A method, device, equipment and medium for predicting reservoir oil and gas distribution

Abstract

This invention relates to the field of geophysical exploration and proposes a method, apparatus, equipment, and medium for predicting reservoir oil and gas distribution. The method includes: acquiring time-frequency electromagnetic data and seismic data of the study area; extracting time-frequency electromagnetic attribute data and seismic attribute data of the reservoir at a predetermined depth range from the time-frequency electromagnetic data and seismic data, and performing normalization processing; performing complementary enhancement processing by pairwise multiplication of the normalized time-frequency electromagnetic attribute data and the normalized seismic attribute data to obtain data corresponding to several joint attributes; training a deep learning network based on preset judgment conditions and the data corresponding to the several joint attributes to obtain an oil and gas distribution prediction model; and predicting the oil and gas distribution of the reservoir based on the oil and gas distribution prediction model. The scheme disclosed in this invention avoids errors or multiple solutions in the process of reservoir oil and gas distribution identification.

Description

Technical Field

[0001] This invention relates to the field of geophysical exploration, and in particular to a method, apparatus, equipment and medium for predicting reservoir oil and gas distribution. Background Technology

[0002] Electromagnetic exploration is a geophysical exploration method that generally uses changes in electromagnetic fields observed on the ground to understand changes in the resistivity of subsurface media. Surface electromagnetic methods are extensively studied and applied in oil and gas exploration, with the Time-Frequency Electromagnetic Method (TFEM) being one of the most widely used. TFEM combines time-domain and frequency-domain electromagnetic methods to detect favorable local structures and identify their hydrocarbon potential. It can evaluate the hydrocarbon potential of structures confirmed by seismic activity and, in conjunction with seismic data, identify oil and water resources and delineate oil and gas field boundaries. However, in practical applications, TFEM suffers from multiple solutions.

[0003] Seismic activity is a primary method for oil and gas exploration, providing highly accurate imaging of underground structures, but it is difficult to determine whether oil and gas are present. Seismic properties can predict rock properties, especially whether a trap contains oil. When a trap contains both oil and water, the differences in velocity and wave impedance are small, resulting in weak reflections in seismic properties; even combining multiple seismic properties can easily lead to errors.

[0004] Given that existing technologies for identifying oil and gas distribution via seismic methods are difficult and prone to errors, and that time-frequency electromagnetic methods for identifying oil and gas distribution are prone to multiple solutions, there is an urgent need to improve the prediction methods for reservoir oil and gas distribution in order to avoid errors or multiple solutions in the process of identifying reservoir oil and gas distribution. Summary of the Invention

[0005] In view of this, the present invention proposes a method, apparatus, equipment and medium for predicting reservoir oil and gas distribution, which at least solves the problems of difficulty and error in identifying oil and gas distribution by seismic methods and the problem of multiple solutions in time-frequency electromagnetic methods for identifying oil and gas distribution.

[0006] Based on the above objectives, one aspect of the present invention provides a method for predicting reservoir oil and gas distribution, comprising: acquiring time-frequency electromagnetic data and seismic data of the study area;

[0007] Extract the time-frequency electromagnetic data and the seismic data of the reservoir at a preset depth and perform normalization processing.

[0008] The normalized time-frequency electromagnetic attribute data and the normalized seismic attribute data are multiplied in pairs for complementary enhancement processing to obtain data corresponding to several joint attributes respectively.

[0009] A deep learning network is trained based on preset judgment conditions and the data corresponding to the aforementioned joint attributes to obtain an oil and gas distribution prediction model.

[0010] The oil and gas distribution of the reservoir is predicted based on the oil and gas distribution prediction model.

[0011] In some embodiments, the step of extracting the time-frequency electromagnetic attribute data and seismic attribute data of the reservoir at a preset depth and performing normalization processing includes:

[0012] Extract the resistivity and polarizability data of the reservoir at a preset depth from the time-frequency electromagnetic data;

[0013] Extract the velocity data, shear wave impedance data, and amplitude bright spot data of the reservoir at the preset depth from the seismic data;

[0014] The extracted resistivity data, polarizability data, velocity data, transverse wave impedance data, and amplitude bright spot data of the reservoir at the preset depth are normalized respectively.

[0015] In some embodiments, the step of performing complementary enhancement processing by multiplying the normalized time-frequency electromagnetic attribute data and the normalized seismic attribute data pairwise to obtain data corresponding to several joint attributes includes:

[0016] The resistivity data and polarizability data are respectively multiplied with the velocity data, the transverse wave impedance data and the amplitude bright spot data for complementary enhancement processing to obtain data corresponding to several joint attributes. The several joint attributes include resistivity-velocity joint attribute, resistivity-transverse wave impedance joint attribute, resistivity-amplitude bright spot joint attribute, polarizability-velocity joint attribute, polarizability-transverse wave impedance joint attribute and polarizability-amplitude bright spot joint attribute.

[0017] In some embodiments, the preset judgment conditions include:

[0018] Are the resistivity-velocity joint attribute, the resistivity-transverse wave impedance joint attribute, the resistivity-amplitude bright spot joint attribute, the polarizability-velocity joint attribute, the polarizability-transverse wave impedance joint attribute, and the polarizability-amplitude bright spot joint attribute respectively high resistivity-low velocity, high resistivity-strong transverse wave impedance, high resistivity-amplitude bright spot, high polarizability-low velocity, high polarizability-strong transverse wave impedance, and high polarizability-amplitude bright spot?

[0019] In some embodiments, the step of training a deep learning network based on preset judgment conditions and the data corresponding to the plurality of joint attributes to obtain an oil and gas distribution prediction model includes:

[0020] Determine whether the data corresponding to the aforementioned joint attributes satisfy the following conditions: high resistivity-low velocity, high resistivity-strong transverse wave impedance, high resistivity-amplitude bright spot, high polarizability-low velocity, high polarizability-strong transverse wave impedance, and high polarizability-amplitude bright spot.

[0021] If all conditions are met, the reservoir at the preset depth is confirmed to be an oil-bearing reservoir.

[0022] If a preset judgment condition is not met, the reservoir at the preset depth is confirmed to be an oil-free reservoir.

[0023] Based on the judgment results, a deep learning network is trained to obtain an oil and gas distribution prediction model.

[0024] In some embodiments, the step of extracting the resistivity and polarizability data of the reservoir at a preset depth range from the time-frequency electromagnetic data includes:

[0025] In response to the fact that the time-frequency electromagnetic data is profile survey data, the resistivity data and polarizability data of the reservoir in the preset depth section of the profile are extracted after two-dimensional constrained inversion of the time-frequency electromagnetic data.

[0026] In some embodiments, the step of extracting the resistivity and polarizability data of the reservoir at a preset depth range from the time-frequency electromagnetic data further includes:

[0027] In response to the fact that the time-frequency electromagnetic data is area-based time-frequency electromagnetic exploration data controlled by multiple two-dimensional survey lines, two-dimensional constrained inversion and interpolation processing are performed on the time-frequency electromagnetic data to obtain gridded three-dimensional data;

[0028] Based on the three-dimensional data of the grid, the resistivity and polarizability three-dimensional data of the reservoir in the preset depth section of the profile are extracted.

[0029] In another aspect of the present invention, a device for predicting reservoir oil and gas distribution is provided, comprising: a first module for acquiring time-frequency electromagnetic data and seismic data of the study area;

[0030] The second module is used to extract the time-frequency electromagnetic data and the seismic data of the reservoir at a preset depth and perform normalization processing.

[0031] The third module is used to perform complementary enhancement processing by multiplying the normalized time-frequency electromagnetic attribute data and the normalized seismic attribute data in pairs to obtain data corresponding to several joint attributes respectively.

[0032] The fourth module is used to train a deep learning network based on preset judgment conditions and the data corresponding to the several joint attributes respectively, so as to obtain an oil and gas distribution prediction model.

[0033] The fifth module is used to predict the oil and gas distribution of the reservoir based on the oil and gas distribution prediction model.

[0034] In another aspect of the present invention, an electronic device is provided, including at least one processor; and a memory storing computer instructions executable on the processor, which, when executed by the processor, implement the steps of the above-described method.

[0035] In another aspect of the present invention, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the method steps described above.

[0036] The aforementioned method for predicting reservoir hydrocarbon distribution extracts time-frequency electromagnetic attribute data and seismic attribute data of the reservoir at a preset depth from time-frequency electromagnetic data and seismic data. After normalization, these data are multiplied pairwise to obtain several joint attribute data. A deep learning network is then trained based on preset judgment conditions. The trained hydrocarbon distribution prediction model is used to predict the hydrocarbon distribution of the reservoir. This method avoids errors or multiple solutions in the identification of reservoir hydrocarbon distribution. It can effectively extract weak anomalies in the resistivity profile during electromagnetic inversion, improving the ability of electromagnetic exploration to identify low-amplitude structures and thin, high-resistivity reservoirs such as sand bodies and igneous rocks.

[0037] In addition, the present invention also provides a reservoir oil and gas distribution prediction device, an electronic device, and a computer-readable storage medium, which can achieve the above-mentioned technical effects, and will not be described in detail here. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these drawings without creative effort.

[0039] Figure 1 The flowchart shown is a method for predicting reservoir oil and gas distribution according to an embodiment of the present invention;

[0040] Figure 2 The diagram shown is a schematic representation of a method for predicting reservoir oil and gas distribution according to an embodiment of the present invention.

[0041] Figure 3 The flowchart shown is a process for predicting reservoir oil and gas distribution based on joint attributes according to an embodiment of the present invention.

[0042] Figure 4 A schematic diagram of a reservoir oil and gas distribution prediction device provided in an embodiment of the present invention is shown;

[0043] Figure 5 The diagram shown is a schematic representation of an electronic device according to an embodiment of the present invention;

[0044] Figure 6 The diagram shown is a schematic representation of a computer-readable storage medium provided according to an embodiment of the present invention. Detailed Implementation

[0045] The following describes embodiments of the present invention. However, it should be understood that the disclosed embodiments are merely examples, and other embodiments may take various alternative forms.

[0046] Furthermore, it should be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or apparatus that comprises a list of elements may include not only those elements but also elements not expressly listed or inherent to such process, method, article, or apparatus.

[0047] One or more embodiments of this application will now be described with reference to the accompanying drawings.

[0048] Based on the above objectives, the first aspect of the present invention provides an embodiment of a method for predicting reservoir oil and gas distribution. Figure 1 The flowchart shown is a method for predicting reservoir oil and gas distribution according to an embodiment of the present invention. Figure 1 As shown, a method for predicting reservoir oil and gas distribution includes:

[0049] Step 101: Obtain time-frequency electromagnetic data and seismic data for the study area;

[0050] Step 102: Extract the time-frequency electromagnetic attribute data and seismic attribute data of the reservoir at a preset depth, respectively, and perform normalization processing.

[0051] Step 103: The normalized time-frequency electromagnetic attribute data and the normalized seismic attribute data are multiplied in pairs for complementary enhancement processing to obtain data corresponding to several joint attributes respectively.

[0052] Step 104: Based on the preset judgment conditions and the data corresponding to the several joint attributes, a deep learning network is trained to obtain an oil and gas distribution prediction model.

[0053] Step 105: Predict the oil and gas distribution of the reservoir based on the oil and gas distribution prediction model.

[0054] The aforementioned method for predicting reservoir hydrocarbon distribution extracts time-frequency electromagnetic attribute data and seismic attribute data of reservoirs at a preset depth from time-frequency electromagnetic data and seismic data. After normalization, these data are multiplied pairwise to obtain several joint attribute data. Based on preset judgment conditions, a deep learning network is trained, and the trained hydrocarbon distribution prediction model is used to predict the hydrocarbon distribution of reservoirs in the study area. This method avoids errors or multiple solutions in the identification of reservoir hydrocarbon distribution, effectively extracts weak anomalies in the resistivity profile during electromagnetic inversion, and improves the ability of electromagnetic exploration to identify low-amplitude structures and thin, high-resistivity reservoirs such as sand bodies and igneous rocks.

[0055] According to several embodiments of the present invention, the steps of extracting time-frequency electromagnetic attribute data and seismic attribute data of reservoirs at a preset depth and performing normalization processing include:

[0056] Extract resistivity and polarizability data from the reservoir at a preset depth using time-frequency electromagnetic data;

[0057] Extract velocity data, shear wave impedance data, and amplitude bright spot data of reservoirs within a preset depth range from seismic data;

[0058] The extracted resistivity data, polarizability data, velocity data, shear wave impedance data, and amplitude bright spot data of the reservoir at the preset depth were normalized respectively.

[0059] According to several embodiments of the present invention, the step of performing complementary enhancement processing by pairwise multiplication of normalized time-frequency electromagnetic attribute data and normalized seismic attribute data to obtain data corresponding to several joint attributes includes:

[0060] The resistivity and polarizability data are complementarily enhanced by multiplying them pairwise with the velocity data, transverse wave impedance data, and amplitude bright spot data to obtain data corresponding to several joint attributes. These joint attributes include resistivity-velocity joint attributes, resistivity-transverse wave impedance joint attributes, resistivity-amplitude bright spot joint attributes, polarizability-velocity joint attributes, polarizability-transverse wave impedance joint attributes, and polarizability-amplitude bright spot joint attributes.

[0061] According to several embodiments of the present invention, the preset judgment conditions include:

[0062] Are the resistivity-velocity joint property, resistivity-transverse wave impedance joint property, resistivity-amplitude bright spot joint property, polarizability-velocity joint property, polarizability-transverse wave impedance joint property, and polarizability-amplitude bright spot joint property respectively high resistivity-low velocity, high resistivity-strong transverse wave impedance, high resistivity-amplitude bright spot, high polarizability-low velocity, high polarizability-strong transverse wave impedance, and high polarizability-amplitude bright spot?

[0063] According to several embodiments of the present invention, the steps of training a deep learning network based on preset judgment conditions and data corresponding to several joint attributes to obtain an oil and gas distribution prediction model include:

[0064] Determine whether the data corresponding to several joint attributes satisfy the following conditions: high resistivity-low velocity, high resistivity-strong transverse wave impedance, high resistivity-amplitude bright spot, high polarizability-low velocity, high polarizability-strong transverse wave impedance, and high polarizability-amplitude bright spot.

[0065] If all conditions are met, the reservoir at the preset depth is confirmed to be an oil-bearing reservoir.

[0066] If a preset judgment condition is not met, the reservoir at the preset depth is confirmed to be an oil-free reservoir.

[0067] Based on the judgment results, a deep learning network is trained to obtain an oil and gas distribution prediction model.

[0068] According to several embodiments of the present invention, the steps of extracting resistivity and polarizability data of a reservoir at a predetermined depth from time-frequency electromagnetic data include:

[0069] Since the time-frequency electromagnetic data is profile survey data, the resistivity and polarizability data of the reservoir in the preset depth range are extracted after two-dimensional constrained inversion of the time-frequency electromagnetic data.

[0070] According to several embodiments of the present invention, the step of extracting resistivity and polarizability data of the reservoir at a preset depth range from time-frequency electromagnetic data further includes:

[0071] Since the time-frequency electromagnetic data is area-based time-frequency electromagnetic exploration data controlled by multiple two-dimensional survey lines, two-dimensional constrained inversion and interpolation processing are performed on the time-frequency electromagnetic data to obtain gridded three-dimensional data.

[0072] Based on the three-dimensional data of the grid, the resistivity and polarizability of the reservoir at a preset depth are extracted from the profile.

[0073] To facilitate understanding of the present invention, the following describes in detail a method for predicting reservoir oil and gas distribution based on a specific embodiment.

[0074] Time-frequency electromagnetic (TEM) data and seismic data of the study area were acquired, and their corresponding TEM and seismic attribute data were extracted. Specifically, two-dimensional constrained inversion processing was performed on the TEM data to obtain reservoir resistivity and polarizability. If the acquired TEM data of the study area was profile survey data, two-dimensional constrained inversion processing was performed to extract two-dimensional resistivity and polarizability data of the reservoir at a specific depth within the profile. If the acquired TEM data of the study area was area-based TEM exploration data controlled by multiple two-dimensional survey lines, interpolation processing was performed on the TEM data based on the two-dimensional profile constrained inversion data to obtain gridded three-dimensional data. Based on the gridded three-dimensional data, three-dimensional data volumes of resistivity and polarizability of the reservoir at the same depth within the profile were extracted. The two-dimensional and three-dimensional resistivity and polarizability were normalized to obtain normalized resistivity (R) data and normalized polarizability (P) data of the reservoir at that specific depth.

[0075] Similarly, seismic attributes of the reservoir at the same depth are extracted from the acquired seismic data, including reservoir velocity data, reservoir shear wave impedance data, and amplitude bright spot data. The extracted reservoir velocity data, reservoir shear wave impedance data, and amplitude bright spot data are normalized to obtain normalized reservoir velocity (V) data, normalized reservoir shear wave impedance (Z) data, and normalized amplitude bright spot (H) data.

[0076] Regarding the aforementioned seismic and time-frequency electromagnetic properties, there are certain differences in their sensitivity to oil-bearing reservoirs. Specifically, the resistivity of reservoir traps containing oil and gas differs from those without, with the resistivity of oil-bearing traps being higher than that of water-bearing traps; the polarizability of oil-bearing traps differs from that of water-bearing traps; the velocity of oil-bearing traps differs from that of water-bearing traps; the shear wave impedance of oil-bearing traps differs from that of water-bearing traps, with the shear wave impedance of oil-bearing traps being higher than that of water-bearing traps; and the amplitude bright spots of oil-bearing traps differ from those without, with oil-bearing traps exhibiting amplitude bright spots (strong amplitude).

[0077] Based on the differences in sensitivity between seismic and time-frequency electromagnetic attributes to oil-bearing reservoirs, normalized time-frequency electromagnetic data and normalized seismic data are subjected to complementary enhancement processing through pairwise multiplication to obtain joint attribute data. Specifically, the obtained joint attributes include: resistivity-velocity joint attribute, resistivity-transverse wave impedance joint attribute, resistivity-amplitude bright spot joint attribute, polarizability-velocity joint attribute, polarizability-transverse wave impedance joint attribute, and polarizability-amplitude bright spot joint attribute. Using the data of these six joint attributes as the training sample dataset for a deep learning network, deep learning is used to train the network on these six joint attributes, resulting in an oil and gas distribution prediction model for reservoir identification. This model is then used to predict the oil and gas distribution in the study area.

[0078] This method for predicting reservoir oil and gas distribution can avoid errors or multiple solutions in the process of identifying reservoir oil and gas distribution. It can effectively extract weak anomalies in the resistivity profile during electromagnetic inversion and improve the ability of electromagnetic exploration to identify low-amplitude structures and thin-layered high-resistivity reservoirs such as sand bodies and igneous rocks.

[0079] To facilitate understanding of the present invention, the following describes in further detail a method for predicting reservoir oil and gas distribution based on another specific embodiment of the present invention.

[0080] Figure 2 The diagram shown is a schematic representation of a method for predicting reservoir oil and gas distribution according to an embodiment of the present invention. Figure 2 As shown, a method for predicting reservoir oil and gas distribution includes:

[0081] (1) Obtain time-frequency electromagnetic data of the study area and invert the time-frequency electromagnetic data to obtain the distribution of reservoir resistivity and polarizability data. If it is a two-dimensional survey line, it is profile data; if it is a grid survey network exploration, it is three-dimensional data.

[0082] (2) Normalize the resistivity and polarizability of the two-dimensional and three-dimensional reservoirs to obtain normalized resistivity (R) data and normalized polarizability (P) data of the reservoir at a certain depth.

[0083] (3) Obtain seismic data of the study area and extract relevant attributes of the seismic data, including reservoir velocity data, reservoir shear wave impedance data, amplitude bright spot data, etc.

[0084] (4) The extracted reservoir velocity data, reservoir shear wave impedance data and amplitude bright spot data are normalized to obtain normalized reservoir velocity (V) data, normalized reservoir shear wave impedance (Z) data and normalized amplitude bright spot (H) data.

[0085] (5) Figure 3 A flowchart illustrating the prediction of reservoir oil and gas distribution based on joint attributes according to an embodiment of the present invention is shown. Figure 2 Based on the combination Figure 3 The normalized resistivity (R) and polarizability (P) data are multiplied pairwise by the normalized reservoir velocity (V), normalized reservoir shear wave impedance (Z), and normalized amplitude brightness (H) data, respectively. After complementary enhancement processing, data corresponding to several joint attributes are obtained. Specifically, these include resistivity-velocity (RV), resistivity-shear wave impedance (RZ), resistivity-brightness (RH), polarizability-velocity (PV), polarizability-shear wave impedance (PZ), and polarizability-brightness (PH), and the values ​​corresponding to RV, RZ, RH, PV, PZ, and PH are calculated.

[0086] (6) The values ​​corresponding to RV, RZ, RH, PV, PZ and PH are used as the training sample dataset required by the deep learning network. The deep learning network is trained using the training dataset to obtain the oil and gas distribution prediction model for oil and gas reservoir identification.

[0087] (7) The oil and gas distribution in the study area is predicted by the oil and gas distribution prediction model, and the prediction results are output.

[0088] A second aspect of the present invention provides a device for predicting reservoir oil and gas distribution. Figure 4 A schematic diagram of a reservoir oil and gas distribution prediction device provided in an embodiment of the present invention is shown, as follows: Figure 4 As shown, the system includes: a first module 101, used to acquire time-frequency electromagnetic data and seismic data of the study area; a second module 102, used to extract the time-frequency electromagnetic attribute data and seismic attribute data of the reservoir at a preset depth and perform normalization processing; a third module 103, used to perform complementary enhancement processing by multiplying the normalized time-frequency electromagnetic attribute data and the normalized seismic attribute data pairwise to obtain data corresponding to several joint attributes; a fourth module 104, used to train a deep learning network based on preset judgment conditions and the data corresponding to the several joint attributes to obtain an oil and gas distribution prediction model; and a fifth module 105, used to predict the oil and gas distribution of the reservoir based on the oil and gas distribution prediction model.

[0089] This embodiment discloses a reservoir hydrocarbon distribution prediction device. It extracts time-frequency electromagnetic attribute data and seismic attribute data of reservoirs at a preset depth from time-frequency electromagnetic data and seismic data. After normalization, the data are multiplied pairwise to obtain several joint attribute data. Based on preset judgment conditions, a deep learning network is trained, and the trained hydrocarbon distribution prediction model is used to predict the hydrocarbon distribution of reservoirs in the study area. This reservoir hydrocarbon distribution prediction device can avoid errors or multiple solutions in the reservoir hydrocarbon distribution identification process. It can effectively extract weak anomalies in the resistivity profile during electromagnetic inversion, improving the ability of electromagnetic exploration to identify low-amplitude structures and thin, high-resistivity reservoirs such as sand bodies and igneous rocks.

[0090] It should be noted that the specific limitations of the reservoir oil and gas distribution prediction device can be found in the limitations of the reservoir oil and gas distribution prediction method mentioned above, and will not be repeated here. Each module in the aforementioned reservoir oil and gas distribution prediction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the electronic device, or stored in the memory of the electronic device as software, so that the processor can call and execute the corresponding operations of each module.

[0091] A third aspect of the present invention provides an electronic device, Figure 5 The diagram shown is a schematic representation of an electronic device provided in an embodiment of the present invention. For example... Figure 5 As shown, an electronic device provided by an embodiment of the present invention includes the following modules: at least one processor 021; and a memory 022, the memory 022 storing computer instructions 023 that can be executed on the processor 021, the computer instructions 023 implementing the steps of the method described above when executed by the processor 021.

[0092] The present invention also provides a computer-readable storage medium. Figure 6 The diagram shown is a structural schematic of a computer-readable storage medium provided in an embodiment of the present invention. Figure 6 As shown, computer-readable storage medium 031 stores a computer program 032 that, when executed by a processor, performs the steps of the method described above. The method performed is the same as described above.

[0093] Finally, it should be noted that those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program for setting system parameters can be stored in a computer-readable storage medium. When executed, the program can include the processes of the embodiments of the above methods. The storage medium for the program can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. The above computer program embodiments can achieve the same or similar effects as any of the corresponding foregoing method embodiments.

[0094] Furthermore, the method disclosed in the embodiments of the present invention can also be implemented as a computer program executed by a processor, which may be stored in a computer-readable storage medium. When the computer program is executed by the processor, it performs the functions defined in the method disclosed in the embodiments of the present invention.

[0095] Furthermore, the above-described method steps and system units can also be implemented using a controller and a computer-readable storage medium for storing a computer program that enables the controller to perform the functions of the above-described steps or units.

[0096] Those skilled in the art will also understand that the various exemplary logic blocks, modules, circuits, and algorithm steps described in conjunction with the disclosure herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, the functionality of various illustrative components, blocks, modules, circuits, and steps has been generally described. Whether this functionality is implemented as software or as hardware depends on the specific application and the design constraints imposed on the system as a whole. Those skilled in the art can implement the functionality in various ways for each specific application, but such implementation decisions should not be construed as departing from the scope of the embodiments disclosed herein.

[0097] In one or more exemplary designs, functionality may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functionality may be stored as one or more instructions or code on or transmitted via a computer-readable medium. Computer-readable media include computer storage media and communication media, including any medium that facilitates the transfer of a computer program from one location to another. Storage media may be any available medium accessible to a general-purpose or special-purpose computer. By way of example, and not limitation, computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disc storage devices, disk storage devices or other magnetic storage devices, or any other medium that may be used to carry or store the required program code in the form of instructions or data structures and is accessible to a general-purpose or special-purpose computer or a general-purpose or special-purpose processor. Furthermore, any connection may be appropriately referred to as computer-readable media. For example, if software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the aforementioned coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are all included in the definition of media. As used herein, disks and optical discs include compact discs (CDs), laser discs, optical discs, digital multifunction discs (DVDs), floppy disks, and Blu-ray discs, wherein disks typically reproduce data magnetically, while optical discs reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0098] The above are exemplary embodiments disclosed in this invention. However, it should be noted that various changes and modifications can be made without departing from the scope of the embodiments of this invention as defined by the claims. The functions, steps, and / or actions of the methods according to the disclosed embodiments described herein do not need to be performed in any particular order. Furthermore, although the elements disclosed in the embodiments of this invention may be described or claimed individually, they may be understood as multiple unless explicitly limited to a singular number.

[0099] It should be understood that, as used herein, the singular form “a” is intended to include the plural form as well, unless the context clearly supports an exception. It should also be understood that, as used herein, “and / or” refers to any and all possible combinations of one or more of the associated listed items.

[0100] The embodiment numbers disclosed in the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0101] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0102] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the invention (including the claims) is limited to these examples. Within the framework of the invention, technical features of the above embodiments or different embodiments can be combined, and many other variations of different aspects of the invention exist, which are not provided in the details for the sake of brevity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the invention should be included within the protection scope of the invention.

Claims

1. A method for predicting reservoir oil and gas distribution, characterized in that, include: Acquire time-frequency electromagnetic data and seismic data for the study area; The process involves extracting the time-frequency electromagnetic data and seismic data of the reservoir at a predetermined depth and then normalizing them. This includes: extracting the resistivity and polarizability data of the reservoir from the time-frequency electromagnetic data; extracting the velocity data, shear wave impedance data, and amplitude bright spot data of the reservoir from the seismic data at the predetermined depth; and normalizing the extracted resistivity data, polarizability data, velocity data, shear wave impedance data, and amplitude bright spot data of the reservoir at the predetermined depth. The normalized time-frequency electromagnetic attribute data and the normalized seismic attribute data are subjected to complementary enhancement processing by multiplying them pairwise to obtain data corresponding to several joint attributes. This includes: the resistivity data and the polarizability data are subjected to complementary enhancement processing by multiplying them pairwise with the velocity data, the shear wave impedance data and the amplitude bright spot data to obtain data corresponding to several joint attributes. The several joint attributes include resistivity-velocity joint attributes, resistivity-shear wave impedance joint attributes, resistivity-amplitude bright spot joint attributes, polarizability-velocity joint attributes, polarizability-shear wave impedance joint attributes and polarizability-amplitude bright spot joint attributes. A deep learning network is trained based on preset judgment conditions and the data corresponding to the aforementioned joint attributes to obtain an oil and gas distribution prediction model. The oil and gas distribution of the reservoir is predicted based on the oil and gas distribution prediction model.

2. The method for predicting reservoir oil and gas distribution according to claim 1, characterized in that, The preset judgment conditions include: Are the resistivity-velocity joint attribute, the resistivity-transverse wave impedance joint attribute, the resistivity-amplitude bright spot joint attribute, the polarizability-velocity joint attribute, the polarizability-transverse wave impedance joint attribute, and the polarizability-amplitude bright spot joint attribute respectively high resistivity-low velocity, high resistivity-strong transverse wave impedance, high resistivity-amplitude bright spot, high polarizability-low velocity, high polarizability-strong transverse wave impedance, and high polarizability-amplitude bright spot? 3. The method for predicting reservoir oil and gas distribution according to claim 2, characterized in that, The step of training a deep learning network based on preset judgment conditions and the data corresponding to the several joint attributes to obtain an oil and gas distribution prediction model includes: Determine whether the data corresponding to the aforementioned joint attributes satisfy the following conditions: high resistivity-low velocity, high resistivity-strong transverse wave impedance, high resistivity-amplitude bright spot, high polarizability-low velocity, high polarizability-strong transverse wave impedance, and high polarizability-amplitude bright spot. If all conditions are met, the reservoir at the preset depth is confirmed to be an oil-bearing reservoir. In response to the failure to meet a preset judgment condition, the reservoir at the preset depth is confirmed to be an oil-free reservoir. Based on the judgment results, a deep learning network is trained to obtain an oil and gas distribution prediction model.

4. The method for predicting reservoir oil and gas distribution according to claim 1, characterized in that, The step of extracting the resistivity and polarizability data of the reservoir at a preset depth range from the time-frequency electromagnetic data includes: In response to the fact that the time-frequency electromagnetic data is profile survey data, the resistivity data and polarizability data of the reservoir in the preset depth section of the profile are extracted after two-dimensional constrained inversion of the time-frequency electromagnetic data.

5. The method for predicting reservoir oil and gas distribution according to claim 4, characterized in that, The step of extracting the resistivity and polarizability data of the reservoir at a preset depth range from the time-frequency electromagnetic data further includes: In response to the fact that the time-frequency electromagnetic data is area-based time-frequency electromagnetic exploration data controlled by multiple two-dimensional survey lines, two-dimensional constrained inversion and interpolation processing are performed on the time-frequency electromagnetic data to obtain gridded three-dimensional data; Based on the three-dimensional data of the grid, the resistivity and polarizability three-dimensional data of the reservoir in the preset depth section of the profile are extracted.

6. A device for predicting reservoir oil and gas distribution, characterized in that, include: The first module is used to acquire time-frequency electromagnetic data and seismic data of the study area; The second module is used to extract the time-frequency electromagnetic data and the seismic data of the reservoir at a preset depth and perform normalization processing. The third module is used to perform complementary enhancement processing by multiplying the normalized time-frequency electromagnetic attribute data and the normalized seismic attribute data in pairs to obtain data corresponding to several joint attributes respectively. The fourth module is used to train a deep learning network based on preset judgment conditions and the data corresponding to the several joint attributes respectively, so as to obtain an oil and gas distribution prediction model. The fifth module is used to predict the oil and gas distribution of the reservoir based on the oil and gas distribution prediction model. The second module is further configured to: extract resistivity and polarizability data of the time-frequency electromagnetic data in the reservoir at a preset depth; extract velocity data, shear wave impedance data, and amplitude bright spot data of the seismic data in the reservoir at the preset depth; and normalize the extracted resistivity data, polarizability data, velocity data, shear wave impedance data, and amplitude bright spot data of the reservoir at the preset depth, respectively. The third module is further configured to: perform complementary enhancement processing by multiplying the resistivity data and the polarizability data with the velocity data, the transverse wave impedance data and the amplitude bright spot data in pairs, respectively, to obtain data corresponding to several joint attributes, wherein the several joint attributes include resistivity-velocity joint attributes, resistivity-transverse wave impedance joint attributes, resistivity-amplitude bright spot joint attributes, polarizability-velocity joint attributes, polarizability-transverse wave impedance joint attributes and polarizability-amplitude bright spot joint attributes.

7. An electronic device, characterized in that, include: At least one processor; as well as A memory storing computer instructions executable on the processor, which, when executed by the processor, implement the steps of the method according to any one of claims 1-5.

8. A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-5.

Images