Reservoir dessert identification method

Abstract

The invention provides a reservoir dessert identification method, which comprises the following steps of: S1, dividing reservoir dessert types according to a fracturing result and a production result monitored by an optical fiber outside a pipe; s2, generating a depth data set of rock mechanics by using the drilling data; s3, calibrating a data set of dessert types, logging characteristics and drilling rock breaking characteristics at perforation positions of the horizontal well, and establishing an oil and gas dessert reservoir identification model of the research area through clustering analysis; and S4, inputting the well drilling data and the well logging data into the research area oil and gas sweet spot reservoir identification model, and outputting a sweet spot profile combining the well drilling rock breaking data and the well logging data. According to the invention, the problem of low accuracy of a dessert identification method in the prior art is solved.

Description

Technical Field

[0001] The invention relates to the technical field of oil production engineering, and in particular to a method for identifying sweet spots in a reservoir. Background Art

[0002] Fracturing design is the core of hydraulic fracturing. Accurately identifying the sweet spots of reservoir transformation and matching fractures with reservoirs are the keys to increasing production through fracturing. An existing solution uses a self-developed computing engine to form a weighted OmniLog profile (i.e., sweet spot profile) and mass spectrometry input, and uses the sweet spot profile and drilling specific energy data to establish a well data set. A neural network and optimization algorithm are used to establish a mapping between production capacity and the data set. Through data-driven optimization of the horizontal well perforation cluster location, production capacity prediction, and completion parameters, field tests were conducted on 30 wells in six shale basins, with an average production increase of 27% over the 78 unoptimized wells.

[0003] However, the current sweet spot identification method is based solely on logging data to draw geostress profiles, calculate engineering quality, and form comprehensive evaluation results. Since the data source relies solely on logging curves, it inevitably causes problems such as low vertical resolution (0.125m), errors in rock mechanics parameters (dynamic calculation data), and insufficient dependence of oil and gas content on electrical parameters, making the final results inaccurate and unreliable. Summary of the invention

[0004] The main purpose of the present invention is to provide a reservoir sweet spot identification method to solve the problem of low accuracy of the sweet spot identification method in the prior art.

[0005] In order to achieve the above-mentioned purpose, the present invention provides a reservoir sweet spot identification method, comprising: step S1, dividing the reservoir sweet spot type according to the fracturing results and production results monitored by the optical fiber outside the pipe; step S2, generating a rock mechanics depth data set using drilling data; step S3, calibrating the sweet spot type, logging characteristics and drilling rock breaking characteristic data set of the horizontal well perforation position, and establishing an oil and gas sweet spot reservoir identification model in the study area through cluster analysis; step S4, inputting the drilling data and logging data into the oil and gas sweet spot reservoir identification model in the study area, and outputting a sweet spot profile combining the drilling rock breaking data and the logging data.

[0006] Furthermore, the reservoir sweet spot identification method also includes: the drilling data includes at least one of the drill bit type, drilling torque, drilling fluid density, rotation speed, drilling speed, and mechanical bit pressure.

[0007] Furthermore, the reservoir sweet spot identification method also includes: rock mechanics including rock brittleness and compressive strength.

[0008] Further, step S1 includes: step S11, deploying dual-mode optical fiber outside the casing in the horizontal well; step S12, classifying the reservoir compressibility type F according to the fracturing monitoring result of the dual-mode optical fiber outside the casing, the classification standard of the reservoir compressibility type F is: the reservoir that is not opened during the fracturing process is not compressible, and the compressibility of the fractured layer section is divided into 1-n levels from good to poor according to the liquid injection volume, and the value is inversely proportional to the compressibility; step S13, classifying the reservoir potential type Q according to the production monitoring result of the dual-mode optical fiber outside the casing, the classification standard of the reservoir potential type Q is: the reservoir that has no liquid output during the entire production process is no potential, and the produced reservoir is divided into 1-m levels from high to low according to the oil production or gas production, and the value is inversely proportional to the potential; step S14, classifying the reservoir sweet spot type according to the reservoir compressibility type F and the reservoir potential type Q.

[0009] Further, in step S14, the calculation formula for dividing the reservoir sweet spot type according to the reservoir compressibility type F and the reservoir potential type Q is as follows: Let k = max(m, n), and establish a k-order sweet spot matrix of reservoir compressibility and reservoir potential coupling:

[0010]

[0011] If m≠n occurs, a blank sequence is added to the sweet spot matrix;

[0012] The dessert combination on the diagonal of the coupled dessert matrix is ​​classified as a dessert type, T 11 For the best quality dessert type, T 12 and T 21 For the second-class dessert type, T 13 , T 22 and T 31 For the third premium dessert type... and so on, T mn This is the worst dessert type, and there are a total of 2k-1 dessert types.

[0013] Further, step S2 includes: step S21, calculating the drilling pressure, torque, rotation speed and hydraulic energy of the bottom hole data according to the drilling data, the drilling data including the drill bit type, drilling torque, drilling fluid density, rotation speed, drilling speed and mechanical drilling pressure; step S22, using the calculated drilling pressure, torque, rotation speed and hydraulic energy of the bottom hole data, combined with the first drill bit data to calculate the rock brittleness; step S23, using the calculated drilling pressure, torque, rotation speed and hydraulic energy of the bottom hole data, combined with the second drill bit data to calculate the rock compressive strength; step S24, converting the second point data in the time domain into depth data, and performing depth correction; step S25, normalizing all the obtained data, and interpolating the non-drilling process, the same well depth, and the null value data; step S26, establishing a depth data set of brittleness index and compressive strength that increases with the well depth and is interval by a predetermined value.

[0014] Further, the first drill bit data includes the drill bit diameter, and the second drill bit data includes the drill bit nozzle flow rate and nozzle size, and the predetermined value is 0.01-0.05 meters.

[0015] Furthermore, in step S23, the calculation formula of rock compressive strength is as follows:

[0016]

[0017] Where CCS is the rock compressive strength, unit: MPa; P e is the effective drilling pressure, unit is kN; A b is the cross-sectional area of ​​the drill bit, in mm 2 ; N is the speed, unit RPM; T e is the effective torque, unit is kN·m; V e It is the effective mechanical drilling speed, in m / h.

[0018] Further, step S3 includes: step S31, calibrating the logging feature data set of the horizontal well perforation position, the logging feature data set including at least one of thickness, interpreted permeability, acoustic wave time difference, resistivity, natural gamma, total organic carbon, porosity, oil or gas saturation; step S32, calibrating the drilling sweet spot feature data set corresponding to the horizontal well perforation position, the drilling sweet spot feature data set including brittleness index and compressive strength; step S33, establishing a parameter sample library of the horizontal well perforation position and the reservoir sweet spot type, the logging feature data set, and the drilling sweet spot feature data set, which is divided into no more than 2K-1 Clustering, where K is the number of clusters, measures the similarity between sample points based on Euclidean geometric distance, so that the samples in the clustering reach a predetermined similarity; step S34, using the sum of squared errors as the criterion function, and selecting the optimal clustering center by traversing all sample points to determine the sweet spot type to which the sample belongs; step S35, classifying the classified data into the category of the clustering center corresponding to the minimum square value, and establishing a neural network model; step S36, collecting horizontal well data for deploying external optical fiber monitoring, and training the neural network model to obtain the oil and gas sweet spot reservoir identification model in the study area.

[0019] Furthermore, in step S34, the calculation formula of the error square sum is:

[0020]

[0021] Where SSE is the sum of squared errors; n j is the number of samples in the jth cluster; μ j is the jth cluster center point; x i is the sample point; K is the number of clusters.

[0022] By applying the technical solution of the present invention, the shortcomings of conventional sweet spot identification methods, which rely only on logging curves, have low vertical resolution, large errors in rock mechanics parameters, and cannot be displayed quantitatively, are changed. A sweet spot identification method that is combined with drilling and rock breaking data and is in line with reality, has high resolution, and is quantitative is established. By combining drilling and rock breaking data, the data sources for sweet spot identification are enriched, and the vertical resolution reaches the decimeter level. By combining the monitoring data and knowledge of the optical fiber outside the pipe, the accuracy of sweet spot identification is improved by more than 15%, and the full utilization of the reservoir sweet spots is achieved, the fracture control reserves are increased, and the cumulative production of a single well is greatly increased by more than 10% while reducing the operating cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings constituting a part of the present application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0024] Figure 1 A flow chart showing a method for identifying a reservoir sweet spot according to the present invention is shown;

[0025] Figure 2 A flow chart of step S1 is shown;

[0026] Figure 3 A flow chart of step S2 is shown;

[0027] Figure 4 A flow chart of step S3 is shown. DETAILED DESCRIPTION

[0028] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0029] It should be noted that, unless otherwise specified, all technical and scientific terms used in this application have the same meanings as commonly understood by ordinary technicians in the technical field to which this application belongs.

[0030] In the present invention, unless otherwise specified, the directional words used, such as "up, down, top, bottom", usually refer to the directions shown in the drawings, or to the components themselves in the vertical, perpendicular or gravity directions; similarly, for ease of understanding and description, "inside and outside" refer to the inside and outside relative to the outline of each component itself, but the above-mentioned directional words are not used to limit the present invention.

[0031] In order to solve the problem of low accuracy of the sweet spot identification method in the prior art, the present invention provides a reservoir sweet spot identification method.

[0032] like Figures 1 to 4A reservoir sweet spot identification method shown includes: step S1, dividing the reservoir sweet spot type according to the fracturing results and production results monitored by the optical fiber outside the pipe; step S2, using the drilling data to generate a rock mechanics depth data set; step S3, calibrating the sweet spot type, logging characteristics and drilling rock breaking characteristic data set of the horizontal well perforation position, and establishing an oil and gas sweet spot reservoir identification model in the study area through cluster analysis; step S4, inputting the drilling data and logging data into the oil and gas sweet spot reservoir identification model in the study area, and outputting a sweet spot profile combining the drilling rock breaking data and the logging data.

[0033] The above method of this embodiment changes the shortcomings of conventional sweet spot identification methods that only rely on logging curves, have low vertical resolution, large errors in rock mechanics parameters, and cannot be displayed quantitatively, and establishes a sweet spot identification method that is combined with drilling and rock breaking data, is in line with reality, has high resolution, and is quantitative. By combining drilling and rock breaking data, the data source for sweet spot identification is enriched, and the vertical resolution reaches the decimeter level. By combining the monitoring data and knowledge of the optical fiber outside the pipe, the accuracy of sweet spot identification is improved by more than 15%, the full utilization of the reservoir sweet spots is achieved, the fracture control reserves are increased, and the cumulative production of a single well is greatly increased by more than 10% while reducing the operating cost.

[0034] The reservoir sweet spot identification method of this embodiment is mainly suitable for the sweet spot identification and optimization of perforation positions in horizontal wells, directional wells and highly deviated wells of oil and gas wells.

[0035] In this embodiment, the reservoir sweet spot identification method further includes: the drilling data includes at least one of the drill bit type, drilling torque, drilling fluid density, rotation speed, drilling speed, and mechanical drilling pressure. The drilling data of this embodiment includes drill bit type, drilling torque, drilling fluid density, rotation speed, drilling speed, and mechanical drilling pressure. Similarly, the reservoir sweet spot identification method further includes: the rock mechanics includes rock brittleness and compressive strength. Of course, the above data can also be supplemented with other relevant data as needed.

[0036] Based on the existing sweet spot identification method, this embodiment expands the data source for sweet spot identification. Considering that if drilling data such as high vertical resolution and drilling specific energy that reflects the brittle characteristics of rocks can be added, it will be of great significance to the accuracy and resolution of sweet spot identification. However, the implementation of the above content still faces four difficulties: First, drilling and fracturing belong to different fields. How to convert drilling data into usable data for fracturing sweet spots; second, drilling data is discrete. How to convert it into a continuous, high-resolution depth profile requires complex data processing; third, how to ensure that the sweet spot of the reservoir is consistent with reality. Conventional algorithms, such as selecting high brittleness index reservoirs, often have screening results that are far from the actual fracturing monitoring results and production results; fourth, how to integrate drilling and logging data to establish an evaluation model. In response to the above problems, this embodiment has made targeted designs for steps S1 to S3 so that it can better solve the above problems.

[0037] like Figure 2 As shown, in this embodiment, the step S1, i.e., classifying the reservoir sweet spot type according to the fracturing results and production results monitored by the optical fiber outside the pipe, specifically includes:

[0038] Step S11, deploying dual-mode optical fiber outside casing in horizontal well;

[0039] Step S12, according to the fracturing monitoring result of the dual-mode optical fiber outside the casing, the reservoir compressibility type F is classified, and the classification standard of the reservoir compressibility type F is: the reservoir that is not opened during the fracturing process is not compressible, and the compressibility of the fractured layer section is divided into 1-n levels from good to poor according to the amount of liquid inflow, and the value is inversely proportional to the compressibility, that is, the lower the value, the better the compressibility;

[0040] Step S13, according to the production monitoring result of the dual-mode optical fiber outside the casing, the reservoir potential type Q is classified, and the classification standard of the reservoir potential type Q is: the reservoir without liquid production during the entire production process has no potential, and the production reservoir is divided into 1-m levels from high to low according to the oil production or gas production, and the value is inversely proportional to the potential, that is, the lower the value, the higher the potential;

[0041] Step S14: classify reservoir sweet spots according to the reservoir compressibility type F and the reservoir potential type Q.

[0042] And in the step S14, the calculation formula for dividing the reservoir sweet spot type according to the reservoir compressibility type F and the reservoir potential type Q is as follows: Let k = max (m, n), and establish a k-order sweet spot matrix of reservoir compressibility and reservoir potential coupling:

[0043]

[0044] If m≠n occurs, a blank sequence is added to the sweet spot matrix, and the blanks can be added in the form of symbols, etc., so that the k-order matrix is ​​complete;

[0045] The sweet spot combination on the diagonal line of the coupled sweet spot matrix is ​​classified into a sweet spot type, T 11 For the best quality dessert type, T 12 and T 21 For the second-class dessert type, T 13 , T 22 and T 31 For the third premium dessert type... and so on, T mn This is the worst dessert type, and there are a total of 2k-1 dessert types.

[0046] like Figure 3 As shown, in this embodiment, the step S2, i.e., generating a rock mechanics depth data set using drilling data, specifically includes:

[0047] Step S21, calculating the bottom hole data drilling pressure, torque, rotation speed and hydraulic energy according to the drilling data, wherein the drilling data includes the type of drill bit, drilling torque, drilling fluid density, rotation speed, drilling speed and mechanical drilling pressure;

[0048] Step S22, using the calculated bottom hole data drilling pressure, the torque, the rotation speed and the hydraulic energy, combined with the first drill bit data to calculate the rock brittleness, wherein the first drill bit data includes the drill bit diameter;

[0049] Step S23, using the calculated bottom hole data drilling pressure, the torque, the rotation speed and the hydraulic energy, combined with the second drill bit data to calculate the rock compressive strength, the second drill bit data includes the drill bit nozzle flow rate and nozzle size; wherein the calculation formula of the rock compressive strength is as follows:

[0050]

[0051] In the formula, CCS is the compressive strength of rock, in MPa; P e is the effective drilling pressure, unit is kN; A b is the cross-sectional area of ​​the drill bit, in mm 2 ; N is the speed, unit RPM; T e is the effective torque, unit is kN·m; V e It is the effective mechanical drilling speed, in m / h.

[0052] Step S24, converting the time domain second point data into depth data and performing depth correction;

[0053] Step S25, normalizing all the obtained data, and interpolating the non-drilling process, the same well depth, and the null value data;

[0054] Step S26, establishing a depth data set of brittleness index and compressive strength that increases with well depth and is spaced at predetermined values. The predetermined value in this embodiment is preferably 0.01-0.05 meters.

[0055] like Figure 4 As shown, in this embodiment, the step S3, i.e., calibrating the sweet spot type, logging characteristics and drilling rock breaking characteristic data set of the horizontal well perforation position, and establishing the oil and gas sweet spot reservoir identification model in the study area through cluster analysis, specifically includes:

[0056] Step S31, calibrating a well logging feature data set of a horizontal well perforation position, wherein the well logging feature data set includes at least one of thickness, interpreted permeability, acoustic wave time difference, resistivity, natural gamma, total organic carbon, porosity, and oil or gas saturation, and this embodiment includes all of the above items;

[0057] Step S32, calibrating a drilling sweet spot feature data set corresponding to the horizontal well perforation position, wherein the drilling sweet spot feature data set includes a brittleness index and a compressive strength;

[0058] Step S33, establishing a parameter sample library of the horizontal well perforation position and the reservoir sweet spot type, the logging feature data set, and the drilling sweet spot feature data set, which is divided into no more than 2K-1 clusters, where K is the number of clusters, and the similarity between sample points is measured based on the Euclidean geometric distance, so that the samples in the clusters reach a predetermined similarity;

[0059] Step S34, using the sum of squared errors as the criterion function, and selecting the optimal cluster center by traversing all sample points to determine the sweet spot type to which the sample belongs; wherein the calculation formula for the sum of squared errors is:

[0060]

[0061] In the formula, SSE is the sum of squared errors; n j is the number of samples in the jth cluster; μ j is the jth cluster center point; x i is the sample point; K is the number of clusters.

[0062] Step S35, classifying the classified data into the category to which the cluster center corresponds to the least square value, and establishing a neural network model;

[0063] Step S36, collecting the horizontal well data of the deployed external optical fiber monitoring, and training the neural network model to obtain the oil and gas sweet spot reservoir identification model of the study area.

[0064] In actual use, we can further coring typical wells in the target block, use the cored rocks to conduct triaxial mechanical experiments, obtain the static Young's modulus, Poisson's ratio, compressive strength, fracture toughness, reservoir stress and other measured data of the cored rocks, and establish a conversion relationship calculation model between the measured rock mechanics parameters of the target block and the calculation results of drilling data.

[0065] It should be noted that some data processing methods such as calculation and fitting in the above embodiments are conventional data processing methods in the art, and thus they are not further elaborated in this embodiment.

[0066] From the above description, it can be seen that the above embodiments of the present invention achieve the following technical effects:

[0067] 1. Solve the problem of low accuracy of dessert recognition methods in the prior art;

[0068] 2. Combined with drilling and rock breaking data, it is practical and has high resolution;

[0069] 3. The data sources for sweet spot identification have been enriched, and the vertical resolution has reached the decimeter level;

[0070] 4. Improve the accuracy of sweet spot identification by more than 15%, realize the full utilization of reservoir sweet spots, and increase fracture controlled reserves.

[0071] While reducing operating costs, the cumulative production of a single well has increased by more than 10%.

[0072] Obviously, the above-described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0073] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0074] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0075] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying a reservoir sweet spot, characterized in that: include: Step S1, classifying the reservoir sweet spot type according to the fracturing results and production results monitored by the optical fiber outside the pipe; Step S2, generating a rock mechanics depth data set using drilling data; Step S3, calibrating the sweet spot type, logging characteristics and drilling rock breaking characteristics data set of the horizontal well perforation position, and establishing an oil and gas sweet spot reservoir identification model in the study area through cluster analysis; Step S4, inputting the drilling data and logging data into the oil and gas sweet spot reservoir identification model of the study area, and outputting a sweet spot profile combining the drilling rock breaking data and the logging data.

2. The method for identifying a sweet spot in a reservoir according to claim 1, characterized in that: The reservoir sweet spot identification method further includes: The drilling data includes at least one of drill bit type, drilling torque, drilling fluid density, rotation speed, drilling speed, and mechanical bit pressure.

3. The method for identifying a reservoir sweet spot according to claim 1, characterized in that: The reservoir sweet spot identification method further includes: The rock mechanics include rock brittleness and compressive strength.

4. The method for identifying a sweet spot in a reservoir according to claim 1, characterized in that: The step S1 comprises: Step S11, deploying dual-mode optical fiber outside casing in horizontal well; Step S12, classifying the reservoir compressibility type F according to the fracturing monitoring result of the dual-mode optical fiber outside the casing, wherein the classification standard of the reservoir compressibility type F is: the reservoir that is not opened during the fracturing process is incompressible, and the compressibility of the fractured layer section is divided into 1-n levels from good to poor according to the amount of liquid inflow, and the value is inversely proportional to the compressibility; Step S13, according to the production monitoring result of the dual-mode optical fiber outside the casing, the reservoir potential type Q is classified, and the classification standard of the reservoir potential type Q is: the reservoir without liquid production during the entire production process has no potential, and the production reservoir is divided into 1-m levels from high to low according to the oil production or gas production, and the value is inversely proportional to the potential; Step S14: classify reservoir sweet spots according to the reservoir compressibility type F and the reservoir potential type Q.

5. The method for identifying a sweet spot in a reservoir according to claim 4, characterized in that: In the step S14, the calculation formula for dividing the reservoir sweet spot type according to the reservoir compressibility type F and the reservoir potential type Q is as follows: Let k = max(m, n) and establish the sweet spot matrix of the k-order reservoir compressibility and reservoir potential coupling: If m≠n occurs, a blank sequence is added to the sweet spot matrix; The sweet spot combination on the diagonal of the coupled sweet spot matrix is ​​classified as a sweet spot type, T 11 For the best quality dessert type, T 12 and T 21 For the second-class dessert type, T 13 、T 22 and T 31 For the third premium dessert type... and so on, T mn This is the worst dessert type, and there are a total of 2k-1 dessert types.

6. The method for identifying a sweet spot in a reservoir according to claim 1, characterized in that: The step S2 comprises: Step S21, calculating the bottom hole data drilling pressure, torque, rotation speed and hydraulic energy according to the drilling data, wherein the drilling data includes the type of drill bit, drilling torque, drilling fluid density, rotation speed, drilling speed and mechanical drilling pressure; Step S22, using the calculated bottom hole data drilling pressure, the torque, the rotation speed and the hydraulic energy, combined with the first drill bit data, to calculate the rock brittleness; Step S23, using the calculated bottom hole data drilling pressure, the torque, the rotation speed and the hydraulic energy, combined with the second drill bit data, to calculate the rock compressive strength; Step S24, converting the time domain second point data into depth data and performing depth correction; Step S25, normalizing all the obtained data, and interpolating the non-drilling process, the same well depth, and the null value data; Step S26, establishing a depth data set of brittleness index and compressive strength that increases with well depth and is spaced at predetermined values.

7. The method for identifying a sweet spot in a reservoir according to claim 6, characterized in that: The first drill bit data includes the drill bit diameter, the second drill bit data includes the drill bit nozzle flow rate and nozzle size, and the predetermined value is 0.01-0.05 meters.

8. The method for identifying a sweet spot in a reservoir according to claim 6, characterized in that: In step S23, the calculation formula of the rock compressive strength is as follows: Where CCS is the rock compressive strength, unit: MPa; P e is the effective drilling pressure, unit is kN; A b is the cross-sectional area of ​​the drill bit, in mm 2 ; N is the speed, unit RPM; T e is the effective torque, unit is kN·m; V e It is the effective mechanical drilling speed, in m / h.

9. The method for identifying a reservoir sweet spot according to claim 1, characterized in that: The step S3 comprises: Step S31, calibrating a well logging characteristic data set of a horizontal well perforation position, wherein the well logging characteristic data set includes at least one of thickness, interpreted permeability, acoustic wave time difference, resistivity, natural gamma, total organic carbon, porosity, and oil or gas saturation; Step S32, calibrating a drilling sweet spot feature data set corresponding to the horizontal well perforation position, wherein the drilling sweet spot feature data set includes a brittleness index and a compressive strength; Step S33, establishing a parameter sample library of the horizontal well perforation position and the reservoir sweet spot type, the logging feature data set, and the drilling sweet spot feature data set, which is divided into no more than 2K-1 clusters, where K is the number of clusters, and the similarity between sample points is measured based on the Euclidean geometric distance, so that the samples in the clusters reach a predetermined similarity; Step S34, using the sum of squared errors as the criterion function, and selecting the optimal cluster center by traversing all sample points to determine the type of dessert to which the sample belongs; Step S35, classifying the classified data into the category to which the cluster center corresponds to the least square value, and establishing a neural network model; Step S36, collecting the horizontal well data of the deployed external optical fiber monitoring, and training the neural network model to obtain the oil and gas sweet spot reservoir identification model of the study area.

10. The method for identifying a reservoir sweet spot according to claim 9, characterized in that: In step S34, the calculation formula of the error square sum is: Where SSE is the sum of squared errors; n j is the number of samples in the jth cluster; μ j is the jth cluster center point; x i is the sample point; K is the number of clusters.

Images