the relationship diagram is obtained, and the prediction results of the reservoir distribution based on the reservoir quality factor are verified according to the well logging data.

5. A reservoir distribution prediction device, characterized in that, The prediction device includes: The acquisition unit is used to acquire logging data of the reservoir at different logging depths, wherein the logging data includes the reservoir's permeability, porosity, water saturation, and clay content; A determining unit is used to determine reservoir quality factors based on the well logging data; and The prediction unit is used to predict reservoir distribution based on reservoir quality factor curves generated at different logging depths. The default association is configured to be represented by the following formula: in, It is the reservoir quality factor, It is the permeability at a specified logging depth. It refers to the porosity at a specified logging depth. It is the water saturation at a specified logging depth. It refers to the mud content at a specified logging depth.

6. The prediction device according to claim 5, characterized in that, The prediction unit predicts reservoir distribution, including: Analyze the curve characteristics of reservoir quality factor curves at different logging depths, wherein the curve characteristics include the peak points of the reservoir quality factor curves. Based on the curve characteristics of the reservoir quality factor, the reservoir type corresponding to different curve characteristics is predicted. The reservoir type includes at least one of the following: gas reservoir, gas-deficient reservoir, gas-bearing reservoir, dry reservoir, and water reservoir.

7. The prediction device according to claim 6, characterized in that, The prediction unit predicts the reservoir distribution and further includes: Match the reservoir depth location corresponding to the reservoir quality factor curve with the seismic calibration location of the reservoir to determine the reservoir type of the seismic calibration location that matches the reservoir depth location; The seismic reflection waveform characteristics of the reservoir at the seismic calibration location are analyzed, and the spatial distribution range of different types of reservoirs is predicted based on the spatial distribution pattern of the seismic reflection waveform.

8. A machine-readable storage medium storing instructions for causing a machine to perform the reservoir distribution prediction method according to any one of claims 1-4 of this application.

Images