Methods, apparatus, computer equipment and media for predicting Paleogene reservoir permeability

Abstract

This invention discloses a method, apparatus, computer equipment, and medium for predicting Paleogene reservoir permeability. The method includes: acquiring seismic and well logging data of a target Paleogene region; determining sedimentary facies data, porosity, amplitude spectral gradient, and velocity dispersion data of the target Paleogene region as input variables based on the seismic data; wherein a quantitative correspondence exists between the sedimentary facies data and permeability; determining the sample permeability of drilled wells in the target Paleogene region as an output variable based on the well logging data; and substituting the input and output variables as the original sample set into a preset random forest model to predict the reservoir permeability of the target Paleogene region. By introducing sedimentary facies into the sample data, a phase control effect can be achieved in the random forest regression sample training and decision-making process, thereby making the prediction results more reliable, more consistent with actual geological sedimentary patterns, and increasing the accuracy of permeability prediction.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of seismic exploration and development technology, and in particular to a method, apparatus, computer equipment and medium for predicting the permeability of Paleogene reservoirs. Background Technology

[0002] With the continuous deepening of exploration and development, the Paleogene system has become one of the key areas of exploration. Paleogene reservoirs are characterized by deep burial and rapid facies changes, and their physical properties are mostly characterized by low porosity and low permeability, or ultra-low porosity and ultra-low permeability. Paleogene reservoir permeability is one of the important indicators in oil and gas exploration and development, making accurate and reliable prediction of reservoir permeability particularly necessary.

[0003] Current quantitative research on reservoir permeability can be divided into three aspects: (1) Permeability measurement in rock physics using core laboratory. This method is highly accurate but expensive. In addition, core laboratory measurement is limited by the core sampling range and can only characterize the distribution of reservoir permeability within a very small area. (2) Reservoir permeability obtained based on well logging data. Its accuracy is second only to laboratory measurement and can provide continuous formation reservoir permeability information above the well. However, it is only a "one-sided view" and it is difficult to characterize reservoir permeability in three-dimensional space. (3) Reservoir permeability calculated based on seismic data. Its advantage is that seismic data has a high lateral resolution and can characterize the distribution of reservoir properties in three-dimensional space, thus achieving the effect of permeability prediction. However, the accuracy of permeability obtained by seismic inversion is much lower than that obtained by laboratory measurement and well logging data. Seismic data contains rich geological information. Previous studies have found a clear relationship between various seismic information and reservoir properties. For example, the seismic data amplitude spectrum gradient refers to the rate of change of seismic reflection wave amplitude with frequency within the effective frequency band of seismic data. It highlights the variation characteristics of seismic data amplitude at different frequencies and reveals the variation characteristics of reservoir permeability performance. Therefore, reservoir permeability can be predicted by obtaining amplitude spectral gradient properties from seismic data. Furthermore, porosity can be derived from seismic velocity based on time-averaged equations, and then reservoir permeability can be obtained from the porosity-permeability relationship derived from rock physics analysis of drilled wells. Because seismic waves induce pore fluid flow during propagation, causing seismic wave velocity dispersion and amplitude attenuation, reservoir permeability and fluid properties can be obtained through seismic wave dispersion and attenuation inversion. However, since seismic data is a comprehensive response to multiple formation parameters, and the relationship between reservoir permeability and seismic data is nonlinear, the above methods suffer from multiple solutions and lack stability in predicting reservoir permeability.

[0004] To overcome the limitations of the aforementioned methods, the random forest regression method based on machine learning has been introduced into reservoir prediction. The random forest method, composed of multiple decision trees, boasts advantages such as high prediction accuracy and high tolerance to outliers and noisy data. However, Paleogene reservoirs are characterized by deep burial, rapid facies transitions, and low-quality seismic data. Furthermore, the random forest regression method is purely data-driven, which can lead to similar seismic responses in different sedimentary facies zones resulting in similar reservoir property outputs that often do not match actual geological sedimentary patterns, leading to larger prediction errors. Summary of the Invention

[0005] This invention provides a method, apparatus, computer equipment, and medium for predicting Paleogene reservoir permeability, in order to solve the problem that the prediction results do not match the actual geological sedimentary patterns and the prediction error is too large in the prior art.

[0006] In a first aspect, embodiments of the present invention provide a method for predicting the permeability of Paleogene reservoirs, the method comprising:

[0007] Acquire seismic and well logging data for the target Paleogene region;

[0008] Based on the seismic data, sedimentary facies data, porosity, amplitude spectral gradient, and velocity dispersion data in the target Paleogene region are determined as input variables; wherein, there is a quantitative correspondence between the sedimentary facies data and permeability;

[0009] Based on the well logging data, the permeability of the drilled samples in the target Paleogene region is determined as the output variable;

[0010] The input and output variables are used as the original sample set and substituted into a preset random forest model to predict the reservoir permeability of the target Paleogene region.

[0011] Optionally, the method further includes:

[0012] Based on the well logging data, a basic correspondence between permeability and different sedimentary facies zones was obtained;

[0013] The spatial distribution of different sedimentary facies in the target Paleogene region was determined based on the earthquake data.

[0014] Based on the spatial distribution and the basic correspondence, well logging is used to calibrate the seismic phases to obtain the quantitative correspondence.

[0015] Optionally, the step of substituting the input variables and the output variables as the original sample set into a preset random forest model to predict the reservoir permeability of the target Paleogene region includes:

[0016] The original sample set is resampled using the Bootstrap sampling method to randomly generate multiple training sets, and a corresponding decision tree is generated for each training set.

[0017] The predicted values ​​output by each decision tree are averaged to obtain the predicted reservoir permeability of the target Paleogene region.

[0018] Optionally, determining the sample permeability of drilled wells in the target Paleogene region as an output variable based on the logging data includes:

[0019] The target data used to reflect reservoir permeability in the well logging data are resampled according to the seismic sampling rate to obtain the sample permeability.

[0020] Optionally, determining the porosity in the target Paleogene region based on the seismic data includes:

[0021] The porosity is obtained by porosity inversion.

[0022] Optionally, determining the amplitude spectral gradient in the target Paleogene region based on the seismic data includes:

[0023] The amplitude spectral gradient was determined using spectral analysis and spectral decomposition techniques.

[0024] Optionally, determining the velocity dispersion data of the target Paleogene region based on the seismic data includes:

[0025] The velocity dispersion data were determined using pre-stack seismic dispersion analysis.

[0026] Secondly, embodiments of the present invention also provide a device for predicting the permeability of Paleogene reservoirs, the device comprising:

[0027] The data acquisition module is used to acquire seismic and well logging data for the target Paleogene region;

[0028] The input variable determination module is used to determine sedimentary facies data, porosity, amplitude spectral gradient, and velocity dispersion data in the target Paleogene region as input variables based on the seismic data; wherein, there is a quantitative correspondence between the sedimentary facies data and permeability;

[0029] The output variable determination module is used to determine the sample permeability of drilled wells in the target Paleogene region as an output variable based on the well logging data.

[0030] The permeability prediction module is used to substitute the input variables and the output variables as the original sample set into a preset random forest model to predict the reservoir permeability of the target Paleogene region.

[0031] Thirdly, embodiments of the present invention also provide a computer device, the computer device comprising:

[0032] One or more processors;

[0033] Memory, used to store one or more programs;

[0034] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for predicting Paleogene reservoir permeability provided in any embodiment of the present invention.

[0035] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for predicting Paleogene reservoir permeability provided in any embodiment of the present invention.

[0036] This invention provides a method for predicting the permeability of Paleogene reservoirs. First, seismic and well logging data of the target Paleogene region are acquired. Then, based on the seismic data, sedimentary facies data, porosity, amplitude spectral gradient, and velocity dispersion data of the target Paleogene region are determined as input variables. Next, based on the well logging data, the permeability of drilled well samples in the target Paleogene region is determined as the output variable. The obtained input and output variables are then used as the original sample set and substituted into a pre-set random forest model to predict the reservoir permeability of the target Paleogene region. The method for predicting Paleogene reservoir permeability provided by this invention, by introducing sedimentary facies into the sample data of the random forest model, can play a phase control role in the random forest regression sample training and decision-making process, thereby making the prediction results more reliable and more consistent with actual geological sedimentary patterns, increasing the accuracy of permeability prediction, and better guiding exploration, development, and production. Attached Figure Description

[0037] Figure 1 A flowchart of a method for predicting Paleogene reservoir permeability provided in Embodiment 1 of the present invention;

[0038] Figure 2 This is a schematic diagram of the structure of the Paleogene reservoir permeability prediction device provided in Embodiment 2 of the present invention;

[0039] Figure 3 This is a schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention. Detailed Implementation

[0040] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0041] Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the steps as sequential processes, many of these steps can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the steps can be rearranged. The process can be terminated when its operation is complete, but may also have additional steps not included in the figures. The process can correspond to a method, function, procedure, subroutine, subroutine, etc.

[0042] Example 1

[0043] Figure 1 This is a flowchart illustrating a method for predicting Paleogene reservoir permeability according to Embodiment 1 of the present invention. This embodiment is applicable to predicting Paleogene reservoir permeability. The method can be executed by the Paleogene reservoir permeability prediction device provided in this embodiment, which can be implemented in hardware and / or software, and is generally integrated into a computer device. Figure 1 As shown, the specific steps include the following:

[0044] S11. Obtain seismic and well logging data for the target Paleogene region.

[0045] Specifically, the required seismic and well logging data can be obtained using any existing method, specifically by drilling multiple wells in the target Paleogene region to obtain the required well logging data.

[0046] S12. Based on the seismic data, determine the sedimentary facies data, porosity, amplitude spectrum gradient, and velocity dispersion data in the target Paleogene region as input variables; wherein, there is a quantitative correspondence between the sedimentary facies data and permeability.

[0047] Specifically, sedimentary facies data in the target Paleogene region can be determined based on the obtained seismic data. This sedimentary facies data can conform to geological sedimentary patterns, and can be obtained through analysis of different seismic reflection characteristics. Furthermore, it can be combined with the lithological assemblage characteristics of drilled wells to characterize sedimentary patterns and corresponding sedimentary facies zones. Porosity in the target Paleogene region can also be determined based on the obtained seismic data. Optionally, determining the porosity based on the seismic data includes obtaining the porosity through porosity inversion. Amplitude spectral gradient in the target Paleogene region can also be determined based on the obtained seismic data. Optionally, determining the amplitude spectral gradient based on the seismic data includes determining the amplitude spectral gradient using spectral analysis and spectral decomposition techniques. Velocity dispersion data in the target Paleogene region can also be determined based on the obtained seismic data. Optionally, determining the velocity dispersion data based on the seismic data includes determining the velocity dispersion data using pre-stack seismic dispersion analysis techniques. The obtained sedimentary facies data, porosity, amplitude spectrum gradient, and velocity dispersion data can be used together as input variables for the random forest model used in prediction.

[0048] The method establishes a quantitative correspondence between sedimentary facies data and permeability to ensure that the predicted reservoir permeability better aligns with sedimentary patterns. Optionally, the method further includes: establishing a basic correspondence between permeability and different sedimentary facies zones based on well logging data; determining the spatial distribution of different sedimentary facies in the target Paleogene region based on seismic data; and calibrating the seismic facies using well logging data based on the spatial distribution and the basic correspondence to obtain the quantitative correspondence. Specifically, firstly, by analyzing well logging data from drilled wells, a basic correspondence between permeability and reservoirs in different sedimentary facies zones is established. Then, based on seismic facies analysis using seismic data, the spatial distribution of different sedimentary facies in the target Paleogene region can be characterized. Finally, by calibrating the seismic facies using well logging data, sedimentary facies data conforming to geological sedimentary patterns and the final quantitative correspondence between sedimentary facies and permeability in the target Paleogene region can be obtained. Specifically, this can be the permeability range corresponding to each sedimentary facies zone.

[0049] S13. Based on the well logging data, determine the sample permeability of the drilled wells in the target Paleogene region as the output variable.

[0050] Specifically, the sample permeability of the drilled wells in the target Paleogene area can be extracted based on the obtained logging data. Optionally, determining the sample permeability of the drilled wells in the target Paleogene area from the logging data as the output variable includes: resampling the target data in the logging data that reflects the reservoir permeability at the seismic sampling rate to obtain the sample permeability. The obtained sample permeability can then be used as the output variable backup for the random forest model used for prediction.

[0051] S14. Substitute the input variable and the output variable into the preset random forest model as the original sample set to predict the reservoir permeability of the target Paleogene area.

[0052] Specifically, after determining the input variable and the output variable, the input variable and the output variable can be substituted into the preset random forest model as the original sample set. The random forest method can be used to fit the non-linear relationship between the input variable and the output variable, so as to realize the non-linear prediction of the target Paleogene area and obtain the prediction result of the reservoir permeability through random forest regression. Specifically, half of the original sample set can be randomly selected as the training sample of the random forest, and the remaining can be used as the test sample.

[0053] Among them, optionally, substituting the input variable and the output variable into the preset random forest model to predict the reservoir permeability of the target Paleogene area includes: resampling the original sample set using the Bootstrap sampling method to randomly generate multiple training sets, and generating corresponding decision trees for each training set; taking the average of the predicted values output by each decision tree to obtain the prediction result of the reservoir permeability of the target Paleogene area. Specifically, during the growth process of each decision tree, if the input variable consists of M different types of data, m (0 < m < M) features are randomly selected from them as the subset for splitting at the current node, and the best splitting method is selected from this subset for splitting. Each decision tree will grow completely without pruning, and the value of m remains unchanged during the growth process of the entire forest. For the reservoir permeability to be predicted, each decision tree will output a corresponding predicted value y i , i = 1, 2,..., n, where n is the number of training sets. Then, by taking the average of these n predicted values, the predicted value of the regression forest, that is, the prediction result of the reservoir permeability of the target Paleogene area, can be obtained.

[0054] For example, predicting reservoir permeability in a target Paleogene region reveals significant lateral variations in seismic reflection characteristics and marked seismic facies transitions in the Paleogene strata, as shown by seismic profiles of the region. For instance, near steep slopes exhibit weak, chaotic reflections; near the source, high-frequency, medium-to-strong amplitude, discontinuous progradational reflections are observed; and in depressions far from the source, medium-frequency, medium-to-weak amplitude, continuous reflections are seen. After prediction, a permeability planar map of the Wen-3 section reservoir is obtained and compared with a sedimentary facies planar map of the same section. The prediction results indicate that reservoir permeability is good in the southwestern corner of the target Paleogene region, corresponding to the braided river delta plain and the braided river delta front sedimentary facies zone. The permeability of reservoirs along the northeast-trending control faults to the east is generally low, indicating that this area is mainly located at the root of the fan delta, with dense reservoirs, poor physical properties, and low permeability. The permeability inversion results are very low in the central part of the depression because this area is far from the source, situated in a semi-deep lacustrine to deep lacustrine facies, where reservoir development is poor. The predicted results correspond well with the distribution of sedimentary facies, and the results are more consistent with the geological sedimentary laws and are more reliable.

[0055] The technical solution provided in this invention first acquires seismic and well logging data for the target Paleogene region. Then, based on the seismic data, it determines sedimentary facies data, porosity, amplitude spectral gradient, and velocity dispersion data for the target Paleogene region as input variables. Next, based on the well logging data, it determines the permeability of drilled well samples in the target Paleogene region as the output variable. The obtained input and output variables are then substituted into a pre-defined random forest model as the original sample set to predict the reservoir permeability of the target Paleogene region. By introducing sedimentary facies into the sample data of the random forest model, a phase control effect can be achieved in the random forest regression sample training and decision-making process, making the prediction results more reliable and more consistent with actual geological sedimentary patterns. This increases the accuracy of permeability prediction and can better guide exploration, development, and production.

[0056] Example 2

[0057] Figure 2 This is a schematic diagram of the structure of the Paleogene reservoir permeability prediction device provided in Embodiment 2 of the present invention. This device can be implemented in hardware and / or software, and is generally integrated into a computer device to execute the Paleogene reservoir permeability prediction method provided in any embodiment of the present invention. Figure 2 As shown, the device includes:

[0058] Data acquisition module 21 is used to acquire seismic data and well logging data of the target Paleogene region;

[0059] The input variable determination module 22 is used to determine sedimentary facies data, porosity, amplitude spectrum gradient, and velocity dispersion data in the target Paleogene region as input variables based on the seismic data; wherein, there is a quantitative correspondence between the sedimentary facies data and permeability;

[0060] The output variable determination module 23 is used to determine the sample permeability of drilled wells in the target Paleogene region as an output variable based on the logging data.

[0061] The permeability prediction module 24 is used to substitute the input variables and the output variables as the original sample set into a preset random forest model to predict the reservoir permeability of the target Paleogene region.

[0062] The technical solution provided in this invention first acquires seismic and well logging data for the target Paleogene region. Then, based on the seismic data, it determines sedimentary facies data, porosity, amplitude spectral gradient, and velocity dispersion data for the target Paleogene region as input variables. Next, based on the well logging data, it determines the permeability of drilled well samples in the target Paleogene region as the output variable. The obtained input and output variables are then substituted into a pre-defined random forest model as the original sample set to predict the reservoir permeability of the target Paleogene region. By introducing sedimentary facies into the sample data of the random forest model, a phase control effect can be achieved in the random forest regression sample training and decision-making process, making the prediction results more reliable and more consistent with actual geological sedimentary patterns. This increases the accuracy of permeability prediction and can better guide exploration, development, and production.

[0063] Based on the above technical solution, optionally, the device for predicting the permeability of the Paleogene reservoir also includes:

[0064] The basic correspondence division module is used to divide the basic correspondence between permeability and different sedimentary facies zones based on the well logging data;

[0065] The spatial distribution determination module is used to determine the spatial distribution of different sedimentary facies in the target Paleogene region based on the seismic data.

[0066] The quantitative correspondence determination module is used to calibrate the relative seismic phase using well logging based on the spatial distribution and the basic correspondence to obtain the quantitative correspondence.

[0067] Based on the above technical solution, optionally, the penetration rate prediction module 24 includes:

[0068] The training set generation unit is used to resample the original sample set using the Bootstrap sampling method to randomly generate multiple training sets, and each training set generates a corresponding decision tree.

[0069] The prediction result determination unit is used to average the predicted values ​​output by each decision tree to obtain the predicted reservoir permeability of the target Paleogene region.

[0070] Based on the above technical solution, optionally, the output variable determination module 23 is specifically used for:

[0071] The target data used to reflect reservoir permeability in the well logging data are resampled according to the seismic sampling rate to obtain the sample permeability.

[0072] Based on the above technical solution, optionally, the input variable determination module 22 is specifically used for:

[0073] The porosity is obtained by porosity inversion.

[0074] Based on the above technical solution, optionally, the input variable determination module 22 is specifically used for:

[0075] The amplitude spectral gradient was determined using spectral analysis and spectral decomposition techniques.

[0076] Based on the above technical solution, optionally, the input variable determination module 22 is specifically used for:

[0077] The velocity dispersion data were determined using pre-stack seismic dispersion analysis.

[0078] The Paleogene reservoir permeability prediction device provided in this embodiment of the invention can execute the Paleogene reservoir permeability prediction method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0079] It is worth noting that in the embodiments of the Paleogene reservoir permeability prediction device described above, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0080] Example 3

[0081] Figure 3 This is a schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention, showing a block diagram of an exemplary computer device suitable for implementing the embodiments of the present invention. Figure 3 The computer device shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the present invention. Figure 3 As shown, the computer device includes a processor 31, a memory 32, an input device 33, and an output device 34; the number of processors 31 in the computer device can be one or more. Figure 3 Taking a processor 31 as an example, the processor 31, memory 32, input device 33, and output device 34 in a computer device can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0082] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the Paleogene reservoir permeability prediction method in this embodiment of the invention (e.g., the data acquisition module 21, input variable determination module 22, output variable determination module 23, and permeability prediction module 24 in the Paleogene reservoir permeability prediction device). The processor 31 executes various functional applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory 32, thereby realizing the aforementioned Paleogene reservoir permeability prediction method.

[0083] The memory 32 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 32 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory, or other non-volatile solid-state storage device. In some instances, the memory 32 may further include memory remotely located relative to the processor 31, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0084] Input device 33 can be used to acquire relevant data on the target Paleogene region, and to generate key signal inputs related to user settings and function control of the computer equipment. Output device 34 may include a display screen, which can be used to display prediction results to the user, etc.

[0085] Example 4

[0086] Embodiment 4 of the present invention also provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform a method for predicting the permeability of Paleogene reservoirs, the method comprising:

[0087] Acquire seismic and well logging data for the target Paleogene region;

[0088] Based on the seismic data, sedimentary facies data, porosity, amplitude spectral gradient, and velocity dispersion data in the target Paleogene region are determined as input variables; wherein, there is a quantitative correspondence between the sedimentary facies data and permeability;

[0089] Based on the well logging data, the permeability of the drilled samples in the target Paleogene region is determined as the output variable;

[0090] The input and output variables are used as the original sample set and substituted into a preset random forest model to predict the reservoir permeability of the target Paleogene region.

[0091] Storage media can be any type of memory device or storage device. The term "storage media" is intended to include: mounting media, such as CD-ROMs, floppy disks, or magnetic tape devices; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (e.g., hard disks or optical storage); registers or other similar types of memory elements. Storage media may also include other types of memory or combinations thereof. Furthermore, storage media may reside in a computer system in which the program is executed, or may reside in a different second computer system connected to the computer system via a network (such as the Internet). The second computer system can provide program instructions to the computer for execution. The term "storage media" can include two or more storage media that may reside in different locations (e.g., in different computer systems connected via a network). Storage media may store program instructions (e.g., specifically implemented as a computer program) that can be executed by one or more processors.

[0092] Of course, the computer-executable instructions provided in the embodiments of the present invention are not limited to the method operations described above, but can also perform related operations in the Paleogene reservoir permeability prediction method provided in any embodiment of the present invention.

[0093] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0094] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0095] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0096] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for predicting the permeability of Paleogene reservoirs, characterized in that, include: Acquire seismic and well logging data for the target Paleogene region; Based on the seismic data, sedimentary facies data, porosity, amplitude spectral gradient, and velocity dispersion data in the target Paleogene region are determined as input variables; wherein, there is a quantitative correspondence between the sedimentary facies data and permeability; Based on the well logging data, the permeability of the drilled samples in the target Paleogene region is determined as the output variable; The input variables and the output variables are used as the original sample set and substituted into a preset random forest model to predict the reservoir permeability of the target Paleogene region. The method further includes: Based on the well logging data, a basic correspondence between permeability and different sedimentary facies zones was obtained; The spatial distribution of different sedimentary facies in the target Paleogene region was determined based on the earthquake data. Based on the spatial distribution and the basic correspondence, well logging is used to calibrate the seismic phases to obtain the quantitative correspondence.

2. The method for predicting Paleogene reservoir permeability according to claim 1, characterized in that, The step of substituting the input variables and the output variables as the original sample set into a preset random forest model to predict the reservoir permeability of the target Paleogene region includes: The original sample set is resampled using the Bootstrap sampling method to randomly generate multiple training sets, and a corresponding decision tree is generated for each training set. The predicted values ​​output by each decision tree are averaged to obtain the predicted reservoir permeability of the target Paleogene region.

3. The method for predicting Paleogene reservoir permeability according to claim 1, characterized in that, The step of determining the sample permeability of drilled wells in the target Paleogene region as an output variable based on the well logging data includes: The target data used to reflect reservoir permeability in the well logging data are resampled according to the seismic sampling rate to obtain the sample permeability.

4. The method for predicting Paleogene reservoir permeability according to claim 1, characterized in that, Determining the porosity in the target Paleogene region based on the seismic data includes: The porosity is obtained by porosity inversion.

5. The method for predicting Paleogene reservoir permeability according to claim 1, characterized in that, Determining the amplitude spectral gradient in the target Paleogene region based on the seismic data includes: The amplitude spectral gradient was determined using spectral analysis and spectral decomposition techniques.

6. The method for predicting Paleogene reservoir permeability according to claim 1, characterized in that, The step of determining the velocity dispersion data of the target Paleogene region based on the seismic data includes: The velocity dispersion data were determined using pre-stack seismic dispersion analysis.

7. A device for predicting the permeability of Paleogene reservoirs, characterized in that, include: The data acquisition module is used to acquire seismic and well logging data for the target Paleogene region; The input variable determination module is used to determine sedimentary facies data, porosity, amplitude spectral gradient, and velocity dispersion data in the target Paleogene region as input variables based on the seismic data; wherein, there is a quantitative correspondence between the sedimentary facies data and permeability; The output variable determination module is used to determine the sample permeability of drilled wells in the target Paleogene region as an output variable based on the well logging data. The permeability prediction module is used to substitute the input variables and the output variables as the original sample set into a preset random forest model in order to predict the reservoir permeability of the target Paleogene region. The device further includes: The basic correspondence division module is used to divide the basic correspondence between permeability and different sedimentary facies zones based on the well logging data; The spatial distribution determination module is used to determine the spatial distribution of different sedimentary facies in the target Paleogene region based on the seismic data. The quantitative correspondence determination module is used to calibrate the relative seismic phase using well logging based on the spatial distribution and the basic correspondence to obtain the quantitative correspondence.

8. A computer device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for predicting Paleogene reservoir permeability as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the method for predicting Paleogene reservoir permeability as described in any one of claims 1-6.

Images