Seismic information label data construction method, device, equipment, medium and program
By generating seismic composite traces and synthetic seismic records, and establishing time-depth relationships, the problem of insufficient data utilization in deviated and vertical wells was solved, enabling full utilization of data during the oil and gas field development stage and improving the accuracy and efficiency of reservoir characterization.
Patent Information
- Application Number
- CN202310610944.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-26
- Publication Date
- 2024-11-26
AI Technical Summary
Existing technologies struggle to effectively utilize seismic data from deviated and vertical wells, resulting in a significant amount of deviated well information not being fully utilized during the oil and gas field development phase, which impacts the accuracy of reservoir characterization based on machine learning.
By generating seismic composite traces, synthesizing seismic records, establishing time-depth relationships, and using these relationships to convert seismic time sampling points, labeled data is constructed, enabling unified processing of inclined and vertical wells.
This enables full utilization of seismic information from both deviated and vertical wells, providing a more comprehensive data foundation for machine learning-based reservoir characterization and improving the accuracy and efficiency of reservoir prediction.
Smart Images

Figure CN119024435A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of exploration geophysical technology, and in particular to a method, device, equipment, medium and program for constructing earthquake information label data. Background Art
[0002] This section is intended to provide a background or context to the embodiments recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.
[0003] Reservoir seismic characterization is a description and prediction of the lithology, physical properties and sedimentary phases of underground three-dimensional media based on seismic data, drilling and logging data. Reservoir characterization is of great significance for exploration and development risk assessment, seismic thermal energy development, carbon dioxide storage and geological modeling. Traditional reservoir characterization is mainly based on rock physics models and seismic wave propagation models. When the mapping relationship between reservoir characteristics and seismic elastic characteristics is highly nonlinear, the accuracy of traditional characterization methods is often limited, and the uncertainty of seismic reservoir inversion based on traditional methods directly affects the reservoir prediction results.
[0004] With the rise of artificial intelligence technology, new ideas have been provided for processing high-dimensional seismic data and establishing nonlinear mapping relationships to solve inverse problems in exploration and development. At present, reservoir prediction (such as lithology prediction) based on supervised machine learning mostly follows a basic paradigm: first, machine learning is used to establish a mapping relationship from seismic data to reservoir characteristics at the drilling location, and then the established mapping relationship is extended to the entire three-dimensional work area to obtain a description of reservoir characteristics. However, the construction of the label data required for machine learning requires the definition of the mapping relationship between the input seismic information and the output reservoir characteristics. Usually, the label construction process based on vertical wells includes: extracting seismic information of the well side channel (including seismic records and extracted attributes, etc.) according to the drilling coordinates, and then one-to-one correspondence with the reservoir label of the vertical well can establish the data required for machine learning. When the oil and gas field enters the development stage, according to the needs of oil and gas reservoir development, wells with large well deviations will be used for development. Since the inclined drilling wells span multiple seismic channels, the processing flow previously applicable to vertical wells cannot be directly migrated and used. In summary, how to process inclined wells and vertical wells simultaneously so as to make full use of a large amount of inclined drilling information in the oil and gas field development stage and provide a more sufficient data basis for reservoir characterization based on machine learning has become an urgent problem to be solved. Summary of the invention
[0005] In view of the above problems, embodiments of the present invention provide a method, device, equipment, medium and program for constructing earthquake information label data.
[0006] In a first aspect, an embodiment of the present invention provides a method for constructing earthquake information label data, comprising:
[0007] Acquiring well trajectory data and well logging data, and generating a seismic composite trace according to the well trajectory data;
[0008] Acquire seismic data of a seismic work area, determine a statistical wavelet according to the seismic data, and perform calculations according to the well logging data and the statistical wavelet to obtain a synthetic seismic record;
[0009] Establishing a time-depth relationship according to the seismic composite trace and the synthetic seismic record, and converting the seismic time sampling points of the seismic data using the time-depth relationship to obtain the oblique depth;
[0010] Extracting trajectory coordinates from the well trajectory data according to the deflection depth, and selecting work area coordinates from the coordinate data of the seismic work area according to the trajectory coordinates;
[0011] An index table is established according to the work area coordinates and the earthquake time sampling points, and label data is constructed according to the index table.
[0012] According to an embodiment of the present invention, determining a statistical wavelet according to the seismic data comprises:
[0013] An analysis time window is extracted from the seismic data, and the autocorrelation coefficient of the seismic data within the analysis time window is calculated; the autocorrelation coefficient is calculated using the following formula:
[0014] r=f(t)*f(t)
[0015] Wherein, r represents the autocorrelation coefficient, and f(t) represents the seismic data within the analysis time window t;
[0016] Calculating a frequency spectrum according to the autocorrelation coefficient and the analysis time window using a preset Fourier transform method, and calculating an amplitude spectrum according to the frequency spectrum;
[0017] The Fourier transform method is expressed as:
[0018]
[0019] Wherein, G represents the frequency spectrum, r represents the autocorrelation coefficient, t represents the analysis time window, k represents a preset frequency value, e represents a preset natural constant, π represents a preset pi constant, i represents a preset imaginary unit, and i represents a preset imaginary unit. 2 = -1;
[0020] The amplitude mean values of the plurality of amplitude spectra are calculated, and a statistical wavelet is generated according to the amplitude mean value and a preset standard phase.
[0021] According to an embodiment of the present invention, the step of calculating based on the well logging data and the statistical wavelet to obtain a synthetic seismic record includes:
[0022] Obtaining a first P-wave velocity and a first density of an upper formation and a second P-wave velocity and a second density of a lower formation in the well logging data, calculating a first P-wave impedance according to the first P-wave velocity and the first density, and calculating a second P-wave impedance according to the second P-wave velocity and the second density;
[0023] The first longitudinal wave impedance and the second longitudinal wave impedance are calculated using the following formula:
[0024] z1=v1*ρ1
[0025] z2=v2*ρ2
[0026] Wherein, z1 represents the first longitudinal wave impedance, z2 represents the second longitudinal wave impedance, v1 represents the first longitudinal wave velocity, ρ1 represents the first density, v2 represents the second longitudinal wave velocity, and ρ2 represents the second density;
[0027] generating a reflection coefficient according to the first longitudinal wave impedance and the second longitudinal wave impedance, and generating a reflection coefficient sequence according to the reflection coefficient;
[0028] The reflection coefficient is generated using the following formula:
[0029] re=(z2-z1) / (z2+z1)
[0030] Wherein, re represents the reflection coefficient, z1 represents the first longitudinal wave impedance, and z2 represents the second longitudinal wave impedance;
[0031] Perform convolution calculation according to the reflection coefficient sequence and the statistical wavelet to obtain a synthetic seismic record;
[0032] The following formula is used for convolution calculation to obtain the synthetic seismic record:
[0033] x=w×d
[0034] Wherein, x represents the synthetic seismic record, w represents the statistical wavelet, and d represents the reflection coefficient sequence.
[0035] According to an embodiment of the present invention, the establishing of the time-depth relationship based on the seismic composite trace and the synthetic seismic record includes:
[0036] Adjusting the synthetic seismic record to obtain an updated synthetic seismic record;
[0037] Matching the composite seismic trace and the updated synthetic seismic record, and extracting the logging inclination depth and time according to the matching result;
[0038] A time-depth relationship is generated according to the logging deviation depth and the time.
[0039] According to an embodiment of the present invention, the converting the seismic time sampling points of the seismic data using the time-depth relationship to obtain the slant depth includes:
[0040] Determine whether the earthquake time sampling point is consistent with the target time point in the time-depth relationship;
[0041] When the earthquake time sampling point is inconsistent with the target time point, a time point closest to the earthquake time sampling point is selected from the time-depth relationship, and the target oblique depth corresponding to the time point is used as the oblique depth;
[0042] When the seismic time sampling point is consistent with the target time point, the target oblique depth corresponding to the target time point in the time-depth relationship is extracted, and the target oblique depth is used as the oblique depth.
[0043] According to an embodiment of the present invention, extracting trajectory coordinates from the well trajectory data according to the deviated depth includes:
[0044] Obtaining the drilling deflection depth in the well trajectory data, and calculating a deflection depth index using the drilling deflection depth and the deflection depth;
[0045] The slant depth index is calculated using the following formula:
[0046] L = argmin(|HD|)
[0047] Wherein, L represents the slant depth index, H represents the slant depth, and D represents the drilling slant depth;
[0048] The oblique depth index is placed in a preset rectangular coordinate system to obtain index coordinates corresponding to the oblique depth index, and the index coordinates are used as trajectory coordinates.
[0049] In a second aspect, an embodiment of the present invention provides a device for constructing earthquake information label data, characterized in that it includes:
[0050] A seismic composite trace generation module is used to obtain well trajectory data and well logging data, and generate a seismic composite trace according to the well trajectory data;
[0051] A synthetic seismic record generation module is used to obtain seismic data of a seismic work area, determine a statistical wavelet according to the seismic data, and perform calculations according to the well logging data and the statistical wavelet to obtain a synthetic seismic record;
[0052] A time-depth relationship establishment module, used to establish a time-depth relationship according to the seismic composite trace and the synthetic seismic record, and to convert the seismic time sampling points of the seismic data using the time-depth relationship to obtain the oblique depth;
[0053] A work area coordinate selection module, used for extracting trajectory coordinates from the well trajectory data according to the deflection depth, and selecting work area coordinates from the coordinate data of the seismic work area according to the trajectory coordinates;
[0054] The label data construction module is used to establish an index table according to the work area coordinates and the earthquake time sampling points, and to construct label data according to the index table.
[0055] In a third aspect, an embodiment of the present invention provides an electronic device, comprising:
[0056] processor;
[0057] a memory for storing instructions executable by the processor;
[0058] Wherein, the processor is configured to execute the instructions to implement a method for constructing earthquake information label data as described in the first aspect.
[0059] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for constructing earthquake information label data as described in the first aspect.
[0060] In a fifth aspect, an embodiment of the present invention provides a computer program, characterized in that when the program is executed by a processor, it implements a method for constructing earthquake information label data as described in the first aspect.
[0061] Compared with the prior art, the above technical solution of the present invention has the following beneficial effects:
[0062] The embodiments of the present invention generate seismic composite traces through well trajectory data, thereby ensuring the accuracy of the seismic composite traces; determine statistical sub-waves through seismic data, and perform calculations based on logging data and statistical sub-waves to make the obtained synthetic seismic records more accurate; convert the seismic time sampling points of the seismic data through the time-depth relationship to make the obtained oblique depth more accurate; establish an index table through work area coordinates and seismic time sampling points, and construct label data based on the index table, thereby being able to process oblique wells and vertical wells at the same time, so that a large amount of seismic information in the oil and gas field development stage can be fully utilized, providing a more sufficient data basis for reservoir characterization based on machine learning. BRIEF DESCRIPTION OF THE DRAWINGS
[0063] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0064] Figure 1 The flowchart of the earthquake information label data construction method according to the first embodiment of the present invention is shown;
[0065] Figure 2 A structural schematic diagram showing the distribution of work area coordinates according to the first embodiment of the present invention;
[0066] Figure 3 A schematic diagram showing the distance between the start coordinate and the end coordinate of the well trajectory and the corresponding coding according to the first embodiment of the present invention is shown;
[0067] Figure 4 A schematic diagram showing the structure of reservoir characteristic labels drawn according to the index table, real seismic records and work area coordinates corresponding to different seismic sampling time points according to the first embodiment of the present invention;
[0068] Figure 5 A functional module diagram of a device for constructing earthquake information tag data according to a third embodiment of the present invention is shown;
[0069] Figure 6 A schematic diagram of the composition structure of an electronic device for implementing the earthquake information tag data construction method according to the fourth embodiment of the present invention is shown. DETAILED DESCRIPTION
[0070] The present disclosure is further described below in conjunction with the embodiments shown in the accompanying drawings.
[0071] 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.
[0072] The present invention proposes a method for constructing seismic information label data, which generates seismic composite traces and synthetic seismic records based on well trajectory data, logging data and seismic data, establishes a time-depth relationship based on the seismic composite traces and synthetic seismic records, and uses the time-depth relationship to convert seismic time sampling points to obtain the inclined depth, establishes an index table based on the inclined depth and coordinate information, and finally constructs label data. Compared with traditional methods, the seismic information label data construction method processes inclined wells and vertical wells at the same time, so that a large amount of inclined drilling information in the oil and gas field development stage can be fully utilized, providing a more sufficient data basis for reservoir characterization based on machine learning.
[0073] Embodiment 1
[0074] like Figure 1 As shown, the present invention proposes a method for constructing earthquake information label data, comprising the following steps:
[0075] S1. Acquire well trajectory data and well logging data, and generate a seismic composite trace according to the well trajectory data.
[0076] In the embodiment of the present invention, the well trajectory data includes well depth, well inclination angle and well inclination azimuth, etc.; the well logging data includes longitudinal wave velocity and density, etc.
[0077] In an embodiment of the present invention, the well trajectory data is extracted, seismic records of multiple seismic traces near the well are plotted, and the seismic composite trace is generated based on the multiple seismic records, that is, the seismic composite trace is composed of multiple seismic trace records near the inclined well.
[0078] S2. Acquire seismic data of the seismic work area, determine a statistical wavelet according to the seismic data, perform calculations according to the well logging data and the statistical wavelet, and obtain a synthetic seismic record.
[0079] In the embodiment of the present invention, the seismic work area refers to a target area formed by pre-deployed seismic survey lines; the seismic data includes seismic records of seismic traces and Inline numbers, Xline numbers, X coordinates and Y coordinates of seismic traces.
[0080] In the embodiment of the present invention, determining the statistical wavelet according to the seismic data includes:
[0081] Extracting an analysis time window from the seismic data, and calculating the autocorrelation coefficient of the seismic data within the analysis time window;
[0082] Calculating a frequency spectrum according to the autocorrelation coefficient and the analysis time window using a preset Fourier transform method, and calculating an amplitude spectrum according to the frequency spectrum;
[0083] The amplitude mean values of the plurality of amplitude spectra are calculated, and a statistical wavelet is generated according to the amplitude mean value and a preset standard phase.
[0084] In the embodiment of the present invention, the autocorrelation coefficient is calculated using the following formula:
[0085] r=f(t)*f(t)
[0086] Wherein, r represents the autocorrelation coefficient, and f(t) represents the seismic data within the analysis time window t.
[0087] In the embodiment of the present invention, the Fourier transform method is expressed as:
[0088]
[0089] Wherein, G represents the frequency spectrum, r represents the autocorrelation coefficient, t represents the analysis time window, k represents a preset frequency value, e represents a preset natural constant, π represents a preset pi constant, i represents a preset imaginary unit, and i represents a preset imaginary unit. 2 =-1.
[0090] In an embodiment of the present invention, the analysis time window refers to the time period of the target layer of the reservoir. Calculation based on the seismic data within the time period can accurately reflect the wavelet characteristics of the target layer area; since the reflection coefficient in the seismic data is white noise, the autocorrelation coefficient in the seismic data is equal to the autocorrelation coefficient in the statistical wavelet, therefore, the correlation between the seismic data is calculated to obtain the autocorrelation coefficient; the modulus |G| of the frequency spectrum is calculated, that is, the modulus is the amplitude spectrum; and the average of multiple amplitude spectra is calculated to obtain the amplitude average.
[0091] In the embodiment of the present invention, the standard phase refers to a preset wavelet phase; the seismic wavelet coefficient is determined according to the amplitude mean and the standard phase, and the statistical wavelet is obtained according to the inverse Fourier transform calculation.
[0092] In the embodiment of the present invention, the time range of the seismic data used to calculate the statistical wavelet is 2300ms-2900ms, and the length of the seismic wavelet can be set to 130ms.
[0093] In the embodiment of the present invention, the calculation based on the well logging data and the statistical wavelet to obtain the synthetic seismic record includes:
[0094] Obtaining a first P-wave velocity and a first density of an upper formation and a second P-wave velocity and a second density of a lower formation in the well logging data, calculating a first P-wave impedance according to the first P-wave velocity and the first density, and calculating a second P-wave impedance according to the second P-wave velocity and the second density;
[0095] generating a reflection coefficient according to the first longitudinal wave impedance and the second longitudinal wave impedance, and generating a reflection coefficient sequence according to the reflection coefficient;
[0096] Convolution calculation is performed according to the reflection coefficient sequence and the statistical wavelet to obtain a synthetic seismic record.
[0097] In the embodiment of the present invention, the first longitudinal wave impedance and the second longitudinal wave impedance are calculated using the following formula:
[0098] z1=v1*ρ1
[0099] z2=v2*ρ2
[0100] Among them, z1 represents the first longitudinal wave impedance, z2 represents the second longitudinal wave impedance, v1 represents the first longitudinal wave velocity, ρ1 represents the first density, v2 represents the second longitudinal wave velocity, and ρ2 represents the second density.
[0101] In the embodiment of the present invention, the reflection coefficient is generated using the following formula:
[0102] re=(z2-z1) / (z2+z1)
[0103] Wherein, re represents the reflection coefficient, z1 represents the first longitudinal wave impedance, and z2 represents the second longitudinal wave impedance.
[0104] In the embodiment of the present invention, the following formula is used to perform convolution calculation to obtain the synthetic seismic record:
[0105] x=w×d
[0106] Wherein, x represents the synthetic seismic record, w represents the statistical wavelet, and d represents the reflection coefficient sequence.
[0107] In the embodiment of the present invention, the synthetic seismic record is calculated based on the logging data and the statistical wavelet in order to better describe the waveform changes of the seismic wave and ensure the accuracy of time-depth calibration.
[0108] S3. Establishing a time-depth relationship according to the seismic composite trace and the synthetic seismic record, and using the time-depth relationship to convert the seismic time sampling points of the seismic data to obtain the oblique depth.
[0109] In the embodiment of the present invention, the establishing of the time-depth relationship according to the seismic composite trace and the synthetic seismic record includes:
[0110] Adjusting the synthetic seismic record to obtain an updated synthetic seismic record;
[0111] Matching the composite seismic trace and the updated synthetic seismic record, and extracting the logging inclination depth and time according to the matching result;
[0112] A time-depth relationship is generated according to the logging deviation depth and the time.
[0113] In an embodiment of the present invention, adjusting the synthetic seismic record refers to obtaining the well stratification so that the well stratification and the seismic layer of the seismic work area correspond to each other, and obtaining an updated reflection coefficient sequence, thereby updating the synthetic seismic record using the updated reflection coefficient sequence to obtain an updated synthetic seismic record; aligning the waveform of the seismic composite track and the waveform of the updated synthetic seismic record, extracting the aligned complete data points, obtaining the well logging inclination depth and time of the data points, and establishing a corresponding time-depth relationship based on the well logging inclination depth and the time.
[0114] In the embodiment of the present invention, the step of converting the seismic time sampling points of the seismic data using the time-depth relationship to obtain the slant depth includes:
[0115] Determine whether the earthquake time sampling point is consistent with the target time point in the time-depth relationship;
[0116] When the earthquake time sampling point is inconsistent with the target time point, a time point closest to the earthquake time sampling point is selected from the time-depth relationship, and the target oblique depth corresponding to the time point is used as the oblique depth;
[0117] When the seismic time sampling point is consistent with the target time point, the target oblique depth corresponding to the target time point in the time-depth relationship is extracted, and the target oblique depth is used as the oblique depth.
[0118] In an embodiment of the present invention, the time-depth relationship includes slant depth and time point. Since the earthquake time sampling point may not be an integer, the corresponding time point cannot be accurately found in the time-depth relationship. Therefore, it is determined whether the earthquake time sampling point is consistent with the target time point in the time-depth relationship. When the earthquake time sampling point is inconsistent with the target time point, the time point closest to the earthquake time sampling point in the time-depth relationship is found. For example, the earthquake time sampling point is 2000 milliseconds, and the time point closest to the target time point in the time-depth relationship is 2000.3 milliseconds. Therefore, the slant depth corresponding to 2000.3 milliseconds in the time-depth relationship is used as the slant depth corresponding to the earthquake time sampling point; when the earthquake time sampling point is consistent with the target time point, the target slant depth corresponding to the target time point in the time-depth relationship is used as the slant depth.
[0119] S4. Extracting trajectory coordinates from the well trajectory data according to the deflection depth, and selecting work area coordinates from the coordinate data of the seismic work area according to the trajectory coordinates.
[0120] In an embodiment of the present invention, extracting trajectory coordinates from the well trajectory data according to the deflection depth includes:
[0121] Obtaining the drilling deflection depth in the well trajectory data, and calculating a deflection depth index using the drilling deflection depth and the deflection depth;
[0122] The oblique depth index is placed in a preset rectangular coordinate system to obtain index coordinates corresponding to the oblique depth index, and the index coordinates are used as trajectory coordinates.
[0123] In the embodiment of the present invention, the oblique depth index is calculated using the following formula:
[0124] L = argmin(|HD|)
[0125] Wherein, L represents the slant depth index, H represents the slant depth, and D represents the slant depth of drilling.
[0126] In an embodiment of the present invention, the well trajectory data includes the drilling inclination depth and the trajectory coordinates corresponding to the inclination depth; the rectangular coordinate system refers to the coordinate system where the trajectory coordinates are located, and the calculated inclination depth index is placed in the coordinate system for coordinate conversion to obtain the index coordinates, that is, the trajectory coordinates.
[0127] In the embodiment of the present invention, reference coordinates are traversed from the coordinate data of the seismic work area, the distance between the trajectory coordinates and the reference coordinates is calculated, and the reference coordinates with the closest distance are selected as the work area coordinates after positioning.
[0128] In the embodiment of the present invention, taking carbonate reservoir as an example, the distribution of the work area coordinates is as follows: Figure 2 As shown in FIG. 1 , the distribution of the coordinates (X, Y) of the work area is shown based on the connection diagram of the projection of the reservoir section encountered by 56 wells in the entire carbonate reservoir area (starting coordinates) and the reservoir section drilled out or the drilling stopped (ending coordinates) on the coordinate plane, wherein the black dot represents the starting coordinate and the gray triangle represents the ending coordinate; the distance between the starting coordinate and the ending coordinate and the corresponding coding structure schematic diagram are shown in FIG. Figure 3 As shown, by calculating the distance between the starting coordinate and the ending coordinate, it can be seen that the lateral span of most wells is above 100m, and the maximum span can exceed 1400m, wherein the abscissa represents the corresponding numbers of the 56 wells, and the ordinate represents the distance; according to the span, the traditional label construction method is no longer applicable, and it is necessary to introduce the time-depth relationship, well trajectory data and work area coordinate information to locate the position of discrete reservoir labels in the seismic data, thereby constructing label data.
[0129] S5. Establish an index table according to the work area coordinates and the earthquake time sampling points, and construct label data according to the index table.
[0130] In an embodiment of the present invention, an index table is generated with the seismic sampling time points as column vectors and the work area coordinates as row vectors, wherein the column names of the index table include three groups of data: time-depth relationship data, well trajectory data, and work area coordinate data.
[0131] In an embodiment of the present invention, constructing label data according to the index table refers to performing time-depth conversion, mapping and other processing on the time-depth relationship data (seismic sampling time point, inclination depth), well trajectory data (drilling inclination depth, trajectory coordinates), and work area coordinate data (work area coordinates, reference coordinates) to obtain corresponding drilling and logging information, pre-stack seismic traces, post-stack seismic data, seismic attributes, etc., establish three-dimensional discrete geological feature labels, for example, lithology, fractures, reservoir types and fluids, and generate label data according to the labels and corresponding data.
[0132] In the embodiment of the present invention, the reservoir characteristic labels drawn according to the index table of any well, the real seismic records and the work area coordinates corresponding to different seismic sampling time points are as follows: Figure 4 As shown, the oblique line represents the curve corresponding to the well trajectory data, the black five-pointed star represents the position of the reservoir feature label, the Y-axis represents the seismic sampling time point, the X-axis represents the work area coordinates, and the X-axis is marked with the distance from the current position to the left starting point and the coordinate information. It can be seen from the figure that the current well finally spans 25 seismic channels, and the lateral distance span is 402.3m.
[0133] In the embodiment of the present invention, by establishing Figure 4 The label data corresponding to the reservoir feature labels shown can be directly used as training samples for machine learning. If you need to establish a learning sample with an input as a seismic time series, you can select a seismic sequence along the time axis with (time sampling point, X, Y) as the center based on the index table; if you need to establish a learning sample with one or more seismic slices as the input, you can define the direction of the slice (time slice or profile slice) and select it with (time sampling point, X, Y) as the center; if you need to establish a learning sample with a three-dimensional seismic data body as input, you can select the seismic data body along these three axes with (time sampling point, X, Y) as the center.
[0134] Embodiment 2
[0135] In order to understand the present invention more clearly, a second embodiment is used below to further explain the present invention in which trajectory coordinates are extracted from the well trajectory data according to the deflection depth, and work area coordinates are selected from the coordinate data of the seismic work area according to the trajectory coordinates.
[0136] In an embodiment of the present invention, the well trajectory data includes the drilling deviation depth and the trajectory coordinates corresponding to the deviation depth; positioning is performed according to the deviation depth and the well trajectory data to obtain the trajectory coordinates.
[0137] In the embodiment of the present invention, the step of selecting the work area coordinates from the coordinate data of the seismic work area according to the trajectory coordinates includes:
[0138] traversing and selecting reference coordinates from the coordinate data of the seismic work area, calculating the distance between the reference coordinates and the trajectory coordinates, and determining whether the distance is a minimum value;
[0139] When the distance is not the minimum value, returning to the step of traversing and selecting reference coordinates from the coordinate data of the seismic work area;
[0140] When the distance is the minimum value, the reference coordinates corresponding to the distance are used as the work area coordinates.
[0141] In the embodiment of the present invention, the distance is calculated using the following formula:
[0142] S = min((X1-X2) 2 +(Y1-Y2) 2 )
[0143] Wherein, S represents the distance, (X1, Y1) represents the trajectory coordinates, and (X2, Y2) represents the reference coordinates.
[0144] In an embodiment of the present invention, the coordinate data includes the work area coordinates of multiple seismic work areas. The reference coordinates with the closest distance in the coordinate data of the seismic work area are selected as the work area coordinates after positioning according to the trajectory coordinates, so as to construct the required index table.
[0145] Embodiment 3
[0146] like Figure 5 As shown, this embodiment also provides a functional module diagram of a device for constructing earthquake information label data.
[0147] The earthquake information label data construction device 500 described in this embodiment can be installed in an electronic device. According to the functions to be implemented, the earthquake information label data construction device 500 may include an earthquake composite trace generation module 501, a synthetic earthquake record generation module 502, a time-depth relationship establishment module 503, a work area coordinate selection module 504 and a label data construction module 505. The module described in the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.
[0148] In this embodiment, the functions of each module / unit are as follows:
[0149] The seismic composite trace generation module 501 is used to obtain well trajectory data and well logging data, and generate a seismic composite trace according to the well trajectory data;
[0150] The synthetic seismic record generation module 502 is used to obtain seismic data of the seismic work area, determine the statistical wavelet according to the seismic data, and perform calculations according to the well logging data and the statistical wavelet to obtain a synthetic seismic record;
[0151] The time-depth relationship establishment module 503 is used to establish a time-depth relationship according to the seismic composite trace and the synthetic seismic record, and use the time-depth relationship to convert the seismic time sampling points of the seismic data to obtain the oblique depth;
[0152] The work area coordinate selection module 504 is used to extract trajectory coordinates from the well trajectory data according to the deflection depth, and select the work area coordinates from the coordinate data of the seismic work area according to the trajectory coordinates;
[0153] The label data construction module 505 is used to establish an index table according to the work area coordinates and the earthquake time sampling points, and to construct label data according to the index table.
[0154] In detail, each module described in the earthquake information label data construction device 500 described in the embodiment of the present invention adopts the same technical means as the earthquake information label data construction method described in Example 1 and Example 2 when used, and can produce the same technical effects, which will not be repeated here.
[0155] Embodiment 4
[0156] like Figure 6 As shown, this embodiment also provides a computer electronic device, and the electronic device 600 may include a processor 601, a memory 602, a communication bus 603 and a communication interface 604, and may also include a computer program stored in the memory 602 and executable on the processor 601, such as an earthquake information label data construction program.
[0157] Wherein, the processor 601 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 601 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes various functions and processes data of the electronic device by running or executing programs or modules stored in the memory 602 (for example, executing a seismic information tag data construction program, etc.), and calling data stored in the memory 602.
[0158] The memory 602 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 602 may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 602 may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 602 may also include both an internal storage unit of the electronic device and an external storage device. The memory 602 may not only be used to store application software and various types of data installed in the electronic device, such as the code of the earthquake information tag data construction program, but may also be used to temporarily store data that has been output or is to be output.
[0159] The communication bus 603 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 602 and at least one processor 601, etc.
[0160] The communication interface 604 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.
[0161] The figure only shows an electronic device 600 with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.
[0162] For example, although not shown, the electronic device 600 may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 601 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.
[0163] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.
[0164] The earthquake information tag data construction program stored in the memory 602 in the electronic device 600 is a combination of multiple instructions. When running in the processor 601, it can achieve:
[0165] Acquiring well trajectory data and well logging data, and generating a seismic composite trace according to the well trajectory data;
[0166] Acquire seismic data of a seismic work area, determine a statistical wavelet according to the seismic data, and perform calculations according to the well logging data and the statistical wavelet to obtain a synthetic seismic record;
[0167] Establishing a time-depth relationship according to the seismic composite trace and the synthetic seismic record, and converting the seismic time sampling points of the seismic data using the time-depth relationship to obtain the oblique depth;
[0168] Extracting trajectory coordinates from the well trajectory data according to the deflection depth, and selecting work area coordinates from the coordinate data of the seismic work area according to the trajectory coordinates;
[0169] An index table is established according to the work area coordinates and the earthquake time sampling points, and label data is constructed according to the index table.
[0170] Specifically, the specific implementation method of the processor 601 for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.
[0171] Furthermore, if the module / unit integrated in the electronic device 600 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).
[0172] Embodiment 5
[0173] This embodiment provides a storage medium storing a computer program. When the computer program is executed by a processor, the steps of the earthquake information label data construction method described above are implemented.
[0174] These program codes can also be loaded onto a computer or other programmable data processing device so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions executed on the computer or other programmable device for implementing the process. Figure 1 The steps of a specified function in a process or multiple processes.
[0175] Storage media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, modules of programs or other data. Examples of storage media can include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
[0176] Embodiment 6
[0177] A computer program, characterized in that when the computer program is executed by a processor of an electronic device, it can achieve:
[0178] Acquiring well trajectory data and well logging data, and generating a seismic composite trace according to the well trajectory data;
[0179] Acquire seismic data of a seismic work area, determine a statistical wavelet according to the seismic data, and perform calculations according to the well logging data and the statistical wavelet to obtain a synthetic seismic record;
[0180] Establishing a time-depth relationship according to the seismic composite trace and the synthetic seismic record, and converting the seismic time sampling points of the seismic data using the time-depth relationship to obtain the oblique depth;
[0181] Extracting trajectory coordinates from the well trajectory data according to the deflection depth, and selecting work area coordinates from the coordinate data of the seismic work area according to the trajectory coordinates;
[0182] An index table is established according to the work area coordinates and the earthquake time sampling points, and label data is constructed according to the index table.
[0183] A computer program is a set of instructions that a computer can recognize and execute, and runs on an electronic computer. It is written in a programming language and runs on a target architecture. In order for a computer program to run, the computer needs to load code and data. From the bottom layer of the computer, this is a high-level language (such as Java, C / C++, C#, etc.) code translated into machine language and understood by the CPU for loading. If on a computer that meets most standards, an operating system such as Windows, Linux, etc., loads and executes many programs, in this case, each program is a separate mapping, not all executable programs on the computer. A computer program refers to a coded instruction sequence that can be executed by a computer or other device with information processing capabilities in order to obtain a certain result, or a symbolic instruction sequence or symbolic statement sequence that can be automatically converted into a coded instruction sequence.
[0184] 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. When the terms "include" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or their combinations.
[0185] It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or described herein.
[0186] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.
[0187] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0188] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.
[0189] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.
[0190] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.
[0191] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.
[0192] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.
[0193] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.
Claims
1. A method for constructing earthquake information label data, characterized in that: The method comprises: Acquiring well trajectory data and well logging data, and generating a seismic composite trace according to the well trajectory data; Acquire seismic data of a seismic work area, determine a statistical wavelet according to the seismic data, and perform calculations according to the well logging data and the statistical wavelet to obtain a synthetic seismic record; Establishing a time-depth relationship according to the seismic composite trace and the synthetic seismic record, and converting the seismic time sampling points of the seismic data using the time-depth relationship to obtain the oblique depth; Extracting trajectory coordinates from the well trajectory data according to the deflection depth, and selecting work area coordinates from the coordinate data of the seismic work area according to the trajectory coordinates; An index table is established according to the work area coordinates and the earthquake time sampling points, and label data is constructed according to the index table.
2. The earthquake information label data construction method according to claim 1, characterized in that: The determining of the statistical wavelet according to the seismic data comprises: Extracting an analysis time window from the seismic data, and calculating the autocorrelation coefficient of the seismic data within the analysis time window; The autocorrelation coefficient is calculated using the following formula: r=f(t)*f(t) Wherein, r represents the autocorrelation coefficient, and f(t) represents the seismic data within the analysis time window t; Calculating a frequency spectrum according to the autocorrelation coefficient and the analysis time window using a preset Fourier transform method, and calculating an amplitude spectrum according to the frequency spectrum; The Fourier transform method is expressed as: Wherein, G represents the frequency spectrum, r represents the autocorrelation coefficient, t represents the analysis time window, k represents a preset frequency value, e represents a preset natural constant, π represents a preset pi constant, i represents a preset imaginary unit, and i represents a preset imaginary unit. 2 = -1; The amplitude mean values of the plurality of amplitude spectra are calculated, and a statistical wavelet is generated according to the amplitude mean value and a preset standard phase.
3. The earthquake information label data construction method according to claim 1, characterized in that: The step of calculating according to the well logging data and the statistical wavelet to obtain a synthetic seismic record includes: Obtaining a first P-wave velocity and a first density of an upper formation and a second P-wave velocity and a second density of a lower formation in the well logging data, calculating a first P-wave impedance according to the first P-wave velocity and the first density, and calculating a second P-wave impedance according to the second P-wave velocity and the second density; The first longitudinal wave impedance and the second longitudinal wave impedance are calculated using the following formula: z1=v1*ρ1 z2=v2*ρ2 Wherein, z1 represents the first longitudinal wave impedance, z2 represents the second longitudinal wave impedance, v1 represents the first longitudinal wave velocity, ρ1 represents the first density, v2 represents the second longitudinal wave velocity, and ρ2 represents the second density; generating a reflection coefficient according to the first longitudinal wave impedance and the second longitudinal wave impedance, and generating a reflection coefficient sequence according to the reflection coefficient; The reflection coefficient is generated using the following formula: re=(z2-z1) / (z2+z1) Wherein, re represents the reflection coefficient, z1 represents the first longitudinal wave impedance, and z2 represents the second longitudinal wave impedance; Perform convolution calculation according to the reflection coefficient sequence and the statistical wavelet to obtain a synthetic seismic record; The following formula is used for convolution calculation to obtain the synthetic seismic record: x=w×d Wherein, x represents the synthetic seismic record, w represents the statistical wavelet, and d represents the reflection coefficient sequence.
4. The earthquake information label data construction method according to claim 1, characterized in that: The step of establishing a time-depth relationship based on the composite seismic trace and the synthetic seismic record comprises: Adjusting the synthetic seismic record to obtain an updated synthetic seismic record; Matching the composite seismic trace and the updated synthetic seismic record, and extracting the logging inclination depth and time according to the matching result; A time-depth relationship is generated according to the logging deviation depth and the time.
5. The earthquake information label data construction method according to claim 1, characterized in that: The step of converting the seismic time sampling points of the seismic data using the time-depth relationship to obtain the slant depth includes: Determine whether the earthquake time sampling point is consistent with the target time point in the time-depth relationship; When the earthquake time sampling point is inconsistent with the target time point, a time point closest to the earthquake time sampling point is selected from the time-depth relationship, and the target oblique depth corresponding to the time point is used as the oblique depth; When the seismic time sampling point is consistent with the target time point, the target oblique depth corresponding to the target time point in the time-depth relationship is extracted, and the target oblique depth is used as the oblique depth.
6. The earthquake information label data construction method according to claim 1, characterized in that: The extracting trajectory coordinates from the well trajectory data according to the deviated depth comprises: Obtaining the drilling deflection depth in the well trajectory data, and calculating a deflection depth index using the drilling deflection depth and the deflection depth; The slant depth index is calculated using the following formula: L = argmin(|HD|) Wherein, L represents the slant depth index, H represents the slant depth, and D represents the drilling slant depth; The oblique depth index is placed in a preset rectangular coordinate system to obtain index coordinates corresponding to the oblique depth index, and the index coordinates are used as trajectory coordinates.
7. A device for constructing earthquake information label data, characterized in that: The device comprises: A seismic composite trace generation module is used to obtain well trajectory data and well logging data, and generate a seismic composite trace according to the well trajectory data; A synthetic seismic record generation module is used to obtain seismic data of a seismic work area, determine a statistical wavelet according to the seismic data, and perform calculations according to the well logging data and the statistical wavelet to obtain a synthetic seismic record; A time-depth relationship establishment module, used to establish a time-depth relationship according to the seismic composite trace and the synthetic seismic record, and to convert the seismic time sampling points of the seismic data using the time-depth relationship to obtain the oblique depth; A work area coordinate selection module, used for extracting trajectory coordinates from the well trajectory data according to the deflection depth, and selecting work area coordinates from the coordinate data of the seismic work area according to the trajectory coordinates; The label data construction module is used to establish an index table according to the work area coordinates and the earthquake time sampling points, and to construct label data according to the index table.
8. An electronic device, comprising: processor; a memory for storing instructions executable by the processor; Wherein, the processor is configured to execute the instructions to implement the earthquake information label data construction method as described in any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the program is executed by a processor, the earthquake information label data construction method as described in any one of claims 1 to 6 is implemented.
10. A computer program, characterized in that When the program is executed by a processor, the earthquake information label data construction method as described in any one of claims 1 to 6 is implemented.
