An attribute prediction method, device, equipment and readable storage medium
By using well-seismic cross-analysis and seismic attribute mapping, the problem of inaccurate reservoir prediction caused by the diversity of seismic attributes was solved, and accurate prediction of igneous reservoir thickness was achieved, improving the accuracy and stability of prediction.
Patent Information
- Application Number
- CN202111160559.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-09-30
- Publication Date
- 2025-12-05
- Estimated Expiration
- 2041-09-30
AI Technical Summary
In existing technologies, the diversity of seismic attributes leads to large differences in reservoir prediction results, poor stability, low accuracy, and difficulty in effectively identifying the spatial distribution of igneous reservoirs.
By using well-seismic cross-analysis, the set of sensitive seismic attributes with high cross-correlation coefficients in the seismic attributes of the target area is identified, and the mapping relationship between igneous rock thickness and sensitive seismic attributes is established. Cross-analysis is then performed using well logging and well logging data to improve prediction accuracy.
Effectively determining the spatial distribution of igneous reservoirs improves the accuracy of reservoir parameter prediction and ensures precise prediction of igneous reservoir thickness.
Smart Images
Figure CN115903029B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the field of seismic data comprehensive interpretation, and in particular to an attribute prediction method and device, equipment and a readable storage medium. BACKGROUND
[0002] Seismic reservoir prediction is an important means of detecting oil and gas reservoirs, which can effectively and comprehensively understand the information related to the reservoir geology.
[0003] In the prior art, in the geological exploration stage, other seismic attributes are usually derived by using the amplitude, frequency and phase attributes of the target seismic area.
[0004] However, since there are many types of seismic attributes, the prediction results obtained based on the above three attributes will differ when the prediction object is different, the multi-solution is strong, the stability is poor, and the reservoir prediction accuracy of the prediction area is low. SUMMARY
[0005] The embodiments of the present application provide an attribute prediction method, device, equipment and readable storage medium, which improve the reservoir parameter prediction accuracy of the target area. The technical solution is as follows:
[0006] On the one hand, an attribute prediction method is provided, which is applied to a computer device, and the method comprises:
[0007] Obtaining well logging data and recording well data of a drilled well;
[0008] Determining seismic attributes of the target area based on the well logging data and the recording well data;
[0009] Performing crossplot analysis based on the seismic attributes and the igneous rock thickness of the target area, establishing a crossplot of the target area, and the crossplot is used to indicate a relationship between the amplitude attribute of the drilled well and the igneous rock thickness;
[0010] In response to a crossplot correlation coefficient in the crossplot being within a predetermined threshold range, determining a sensitive seismic attribute set from the seismic attributes;
[0011] Based on the sensitive seismic attribute set, establishing a mapping relationship between the igneous rock thickness and the sensitive seismic attribute set;
[0012] Based on the mapping relationship, determining a reservoir parameter value of the target area, and the reservoir parameter value includes an igneous rock reservoir thickness.
[0013] On the other hand, an attribute prediction device is provided, and the device comprises:
[0014] An acquisition module is configured to acquire well logging data and recording well data of a drilled well;
[0015] determining a seismic attribute of a target area where the drilled well is located based on the logging data and the well logging data;
[0016] constructing a crossplot of the target area based on the seismic attribute and the igneous rock thickness, the crossplot being used to indicate a relationship between the amplitude attribute of the drilled well and the igneous rock thickness;
[0017] The determining module is further configured to determine a sensitive seismic attribute set from the seismic attribute in response to a crossplot correlation coefficient corresponding to the crossplot being within a predetermined threshold range.
[0018] The constructing module is further configured to establish a mapping relationship between the igneous rock thickness and the sensitive seismic attribute set based on the sensitive seismic attribute set.
[0019] The determining module is further configured to determine a reservoir parameter value of the target area based on the mapping relationship, the reservoir parameter value including an igneous rock reservoir thickness.
[0020] In another aspect, a computer device is provided, the computer device comprising a processor and a memory, the memory storing at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by the processor to implement the attribute prediction method according to any one of the above embodiments of the present application.
[0021] In another aspect, a computer readable storage medium is provided, the storage medium storing at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded and executed by a processor to implement the attribute prediction method according to any one of the above embodiments of the present application.
[0022] In another aspect, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the attribute prediction method according to any one of the above embodiments.
[0023] The technical solutions provided by the embodiments of the present application have at least the following beneficial effects:
[0024] Based on existing well logging and well logging data within the target area, the sensitive seismic attribute set with high correlation among the cross correlation coefficients of seismic attributes in the target area is determined by well-seismic cross-plot analysis. Based on the sensitive attribute set, the thickness of igneous reservoirs at the drilled well points is predicted, effectively realizing the spatial distribution of igneous reservoirs and improving the accuracy of prediction. Attached Figure Description
[0025] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0026] Figure 1 This is a schematic diagram of the implementation environment of the attribute prediction method provided in an exemplary embodiment of this application;
[0027] Figure 2 This is a flowchart of the steps of an attribute prediction method provided in an exemplary embodiment of this application;
[0028] Figure 3 This is a flowchart of the steps of an attribute prediction method provided in another exemplary embodiment of this application;
[0029] Figure 4 This is a structural block diagram of an attribute prediction apparatus provided in an exemplary embodiment of this application;
[0030] Figure 5 This is a structural block diagram of an attribute prediction apparatus provided in another exemplary embodiment of this application;
[0031] Figure 6 This is a schematic diagram of the structure of a server provided in an exemplary embodiment of this application. Detailed Implementation
[0032] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application is provided in conjunction with the accompanying drawings.
[0033] First, let's introduce the terminology used in this application:
[0034] Seismic attribute: refers to useful information extracted from seismic data after mathematical transformation, which is used to indicate geological abnormal phenomena that are not easy to find in original seismic data, mainly involving amplitude, instantaneous, wavelet and other attributes, including but not limited to the geometric, kinematic, dynamic and statistical characteristics of seismic waves. Based on kinematics and dynamics, seismic attributes are divided into: amplitude, frequency, phase, energy, waveform, wave impedance, wave velocity, correlation and ratio. Among the six categories of seismic attributes, there are also several small categories of attributes. In the embodiments of the present application, different seismic attributes reflect different aspects of the same geological body (referred to as target area in the embodiments of the present application). How to screen out a sensitive seismic attribute set of the target area (target geological body) from the seismic attributes is a problem to be solved in the current oil and gas reservoir exploration.
[0035] Sensitive seismic attribute: different seismic attributes have different sensitivities to different geological information. For example, geology A is more sensitive to frequency and phase of seismic attribute, that is, geology A is greatly affected by frequency and phase. In subsequent research and prediction of the seismic attribute corresponding to geology A, the focus is on frequency and phase. Based on the main influence of frequency and phase and the influence of other seismic attributes, the accuracy of predicting the reservoir information corresponding to geology A is improved.
[0036] Igneous rock: used to indicate a kind of rock formed after magma cooling. The lithology of igneous rock is complex, and the lateral characteristics between rock layers also have variability. In related technologies, based on the analysis of igneous rock reservoir parameters in a single well, only using magnetic data or only using seismic data to simply predict the lateral characteristics between igneous rock layers cannot guarantee the completeness and correctness of the obtained data. Using the attribute prediction method provided in the embodiments of the present application, the existing seismic data is comprehensively combined to reasonably predict the reservoir parameters of the igneous rock in the target area (target geological body).
[0037] Secondly, combined with the above introduction of the terms, combined with Figure 1 The implementation environment related to the attribute prediction method shown in the embodiments of the present application is described as follows. Figure 1 As shown in the figure, the implementation environment includes a terminal 110 and a server 120. The terminal 110 can perform data interaction / data communication with the server 120 through a wired network or a wireless network.
[0038] The terminal 110 sends an information acquisition instruction to the server 120, and the server 120 acquires at least one of the drilled well, the logging data of the drilled well, the path data of the drilled well, and the target area where the drilled well is located from the database according to the information acquisition instruction.
[0039] The server 120 determines seismic attributes of the target area based on the logging data and the well logging data of the drilled well, performs crossplot analysis on the seismic attributes and the igneous rock thickness of the target area, determines a corresponding sensitive seismic attribute set of the target area, predicts reservoir parameter values of the target area based on the sensitive seismic attribute set, and obtains a prediction result.
[0040] The server 120 feeds back the prediction result to the terminal 110.
[0041] The terminal 110 can be a smart terminal such as a smartphone, a tablet computer, a computer, or the like that can integrate data.
[0042] The server 120 can be a server corresponding to the terminal 110, can also be a server cluster composed of a plurality of servers, or can be a cloud computing service center. The server 120 corresponds to a database integrating related data of drilled wells. The server 120 is configured to provide background services for the terminal 110. Optionally, the server 120 undertakes main computing work, and the terminal 110 undertakes secondary computing work. Alternatively, the terminal 110 undertakes main computing work, and the server undertakes secondary computing work. Alternatively, the server 120 and the terminal 110 adopt a distributed computing architecture to coordinate computing.
[0043] It should be noted that the terminal 110 can refer to a plurality of devices or one of the plurality of devices. The embodiments of the present application are only illustrated by taking the terminal 110 as an example.
[0044] In combination with the above introduction of the terms and the introduction of the implementation environment, please refer to Figure 2 , Figure 2 is a flowchart of an attribute prediction method provided by the embodiments of the present application. The attribute prediction method is applied to a server in an implementation environment shown in Figure 1 , and includes the following steps.
[0045] In step 201, logging data and well logging data of a drilled well in a target area are obtained.
[0046] In the present embodiment, the related data of the drilled well is stored in a local terminal or in a database. The related data of the drilled well includes, but is not limited to, logging data, well logging data, oil testing data, production data, and igneous rock thickness. The well logging data is used to indicate statistics of wellbore return information of the drilled well during drilling. The logging data is used to measure physical parameters of the drilled well location by using physical characteristics after the drilled well reaches a well depth. The igneous rock thickness is used to indicate the total thickness of the igneous rock at the drilled well point.
[0047] Optionally, the terminal responds to a selection operation of the target area, which can be a touch operation or a control operation identified through voice recognition technology or image recognition technology; the terminal sends the selection operation to the server, the server determines the target area from the selection operation, and obtains the well logging data and logging data of the drilled wells in the target area from the database.
[0048] In step 202, seismic attributes of the target area where the drilled well is located are determined based on the well logging data and the logging data.
[0049] In some embodiments, the server establishes a preset geological model based on the well logging data and the logging data, which can be a one-dimensional geological model, a two-dimensional geological model, or a three-dimensional geological model, and the present application does not limit it. In the present embodiment, the preset geological model selects a two-dimensional geological model.
[0050] In some embodiments, the server obtains the number of all drilled wells in the target area and the seismic interpretation corresponding to the target area, establishes a well-to-well geological profile based on the number of all drilled wells, the two-dimensional geological model, and the seismic interpretation, and the well-to-well geological profile is used to indicate the geological conditions corresponding to all drilled wells in the target area, wherein the well-to-well geological profile is composed of different geological profiles, for example, the well-to-well geological profile corresponding to the target area A includes geological profile a layer, geological profile b layer, geological profile c layer, and geological profile d layer.
[0051] Optionally, the server can determine the lateral variation characteristics of the target area through the well-to-well geological profile, and draw different histograms or two-dimensional data analysis graphs, which are directly fed back to the terminal, and relevant personnel predict the relevant attributes in the target area based on the feedback results of the server.
[0052] In the present embodiment, the server constructs a velocity model corresponding to the well-to-well geological profile through the acoustic curve, and performs forward modeling on the velocity model corresponding to the target area by using the wavelet convolution method to obtain the forward seismic profile corresponding to the target area.
[0053] In the present embodiment, the server extracts seismic attributes of the target area along the interlayer based on the forward data in the forward seismic profile, and the seismic attributes of the target area are all conventional seismic attributes, including but not limited to amplitude, frequency, phase, energy, waveform, wave impedance, wave velocity, correlation, and ratio.
[0054] In step 203, cross-plot analysis is performed based on the seismic attributes and the igneous rock thickness of the target area to establish a cross-plot of the target area.
[0055] In this embodiment, the server constructs a crossplot of the target region according to the extracted seismic attributes of the target region and the igneous rock thickness at the drilled well points, the crossplot is used to indicate a relationship between an amplitude attribute in the seismic attributes and the igneous rock thickness, and the amplitude attribute can be specifically indicated as a root mean square amplitude attribute.
[0056] Optionally, the server determines a crossplot correlation coefficient based on the crossplot, the crossplot correlation coefficient is used to indicate a correlation degree between the seismic attributes of the target region and the igneous rock thickness.
[0057] In another embodiment, the server can also obtain the logging sensitive parameters of the drilled well from the database, and directly determine the crossplot correlation coefficient based on the logging sensitive parameters and the corresponding interlayer seismic attributes of the target region.
[0058] In step 204, a sensitive seismic attribute set is determined from the seismic attributes in response to the crossplot correlation coefficient corresponding to the crossplot being within a predetermined threshold range.
[0059] In this embodiment, the crossplot includes crossplot points between all seismic attributes corresponding to the target region and the igneous rock thickness, the server determines whether the crossplot correlation coefficient is within a preset threshold range, and determines the sensitive seismic attribute set from the seismic attributes based on the determination result, that is, the sensitive seismic attribute set is determined from the seismic attributes in response to the crossplot correlation coefficient corresponding to the crossplot being within a predetermined threshold range.
[0060] The sensitive seismic attribute set includes seismic attributes having a strong correlation with the igneous rock thickness, that is, the seismic attributes in the sensitive seismic attribute set have an important influence on predicting the igneous rock related reservoir parameters.
[0061] In step 205, a mapping relationship between the igneous rock thickness and the sensitive seismic attribute set is established based on the sensitive seismic attribute set.
[0062] The server establishes the mapping relationship between the sensitive seismic attribute set and the igneous rock thickness, the mapping relationship can be stored in the form of a table or a tuple, and the present application does not limit this.
[0063] Optionally, the server can feed back the table or tuple corresponding to the mapping relationship to the terminal, and further apply it by relevant personnel to predict the igneous rock thickness at the drilled well points of the target region.
[0064] In step 206, a reservoir parameter value of the target region is determined based on the mapping relationship.
[0065] In some embodiments, the server generates reservoir parameter values of the target region according to a mapping relationship between the igneous rock thickness and the sensitive seismic attribute set, the reservoir parameter values being results predicted based on relevant data of drilled wells in the target region, and including but not limited to the igneous rock reservoir thickness. That is, the server predicts the igneous rock reservoir thickness at the drilled well points in the target region based on the device relationship.
[0066] In summary, the attribute prediction method provided in the embodiments of the present application determines a sensitive seismic attribute set with higher correlation in the crossplot correlation coefficients of the seismic attributes of the target region by the well-to-seismic crossplot analysis method based on the logging data and mud logging data of the drilled wells in the existing target region, and completes the prediction of the igneous rock reservoir thickness at the drilled well points according to the sensitive attribute set, effectively implements the spatial distribution of the igneous rock reservoir, and improves the prediction accuracy.
[0067] Please refer to Figure 3 , Figure 3 is a flowchart of the attribute prediction method provided in the embodiments of the present application, which is applied to a server in an implementation environment shown in Figure 1 and includes the following steps.
[0068] Step 301: Obtain logging data and mud logging data of drilled wells in a target region.
[0069] Optionally, the relevant data of the drilled wells are stored in a local terminal or in a database; the relevant data of the drilled wells include but are not limited to logging data, mud logging data, oil testing data, production data, and igneous rock thickness of the drilled wells, wherein the mud logging data is used to indicate the statistics of the wellbore return information of the drilled wells in the drilling process, the logging data is used to measure the physical parameters of the drilled well position by using the physical characteristics after the drilled well reaches the well depth, and the igneous rock thickness is used to indicate the total thickness of the igneous rock at the drilled well point.
[0070] The flow of this step is the same as that of step 201, which will not be repeated here.
[0071] Step 302: Determine a sensitive seismic attribute set corresponding to the drilled wells.
[0072] The server establishes a preset geological model based on the logging data and the mud logging data, which can be a one-dimensional geological model, a two-dimensional geological model, or a three-dimensional geological model, and the present application does not limit this. In the present embodiment, the preset geological model selects a two-dimensional geological model.
[0073] The flow of this step is the same as that of steps 202 to 204, which will not be repeated here.
[0074] Step 303, using a supervised neural network to perform pattern recognition to filter a sensitive seismic attribute subset from the sensitive seismic attribute set.
[0075] Optionally, the server inputs the sensitive seismic attribute set obtained in the above steps into the supervised neural network for recognition, filters the sensitive seismic attribute subset, and takes the sensitive seismic attribute subset as the selected attribute (target attribute / sample attribute) of pattern recognition.
[0076] Optionally, the server takes the sensitive attribute subset as sample data to retrain, and the training process can refer to steps 304 to 306 described below, which are not described in detail here.
[0077] Step 304, based on the sensitive seismic attribute subset and the igneous rock thickness, a spatial relationship is established.
[0078] In the embodiment of the application, the server establishes a spatial relationship between the determined sensitive seismic attribute subset and the igneous rock thickness, which can be embodied in a two-dimensional geological space graph, a three-dimensional geological space graph, etc. The geological space graph established based on the spatial relationship is used to reflect the influence degree of each sensitive seismic attribute subset in the target area on the igneous rock thickness. Optionally, the spatial relationship can also be used to calculate the reservoir parameter value of the target area, so as to achieve the purpose of predicting the igneous rock thickness.
[0079] Step 305, inputting the spatial relationship into the supervised neural network for training to obtain a mapping relationship.
[0080] The well reservoir sensitive parameter of the drilled well is obtained from the database. The well reservoir sensitive parameter can be a parameter set obtained by forward modeling based on the original data of the drilled well, or a parameter set directly determined by a seismic interpretation system, which is not limited in the application.
[0081] The well reservoir sensitive parameter is taken as the output expected value of the supervised neural network, and the sensitive seismic attribute subset in the mapping relationship is converged to obtain a prediction result.
[0082] Step 306, based on the mapping relationship, the reservoir parameter value of the target area is determined.
[0083] Optionally, the server optimizes the prediction parameters in the supervised neural network model based on the prediction result of the supervised neural network model to obtain a prediction model.
[0084] The target area is input into the prediction model to obtain a prediction result corresponding to the target area, and the server takes the prediction result as the reservoir parameter value of the target area, which includes the igneous rock reservoir thickness, and feeds back to the terminal.
[0085] In summary, the attribute prediction method provided in the embodiments of the present application determines a sensitive seismic attribute set with higher correlation in cross-plot correlation coefficients of seismic attributes in a target area through well-seismic cross-plot analysis based on logging data and well logging data of drilled wells in the target area, and predicts the igneous reservoir thickness at the drilled well points according to the sensitive attribute set, effectively implements the spatial distribution of the igneous reservoir, and improves the prediction accuracy.
[0086] In the embodiments, the sensitive seismic attribute set is further identified to obtain a sensitive seismic attribute subset by using a neural network identification model, the sensitive seismic attribute subset is taken as a training sample of the neural network identification model, the prediction result is further converged, and the accuracy of the attribute prediction is ensured.
[0087] Please refer to Figure 4 , Figure 4 is a structural block diagram of an attribute prediction device provided in an embodiment of the present application, and the device includes an acquisition module 401, a determination module 402, and a construction module 403.
[0088] The acquisition module 401 is configured to acquire logging data and well logging data of drilled wells.
[0089] The determination module 402 is configured to determine seismic attributes of a target area where the drilled wells are located based on the logging data and the well logging data.
[0090] The construction module 403 is configured to perform cross-plot analysis based on the seismic attributes and igneous thickness of the target area, establish a cross-plot graph of the target area, and use the cross-plot graph to indicate a relationship graph between amplitude attributes of the drilled wells and the igneous thickness.
[0091] The determination module 402 is further configured to determine a sensitive seismic attribute set from the seismic attributes in response to cross-plot correlation coefficients in the cross-plot graph being within a predetermined threshold range.
[0092] The construction module 403 is further configured to establish a mapping relationship between the igneous thickness and the sensitive seismic attribute set based on the sensitive seismic attribute set.
[0093] The determination module 402 is further configured to determine reservoir parameter values of the target area based on the mapping relationship, and the reservoir parameter values include igneous reservoir thickness.
[0094] In an optional embodiment, as Figure 5 shown, the device further includes:
[0095] The construction module 403 is further configured to establish a preset geological model and a well pair geological profile based on the logging data and the mud logging data, construct a velocity model corresponding to the well pair geological profile through a sound wave curve, and establish a forward seismic profile by forward modeling the velocity model using wavelet convolution.
[0096] The extraction module 404 is configured to extract seismic attributes of the drilled well area along layers based on forward data in the forward seismic profile.
[0097] In an optional embodiment, the cross-correlation coefficient is determined by the interlayer seismic attributes of the drilled well and the logging sensitive parameters of the drilled well.
[0098] In an optional embodiment, the well pair geological profile is further configured to determine a lateral variation feature of geology in the target area.
[0099] In an optional embodiment, as shown in Figure 5 The device further includes:
[0100] The screening module 405 is configured to screen a sensitive seismic attribute subset from the sensitive seismic attribute set by using a supervised neural network for pattern recognition.
[0101] The construction module 403 is further configured to establish a spatial relationship based on the sensitive seismic attribute subset and the igneous rock thickness.
[0102] The determination module 402 is further configured to input the spatial relationship into the supervised neural network for training to obtain the mapping relationship.
[0103] In an optional embodiment, as shown in Figure 5 The device further includes:
[0104] The acquisition module 401 is further configured to acquire an on-well reservoir sensitive parameter of the drilled well.
[0105] The determination module 402 is further configured to converge the mapping relationship by using the on-well reservoir sensitive parameter to obtain a prediction result.
[0106] In an optional embodiment, as shown in Figure 5 The device further includes:
[0107] The prediction module 406 is configured to take the prediction result as the reservoir parameter value of the target area.
[0108] In summary, the attribute prediction device provided by the embodiment of the present application determines a sensitive seismic attribute set with higher correlation in the crossplot correlation coefficient in the seismic attribute of the target area based on the logging data and mud logging data of the drilled well in the existing target area, and predicts the igneous reservoir thickness at the drilled well point according to the sensitive attribute set, effectively implements the spatial distribution of the igneous reservoir, and improves the prediction accuracy.
[0109] Please refer to Figure 6 , Figure 6 The structure schematic diagram of the server provided by an example embodiment of the present application is shown. The server can be Figure 1 The server is shown. Specifically:
[0110] The server 120 includes a central processing unit (CPU) 601, a system memory 604 including a random access memory (RAM) 602 and a read-only memory (ROM) 603, and a system bus 605 connecting the system memory 604 and the central processing unit 601. The server 120 also includes a basic input / output system (I / O system) 606 to facilitate the transfer of information between the various devices within the computer, and a mass storage device 607 for storing an operating system 613, application programs 614, and other program modules 615.
[0111] The basic input / output system 606 includes a display 608 for displaying information and an input device 609 such as a mouse, keyboard, or the like for inputting information by a user. The display 608 and the input device 609 are both connected to the central processing unit 601 through an input / output controller 610 connected to the system bus 605. The basic input / output system 606 can also include the input / output controller 610 for receiving and processing input from a plurality of other devices such as a keyboard, a mouse, or an electronic stylus, etc. Similarly, the input / output controller 610 also provides output to a display screen, a printer, or other types of output devices.
[0112] The mass storage device 607 is connected to the central processing unit 601 through a mass storage controller (not shown) connected to the system bus 605. The mass storage device 607 and its associated computer readable medium provide non-volatile storage for the server 120. That is, the mass storage device 607 can include a computer readable medium (not shown) such as a hard disk or a compact disc read only memory (CD-ROM) drive.
[0113] Without loss of generality, the computer readable medium can include computer storage media and communication media. Computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, erasable programmable read only memory (EPROM, EEPROM), flash memory or other solid state memory technology, CD-ROM, digital versatile disks (DVD), or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices. Of course, computer storage media does not limit to the above-mentioned several kinds. The system memory 604 and the mass storage device 607 mentioned above can be collectively referred to as a memory.
[0114] According to various embodiments of the present application, the server 120 can also run on a remote computer connected to the network through a network connection such as the Internet. That is, the server 120 can be connected to the network 612 through the network interface unit 611 connected to the system bus 605, or can be connected to other types of networks or remote computer systems (not shown) using the network interface unit 611.
[0115] The above-mentioned memory further includes one or more programs, one or more programs are stored in the memory and are configured to be executed by the CPU.
[0116] Embodiments of the present application also provide a computer device including a processor and a memory, the memory storing at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by the processor to implement the attribute prediction method provided by the above-mentioned method embodiments.
[0117] Embodiments of the present application also provide a computer readable storage medium, the computer readable storage medium storing at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by the processor to implement the attribute prediction method provided by the above-mentioned method embodiments.
[0118] The embodiment of the present application further provides a computer program product or computer program, which comprises computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the attribute prediction method in any of the above embodiments.
[0119] Optionally, the computer readable storage medium can include a read only memory (ROM), a random access memory (RAM), a solid state disk (SSD), an optical disk, or the like. The random access memory can include a resistance random access memory (ReRAM) and a dynamic random access memory (DRAM). The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.
[0120] Those skilled in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by hardware, or by a program instructing related hardware to complete, and the program can be stored in a computer readable storage medium. The above-mentioned storage medium can be a read only memory, a magnetic disk or an optical disk.
[0121] The above-mentioned is only the optional embodiment of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims
1. An attribute prediction method characterized by, The method is applied to a computer device and comprises the following steps: Obtaining well logging data and mud logging data of drilled wells in a target area; Establishing a joint well geologic profile based on the well logging data and the mud logging data, the joint well geologic profile being used to indicate corresponding geologic conditions of all drilled wells in the target area, and the joint well geologic profile being composed of different geologic profiles; Constructing a velocity model corresponding to the joint well geologic profile through a sound wave curve; Performing forward modeling on the velocity model by using wavelet convolution to establish a forward seismic profile; Extracting seismic attributes along interlayers based on forward data in the forward seismic profile; Performing crossplot analysis based on the seismic attributes and igneous rock thickness of the target area to establish a crossplot of the target area, the crossplot being used to indicate a relationship between amplitude attributes in the seismic attributes and igneous rock thickness at well points of the drilled wells; Determining a sensitive seismic attribute set from the seismic attributes in response to a crossplot correlation coefficient corresponding to the crossplot being within a predetermined threshold range; Performing pattern recognition by using a supervised neural network to screen a sensitive seismic attribute subset from the sensitive seismic attribute set; Establishing a spatial relationship based on the sensitive seismic attribute subset and the igneous rock thickness; Inputting the spatial relationship into the supervised neural network for training to obtain a mapping relationship, the mapping relationship being used to represent a mapping relationship between the igneous rock thickness and the sensitive seismic attribute subset; Obtaining on-well reservoir sensitive parameters of the drilled wells; Converging the sensitive seismic attribute subset in the mapping relationship by taking the on-well reservoir sensitive parameters as output expected values of the supervised neural network to obtain a prediction result; Optimizing prediction parameters in the supervised neural network based on the prediction result to obtain a prediction model; Inputting the target area into the prediction model to obtain reservoir parameter values of the target area, the reservoir parameter values including igneous rock thickness.
2. The method of claim 1, wherein, The crossplot correlation coefficient is determined by interlayer seismic attributes of the target area and well logging sensitive parameters of the drilled wells.
3. The method according to any one of claims 1 to 2, characterized in that, The joint well geologic profile is also used to determine lateral variation characteristics of geology in the target area.
4. An attribute prediction device characterized by comprising: The device is applied to a computer device and comprises the following steps: An obtaining module is configured to obtain well logging data and mud logging data of drilled wells in a target area; A determining module is configured to establish a joint well geologic profile based on the well logging data and the mud logging data, the joint well geologic profile being used to indicate corresponding geologic conditions of all drilled wells in the target area, and the joint well geologic profile being composed of different geologic profiles; construct a velocity model corresponding to the joint well geologic profile through a sound wave curve; perform forward modeling on the velocity model by using wavelet convolution to establish a forward seismic profile; and extract seismic attributes along interlayers based on forward data in the forward seismic profile; A constructing module is configured to perform crossplot analysis based on the seismic attributes and igneous rock thickness of the target area to establish a crossplot of the target area, the crossplot being used to indicate a relationship between amplitude attributes of the drilled wells and the igneous rock thickness. The determination module is further configured to determine a sensitive seismic attribute set from the seismic attributes in response to a correlation coefficient corresponding to the crossplot being within a predetermined threshold range; The construction module is further configured to filter a sensitive seismic attribute subset from the sensitive seismic attribute set by using a supervised neural network for pattern recognition, to establish a spatial relationship based on the sensitive seismic attribute subset and the igneous rock thickness, to input the spatial relationship into the supervised neural network for training, and to obtain a mapping relationship, which represents a mapping relationship between the igneous rock thickness and the sensitive seismic attribute subset; The determination module is further configured to obtain an on-well reservoir sensitive parameter of the drilled well, to take the on-well reservoir sensitive parameter as an output expected value of the supervised neural network, to perform convergence on the sensitive seismic attribute subset in the mapping relationship to obtain a prediction result, to optimize a prediction parameter in the supervised neural network based on the prediction result to obtain a prediction model, and to input the target region into the prediction model to obtain a reservoir parameter value of the target region, the reservoir parameter value including the igneous rock thickness.
5. A computer device, comprising: The computer device includes a processor and a memory, and the memory stores at least one instruction which is loaded and executed by the processor to implement the attribute prediction method according to any one of claims 1 to 3.
6. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set are loaded and executed by the processor to implement the attribute prediction method according to any one of claims 1 to 3.