Method and system for drawing lithogenous phase plane distribution diagram, electronic equipment and storage medium

Abstract

The invention relates to the technical field of stratum exploration and development and data processing visualization, and provides a lithogenous phase plane distribution diagram drawing method and system, electronic equipment and a storage medium, and the method comprises the steps: reconstructing a well information data matrix based on regional range latitude and longitude coordinates; constructing a regional lithogenous phase prediction matrix based on the latitude and longitude coordinates of the data points; updating data points in the regional lithogenous phase prediction matrix based on the reconstructed well information data matrix; determining an unknown data point information list in the updated regional lithogenous phase prediction matrix based on the delineated radius; calculating the weight of each lithogenous facies type label in the unknown data point information list, and assigning the maximum weight lithogenous facies type label to the unknown data point; and drawing a lithogenous phase plane distribution diagram based on the lithogenous phase type labels corresponding to the data points in the regional lithogenous phase prediction matrix. On the basis of a multi-well lithogenous phase identification result, namely, under the condition of a lithogenous phase type label, a lithogenous phase type label of an unknown data point in an area is predicted, and a lithogenous phase plane distribution diagram is drawn.

Description

Technical Field

[0001] This disclosure belongs to the field of stratigraphic exploration and development and data processing visualization technology, and in particular relates to methods, systems, electronic devices and storage media for drawing diagenetic facies plane distribution maps. Background Technology

[0002] In the fields of geological exploration and earth sciences, understanding the distribution of lithology underground has always been a crucial issue in geology. Well logging is an important means of obtaining reservoir physical parameters and discovering and evaluating oil and gas reservoirs and predicting oil and gas reserves. With the continuous iteration of machine learning technology, the technique of predicting diagenetic facies using single-well logging data has become relatively mature. While machine learning methods can predict the diagenetic facies types of multiple wells within a block, a method for drawing a planar distribution map of the block's diagenetic facies using the results of multi-well identification is lacking.

[0003] Currently, machine learning has made significant progress in areas such as fine-grained classification of complex lithologies and facies, fluid identification, fracture identification and classification, reservoir classification, well logging curve reconstruction, reservoir parameter prediction, imaging well logging image processing, and intelligent well logging characterization of reservoir micropore structure. For example, machine learning-based methods for predicting the diagenetic facies of tight sandstone reservoirs can automatically classify and predict the diagenetic facies types of tight sandstone reservoirs using both unsupervised and supervised machine learning models. Furthermore, researchers have explored how to improve the performance of machine learning models by optimizing feature selection, especially when dealing with sparse well logging data.

[0004] The drawing of diagenetic facies plane distribution maps typically employs methods such as intersection maps and diagenetic coefficient contour lines. Patent CN118114542A discloses a method for drawing diagenetic facies plane distribution maps based on single-well TOC and brittle mineral content estimation. However, the accuracy of this method may be affected by the actual characteristics of the rock type and TOC and mineral content in the study area, requiring high accuracy of well logging data. Therefore, it still relies on well logging data for lithological plane division. Consequently, existing technologies lack methods for drawing diagenetic facies plane distribution maps based on multi-well diagenetic facies identification results. Summary of the Invention

[0005] To address the aforementioned issues, this invention discloses a method, system, electronic device, and storage medium for drawing diagenetic facies planar distribution maps. By using known single-well information within a region to predict unknown diagenetic facies type tags, it is possible to draw diagenetic facies planar distribution maps.

[0006] This invention is achieved through the following technical solution:

[0007] A well information data matrix is ​​established based on information from multiple individual wells; the individual well information includes: the coordinates of the individual well and the diagenetic facies type label corresponding to the individual well.

[0008] Define the delineation radius, the latitude and longitude coordinates of the region, and the latitude and longitude coordinates of the data points; reconstruct the well information data matrix based on the latitude and longitude coordinates of the region; construct the regional diagenetic facies prediction matrix based on the latitude and longitude coordinates of the data points;

[0009] The data points in the regional diagenetic facies prediction matrix are updated based on the reconstructed well information data matrix to obtain the updated regional diagenetic facies prediction matrix. In the regional diagenetic facies prediction matrix, the data points that have not been updated are called unknown data points, and the updated data points are called known data points.

[0010] Based on the delineated radius, the list of unknown data points in the updated regional diagenetic facies prediction matrix is ​​determined; the weight of each diagenetic facies type label in the list of unknown data points is calculated, and the diagenetic facies type label with the largest weight is assigned to the unknown data point to obtain the final regional diagenetic facies prediction matrix.

[0011] Based on the diagenetic facies type labels corresponding to the data points in the final regional diagenetic facies prediction matrix, a diagenetic facies planar distribution map is drawn.

[0012] Furthermore,

[0013] The list of unknown data points in the updated regional diagenetic facies prediction matrix, determined based on the delineated radius, includes:

[0014] Find known data points whose distance from the unknown data points is less than or equal to the defined radius;

[0015] The found known data points are used as the list of unknown data points in the updated regional diagenetic facies prediction matrix.

[0016] Furthermore,

[0017] Define the number of delineated wells; the calculation of the weight of each diagenetic facies type label in the unknown data point information list includes:

[0018] When the number of known data points that meet the near-well condition in the unknown data point information list is greater than or equal to the number of delineated wells, the unknown data points are determined to belong to a dense logging area. The weight of each diagenetic facies type label in the unknown data point information list is calculated using the inverse radial basis function interpolation method. The near-well condition is that the distance between the known data point and the unknown data point is less than or equal to the near-well radius. The near-well radius is the near-well coefficient multiplied by the delineated radius, and the near-well coefficient is less than 1.

[0019] Furthermore,

[0020] Define the number of delineated wells; the calculation of the weight of each diagenetic facies type label in the unknown data point information list includes:

[0021] If the number of known data points that meet the near-well conditions in the unknown data point information list is less than the number of delineated wells, and the number of known data points in the unknown data point information list is greater than the number of delineated wells, then the unknown data point is determined to belong to a sparse logging area.

[0022] The inverse distance weighted interpolation method is used to calculate the weight of each diagenetic facies type label in the information list of unknown data points.

[0023] Furthermore,

[0024] After determining that the unknown data points belong to sparse logging areas, the method further includes:

[0025] Determine whether the number of known data points in the unknown data point information list is greater than the number of delineated wells;

[0026] The inverse distance weighted interpolation method is used to calculate the weight of each diagenetic facies type label in the unknown data point information list, specifically including:

[0027] When the number of known data points in the unknown data point information list is greater than the number of delineated wells, the inverse distance weighted interpolation method is used to calculate the label weight of each diagenetic facies type in the unknown data point information list.

[0028] When the number of known data points in the unknown data point information list is less than the number of delineated wells, the inverse distance weighted interpolation method is used to calculate the label weights of each diagenetic facies type for known data points in the unknown data point information list that meet the near-well conditions.

[0029] This invention also provides a system for drawing diagenetic facies plane distribution maps based on multi-well identification. The system includes: a well information data matrix establishment unit, a prediction matrix construction unit, a prediction matrix update unit, a prediction matrix determination unit, and a drawing unit, wherein:

[0030] A well information data matrix establishment unit is used to establish a well information data matrix based on multiple individual well information; the individual well information includes: the coordinates of the individual well and the diagenetic facies type label corresponding to the individual well.

[0031] The prediction matrix construction unit is used to define the delineation radius, the latitude and longitude coordinates of the region, and the latitude and longitude coordinates of the data points; reconstruct the well information data matrix based on the latitude and longitude coordinates of the region; and construct the regional diagenetic facies prediction matrix based on the latitude and longitude coordinates of the data points.

[0032] The prediction matrix update unit is used to update the data points in the regional diagenetic facies prediction matrix based on the reconstructed well information data matrix, so as to obtain the updated regional diagenetic facies prediction matrix. In this matrix, the data points that have not been updated are called unknown data points, and the updated data points are called known data points.

[0033] The prediction matrix determination unit is used to determine the list of unknown data points in the updated regional diagenetic facies prediction matrix based on the delineated radius; calculate the weight of each diagenetic facies type label in the list of unknown data points, and assign the diagenetic facies type label with the largest weight to the unknown data point to obtain the final regional diagenetic facies prediction matrix.

[0034] The drawing unit is used to draw a planar distribution map of diagenetic facies based on the diagenetic facies type labels corresponding to the data points in the final regional diagenetic facies prediction matrix.

[0035] Furthermore,

[0036] The prediction matrix determination unit is specifically used to find known data points from the known data points whose distance from the unknown data points is less than or equal to the delineated radius; and to use the found known data points as the list of unknown data points in the updated regional lithogenesis prediction matrix.

[0037] Furthermore,

[0038] The prediction matrix construction unit is also used to define the number of delineated wells;

[0039] The prediction matrix determination unit is specifically used to determine that the unknown data point belongs to a dense logging area when the number of known data points that meet the near-well condition in the unknown data point information list is greater than or equal to the number of delineated wells. The unit uses the inverse radial basis function interpolation method to calculate the label weight of each diagenetic facies type in the unknown data point information list. The near-well condition is that the distance between the known data point and the unknown data point is less than or equal to the near-well radius. The near-well radius is the near-well coefficient multiplied by the delineated radius, and the near-well coefficient is less than 1.

[0040] The present invention also provides a computer-readable storage medium, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0041] Memory, used to store computer programs;

[0042] The processor, when executing the program stored in the memory, implements the aforementioned steps of the method for drawing the diagenetic facies plane distribution map.

[0043] The present invention also provides a computer storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, it implements the aforementioned steps of the method for drawing a diagenetic facies plane distribution map.

[0044] Compared with the prior art, this disclosure has the following advantages:

[0045] 1. Based on the diagenetic facies identification results of multiple wells, i.e., the diagenetic facies type labels, it can predict the diagenetic facies type labels of unknown data points in the region and draw a diagenetic facies plane distribution map;

[0046] 2. Different interpolation methods are used to calculate diagenetic facies type labels for logging sections with different characteristics. This reduces the use of logging data when drawing plan maps, focuses on the processing of diagenetic facies identification results, improves data processing efficiency, and thus improves drawing efficiency, making it more universal.

[0047] Other features and advantages of this disclosure will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the disclosure. The objects and other advantages of this disclosure may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this disclosure 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 some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 A flowchart of a method for drawing a diagenetic facies plane distribution map according to an embodiment of the present disclosure is shown;

[0050] Figure 2 A single-well logging curve and lithofacies diagram according to an embodiment of the present disclosure is shown;

[0051] Figure 3 A diagenetic facies planar distribution map drawing result is shown according to an embodiment of the present disclosure. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0053] like Figure 1 As shown in this embodiment, a method for drawing a diagenetic facies plane distribution map based on multi-well identification is disclosed. This method, based on multi-well identification, includes the following steps:

[0054] S1. Obtain the coordinates of multiple single wells and their corresponding diagenetic facies type labels, and establish a well information data matrix.

[0055] Multiple well coordinates and their corresponding diagenetic facies type labels can be stored in the form of a well information data matrix, where each row of the data matrix represents a single well. The well information data matrix is ​​represented as X. i =[x i ,y i ,K i ]∈R m×3 X i The elements in the table represent the longitude coordinates x of a single well. i Latitude coordinates y i and the corresponding diagenetic facies type label K of the strata i m is the number of single-well information groups in the data matrix, where the diagenetic facies type label is discrete and indicative, and can be represented by discrete values, which do not have physical meaning.

[0056] S2. Define the number of wells to be delineated, the delineation radius, the regional range information, and the latitude and longitude coordinates of the data points; reconstruct the well information data matrix based on the latitude and longitude coordinates of the regional range; construct the regional diagenetic facies prediction matrix based on the latitude and longitude coordinates of the data points.

[0057] Wherein, the radius R is defined. c The maximum geographical distance affected by information from a single well is used to delineate the number of wells, N. w This represents the minimum number of sets of single-well information required to predict diagenetic facies. More precisely, it is the minimum number of sets of single-well information required to predict diagenetic facies using all single-well information within a defined radius when near-wellbore conditions are not met. The regional extent information includes the latitude and longitude coordinates of the two endpoints of the region rectangle.

[0058] The specific methods of S2 include the following S2.1 to S2.4:

[0059] S2.1. Based on the regional scope information, define the latitude and longitude range of the region, filter single-well information that conforms to the regional scope from the well information data matrix, and reconstruct the well information data matrix R. n×3 Where n represents the number of filtered single-well information groups; the data matrix is ​​represented as X. i =[x i ,y i ,K i ]∈R n×3 The data meets the condition Lon L ≤x i ≤Lon H ,Lat L ≤y i ≤Lat H .

[0060] Among them, LonH and Lon L The maximum and minimum longitude values ​​representing the region, Lat H and Lat L This represents the maximum and minimum latitude values ​​within the region.

[0061] S2.2. Divide the region into equal intervals along the longitude and latitude directions, dividing it into q parts along the longitude direction and p parts along the latitude direction, to obtain a planar grid map with p×q grids. Then, the regional lithologic facies prediction matrix S can be constructed. p×q The matrix is ​​initialized to 0 or empty, with a unit spacing of Δx in the longitude direction and Δy in the latitude direction.

[0062] S2.3, Define data point s ij The latitude and longitude coordinates represented are:

[0063]

[0064] Among them, s ij Representative regional diagenetic facies prediction matrix S p×q The data in the i-th row and j-th column of the diagram represents the center of each grid in the planar grid diagram.

[0065] S2.4 Define the formula for the true distance between any two data points.

[0066] For any two distinct data points s in the data matrix A With s B :

[0067] Longitude distance

[0068] Latitude distance is

[0069] The actual distance between two points is The latitude and longitude coordinates of the data points are expressed in degrees, and the distance unit is km.

[0070] S3, Based on reconstructed well information data R n×3 The data points in the regional diagenetic facies prediction matrix are updated to obtain the updated regional diagenetic facies prediction matrix.

[0071] The specific method for updating the regional diagenetic facies prediction matrix can be implemented in the following ways:

[0072] Using the reconstructed single-well information data matrix, the diagenetic facies type label of the single-well information is assigned to the data point s at the corresponding coordinates. ij, data points with assigned diagenetic facies type labels become known data points, and data points without assigned diagenetic facies type labels become unknown data points. At this point, the initialized regional diagenetic facies prediction matrix S is formed. * ;

[0073] Specifically, for any set of single-well information [x k ,y k ,K k ], can be used for data points s ij Assign values ​​according to the following rules:

[0074]

[0075] in, The data point with the diagenetic facies type label assigned to well information with serial number k, K k The diagenetic facies type label K represents the well information with serial number k.

[0076] S4. Based on the delineated radius, determine the list of unknown data points in the updated regional diagenetic facies prediction matrix; calculate the weight of each diagenetic facies type label in the list of unknown data points, and assign the diagenetic facies type label with the largest weight to the unknown data point to obtain the final regional diagenetic facies prediction matrix.

[0077] Specifically, for unknown data points, an information list is constructed by searching for known data points whose distance from the unknown data points is less than or equal to the delineated radius. The found known data points are used as the information list of unknown data points in the updated regional diagenetic facies prediction matrix. The single-well information contained in the information list is classified and stored according to the diagenetic facies type label.

[0078] Specifically, the following formula can be used to store single-well information at unknown data points:

[0079]

[0080] Among them, s k This represents a known data point, where R represents the coordinate information of that data point. c This represents the defined radius.

[0081] by Figure 2 Taking the diagenetic facies identification results as an example, there are 5 types of diagenetic facies, represented by 1 to 5. Then, the unknown data points s after classification... ij The information list can be represented as:

[0082] After extending the information from known data points to unknown data points, a complete regional lithogenesis prediction matrix S is formed. p×q .

[0083] The above calculation of the weights of each diagenetic facies type label in the unknown data point information list, and the assignment of the diagenetic facies type label with the highest weight to the unknown data point, yields the final regional diagenetic facies prediction matrix, which can be achieved through the following steps S4.1 to S4.5:

[0084] S4.1. Use the number of delineated wells to determine if the amount of data for unknown data points is sufficient; for unknown data points whose data amount meets the requirements for the number of delineated wells, analyze whether the unknown data points belong to dense logging areas, and determine whether the information list of unknown data points meets the following conditions:

[0085]

[0086] Where γ represents the near-wellbore coefficient, which is less than 1 and is a constant, and can take a value of 0.3. Here, γR c That is, the near-well radius. This is the near-wellbore condition, meaning the distance between known and unknown data points is less than or equal to the near-wellbore radius. This represents a known data point in the unknown data point information list with the diagenetic facies label K and the distance number d, where d represents the distance number under the same diagenetic facies type. The two data point parameters in the distance formula are ignored here.

[0087] If the conditions are met, it is identified as a dense logging area; otherwise, it is identified as a sparse logging area.

[0088] S4.2 For sparse logging sections, the inverse distance weighted interpolation method is used to calculate the unknown data points s. ij Various diagenetic facies types tags ij (K b Weighting:

[0089]

[0090] Where b represents the diagenetic facies label type number, v represents the ordinal number of the diagenetic facies label type, and w represents the total number of diagenetic facies types. Zhong K b The diagenetic facies type is represented by the number b, and d represents the distance number within the same diagenetic facies type. b This represents the total number of distance parameters included under the diagenetic facies type numbered b;

[0091] After obtaining the weights of each diagenetic facies, the diagenetic facies type label with the highest weight is taken as the diagenetic facies type label for that data point, that is:

[0092] s ij =K

[0093] sts ij (K)=max(s ij (K b ))

[0094] S4.3 For densely logged sections, the radial basis function is used to calculate the weight of each diagenetic facies type label:

[0095]

[0096] Where ε is a scale parameter, c d It is a coefficient associated with known data points.

[0097] After obtaining the weights of each diagenetic facies, the diagenetic facies type label with the highest weight is taken as the diagenetic facies type label for that data point:

[0098] s ij =K

[0099] sts ij (K)=max(s ij (K b ))

[0100] S4.4 For unknown data points that do not meet the required number of delineated wells, determine whether the following near-well conditions are met:

[0101]

[0102] If the near-wellbore condition is met, then for the unknown data point, only the near-wellbore data is interpolated using the inverse distance weighted interpolation method to calculate the diagenetic facies type label for that data point;

[0103]

[0104] s ij =K

[0105] sts ij (K)=max(s ij (K b ))

[0106] Unknown data points that meet near-well conditions can also be classified as sparse logging zones.

[0107] S4.5 If the list of unknown data points does not meet all of the above conditions, then the diagenetic facies type label of that data point is considered to be empty.

[0108] At this point, the diagenetic facies matrix S is obtained by integrating the calculation results from all cases.

[0109] The general idea behind S4.1-S4.5 is to analyze the distance relationship between multiple single wells for unknown data points and use interpolation functions to weight and determine the lithological type label for each pixel.

[0110] S5. Based on the diagenetic facies type labels corresponding to the data points in the final regional diagenetic facies prediction matrix, draw a diagenetic facies planar distribution map.

[0111] Based on the final regional diagenetic facies matrix, different colors are assigned to labels for different diagenetic facies types. The image is divided into a grid with the same dimension as the diagenetic facies matrix in the planar map, and the corresponding colors are applied to the planar map according to the diagenetic facies matrix data, forming a planar distribution map of diagenetic facies. In the planar map, the horizontal axis represents longitude coordinates, increasing from left to right, and the vertical axis represents latitude coordinates, increasing from bottom to top. Geographical directions, diagenetic facies legends, and image cartographic information are labeled near the image. After forming the complete image, the planar distribution map of diagenetic facies is output, as shown in the image. Figure 3 As shown.

[0112] Based on the same inventive concept, this invention also provides a system for drawing diagenetic facies plane distribution maps based on multi-well identification. The system includes: a well information data matrix establishment unit, a prediction matrix construction unit, a prediction matrix update unit, a prediction matrix determination unit, and a drawing unit, wherein:

[0113] A well information data matrix establishment unit is used to establish a well information data matrix based on multiple individual well information; the individual well information includes: the coordinates of the individual well and the diagenetic facies type label corresponding to the individual well.

[0114] The prediction matrix construction unit is used to define the delineation radius, the latitude and longitude coordinates of the region, and the latitude and longitude coordinates of the data points; reconstruct the well information data matrix based on the latitude and longitude coordinates of the region; and construct the regional diagenetic facies prediction matrix based on the latitude and longitude coordinates of the data points.

[0115] The prediction matrix update unit is used to update the data points in the regional diagenetic facies prediction matrix based on the reconstructed well information data matrix, so as to obtain the updated regional diagenetic facies prediction matrix. In this matrix, the data points that have not been updated are called unknown data points, and the updated data points are called known data points.

[0116] The prediction matrix determination unit is used to determine the list of unknown data points in the updated regional diagenetic facies prediction matrix based on the delineated radius; calculate the weight of each diagenetic facies type label in the list of unknown data points, and assign the diagenetic facies type label with the largest weight to the unknown data point to obtain the final regional diagenetic facies prediction matrix.

[0117] The drawing unit is used to draw a planar distribution map of diagenetic facies based on the diagenetic facies type labels corresponding to the data points in the final regional diagenetic facies prediction matrix.

[0118] Preferably, the prediction matrix determination unit is specifically used to find known data points from the known data points whose distance from the unknown data points is less than or equal to the delineated radius; and to use the found known data points as the list of unknown data points in the updated regional lithogenesis prediction matrix.

[0119] Preferably, the prediction matrix construction unit is also used to define the number of delineated wells;

[0120] The prediction matrix determination unit is specifically used to determine that the unknown data point belongs to a dense logging area when the number of known data points that meet the near-well condition in the unknown data point information list is greater than or equal to the number of delineated wells. The unit uses the inverse radial basis function interpolation method to calculate the label weight of each diagenetic facies type in the unknown data point information list. The near-well condition is that the distance between the known data point and the unknown data point is less than or equal to the near-well radius. The near-well radius is the near-well coefficient multiplied by the delineated radius, and the near-well coefficient is less than 1.

[0121] Preferably, the prediction matrix construction unit is also used to define the number of delineated wells;

[0122] The prediction matrix determination unit is specifically used to determine that the unknown data point belongs to a sparse logging section when the number of known data points that meet the near-well conditions in the unknown data point information list is less than the number of delineated wells, and the number of known data points in the unknown data point information list is greater than the number of delineated wells; and to calculate the label weight of each diagenetic facies type in the unknown data point information list using the inverse distance weighted interpolation method.

[0123] Preferably, the prediction matrix determination unit is specifically used to determine whether the number of known data points in the unknown data point information list is greater than the number of delineated wells; when the number of known data points in the unknown data point information list is greater than the number of delineated wells, the inverse distance weighted interpolation method is used to calculate the label weight of each diagenetic facies type in the unknown data point information list; when the number of known data points in the unknown data point information list is less than the number of delineated wells, the inverse distance weighted interpolation method is used to calculate the label weight of each diagenetic facies type of known data points in the unknown data point information list that meet the near-well conditions.

[0124] Based on the above disclosure, the present invention also provides an electronic device. The electronic device of this embodiment includes at least one processor and at least one storage medium electrically connected to the processor. The storage medium is electrically connected to the processor, wherein the storage medium stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described above.

[0125] Based on the same inventive concept, the present invention also provides a storage medium storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method as described above.

[0126] Although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A method for drawing a planar distribution map of diagenetic facies, characterized in that, The method includes, A well information data matrix is ​​established based on information from multiple individual wells; the individual well information includes: the coordinates of the individual well and the diagenetic facies type label corresponding to the individual well. Define the delineation radius, the latitude and longitude coordinates of the region, and the latitude and longitude coordinates of the data points; reconstruct the well information data matrix based on the latitude and longitude coordinates of the region; construct the regional diagenetic facies prediction matrix based on the latitude and longitude coordinates of the data points; The data points in the regional diagenetic facies prediction matrix are updated based on the reconstructed well information data matrix to obtain the updated regional diagenetic facies prediction matrix. In the regional diagenetic facies prediction matrix, the data points that have not been updated are called unknown data points, and the updated data points are called known data points. Based on the delineated radius, the list of unknown data points in the updated regional diagenetic facies prediction matrix is ​​determined; the weight of each diagenetic facies type label in the list of unknown data points is calculated, and the diagenetic facies type label with the largest weight is assigned to the unknown data point to obtain the final regional diagenetic facies prediction matrix. Based on the diagenetic facies type labels corresponding to the data points in the final regional diagenetic facies prediction matrix, a diagenetic facies planar distribution map is drawn.

2. The method according to claim 1, characterized in that, The list of unknown data points in the updated regional diagenetic facies prediction matrix, determined based on the delineated radius, includes: Find known data points whose distance from the unknown data points is less than or equal to the defined radius; The found known data points are used as the list of unknown data points in the updated regional diagenetic facies prediction matrix.

3. The method according to claim 2, characterized in that, Define the number of delineated wells; the calculation of the weight of each diagenetic facies type label in the unknown data point information list includes: When the number of known data points that meet the near-well condition in the unknown data point information list is greater than or equal to the number of delineated wells, the unknown data points are determined to belong to a dense logging area. The weight of each diagenetic facies type label in the unknown data point information list is calculated using the inverse radial basis function interpolation method. The near-well condition is that the distance between the known data point and the unknown data point is less than or equal to the near-well radius. The near-well radius is the near-well coefficient multiplied by the delineated radius, and the near-well coefficient is less than 1.

4. The method according to claim 2 or 3, characterized in that, Define the number of delineated wells; the calculation of the weight of each diagenetic facies type label in the unknown data point information list includes: When the number of known data points that meet the near-well conditions in the unknown data point information list is less than the number of delineated wells, and the number of known data points in the unknown data point information list is greater than the number of delineated wells, the unknown data points are determined to belong to a sparse logging area. The inverse distance weighted interpolation method is used to calculate the weight of each diagenetic facies type label in the information list of unknown data points.

5. The method according to claim 4, characterized in that, After determining that the unknown data point belongs to a sparse logging zone, the method further includes: Determine whether the number of known data points in the unknown data point information list is greater than the number of delineated wells; The calculation of the diagenetic facies type label weights in the unknown data point information list using the inverse distance weighted interpolation method specifically includes: When the number of known data points in the unknown data point information list is greater than the number of delineated wells, the inverse distance weighted interpolation method is used to calculate the label weight of each diagenetic facies type in the unknown data point information list. When the number of known data points in the unknown data point information list is less than the number of delineated wells, the inverse distance weighted interpolation method is used to calculate the label weights of each diagenetic facies type for known data points in the unknown data point information list that meet the near-well conditions.

6. A system for drawing diagenetic facies plane distribution maps based on multi-well identification, characterized in that, The system includes: a well information data matrix establishment unit, a prediction matrix construction unit, a prediction matrix update unit, a prediction matrix determination unit, and a drawing unit, wherein: A well information data matrix establishment unit is used to establish a well information data matrix based on multiple individual well information; the individual well information includes: the coordinates of the individual well and the diagenetic facies type label corresponding to the individual well. The prediction matrix construction unit is used to define the delineation radius, the latitude and longitude coordinates of the region, and the latitude and longitude coordinates of the data points; reconstruct the well information data matrix based on the latitude and longitude coordinates of the region; and construct the regional diagenetic facies prediction matrix based on the latitude and longitude coordinates of the data points. The prediction matrix update unit is used to update the data points in the regional diagenetic facies prediction matrix based on the reconstructed well information data matrix, so as to obtain the updated regional diagenetic facies prediction matrix. In this matrix, the data points that have not been updated are called unknown data points, and the updated data points are called known data points. The prediction matrix determination unit is used to determine the list of unknown data points in the updated regional diagenetic facies prediction matrix based on the delineated radius; calculate the weight of each diagenetic facies type label in the list of unknown data points, and assign the diagenetic facies type label with the largest weight to the unknown data point to obtain the final regional diagenetic facies prediction matrix. The drawing unit is used to draw a planar distribution map of diagenetic facies based on the diagenetic facies type labels corresponding to the data points in the final regional diagenetic facies prediction matrix.

7. The system according to claim 6, characterized in that, The prediction matrix determination unit is specifically used to find known data points from the known data points whose distance from the unknown data points is less than or equal to the delineated radius; and to use the found known data points as the list of unknown data points in the updated regional lithogenesis prediction matrix.

8. The system according to claim 7, characterized in that, The prediction matrix construction unit is used to define the number of delineated wells; The prediction matrix determination unit is specifically used to determine that the unknown data point belongs to a dense logging area when the number of known data points that meet the near-well condition in the unknown data point information list is greater than or equal to the number of delineated wells. The unit uses the inverse radial basis function interpolation method to calculate the label weight of each diagenetic facies type in the unknown data point information list. The near-well condition is that the distance between the known data point and the unknown data point is less than or equal to the near-well radius. The near-well radius is the near-well coefficient multiplied by the delineated radius, and the near-well coefficient is less than 1.

9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the method described in any one of claims 1-5.

10. A computer storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method described in any one of claims 1-5.

Images