Earthquake reservoir prediction result evaluation method

Abstract

The embodiment of the invention relates to the technical field of seismic reservoir prediction, and particularly discloses a seismic reservoir prediction result evaluation method, which comprises the following steps: collecting and integrating historical data of a target seismic reservoir, generating standard acquisition data and a seismic reservoir prediction map, selecting a plurality of verification points, and performing error comparison verification. Geological constraint matching and reservoir simulation analysis are carried out on the seismic reservoir prediction map, and a confidence assessment level is generated and displayed; through collection and integration of historical data, construction of a seismic reservoir prediction map, acquisition of actual drilling data, error comparison verification, geological constraint matching and economic evaluation, comprehensive assessment analysis and generation of a confidence assessment level, a prediction result can be systematically, quantitatively, comprehensively and accurately assessed, and the accuracy of the prediction result is improved. The uncertainty risk of oil-gas exploration decision making is reduced, and the problems of resource waste, low development efficiency and the like are avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of seismic reservoir prediction, and particularly relates to a method for evaluating the results of seismic reservoir prediction. Background Art

[0002] A seismic reservoir is a subsurface geological body identified and described through seismic exploration techniques (such as seismic wave reflection, refraction, etc.) that has the ability to store oil, gas, or fluids. It can reveal the spatial distribution, physical property parameters, and fluid properties of the reservoir through seismic data, providing a key basis for oil and gas exploration and development.

[0003] Seismic reservoir prediction is a process of quantitatively or qualitatively predicting the spatial distribution, physical property parameters (such as porosity, permeability), and fluid properties (such as oil, gas, water) of a reservoir by using the subsurface geological information obtained through seismic exploration techniques (such as seismic wave reflection, refraction, etc.) and combining multi-source data such as geology, logging, and core.

[0004] In the prior art, seismic reservoir prediction, as a key link in oil and gas exploration and development, has been widely applied. However, after completing seismic reservoir prediction, there is usually a lack of a systematic and quantitative evaluation mechanism to comprehensively and accurately evaluate the prediction results, increasing the uncertainty risk of oil and gas exploration decisions and easily causing problems such as resource waste and low development efficiency. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide a method for evaluating the results of seismic reservoir prediction, aiming to solve the problems raised in the background art.

[0006] To achieve the above purpose, the embodiments of the present invention provide the following technical solutions:

[0007] A method for evaluating the results of seismic reservoir prediction, the method specifically includes the following steps:

[0008] Collect and integrate historical data of the target seismic reservoir to generate collected and integrated data, and perform data preprocessing on the collected and integrated data to generate standard acquisition data;

[0009] Select a basic training network, input the standard acquisition data, train and test the basic training network to generate a seismic reservoir prediction map;

[0010] Select multiple verification points, collect actual drilling data, and obtain predicted drilling data through the seismic reservoir prediction map, perform error comparison verification to obtain predicted error data;

[0011] Perform geological constraint matching on the seismic reservoir prediction map to obtain matching anomaly data;

[0012] Perform reservoir simulation analysis on the seismic reservoir prediction map, obtain simulated production data, and obtain actual production data for economic evaluation to obtain economic evaluation data;

[0013] Perform comprehensive analysis on the prediction error data, the matching anomaly data, and the economic evaluation data to generate and display a confidence evaluation level.

[0014] As a further limitation of the technical solution of the embodiment of the present invention, the collection and integration of historical data for the target seismic reservoir, generating collection and integration data, and performing data preprocessing on the collection and integration data to generate standard acquisition data specifically include the following steps:

[0015] Determine the target seismic reservoir;

[0016] Collect historical seismic data, historical drilling data, and geological data of the target seismic reservoir;

[0017] Integrate the historical seismic data, the historical drilling data, and the geological data to generate collection and integration data;

[0018] Perform data preprocessing on the collection and integration data to generate standard acquisition data.

[0019] As a further limitation of the technical solution of the embodiment of the present invention, the data preprocessing of the collection and integration data to generate standard acquisition data specifically includes the following steps:

[0020] Perform time / depth alignment on the collection and integration data;

[0021] Perform noise identification and filtering processing on the collection and integration data;

[0022] Perform missing value identification and filling on the collection and integration data;

[0023] Generate standard acquisition data.

[0024] As a further limitation of the technical solution of the embodiment of the present invention, the selection of a basic training network, inputting the standard acquisition data, and training and testing the basic training network to generate a seismic reservoir prediction map specifically include the following steps:

[0025] Select a basic training network;

[0026] Input the standard acquisition data and divide it into a training set and a test set;

[0027] Through the training set and the test set, train and test the basic training network to generate a seismic reservoir prediction map, and the seismic reservoir prediction map includes a porosity map, a fluid type map, and a rock physics model.

[0028] As a further limitation of the technical solution of the embodiment of the present invention, the expression of the rock physics modeling is:

[0029] ;

[0030] wherein, is the bulk modulus of the rock, is the bulk modulus of the dry rock, is the bulk modulus of the mineral, is the porosity, is the bulk modulus of the fluid.

[0031] As a further limitation of the technical solution of the embodiment of the present invention, the steps of selecting a plurality of verification points, collecting actual drilling data, and obtaining predicted drilling data through the seismic reservoir prediction map, and performing error comparison verification to obtain predicted error data specifically include the following steps:

[0032] Perform verification planning and select a plurality of verification points;

[0033] Perform actual drilling collection at a plurality of the verification points to obtain actual drilling data;

[0034] In the seismic reservoir prediction map, perform drilling prediction analysis on a plurality of the verification points to obtain predicted drilling data;

[0035] Compare and verify the predicted drilling data with the actual drilling data to obtain predicted error data.

[0036] As a further limitation of the technical solution of the embodiment of the present invention, the steps of comparing and verifying the predicted drilling data with the actual drilling data to obtain predicted error data specifically include the following steps:

[0037] Compare the predicted drilling data with the actual drilling data and calculate the absolute error;

[0038] Compare the predicted drilling data with the actual drilling data and calculate the relative error;

[0039] Compare the predicted drilling data with the actual drilling data and calculate the root mean square error;

[0040] Perform comprehensive statistics on the absolute error, the relative error, and the root mean square error to generate predicted error data.

[0041] As a further limitation of the technical solution of the embodiment of the present invention, the steps of performing geological constraint matching on the seismic reservoir prediction map to obtain matching anomaly data specifically include the following steps:

[0042] Match the relevant actual geological model according to the seismic reservoir prediction map;

[0043] Based on the actual geological model, perform sedimentary facies matching on the seismic reservoir prediction map and record the sedimentary facies matching data;

[0044] Based on the actual geological model, perform fault constraint analysis on the seismic reservoir prediction map and record the fault constraint analysis data;

[0045] Comprehensively analyze the sedimentary facies matching data and the fault constraint analysis data to conduct anomaly investigation and record the matching anomaly data.

[0046] As a further limitation of the technical solution of the embodiment of the present invention, the reservoir simulation analysis of the seismic reservoir prediction map, obtaining the simulated production data, obtaining the actual production data, and performing economic evaluation, and obtaining the economic evaluation data specifically include the following steps:

[0047] Input reservoir simulation parameters;

[0048] According to the reservoir simulation parameters, perform reservoir simulation analysis on the seismic reservoir prediction map to obtain the simulated production data;

[0049] Obtain the actual production data;

[0050] Based on the actual production data, perform economic verification evaluation on the simulated production data to obtain the economic evaluation data.

[0051] As a further limitation of the technical solution of the embodiment of the present invention, the comprehensive analysis of the prediction error data, the matching anomaly data and the economic evaluation data, generating a confidence evaluation level and displaying it specifically include the following steps:

[0052] Conduct evaluation planning on the prediction error data, the matching anomaly data and the economic evaluation data to obtain the evaluation weight data;

[0053] According to the evaluation weight data, comprehensively evaluate the prediction error data, the matching anomaly data and the economic evaluation data to generate a comprehensive evaluation value;

[0054] According to the comprehensive evaluation value, match the corresponding confidence evaluation level;

[0055] Display the confidence evaluation level.

[0056] Compared with the prior art, the beneficial effects of the present invention are:

[0057] In the embodiments of the present invention, historical data of the target seismic reservoir is collected and integrated to generate standard acquisition data; a seismic reservoir prediction map is generated; multiple verification points are selected for error comparison and verification; geological constraint matching is performed on the seismic reservoir prediction map; reservoir simulation analysis is performed on the seismic reservoir prediction map; and a confidence evaluation level is generated and displayed. It can collect and integrate historical data, construct a seismic reservoir prediction map, collect actual drilling data, perform error comparison and verification, geological constraint matching and economic evaluation, and conduct comprehensive evaluation and analysis to generate a confidence evaluation level. It can comprehensively and accurately evaluate the prediction results in a systematic and quantitative manner, reduce the uncertainty risk of oil and gas exploration decisions, and avoid problems such as resource waste and low development efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0059] Figure 1 The flowchart of the method provided by the embodiments of the present invention is shown.

[0060] Figure 2 The flowchart of the collection and integration of historical data in the method provided by the embodiments of the present invention is shown.

[0061] Figure 3 The flowchart of generating standard acquisition data in the method provided by the embodiments of the present invention is shown.

[0062] Figure 4 The flowchart of generating a seismic reservoir prediction map in the method provided by the embodiments of the present invention is shown.

[0063] Figure 5 The flowchart of performing error comparison and verification in the method provided by the embodiments of the present invention is shown.

[0064] Figure 6 The flowchart of obtaining prediction error data in the method provided by the embodiments of the present invention is shown.

[0065] Figure 7 The flowchart of performing geological constraint matching in the method provided by the embodiments of the present invention is shown.

[0066] Figure 8 The flowchart of performing reservoir simulation analysis in the method provided by the embodiments of the present invention is shown.

[0067] Figure 9 The flowchart of generating a confidence evaluation level in the method provided by the embodiments of the present invention is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0068] In order to make the objectives, technical solutions, and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0069] It can be understood that in the prior art, seismic reservoir prediction, as a key link in oil and gas exploration and development, has been widely applied. However, after completing seismic reservoir prediction, there is usually a lack of a systematic and quantitative evaluation mechanism to comprehensively and accurately evaluate the prediction results, which increases the uncertainty risk of oil and gas exploration decisions and is also prone to problems such as resource waste and low development efficiency.

[0070] To solve the above problems, in the embodiments of the present invention, historical data of the target seismic reservoir is collected and integrated to generate collected and integrated data, and the collected and integrated data is preprocessed to generate standard acquisition data; a basic training network is selected, the standard acquisition data is input, the basic training network is trained and tested to generate a seismic reservoir prediction map; multiple verification points are selected, actual drilling data is collected, and through the seismic reservoir prediction map, predicted drilling data is obtained, error comparison verification is performed to obtain predicted error data; geological constraint matching is performed on the seismic reservoir prediction map to obtain matching anomaly data; reservoir simulation analysis is performed on the seismic reservoir prediction map to obtain simulated production data, and actual production data is obtained for economic evaluation to obtain economic evaluation data; comprehensive analysis is performed on the predicted error data, matching anomaly data, and economic evaluation data to generate a confidence evaluation level and display it. It can collect and integrate historical data, construct a seismic reservoir prediction map, collect actual drilling data, perform error comparison verification, geological constraint matching, and economic evaluation, and perform comprehensive evaluation and analysis to generate a confidence evaluation level, which can systematically and quantitatively evaluate the prediction results comprehensively and accurately, reduce the uncertainty risk of oil and gas exploration decisions, and avoid problems such as resource waste and low development efficiency.

[0071] Figure 1 The flowchart of the method provided by the embodiments of the present invention is shown.

[0072] Specifically, a method for evaluating the result of seismic reservoir prediction, the method specifically includes the following steps:

[0073] Step S101, collect and integrate historical data of the target seismic reservoir to generate collected and integrated data, and preprocess the collected and integrated data to generate standard acquisition data.

[0074] In an embodiment of the present invention, by determining a target seismic reservoir, historical seismic data, historical drilling data, and geological data of the target seismic reservoir are collected. Among them, the historical seismic data includes pre-stack seismic data, post-stack seismic data, etc., the historical drilling data includes logging curve data, porosity data, permeability data, etc., and the geological data includes fault model data, regional tectonic data, sedimentary facies belt distribution data, etc. Then, the historical seismic data, historical drilling data, and geological data are integrated to generate collected and integrated data. Furthermore, time / depth alignment (bringing the historical seismic data and historical drilling data to the same time / depth domain), noise identification and filtering processing (which can be FK filtering or wavelet transform), and missing identification and filling are performed on the collected and integrated data to implement preprocessing of the collected and integrated data and generate standard acquisition data.

[0075] Specifically, Figure 2 FIG. shows the flow chart of the collection and integration of historical data in the method provided by the embodiment of the present invention.

[0076] Among them, in the preferred embodiment provided by the present invention, the collection and integration of historical data for the target seismic reservoir, generating collected and integrated data, and performing data preprocessing on the collected and integrated data to generate standard acquisition data specifically include the following steps:

[0077] Step S1011, determine the target seismic reservoir;

[0078] Step S1012, collect the historical seismic data, historical drilling data, and geological data of the target seismic reservoir;

[0079] Step S1013, integrate the historical seismic data, the historical drilling data, and the geological data to generate collected and integrated data;

[0080] Step S1014, perform data preprocessing on the collected and integrated data to generate standard acquisition data.

[0081] Specifically, Figure 3 FIG. shows the flow chart of generating standard acquisition data in the method provided by the embodiment of the present invention.

[0082] Among them, in the preferred embodiment provided by the present invention, the data preprocessing of the collected and integrated data to generate standard acquisition data specifically includes the following steps:

[0083] Step S10141, perform time / depth alignment on the collected and integrated data;

[0084] Step S10142, perform noise identification and filtering processing on the collected and integrated data;

[0085] Step S10143, perform missing value identification and filling on the collected and integrated data;

[0086] Step S10144, generate standard acquisition data.

[0087] Furthermore, the evaluation method for the seismic reservoir prediction result further includes the following steps:

[0088] Step S102, select a basic training network, input the standard acquisition data, train and test the basic training network, and generate a seismic reservoir prediction map.

[0089] In the embodiment of the present invention, a basic training network (random forest or convolutional neural network) is selected, and the standard acquisition data is input. By dividing the standard acquisition data, a training set and a test set are obtained. Then, through the training set and the test set, the basic training network is trained and tested to generate a seismic reservoir prediction map including a porosity map, a fluid type map, and rock physics modeling. In the seismic reservoir prediction map, the parameter levels are marked with color gradients or contour lines. Specifically, the expression of rock physics modeling is:

[0090] ;

[0091] where, is the rock bulk modulus, is the dry rock bulk modulus, is the mineral bulk modulus, is the porosity, is the fluid bulk modulus.

[0092] Specifically, Figure 4 shows the flowchart of generating a seismic reservoir prediction map in the method provided by the embodiment of the present invention.

[0093] Among them, in the preferred embodiment provided by the present invention, the steps of selecting the basic training network, inputting the standard acquisition data, training and testing the basic training network, and generating a seismic reservoir prediction map specifically include the following steps:

[0094] Step S1021, select a basic training network;

[0095] Step S1022, input the standard acquisition data and divide it into a training set and a test set;

[0096] Step S1023, through the training set and the test set, train and test the basic training network to generate a seismic reservoir prediction map, and the seismic reservoir prediction map includes a porosity map, a fluid type map, and rock physics modeling.

[0097] Furthermore, the evaluation method for the seismic reservoir prediction result further includes the following steps:

[0098] Step S103: Select multiple verification points, collect actual drilling data, and obtain predicted drilling data through the seismic reservoir prediction map for error comparison verification to obtain predicted error data.

[0099] In the embodiment of the present invention, based on the seismic reservoir prediction map, a verification plan is carried out. Multiple verification points are selected, actual drilling is carried out at multiple verification points to obtain actual drilling data, and in the seismic reservoir prediction map, drilling prediction analysis is carried out on multiple verification points to obtain predicted drilling data. By comparing the error between the predicted drilling data and the actual drilling data, the absolute error, relative error, and root mean square error are calculated, and then the absolute error, relative error, and root mean square error are comprehensively statistically analyzed to generate predicted error data, realizing the quantification of the deviation between the prediction and the actual reservoir parameters.

[0100] Specifically, Figure 5 Fig. shows the flowchart of error comparison verification in the method provided by the embodiment of the present invention.

[0101] Among them, in the preferred embodiment provided by the present invention, the steps of selecting multiple verification points, collecting actual drilling data, obtaining predicted drilling data through the seismic reservoir prediction map for error comparison verification to obtain predicted error data specifically include the following steps:

[0102] Step S1031: Carry out a verification plan and select multiple verification points;

[0103] Step S1032: Carry out actual drilling at multiple verification points to obtain actual drilling data;

[0104] Step S1033: In the seismic reservoir prediction map, carry out drilling prediction analysis on multiple verification points to obtain predicted drilling data;

[0105] Step S1034: Compare the error between the predicted drilling data and the actual drilling data for verification to obtain predicted error data.

[0106] Specifically, Figure 6 Fig. shows the flowchart of obtaining predicted error data in the method provided by the embodiment of the present invention.

[0107] Among them, in the preferred embodiment provided by the present invention, the steps of comparing the error between the predicted drilling data and the actual drilling data for verification to obtain predicted error data specifically include the following steps:

[0108] Step S10341: Compare the predicted drilling data with the actual drilling data and calculate the absolute error;

[0109] Step S10342: Compare the predicted drilling data with the actual drilling data and calculate the relative error;

[0110] Step S10343: Compare the predicted drilling data with the actual drilling data and calculate the root mean square error;

[0111] Step S10344: Conduct comprehensive statistics on the absolute error, the relative error, and the root mean square error to generate prediction error data.

[0112] Furthermore, the method for evaluating the seismic reservoir prediction result further includes the following steps:

[0113] Step S104: Perform geological constraint matching on the seismic reservoir prediction map to obtain matching anomaly data.

[0114] In an embodiment of the present invention, according to the seismic reservoir prediction map, match the relevant actual geological model, and then based on the actual geological model, perform sedimentary facies matching on the seismic reservoir prediction map, record the sedimentary facies matching data, and based on the actual geological model, perform fault constraint analysis on the seismic reservoir prediction map, record the fault constraint analysis data. Furthermore, comprehensively analyze the sedimentary facies matching data and the fault constraint analysis data to conduct anomaly investigation, record the matching anomaly data, and verify whether the prediction result conforms to geological laws.

[0115] Specifically, Figure 7 The flowchart of performing geological constraint matching in the method provided by the embodiment of the present invention is shown.

[0116] Among them, in the preferred embodiment provided by the present invention, the step of performing geological constraint matching on the seismic reservoir prediction map to obtain matching anomaly data specifically includes the following steps:

[0117] Step S1041: According to the seismic reservoir prediction map, match the relevant actual geological model;

[0118] Step S1042: Based on the actual geological model, perform sedimentary facies matching on the seismic reservoir prediction map and record the sedimentary facies matching data;

[0119] Step S1043: Based on the actual geological model, perform fault constraint analysis on the seismic reservoir prediction map and record the fault constraint analysis data;

[0120] Step S1044: Comprehensively analyze the sedimentary facies matching data and the fault constraint analysis data to conduct anomaly investigation and record the matching anomaly data.

[0121] Furthermore, the method for evaluating the seismic reservoir prediction result further includes the following steps:

[0122] Step S105: Conduct reservoir simulation analysis on the seismic reservoir prediction map, obtain simulated production data, and obtain actual production data for economic evaluation to acquire economic evaluation data.

[0123] In an embodiment of the present invention, by inputting reservoir simulation parameters, and then based on the reservoir simulation parameters, conducting reservoir simulation analysis on the seismic reservoir prediction map to obtain simulated production data, and obtaining actual production data. Taking the actual production data as the standard, conducting economic verification evaluation on the simulated production data to obtain economic evaluation data, thereby realizing the verification analysis of economy.

[0124] Specifically, Figure 8 shows the flowchart of reservoir simulation analysis in the method provided by the embodiment of the present invention.

[0125] Among them, in the preferred embodiment provided by the present invention, the steps of conducting reservoir simulation analysis on the seismic reservoir prediction map, obtaining simulated production data, obtaining actual production data, conducting economic evaluation, and obtaining economic evaluation data specifically include the following steps:

[0126] Step S1051: Input reservoir simulation parameters;

[0127] Step S1052: Based on the reservoir simulation parameters, conduct reservoir simulation analysis on the seismic reservoir prediction map to obtain simulated production data;

[0128] Step S1053: Obtain actual production data;

[0129] Step S1054: Based on the actual production data, conduct economic verification evaluation on the simulated production data to obtain economic evaluation data.

[0130] Furthermore, the evaluation method for the seismic reservoir prediction result further includes the following steps:

[0131] Step S106: Conduct comprehensive analysis on the prediction error data, the matching anomaly data, and the economic evaluation data to generate and display a confidence evaluation level.

[0132] In an embodiment of the present invention, conduct evaluation planning on the prediction error data, the matching anomaly data, and the economic evaluation data to obtain evaluation weight data. Then, according to the evaluation weight data, conduct comprehensive evaluation on the prediction error data, the matching anomaly data, and the economic evaluation data to generate a comprehensive evaluation value. In a preset evaluation level table, match the corresponding confidence evaluation level according to the comprehensive evaluation value, and visually display the confidence evaluation level.

[0133] Specifically, Figure 9 shows the flowchart of generating a confidence evaluation level in the method provided by the embodiment of the present invention.

[0134] Among them, in the preferred embodiment provided by the present invention, the comprehensive analysis of the prediction error data, the matching anomaly data, and the economic evaluation data to generate a confidence evaluation level and display it specifically includes the following steps:

[0135] Step S1061: Perform an evaluation plan on the prediction error data, the matching anomaly data, and the economic evaluation data to obtain evaluation weight data;

[0136] Step S1062: According to the evaluation weight data, comprehensively evaluate the prediction error data, the matching anomaly data, and the economic evaluation data to generate a comprehensive evaluation value;

[0137] Step S1063: Match the corresponding confidence evaluation level according to the comprehensive evaluation value;

[0138] Step S1064: Display the confidence evaluation level.

[0139] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps does not have a strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages do not necessarily have to be executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages does not necessarily have to be sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0140] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0141] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0142] The above embodiments only represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

[0143] The above is only the preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An evaluation method for the prediction results of seismic reservoirs, characterized in that, The method specifically includes the following steps: Collect and integrate historical data of the target seismic reservoir to generate collected and integrated data, and perform data preprocessing on the collected and integrated data to generate standard acquisition data; Select a basic training network, input the standard acquisition data, train and test the basic training network to generate a seismic reservoir prediction map; Select multiple verification points, collect actual drilling data, and obtain predicted drilling data through the seismic reservoir prediction map, perform error comparison verification to obtain predicted error data; Perform geological constraint matching on the seismic reservoir prediction map to obtain matching anomaly data; Perform reservoir simulation analysis on the seismic reservoir prediction map to obtain simulated production data, and obtain actual production data, perform economic evaluation to obtain economic evaluation data; Comprehensively analyze the predicted error data, the matching anomaly data, and the economic evaluation data to generate a confidence evaluation level and display it.

2. The evaluation method of the seismic reservoir prediction result according to claim 1, characterized in that The collection and integration of historical data of the target seismic reservoir to generate collected and integrated data, and the data preprocessing of the collected and integrated data to generate standard acquisition data specifically include the following steps: Determine the target seismic reservoir; Collect historical seismic data, historical drilling data, and geological data of the target seismic reservoir; Integrate the historical seismic data, the historical drilling data, and the geological data to generate collected and integrated data; Perform data preprocessing on the collected and integrated data to generate standard acquisition data.

3. The evaluation method of the seismic reservoir prediction result according to claim 2, characterized in that The data preprocessing of the collected and integrated data to generate standard acquisition data specifically includes the following steps: Perform time / depth alignment on the collected and integrated data; Perform noise identification and filtering on the collected and integrated data; Perform missing identification and filling on the collected and integrated data; Generate standard acquisition data.

4. The evaluation method for the prediction result of seismic reservoirs according to claim 1, characterized in that, The selection of the basic training network, input of the standard acquisition data, training and testing of the basic training network to generate a seismic reservoir prediction map specifically includes the following steps: Select a basic training network; Input the standard acquisition data and divide it into a training set and a test set; Train and test the basic training network through the training set and the test set to generate a seismic reservoir prediction map, and the seismic reservoir prediction map includes a porosity map, a fluid type map, and rock physics modeling.

5. The evaluation method of the seismic reservoir prediction result according to claim 4, wherein, The expression of the rock physics modeling is: ； Among them, is the bulk modulus of rock, is the bulk modulus of dry rock, is the bulk modulus of ore minerals, is the porosity, is the bulk modulus of fluid.

6. The evaluation method of the seismic reservoir prediction result according to claim 1, characterized in that The selection of multiple verification points, collection of actual drilling data, and obtaining of predicted drilling data through the seismic reservoir prediction map, performing error comparison verification to obtain predicted error data specifically includes the following steps: Conduct a verification plan and select multiple verification points; Perform actual drilling acquisition at multiple verification points to obtain actual drilling data; In the seismic reservoir prediction map, perform drilling prediction analysis on multiple verification points to obtain predicted drilling data; Compare and verify the predicted drilling data with the actual drilling data to obtain predicted error data.

7. The evaluation method of the seismic reservoir prediction result according to claim 6, characterized in that, The comparison and verification of the predicted drilling data with the actual drilling data to obtain predicted error data specifically includes the following steps: Compare the predicted drilling data with the actual drilling data and calculate the absolute error; Compare the predicted drilling data with the actual drilling data and calculate the relative error; Compare the predicted drilling data with the actual drilling data and calculate the root mean square error; Conduct a comprehensive statistics on the absolute error, the relative error and the root mean square error to generate prediction error data.

8. The evaluation method of the seismic reservoir prediction result according to claim 1, characterized in that The geological constraint matching of the seismic reservoir prediction map to obtain matching anomaly data specifically includes the following steps: Match the relevant actual geological model according to the seismic reservoir prediction map; Based on the actual geological model, conduct sedimentary facies matching on the seismic reservoir prediction map and record the sedimentary facies matching data; Based on the actual geological model, conduct fault constraint analysis on the seismic reservoir prediction map and record the fault constraint analysis data; Comprehensively analyze the sedimentary facies matching data and the fault constraint analysis data, conduct anomaly investigation and record the matching anomaly data.

9. The evaluation method of the seismic reservoir prediction result according to claim 1, characterized in that The reservoir simulation analysis of the seismic reservoir prediction map to obtain simulated production data, obtain actual production data, conduct economic evaluation, and obtain economic evaluation data specifically includes the following steps: Input reservoir simulation parameters; Based on the reservoir simulation parameters, conduct reservoir simulation analysis on the seismic reservoir prediction map to obtain simulated production data; Obtain actual production data; Based on the actual production data, conduct economic verification evaluation on the simulated production data to obtain economic evaluation data.

10. The evaluation method of the seismic reservoir prediction result according to claim 1, characterized in that, The comprehensive analysis of the prediction error data, the matching anomaly data and the economic evaluation data to generate a confidence evaluation level and display it specifically includes the following steps: Conduct an evaluation plan on the prediction error data, the matching anomaly data and the economic evaluation data to obtain evaluation weight data; According to the evaluation weight data, conduct a comprehensive evaluation on the prediction error data, the matching anomaly data and the economic evaluation data to generate a comprehensive evaluation value; Match the corresponding confidence evaluation level according to the comprehensive evaluation value; Display the confidence evaluation level.

Images