Well-seismic joint reservoir prediction method, device and electronic equipment

Abstract

Embodiments of the present application disclose a well-seismic joint reservoir prediction method, device and electronic equipment. The well-seismic joint reservoir prediction method comprises: selecting seismic attributes and performing standardization processing on the selected seismic attributes; obtaining a seismic attribute variogram plan based on the standardization-processed seismic attributes; establishing a relationship between the standardization-processed seismic attributes and reservoir parameters based on the seismic attribute variogram plan; and predicting the reservoir based on the relationship. The selected seismic attributes are used to obtain a seismic attribute variogram plan, thereby establishing a relationship between the standardization-processed seismic attributes and reservoir parameters, and the prediction of the reservoir is realized based on the established relationship between the standardization-processed seismic attributes and reservoir parameters. The seismic attributes are integrated into the prediction of the reservoir parameters, thereby improving the accuracy of the prediction results.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of seismic exploration data interpretation, and more particularly relates to a well-seismic joint reservoir prediction method, device and electronic equipment. BACKGROUND

[0002] Seismic exploration data interpretation work is to use seismic data interpretation software to interpret seismic data in a man-machine interactive manner. Based on the migration seismic data body, technical personnel combine the interpretation software with the understanding and experience of the structural rules and wave group characteristics in the work area to comprehensively develop interpretation work of geological structure, oil and gas conditions, etc.

[0003] Reservoir parameter prediction is one of the basic work for finding oil and gas reserves, and plays a very important role in the development and design process of the reservoir. The purpose of reservoir characterization is to comprehensively integrate geological information such as background information of the study area, seismic data, well data and other types of data as much as possible, and as much as possible to truly depict the spatial distribution of geological variables in the selected area. Among them, the interwell prediction technology is the core part of petroleum geostatistics. At present, the main method is to predict the sandstone thickness based on well data. The existing methods include inverse distance method, ordinary Kriging method, indicator Kriging method, and reservoir characterization conditional simulation technology such as sequential Gaussian simulation and sequential indicator simulation.

[0004] With the continuous exploration and development, the well site is continuously deployed, and the data of the work area are gradually enriched. However, the existing ordinary Kriging and sequential Gaussian simulation do not fully utilize the rich data, and therefore there is a problem of inaccurate prediction results. SUMMARY

[0005] Therefore, the embodiments of the present application provide a well-seismic joint reservoir prediction method, device and electronic equipment, which at least solve the problem of inaccurate prediction results in the prior art.

[0006] In a first aspect, the embodiments of the present application provide a well-seismic joint reservoir prediction method, comprising:

[0007] selecting seismic attributes and performing standardization processing on the selected seismic attributes;

[0008] obtaining a seismic attribute variogram planar graph based on the standardization-processed seismic attributes;

[0009] establishing a relationship between the standardization-processed seismic attributes and reservoir parameters based on the seismic attribute variogram planar graph;

[0010] predicting the reservoir based on the relationship.

[0011] Optionally, the selecting seismic attributes and performing standardization processing on the selected seismic attributes comprises:

[0012] combining the acquired seismic attribute information and the well point information;

[0013] establishing a relationship between the seismic attribute information and logging data based on the seismic attribute information sensitive to sandstone thickness, the logging data being well point information along a survey line;

[0014] establishing a crossplot of the seismic attribute information and the logging data based on the relationship between the seismic attribute information and the logging data;

[0015] performing a correlation analysis on the crossplot and selecting seismic attribute information related to reservoir parameters.

[0016] Optionally, the seismic attribute is selected and standardized, including:

[0017] defining a deviation of the intersecting survey line seismic attribute at the intersection point;

[0018] obtaining a deviation of the intersecting survey line seismic attribute from the mean value of the seismic attribute at the intersection point based on the mean value of the seismic attribute at the intersection point;

[0019] standardizing the seismic attribute based on the deviation of the seismic attribute and the deviation of the mean value of the seismic attribute.

[0020] Optionally, in the seismic attribute information sensitive to sandstone thickness, the seismic attribute information sensitive to sandstone thickness at least includes average instantaneous frequency and root mean square amplitude.

[0021] Optionally, a relationship between the standardized seismic attribute and reservoir parameters is established based on the planar map of the seismic attribute variogram function, including:

[0022] searching for well points near a survey point on a survey line based on the seismic attribute, and establishing a relationship between the survey line attribute and the well data;

[0023] obtaining a local cumulative distribution function of the survey point based on the relationship between the survey line attribute and the well data.

[0024] Optionally, the reservoir is predicted based on the relationship, including:

[0025] designating a random path to be accessed by a network element;

[0026] searching for nearby points of a grid point in the network element, and solving a Kriging equation set to obtain a local cumulative distribution function of the grid point;

[0027] predicting reservoir parameters based on the local cumulative distribution function.

[0028] Optionally, the search for the nearby points of the grid point in the network unit, and solve the Kriging equation set, obtain the local cumulative distribution function of the grid point, including:

[0029] Solve the Kriging equation, obtain the weight of each measuring point to the grid point, thereby obtaining the local cumulative distribution function of the grid point.

[0030] Optionally, the reservoir parameter is predicted based on the local cumulative distribution function, including:

[0031] A value is randomly extracted from the local conditional distribution function as the simulation value of the grid point, and the obtained simulation value is added to the original well data until the grid node is simulated.

[0032] In a second aspect, the embodiment of the present application further provides a well-seismic joint reservoir prediction device, including:

[0033] The selecting module is used for selecting seismic attributes and performing standardization processing on the selected seismic attributes;

[0034] The variogram module is used for obtaining a seismic attribute variogram plane based on the standardization processed seismic attributes;

[0035] The relationship establishing module is used for establishing a relationship between the standardization processed seismic attributes and the reservoir parameters based on the seismic attribute variogram plane;

[0036] The prediction module is used for predicting the reservoir based on the relationship.

[0037] In a third aspect, the embodiment of the present application further provides an electronic device, including:

[0038] The memory stores executable instructions;

[0039] The processor runs the executable instructions in the memory to realize the well-seismic joint reservoir prediction method in any one of the first aspect.

[0040] The present application selects seismic attributes, and obtains a seismic attribute variogram plane based on the selected seismic attributes, thereby establishing a relationship between the standardization processed seismic attributes and the reservoir parameters, and realizing the prediction of the reservoir based on the established relationship between the standardization processed seismic attributes and the reservoir parameters, and integrating the seismic attributes into the prediction of the reservoir parameters, so as to improve the accuracy of the prediction results.

[0041] Other features and advantages of the present application will be described in detail in the following specific embodiment part. BRIEF DESCRIPTION OF DRAWINGS

[0042] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which like reference characters refer to like parts throughout the figures, and in which:

[0043] Figure 1 A sandstone thickness variogram anisotropy plane diagram of one embodiment of the present application is shown;

[0044] Figure 2 A flow chart of a well-to-seismic joint reservoir prediction method of one embodiment of the present application is shown;

[0045] Figure 3a A pre-normalization seismic attribute diagram of one embodiment of the present application is shown;

[0046] Figure 3b A post-normalization seismic attribute diagram of one embodiment of the present application is shown;

[0047] Figure 4a A pre-normalization cross-line intersection seismic attribute crossplot of one embodiment of the present application is shown;

[0048] Figure 4b A post-normalization cross-line intersection seismic attribute crossplot of one embodiment of the present application is shown;

[0049] Figure 5 A major-minor direction root mean square amplitude variogram value diagram of one embodiment of the present application is shown;

[0050] Figure 6 A theoretical variogram plane diagram of root mean square amplitude of one embodiment of the present application is shown;

[0051] Figure 7 A mean instantaneous frequency constrained well-to-seismic joint prediction sandstone thickness diagram of one embodiment of the present application is shown;

[0052] Figure 8 A root mean square amplitude constrained well-to-seismic joint prediction sandstone thickness diagram of one embodiment of the present application is shown;

[0053] Figure 9 A two attribute constrained well-to-seismic joint prediction sandstone thickness diagram of one embodiment of the present application is shown, the two attributes being mean instantaneous frequency and root mean square amplitude. DETAILED DESCRIPTION

[0054] Preferred embodiments of the present application will be described in greater detail below. While the preferred embodiments of the present application are described below, it is to be understood that the present application can be embodied in various forms without being limited to the embodiments set forth herein.

[0055] A well-seismic joint reservoir prediction method, comprising:

[0056] Selecting seismic attributes and performing standardization processing on the selected seismic attributes;

[0057] Obtaining a seismic attribute variogram planar map based on the standardization-processed seismic attributes;

[0058] Establishing a relationship between the standardization-processed seismic attributes and reservoir parameters based on the seismic attribute variogram planar map;

[0059] Performing reservoir prediction based on the relationship.

[0060] Optionally, the selecting seismic attributes and performing standardization processing on the selected seismic attributes comprise:

[0061] Combining the obtained seismic attribute information and well point information;

[0062] Based on the sandstone thickness-sensitive seismic attribute information, a relationship between the seismic attribute information and well logging data corresponding to the well point information is established;

[0063] Based on the relationship between the seismic attribute information and the well logging data, a crossplot of the seismic attribute information and the well logging data is established;

[0064] Performing correlation analysis on the crossplot, and selecting seismic attribute information related to reservoir parameters.

[0065] Optionally, the selecting seismic attributes and performing standardization processing on the selected seismic attributes comprise:

[0066] Defining a deviation of the intersecting line seismic attribute at the intersection point;

[0067] Based on the mean value of the seismic attribute at the intersection point, a deviation of the intersecting line seismic attribute from the mean value of the seismic attribute at the intersection point is obtained;

[0068] Performing standardization processing on the seismic attribute based on the deviation of the seismic attribute and the deviation of the mean value of the seismic attribute.

[0069] Optionally, in the sandstone thickness-sensitive seismic attribute information, the sandstone thickness-sensitive seismic attribute information at least includes: average instantaneous frequency and root mean square amplitude.

[0070] Optionally, the establishing a relationship between the standardization-processed seismic attributes and reservoir parameters based on the seismic attribute variogram planar map comprises:

[0071] Based on the seismic attribute, searching for a well point near a measuring point on a measuring line, and establishing a relationship between the measuring line attribute and the well data;

[0072] The local cumulative distribution function of the measuring point is obtained based on the relationship between the measuring line attribute and the well data.

[0073] Optionally, the reservoir reservoir is predicted based on the relationship, comprising:

[0074] Specifying a random path to be accessed by the network element;

[0075] Searching for the nearby points of the grid point in the network element, and solving the Kriging equation set to obtain the local cumulative distribution function of the grid point;

[0076] The reservoir reservoir parameter is predicted based on the local cumulative distribution function.

[0077] Optionally, the searching for the nearby points of the grid point in the network element, and solving the Kriging equation set to obtain the local cumulative distribution function of the grid point, comprises:

[0078] Solving the Kriging equation to obtain the weight of each measuring point to the grid point, so as to obtain the local cumulative distribution function of the grid point.

[0079] Optionally, the reservoir reservoir parameter is predicted based on the local cumulative distribution function, comprising:

[0080] A value is randomly extracted from the local conditional distribution function as the simulation value of the grid point, and the obtained simulation value is added to the original well data until the grid node is simulated.

[0081] Embodiment one:

[0082] The basic idea of the application of the multi-source information space structure feature analysis technology in seismic interpretation is:

[0083] Based on the Kriging method, combined with the sequential idea and the random modeling idea, the well-seismic joint prediction of reservoir reservoir parameters is proposed. The main idea of this method is to integrate the seismic information into the prediction of reservoir parameters in the form of local cumulative distribution function with a certain weight, and to give the prediction result of the reservoir parameters of the research area under a certain risk. The difference between the model results reflects the uncertainty caused by the lack of sufficient data and other reasons.

[0084] (1) Seismic attribute selection and standardization:

[0085] The seismic attribute information and the well point information are combined, that is, the correlation between the seismic attribute and the sandstone thickness, and the spatial structure feature between the seismic attribute and the sandstone thickness are combined. The purpose of standardization is to eliminate the differences in dimension, size and change range.

[0086] Suppose the total number of seismic lines is L, and there are N intersection points in space, each of which corresponds to the seismic attributes of two intersecting lines, and the i-th intersection point can be expressed as Where j, k are the serial numbers of the intersecting lines. Define the deviation of the intersecting line seismic attribute at the N intersection points as:

[0087]

[0088] The defined deviation value can reflect the pros and cons of the normalized seismic attribute. If the deviation value is smaller, it means that the comparability of the seismic attribute between the lines is better. Adjust and optimize the standardization parameter to reduce the deviation of the seismic attribute between the lines, where represents the minimum value of the extreme value normalization; represents the maximum value of the extreme value normalization.

[0089] For the intersection point The average of the seismic attribute at the intersection point is The deviation of the intersecting line seismic attribute and is:

[0090]

[0091]

[0092] According to the calculated deviation, adjust the normalized seismic attribute of the intersecting line:

[0093]

[0094]

[0095] Where α and β are adjustment coefficients, which can be randomly adjusted in the calculation process. Repeat the above process for iterative calculation, and the final normalized processing parameter

[0096] The seismic attributes sensitive to sandstone thickness include average instantaneous frequency (FreQ) and root mean square amplitude (RMS), etc. For well point data along the line, the corresponding relationship between seismic attribute values and well logging data can be established directly. Through the establishment of a cross plot of seismic attribute and well logging data, correlation analysis can be performed, and the seismic attribute that has a greater impact on reservoir parameters can be selected.

[0097] (2) Seismic attribute variogram plan

[0098] The main direction and the secondary direction of the reservoir parameter variation can be found by analyzing the experimental variogram plan of the reservoir parameter. The seismic attribute and the variation direction of the reservoir parameter are consistent, but the variation range is different. The main direction and the secondary direction of the variation range of the seismic attribute can be found by the variogram of the seismic line. Then the coordinate transformation can be carried out to obtain the variogram plan of the seismic data, as shown in Fig. 1. Figure 1

[0099] The variation range of the u direction is the largest, and it is a u , and the u direction is called the main direction of the variogram. The variation range of the v direction is the smallest, and it is a v , and the v direction is called the secondary direction of the variogram. θ is called the azimuth angle of the main direction. The ratio k (k < 1) of a u to a v is called the anisotropy ratio.

[0100] (3) Relationship between the seismic attribute and the reservoir parameter

[0101] The relationship between the seismic attribute and the well data can be expressed by the probability. Taking the root mean square amplitude as an example, for the well point data not passing through the line, the nearest well point is searched for the measuring point on the line, and the corresponding reservoir parameter value is found. If a certain distance is not found, the measuring point on the next side line is searched. Then the root mean square amplitude-sandstone thickness distribution map can be obtained. For a root mean square amplitude interval, there are multiple sandstone thickness well point numbers. Therefore, the conditional cumulative distribution function of the reservoir parameter corresponding to each root mean square amplitude interval can be calculated. When the seismic attribute of the measuring point on a certain line falls in a certain interval, the conditional cumulative distribution function of the measuring point can be known.

[0102] (4) Joint well-seismic prediction

[0103] A random path passing through all the grid nodes is randomly generated. For the grid node to be estimated, the measuring points of the nearby seismic lines are searched. According to the relationship between the seismic attribute and the well data, the local cumulative distribution function of each measuring point can be obtained. By solving the Kriging equation, the weight of each measuring point to the estimated point can be known. Then the local cumulative distribution of the estimated grid node can be calculated. A value is randomly extracted from the local conditional distribution function as the simulation value of the point, and the new simulated value is added to the original well data. The above steps are repeated until all the grid nodes are simulated, and the joint well-seismic simulation of the study area is completed. Of course, the realization of the equal probability is roughly the same trend, and the local details may be different.

[0104] The specific steps are shown in Fig. 4. Figure 2 Figures 3a to 9 The sample in the implementation process is shown in Fig. 5.

[0105] ​​Embodiment two:

[0106] A well-seismic joint reservoir prediction device comprises:

[0107] A selection module is configured to select seismic attributes and perform standardization processing on the selected seismic attributes.

[0108] A variogram module is configured to obtain a seismic attribute variogram map based on the standardization-processed seismic attributes.

[0109] A relationship establishment module is configured to establish a relationship between the standardization-processed seismic attributes and reservoir parameters based on the seismic attribute variogram map.

[0110] A prediction module is configured to predict a reservoir based on the relationship.

[0111] Optionally, the selection of seismic attributes and the standardization processing on the selected seismic attributes comprise:

[0112] Combining the obtained seismic attribute information and well point information;

[0113] Based on the seismic attribute information sensitive to sandstone thickness, a relationship between the seismic attribute information and well log data corresponding to the seismic attribute information is established, and the well log data is well point information obtained through a measuring line.

[0114] Based on the relationship between the seismic attribute information and the well log data, a cross plot of the seismic attribute information and the well log data is established.

[0115] Correlation analysis is performed on the cross plot, and seismic attribute information related to reservoir parameters is selected.

[0116] Optionally, the selection of seismic attributes and the standardization processing on the selected seismic attributes comprise:

[0117] Defining a deviation of the intersecting line seismic attribute at the intersection point;

[0118] Based on the mean value of the seismic attribute at the intersection point, a deviation of the intersecting line seismic attribute from the mean value of the seismic attribute at the intersection point is obtained.

[0119] The seismic attribute is standardized based on the deviation of the seismic attribute and the deviation of the mean value of the seismic attribute.

[0120] Optionally, in the seismic attribute information sensitive to sandstone thickness, the seismic attribute information sensitive to sandstone thickness at least includes average instantaneous frequency and root mean square amplitude.

[0121] Optionally, the establishment of the relationship between the standardization-processed seismic attributes and the reservoir parameters based on the seismic attribute variogram map comprises:

[0122] The well point near the measuring point on the measuring line in the seismic attribute is searched to establish the relationship between the measuring line attribute and the well data;

[0123] The local cumulative distribution function of the measuring point is obtained based on the relationship between the measuring line attribute and the well data.

[0124] Optionally, the reservoir reservoir is predicted based on the relationship, comprising:

[0125] The random path to be accessed is simulated by specifying a network unit;

[0126] The nearby point of the grid point in the network unit is searched, and the Kriging equation set is solved to obtain the local cumulative distribution function of the grid point;

[0127] The reservoir reservoir parameter is predicted based on the local cumulative distribution function.

[0128] Optionally, the nearby point of the grid point in the network unit is searched, and the Kriging equation set is solved to obtain the local cumulative distribution function of the grid point, comprising:

[0129] The Kriging equation is solved to obtain the weight of each measuring point to the grid point, so as to obtain the local cumulative distribution function of the grid point.

[0130] Optionally, the reservoir reservoir parameter is predicted based on the local cumulative distribution function, comprising:

[0131] A value is randomly extracted from the local conditional distribution function as the simulation value of the grid point, and the obtained simulation value is added to the original well data until the grid node is simulated.

[0132] Embodiment three:

[0133] The electronic device provided by the embodiment of the application comprises a memory and a processor,

[0134] The memory stores executable instructions;

[0135] The processor runs the executable instructions in the memory to implement the well-seismic joint reservoir prediction method.

[0136] The memory is used for storing non-transient computer readable instructions. Specifically, the memory can include one or more computer program products, which can include various forms of computer readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory, etc. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc.

[0137] The processor can be a central processing unit (CPU) or other form of processing unit that has data processing and / or instruction execution capabilities, and can control other components in the electronic device to perform desired functions. In one embodiment of the present application, the processor is used to run the computer readable instructions stored in the memory.

[0138] Those skilled in the art will understand that, in order to solve the technical problem of how to obtain a good user experience effect, the embodiment can also include well-known structures such as a communication bus, an interface, and the like, which should also be included in the protection scope of the present application.

[0139] Detailed descriptions of the embodiments can refer to the corresponding descriptions in the foregoing embodiments, which will not be repeated here.

[0140] Embodiment Four

[0141] The embodiment of the present application provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to realize a wellbore-seismic joint reservoir prediction method.

[0142] The computer readable storage medium according to the embodiment of the present application has non-transitory computer readable instructions stored thereon. When the non-transitory computer readable instructions are run by a processor, all or part of the steps of the method of each embodiment of the present application described above are executed.

[0143] The computer readable storage medium described above includes but is not limited to optical storage media (for example, CD-ROM and DVD), magneto-optical storage media (for example, MO), magnetic storage media (for example, magnetic tape or mobile hard disk), media with built-in rewritable non-volatile memory (for example, memory card), and media with built-in ROM (for example, ROM cartridge).

[0144] The above has described the embodiments of the present application. The above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes are obvious to those skilled in the art without departing from the scope and spirit of the described embodiments.

Claims

1. A method of joint seismic and well-based reservoir prediction, characterized in that, The method comprises the following steps: selecting seismic attributes and normalizing the selected seismic attributes; obtaining a seismic attribute variogram plane based on the normalized seismic attributes; establishing a relationship between the normalized seismic attributes and reservoir parameters based on the seismic attribute variogram plane; predicting the reservoir based on the relationship. The method comprises the following steps: combining the obtained seismic attribute information and well point information; establishing a relationship between the seismic attribute information and logging data corresponding to the seismic attribute information based on the seismic attribute information sensitive to sandstone thickness, wherein the logging data is well point information obtained through a measuring line; establishing a crossplot of the seismic attribute information and the logging data based on the relationship between the seismic attribute information and the logging data; performing correlation analysis on the crossplot to select seismic attribute information related to reservoir parameters. The method comprises the following steps: defining a deviation of the intersecting measuring line seismic attribute at the intersection point; obtaining a deviation of the intersecting measuring line seismic attribute from the mean value of the seismic attribute at the intersection point; normalizing the seismic attribute based on the deviation of the seismic attribute and the deviation of the mean value of the seismic attribute. The method comprises the following steps: searching for well points near a measuring point on a measuring line based on the seismic attribute to establish a relationship between the measuring line attribute and the well data; obtaining a local cumulative distribution function of the measuring point based on the relationship between the measuring line attribute and the well data. The method comprises the following steps: specifying a network unit to simulate a random path to be accessed; searching for points near a grid point in the network unit and solving a Kriging equation set to obtain a local cumulative distribution function of the grid point; predicting the reservoir parameter based on the local cumulative distribution function. The method comprises the following steps:

2. The seismic-to-well integrated reservoir prediction method of claim 1, wherein, solving the Kriging equation to obtain a weight of the grid point with respect to each measuring point, thereby obtaining the local cumulative distribution function of the grid point. The method comprises the following steps:

3. The method according to claim 1, wherein, randomly extracting a value from the local conditional distribution function as a simulation value of the grid point, and adding the obtained simulation value to the original well data until all grid nodes are simulated. The method comprises the following steps:

4. A device for joint well-seismic reservoir prediction of an oil reservoir, characterized in that, a selecting module for selecting seismic attributes and normalizing the selected seismic attributes; a variogram module for obtaining a seismic attribute variogram plane based on the normalized seismic attributes; a relationship establishing module for establishing a relationship between the normalized seismic attributes and reservoir parameters based on the seismic attribute variogram plane; a prediction module for predicting the reservoir based on the relationship. ​ The selected seismic attribute is standardized, and the method comprises the following steps: combining the obtained seismic attribute information and well point information; establishing a relationship between the seismic attribute information and logging data based on the sensitivity of the seismic attribute information to sandstone thickness, wherein the logging data is well point information along a survey line; establishing a crossplot of the seismic attribute information and the logging data based on the relationship between the seismic attribute information and the logging data; performing correlation analysis on the crossplot and selecting seismic attribute information related to reservoir parameters; The selected seismic attribute is standardized, and the method comprises the following steps: defining the deviation of the intersecting survey line seismic attribute at the intersection point; obtaining the deviation of the intersecting survey line seismic attribute from the average seismic attribute at the intersection point; standardizing the seismic attribute based on the deviation of the seismic attribute and the deviation of the average seismic attribute; In the sensitivity of the seismic attribute information to sandstone thickness, the sensitivity of the seismic attribute information to sandstone thickness at least includes: average instantaneous frequency and root mean square amplitude; The relationship between the standardized seismic attribute and the reservoir parameters is established based on the seismic attribute variogram plan, and the method comprises the following steps: searching for nearby well points based on the survey line attribute and the well data; obtaining the local cumulative distribution function of the survey point based on the relationship between the survey line attribute and the well data; The relationship between the standardized seismic attribute and the reservoir parameters is established based on the seismic attribute variogram plan, and the method comprises the following steps: specifying a network unit to simulate a random path to be accessed; searching for nearby points of the grid point in the network unit and solving the Kriging equation set to obtain the local cumulative distribution function of the grid point; predicting the reservoir parameters based on the local cumulative distribution function.

5. An electronic device, comprising: The electronic device comprises: a memory storing executable instructions; a processor running the executable instructions in the memory to implement the well-seismic joint reservoir prediction method of any one of claims 1-3.

Images