Coal rock gas sweet spot area determination method and device, electronic equipment and medium

Abstract

The invention discloses a method and a device for determining a sweet spot area of coal rock gas, electronic equipment and a medium. The method comprises the following steps: determining a three-dimensional seismic pure wave data volume of to-be-processed coal rock gas; according to the three-dimensional seismic pure wave data body, determining a trap type identification result, a coal seam thickness prediction result, a gas source fracture prediction result and an oil gas range prediction result of the to-be-processed coal rock gas; and according to the trap type identification result, the coal seam thickness large prediction result, the gas source fracture existence prediction result and the oil gas range prediction result, determining the sweet spot area of the to-be-processed coal rock gas. According to the method, accurate prediction of the sweet spot area of the coal rock gas reservoir can be realized, so that the success rate of drilling is improved, and the exploration investment cost is saved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of geophysical technology, and in particular to a coal rock gas sweet spot area determination method and device, electronic equipment and medium. BACKGROUND

[0002] The "sweet spot" reservoir refers to a high-quality reservoir with relatively good development and industrial oil and gas flow in a low porosity and low permeability background. The "sweet spot" development area (high yield enrichment area) of coal rock gas is mainly controlled by four factors, i.e. structure (fault nose or fault block), coal rock thickness, gas source fault, and gas saturation. The coal rock thickness of the "sweet spot" area of coal rock gas is small, the vertical fault throw of the gas source fault is small, and the gas-bearing range is difficult to predict. A single geophysical method cannot accurately predict the planar distribution of the "sweet spot" reservoir of coal rock gas. Therefore, there is an urgent need for a planar distribution prediction method for the "sweet spot" area of coal rock gas to accurately predict the planar distribution of the "sweet spot" reservoir of coal rock gas. SUMMARY

[0003] The present application provides a coal rock gas sweet spot area determination method, device, electronic equipment and medium to accurately predict the coal rock gas sweet spot area.

[0004] In a first aspect, the present application provides a coal rock gas sweet spot area determination method, which comprises:

[0005] determining a three-dimensional seismic pure wave data volume of the coal rock gas to be processed;

[0006] determining a trap type identification result, a coal seam thickness prediction result, a gas source fault prediction result, and an oil and gas range prediction result of the coal rock gas to be processed according to the three-dimensional seismic pure wave data volume;

[0007] determining a sweet spot area of the coal rock gas to be processed according to the trap type identification result, the coal seam thickness prediction result, the gas source fault prediction result, and the oil and gas range prediction result.

[0008] In a second aspect, the present application also provides a coal rock gas sweet spot area determination device, which comprises:

[0009] a three-dimensional seismic pure wave data volume determination module for determining a three-dimensional seismic pure wave data volume of the coal rock gas to be processed;

[0010] a prediction module for determining a trap type identification result, a coal seam thickness prediction result, a gas source fault prediction result, and an oil and gas range prediction result of the coal rock gas to be processed according to the three-dimensional seismic pure wave data volume;

[0011] a sweet spot area determination module for determining a sweet spot area of the coal rock gas to be processed according to the trap type identification result, the coal seam thickness prediction result, the gas source fault prediction result, and the oil and gas range prediction result.

[0012] Thirdly, embodiments of the present invention also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for determining the sweet spot region of coalbed methane as described in any of the embodiments of the present invention.

[0013] Fourthly, embodiments of the present invention also provide a storage medium for storing computer-executable instructions, which, when executed by a computer processor, are used to perform the method for determining a sweet spot region of coal shale gas as described in any of the embodiments of the present invention.

[0014] The technical solution of this invention processes the three-dimensional seismic pure wave data of the coal-rock gas to be processed, identifying trap types, predicting coal seam thickness, predicting gas source fractures, and predicting oil and gas extent. Based on the trap type identification results, coal seam thickness prediction results, gas source fracture prediction results, and oil and gas extent prediction results, the sweet spot region of the coal-rock gas to be processed is determined. This technical solution can accurately predict the planar distribution of sweet spot reservoirs for coal-rock gas, improve drilling success rates, and save exploration investment costs.

[0015] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of a method for determining a sweet spot region of coal shale gas according to Embodiment 1 of the present invention;

[0018] Figure 2 This is a schematic diagram of the distribution pattern of coal rock gas in cross-section and plane provided in Embodiment 1 of the present invention;

[0019] Figure 3 This is a gas source fracture prediction plan view of coal and rock gas provided in Embodiment 1 of the present invention;

[0020] Figure 4 This is a cross-sectional and planar schematic diagram of a coal-rock gas oil and gas range prediction method provided in Embodiment 1 of the present invention;

[0021] Figure 5 This is a schematic diagram of a coal-rock-gas superposition region provided in Embodiment 1 of the present invention;

[0022] Figure 6 This is a schematic diagram of the structure of a device for determining the sweet spot region of coal rock gas according to Embodiment 2 of the present invention;

[0023] Figure 7 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. In the embodiments of this application, certain software, components, models, and other existing industry solutions may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solutions of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0026] The acquisition, transmission, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0027] Example 1

[0028] Figure 1The flowchart of a method for determining sweet spots in coal gas according to Embodiment 1 of the present invention is provided. This embodiment is applicable to the prediction of sweet spots in coal gas reservoirs. The method can be executed by a device for determining sweet spots in coal gas, which can be implemented in hardware and / or software and can be configured in an electronic device.

[0029] like Figure 1 As shown, the method includes:

[0030] S110. Determine the three-dimensional seismic pure wave data volume of the coal and shale gas to be processed.

[0031] Among them, the coal shale gas to be processed refers to the coal shale gas for which sweet spot regions need to be identified to guide the adjustment of horizontal well trajectories. A 3D seismic pure wave data volume refers to a data volume formed by recording and organizing information such as amplitude, frequency, and phase of a series of seismic waves in three-dimensional space. 3D seismic pure wave data volumes can be obtained through seismic acquisition equipment such as seismic detectors, and the acquired raw data undergoes a series of processing operations such as denoising, filtering, amplitude recovery, and superposition.

[0032] Three-dimensional seismic pure wave data volumes can identify underground geological structures such as faults and folds; predict and interpret the lithology of underground strata; and provide detailed information about the strata, such as stratum thickness and interface undulations. Therefore, in this embodiment, based on the three-dimensional seismic pure wave data volumes of the coal-rock gas to be processed, subsequent trap type identification, coal-rock thickness prediction, gas source fracture prediction, and oil and gas range prediction are performed, ultimately determining the planar distribution range of the "sweet spot" reservoir.

[0033] S120. Based on the three-dimensional seismic pure wave data volume, determine the trap type identification results, coal seam thickness prediction results, gas source fracture prediction results, and oil and gas range prediction results of the coal and rock gas to be processed.

[0034] In this context, a trap refers to a seismic structure capable of accumulating and storing oil and gas, a high-yield and enriched area of ​​coal and gas, also known as a "sweet spot" region. The trap type is typically a fault nose or a fault block. A fault nose is a trap formed by a combination of faults and nose-like structures, while a fault block is an independent fault-block body formed by multiple faults intersecting each other. Seismic interpretation software can be used to interpret 3D seismic pure wave data volumes, extract depth information of stratigraphic interfaces, draw structural maps, and identify trap types based on these maps. Sedimentary facies studies can also be conducted on 3D seismic pure wave data volumes to infer the location of favorable facies zones by analyzing the depositional process and distribution patterns of the coal and gas to be processed. This embodiment does not limit the specific method for trap type identification.

[0035] "Sweet spots" typically represent areas with thicker coal seams. Coal seam thickness prediction can be achieved using methods based on seismic attributes. For example, by analyzing the amplitude and frequency attributes of 3D seismic pure wave data volumes, coal seam thickness can be predicted. Within the tuned thickness range, generally, the stronger the reflected wave amplitude, the greater the coal seam thickness; the lower the dominant frequency of the seismic wave, the greater the predicted coal seam thickness. Alternatively, impedance inversion can be performed on 3D seismic pure wave data volumes. The impedance of the coal seam differs significantly from that of the surrounding rock. By inverting the impedance of the strata, the coal seam thickness can be predicted based on the changes in impedance. This embodiment does not limit the specific method used for coal seam thickness prediction.

[0036] Gas source fractures refer to fractures in oil and gas basins that play a crucial role in the migration and accumulation of natural gas. The "sweet spots" of coal-fired gas typically exhibit small vertical displacements in gas source fractures; therefore, the accuracy of gas source fracture prediction is particularly important. Gas source fractures can be identified by analyzing stratigraphic distribution, contact relationships, and lithological variation characteristics through geological mapping and stratigraphic correlation. Furthermore, the location of gas source fractures can be predicted by finely interpreting 3D seismic pure wave data volumes, analyzing the geometric morphology and energy variations of reflected wave phase axes, and by processing and interpreting gravity and magnetic exploration data to analyze the distribution and characteristics of anomalies. This embodiment does not limit the specific methods used for gas source fracture prediction.

[0037] Oil and gas extent is the area where oil and gas may accumulate. Oil and gas extent prediction can be achieved through AVO analysis or through seismic attribute analysis of three-dimensional seismic pure wave data volumes, such as amplitude attributes and frequency attributes. This embodiment does not limit the specific method used for oil and gas extent prediction.

[0038] Furthermore, based on the 3D seismic pure wave data volume, the trap type identification results of the coal and gas to be processed are determined, including:

[0039] A1. Based on the three-dimensional seismic pure wave data volume, the top and bottom layers of the coal and rock gas to be processed are calibrated;

[0040] A2. Perform a 90° phase shift on the calibrated top and bottom layer data volumes;

[0041] A3. Based on the global automatic seismic sequence stratigraphy interpretation technology, interpret the top and bottom layers after phase shift, compile structural maps, and determine the trap type identification results of the coal and rock gas to be processed.

[0042] Specifically, based on the 3D seismic pure wave data volume, the top and bottom layers of the coal and gas to be processed are calibrated. Synthetic seismic records are generated using a convolution model based on the sonic transit time and density logging curves from the well. The synthetic seismic records are then compared with the 3D seismic pure wave data volume at the well location to preliminarily determine the top and bottom layers of the coal and gas to be processed, and the top and bottom layers are then calibrated.

[0043] A 90° phase shift of the top and bottom layers can help identify and interpret the coal and rock thickness distribution, and facilitate lateral stratigraphic correlation.

[0044] Global automatic seismic sequence stratigraphy is a technique that uses computer algorithms and specific mathematical models to comprehensively analyze the entire seismic data volume and automatically identify and delineate seismic sequence stratigraphic units.

[0045] In this embodiment, global automatic seismic sequence stratigraphy is used to identify reflection patterns in 3D seismic pure wave data volumes using computer algorithms. Different stratigraphic interfaces exhibit different reflection characteristics on seismic profiles, such as strong reflections, continuous reflections, and discontinuous reflections. Pattern recognition algorithms automatically detect changes in these reflection characteristics to determine the top and bottom layers of the coal-rock gas to be processed. Trap types are identified by analyzing the geometric morphology of the reflection wave phase axes in the 3D seismic pure wave data volumes. For example, global automatic seismic sequence stratigraphy can detect the discontinuity of reflection wave phase axes, thereby determining the location and displacement of faults and identifying fault block traps.

[0046] Furthermore, based on the 3D seismic pure wave data volume, the predicted coal seam thickness is determined, including:

[0047] B1. Perform frequency division processing on the three-dimensional seismic pure wave data volume to obtain frequency-divided seismic trace data, and perform integration operation on the frequency-divided seismic trace data to obtain channel-divided integrated data.

[0048] B2. Input the frequency-division seismic trace data and channel-division integral data into the pre-trained coal seam thickness prediction model to obtain the coal seam thickness prediction results output by the coal seam thickness prediction model.

[0049] The coal seam thickness prediction model is obtained by training a pre-set machine learning model based on the sample frequency-division seismic trace data and sample channel integral data corresponding to the sample well. During model training, the seismic trace matching the sample well is used as the feature vector, and the natural gamma logging curve of the sample well is used as the label of the sample well.

[0050] Specifically, on the three-dimensional seismic pure wave data volume of the coal and shale gas to be processed, high-frequency data (e.g., dominant frequency 50Hz), mid-frequency data (e.g., dominant frequency 35Hz), and low-frequency data (e.g., dominant frequency 30Hz) are selected to obtain frequency-division seismic trace data. The amplitude values ​​of the frequency-division seismic trace data are integrated over a certain depth range to obtain channel-division integrated data.

[0051] The frequency-division seismic trace data and channel-division integral data are input into the coal seam thickness prediction model, and the coal seam thickness prediction model outputs the coal seam thickness prediction results. Figure 2 A schematic diagram of the distribution morphology of coal and rock in cross-section and plan view is provided, such as Figure 2 (a) shows a schematic diagram of a coal and rock profile. Figure 2 (b) is a schematic diagram of coal and rock in a plane. The distribution pattern of coal and rock in the cross section and plane can be used as the result of coal seam thickness prediction.

[0052] For the training process of the coal seam thickness prediction model, specifically, the natural gamma logging curve is the logging curve obtained by performing natural gamma logging on sample wells. When matching the well and seismic information of the sample wells, the sampling interval of the natural gamma logging curve is enlarged to be the same as the seismic sampling interval, for example, 1 ms. High-frequency data (e.g., dominant frequency 50Hz), mid-frequency data (e.g., dominant frequency 35Hz), and low-frequency data (e.g., dominant frequency 30Hz) are selected from the 3D seismic pure wave data volume of the sample wells to obtain sample frequency-division seismic trace data. The amplitude values ​​of the sample frequency-division seismic trace data are integrated within a certain depth range to obtain sample channel-division integrated data.

[0053] The sample wells' corresponding frequency-division seismic trace data and sample channel-division integral data are used as input data for the machine learning model. Furthermore, the sample wells can be divided into training, testing, and validation sets. For example, 60% of the sample wells' corresponding frequency-division seismic trace data and sample channel-division integral data can be used as the training set, 20% as the testing set, and 20% as the validation set.

[0054] When the machine learning model processes each input data, it extracts the seismic traces that match the sample well, that is, the seismic traces around the sample well, as feature vectors, and uses the natural gamma logging curve of the sample well as labels to train the machine learning model, and finally obtains the trained coal seam thickness prediction model.

[0055] In this embodiment, the natural gamma logging curve is used as a label to train the coal seam thickness prediction model. The advantage of this setting is that the volume attribute values ​​of the inversion data obtained from the natural gamma logging curve reflect the distribution characteristics of natural gamma to a certain extent, thereby predicting the distribution pattern of coal and rock in the profile and plane.

[0056] Furthermore, based on the 3D seismic pure wave data volume, the predicted gas source fracture results are determined, including:

[0057] C1. Interpretive processing of 3D seismic pure wave data volume is performed through guided filtering and low-frequency filtering;

[0058] C2. Based on the three-dimensional seismic pure wave data volume after interpretive processing, determine the seismic data elements, number of samples, and fault response characteristics;

[0059] C3. Input the seismic data elements, number of samples, and fault response characteristics into the pre-trained gas source fracture prediction model to obtain the gas source fracture prediction results output by the gas source fracture prediction model.

[0060] The gas source fracture prediction model is obtained by training a pre-set machine learning model based on the sample seismic data surface elements, sample sampling number, and sample fault response characteristics corresponding to the sample wells.

[0061] Among them, guided filtering is a filtering method based on a local linear model, which can effectively remove noise from 3D seismic pure wave data volumes while preserving the geological structure and boundary information, and enhancing specific geological features within the data volume. Low-frequency filtering mainly operates on the frequency components of 3D seismic pure wave data volumes, removing high-frequency noise while highlighting large-scale geological structures.

[0062] In this embodiment, the combination of guided filtering and low-frequency filtering methods for interpreting 3D seismic pure wave data can enhance the response characteristics of fault seismic data. For example, guided filtering may highlight stratigraphic interfaces, while low-frequency filtering can make the overall morphology of the fault clearer, facilitating the analysis of fault structures.

[0063] Seismic data elements are small, three-dimensional regions defined during seismic data acquisition and processing, facilitating the regularization of seismic data. Seismic data elements can allocate seismic data from different excitation and reception points according to their spatial location, thereby improving the efficiency and accuracy of data processing. The number of samples refers to the number of points where the seismic wave signal is discretely sampled in the time domain during seismic data acquisition. On a seismic profile, the most obvious response characteristic of a fault is the discontinuity of the reflection wave's phase axis. Due to the presence of a fault, the strata shift, and the originally continuous reflection interface becomes discontinuous on both sides of the fault, resulting in temporal displacement of the reflected wave.

[0064] The seismic data elements, sampling number, and fault response characteristics are used as input data and fed into the gas source fracture prediction model, which then outputs the gas source fracture prediction results. Figure 3 A gas source fracture prediction planar diagram of coal and rock is provided, which serves as the prediction result of gas source fracture.

[0065] The training process for the gas source fracture prediction model involves interpreting the 3D seismic pure wave data volume of the sample wells to determine the corresponding seismic data elements, sampling number, and fault response characteristics. It's important to note that the size of the seismic data elements corresponding to the sample wells should be consistent with the size of the seismic data elements for the coal and shale gas to be processed. Using the seismic data elements, sampling number, and fault response characteristics of the sample wells as input data, a pre-set machine learning model is trained to obtain the trained gas source fracture prediction model. To improve the accuracy of fault prediction, different gas source fracture prediction models can be trained for sample wells with different fault properties and different vertical fault displacements. When predicting the gas source fractures of the coal and shale gas to be processed, the model that best matches the coal and shale gas is selected to improve the accuracy of the prediction.

[0066] Furthermore, based on the 3D seismic pure wave data volume, the predicted hydrocarbon extent is determined, including:

[0067] D1. Determine the pre-stack common reflection point gathers based on the 3D seismic pure wave data volume;

[0068] D2. Perform at least one preprocessing step on the pre-stack common reflection point gather, including: noise reduction, gather flattening, and harmonic processing;

[0069] D3. The pre-processed pre-stack common reflection point gathers are subjected to angle gather forward modeling, and the sensitive attributes for oil and gas range prediction are determined based on the angle gather forward modeling results.

[0070] D4. Based on the sensitive attributes of oil and gas range prediction, perform oil and gas range prediction by changing the pre-stack amplitude with the offset, and obtain the oil and gas range prediction results.

[0071] Pre-stack CRP (Common Reflection Point) gathers are data sets formed by grouping seismic traces with the same reflection point together in seismic exploration. In 3D seismic pure wave data volumes, seismic traces with the same reflection point are selected to form pre-stack CRP gathers.

[0072] The purpose of preprocessing pre-stack CRP gathers is to optimize their quality. Oil and gas extent prediction requires seismic data with high fidelity, high signal-to-noise ratio, and high resolution. Therefore, it is necessary to optimize the data quality of pre-stack CRP gathers to ensure the accuracy of oil and gas extent prediction.

[0073] Specifically, random noise in pre-stack CRP gather data can be removed by filtering techniques, coherent noise such as multiple waves can be eliminated by predictive deconvolution, and coherent noise such as surface waves can be removed by frequency-wavenumber domain (FK domain) filtering. This embodiment does not limit the specific method of denoising.

[0074] For seismic traces with the same reflection point in the same gather, the phase axis of their reflected waves should be horizontal (i.e., flattened). That is, at the zero offset time point, all seismic waves from the same reflection point should be time-aligned. Gather flattening can be performed using dynamic correction formulas, etc. This embodiment does not limit the specific method of gather flattening.

[0075] Harmonic processing refers to high-frequency recovery of pre-stack common reflection point (CRP) gather data to improve its resolution. This can be achieved by performing spectral analysis on the pre-stack CRP gather to determine the signal's spectral characteristics, particularly identifying harmonic frequency components. Based on the harmonic analysis results, a suitable deconvolution algorithm is designed, and high-frequency recovery is performed by adjusting and optimizing relevant parameters within the algorithm. However, this embodiment does not limit the specific methods of harmonic processing and high-frequency recovery.

[0076] Angle gather forward modeling refers to grouping seismic traces with the same incident or reflection angle together. The data obtained from angle gather forward modeling is an important foundation for AVO (Amplitude Versus Offset) analysis. Specifically, angle gather forward modeling is performed using the characteristics of P-wave and S-wave velocity and density curves after coal and rock fluid substitution. The forward modeling shows that the coal and rock amplitude increases with increasing gas saturation, and the P+G fluid factor also increases with increasing gas saturation. Therefore, the P+G attribute can be used as a sensitive attribute for predicting the planar oil and gas extent. The P attribute is related to the intercept term obtained from the simplified or approximate Zoeppritz equation in AVO analysis, while the G attribute is related to the gradient of the reflection coefficient with the offset in AVO analysis. By jointly analyzing the P+G attributes, anomalous areas associated with oil and gas can be identified more effectively.

[0077] Figure 4 A cross-sectional and planar schematic diagram for predicting the oil and gas extent of coal and rock is provided. Figure 4 (a) is a schematic diagram of the predicted oil and gas range profile. Figure 4 (b) is a schematic diagram of the planar prediction of oil and gas range.

[0078] S130. Based on the trap type identification results, coal seam thickness prediction results, gas source fracture prediction results, and oil and gas range prediction results, determine the sweet spot region of the coal rock gas to be processed.

[0079] In this embodiment, the sweet spot region is controlled by four factors: trap type, coal seam thickness, gas source fracture, and gas abundance. The sweet spot region is usually a trap type of fault block or fault nose, with a large coal seam thickness, gas source fracture, and high gas abundance.

[0080] Furthermore, S130 may include:

[0081] S1. Determine the overlapping area of ​​the predicted coal seam thickness, gas source fracture, and oil and gas range.

[0082] S2. If the trap type identification result of the overlapping area is determined to be a broken nose or a broken block, then the overlapping area is regarded as the sweet spot area of ​​the coal and rock gas to be processed.

[0083] Specifically, the planar maps corresponding to the predicted coal seam thickness, gas source fracture, and oil and gas range can be overlaid to determine the overlapping area. Figure 5 A schematic diagram of the overlapping region is provided, such as... Figure 5 As shown, the overlapping area of ​​the planar maps corresponding to the coal seam thickness prediction results, gas source fracture prediction results, and oil and gas range prediction results is taken as the superimposed area. The superimposed area is characterized by a large coal seam thickness, the presence of gas source fractures, the presence of oil and gas ranges, and a large gas abundance.

[0084] Furthermore, the trap type of the overlapping area is checked. The trap type of the sweet spot area is usually a fault block or a fault nose. Therefore, if the trap type of the overlapping area is a fault nose or a fault block, the overlapping area is the sweet spot area of ​​the coal and rock gas to be processed.

[0085] Following S130, it also includes: adjusting the designed horizontal well trajectory based on the sweet spot region of the coal and rock gas to be processed.

[0086] Specifically, to improve drilling success rates, it is necessary to ensure that the well trajectory of horizontal wells remains within the sweet spot region. Therefore, real-time monitoring of the horizontal well trajectory and dynamic adjustment of the designed horizontal well trajectory when it deviates from or shows a tendency to deviate from the sweet spot region can improve drilling success rates and save exploration investment costs.

[0087] The technical solution of this invention processes the three-dimensional seismic pure wave data of the coal-rock gas to be processed, identifying trap types, predicting coal seam thickness, predicting gas source fractures, and predicting oil and gas extent. Based on the trap type identification results, coal seam thickness prediction results, gas source fracture prediction results, and oil and gas extent prediction results, the sweet spot region of the coal-rock gas to be processed is determined. This technical solution can accurately predict the planar distribution of sweet spot reservoirs for coal-rock gas, improve drilling success rates, and save exploration investment costs.

[0088] Example 2

[0089] Figure 6 This is a schematic diagram of a device for determining a sweet spot region of coal shale gas according to Embodiment 2 of the present invention. Figure 6 As shown, the device includes:

[0090] The 3D seismic pure wave data volume determination module 210 is used to determine the 3D seismic pure wave data volume of the coal and rock gas to be processed;

[0091] The prediction module 220 is used to determine the trap type identification result, coal seam thickness prediction result, gas source fracture prediction result, and oil and gas range prediction result of the coal and rock gas to be processed based on the three-dimensional seismic pure wave data volume.

[0092] The sweet spot region determination module 230 is used to determine the sweet spot region of the coalbed methane to be processed based on the trap type identification results, coal seam thickness prediction results, gas source fracture prediction results, and oil and gas range prediction results.

[0093] The technical solution of this invention processes the three-dimensional seismic pure wave data of the coal-rock gas to be processed, identifying trap types, predicting coal seam thickness, predicting gas source fractures, and predicting oil and gas extent. Based on the trap type identification results, coal seam thickness prediction results, gas source fracture prediction results, and oil and gas extent prediction results, the sweet spot region of the coal-rock gas to be processed is determined. This technical solution can accurately predict the planar distribution of sweet spot reservoirs for coal-rock gas, improve drilling success rates, and save exploration investment costs.

[0094] Based on the above embodiments, optionally, the prediction module 220 includes:

[0095] Top and bottom layer calibration units are used to calibrate the top and bottom layers of the coal and rock gas to be processed based on the three-dimensional seismic pure wave data volume.

[0096] The phase shift unit is used to perform a 90° phase shift on the calibrated top and bottom bit data volumes;

[0097] The trap type identification unit is used to interpret the top and bottom layers after phase shift based on global automatic seismic sequence stratigraphy, compile structural maps, and determine the trap type identification results of the coal and rock gas to be processed.

[0098] Based on the above embodiments, optionally, the prediction module 220 includes:

[0099] The data acquisition unit is used to perform frequency division processing on the three-dimensional seismic pure wave data volume to obtain frequency-divided seismic trace data, and to perform integration operation on the frequency-divided seismic trace data to obtain channel-divided integrated data.

[0100] The coal seam thickness prediction unit is used to input frequency-division seismic trace data and channel-division integral data into the pre-trained coal seam thickness prediction model to obtain the coal seam thickness prediction result output by the coal seam thickness prediction model.

[0101] The coal seam thickness prediction model is obtained by training a pre-set machine learning model based on the sample frequency-division seismic trace data and sample channel integral data corresponding to the sample well. During model training, the seismic trace matching the sample well is used as the feature vector, and the natural gamma logging curve of the sample well is used as the label of the sample well.

[0102] Based on the above embodiments, optionally, the prediction module 220 includes:

[0103] The interpretive processing unit is used to interpret the three-dimensional seismic pure wave data volume through guided filtering and low-frequency filtering;

[0104] The input data determination unit is used to determine the seismic data elements, number of samples, and fault response characteristics based on the three-dimensional seismic pure wave data volume after interpretive processing.

[0105] The gas source fracture prediction unit is used to input the seismic data surface elements, sampling number and fault response characteristics into the pre-trained gas source fracture prediction model to obtain the gas source fracture prediction results output by the gas source fracture prediction model.

[0106] The gas source fracture prediction model is obtained by training a pre-set machine learning model based on the sample seismic data surface elements, sample sampling number, and sample fault response characteristics corresponding to the sample wells.

[0107] Based on the above embodiments, optionally, the prediction module 220 includes:

[0108] The pre-stack common reflection point gather determination unit is used to determine the pre-stack common reflection point gather based on the 3D seismic pure wave data volume.

[0109] The preprocessing unit is used to perform at least one preprocessing on the pre-stack common reflection point gather, including: denoising, gather flattening and harmonic processing;

[0110] Angle gather forward modeling unit is used to perform angle gather forward modeling on pre-processed pre-stack common reflection point gathers, and to determine the sensitive attributes for oil and gas range prediction based on the angle gather forward modeling results.

[0111] The oil and gas range prediction unit is used to predict the oil and gas range by changing the pre-stack amplitude with the offset based on the sensitive attributes of oil and gas range prediction, and obtain the oil and gas range prediction results.

[0112] Based on the above embodiments, optionally, the dessert area determination module 230 includes:

[0113] The overlapping region determination unit is used to determine the overlapping region of the coal seam thickness prediction results, gas source fracture prediction results, and oil and gas range prediction results.

[0114] The sweet spot region determination unit is used to identify the overlapping region as a sweet spot region of the coal and rock gas to be processed if the identification result of the trap type of the overlapping region is a broken nose or a broken block.

[0115] Optionally, based on the above embodiments, the apparatus further includes:

[0116] The horizontal well trajectory adjustment module is used to adjust the designed horizontal well trajectory according to the sweet spot region of the coal and rock gas to be processed.

[0117] The apparatus for determining the sweet spot region of coal shale gas provided in the embodiments of the present invention can execute the method for determining the sweet spot region of coal shale gas provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0118] Example 3

[0119] Figure 7 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0120] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0121] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0122] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method for determining sweet spots in coal shale gas.

[0123] In some embodiments, the method for determining the sweet spot region may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining the sweet spot region described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for determining the sweet spot region of coal shale gas by any other suitable means (e.g., by means of firmware).

[0124] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0125] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0126] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0127] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0128] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0129] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0130] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0131] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining a sweet spot region of coal shale gas, characterized in that, include: Determine the three-dimensional seismic pure wave data volume of the coal and rock gas to be processed; Based on the three-dimensional seismic pure wave data volume, the trap type identification results, coal seam thickness prediction results, gas source fracture prediction results, and oil and gas range prediction results of the coal and rock gas to be processed are determined. Based on the trap type identification results, coal seam thickness prediction results, gas source fracture prediction results, and oil and gas range prediction results, the sweet spot region of the coal rock gas to be processed is determined.

2. The method according to claim 1, characterized in that, Based on the 3D seismic pure wave data volume, the trap type identification results of the coal and rock gas to be processed are determined, including: Based on the three-dimensional seismic pure wave data volume, the top and bottom layers of the coal and rock gas to be processed are calibrated; A 90° phase shift is applied to the data volumes of the calibrated top and bottom layers; Based on global automatic seismic sequence stratigraphy, the top and bottom layers after phase shift are interpreted, structural maps are compiled, and the trap type identification results of the coal and rock gas to be processed are determined.

3. The method according to claim 1, characterized in that, Based on the 3D seismic pure wave data volume, the predicted coal seam thickness is determined, including: Frequency division processing is performed on the three-dimensional seismic pure wave data volume to obtain frequency-divided seismic trace data, and integration operation is performed on the frequency-divided seismic trace data to obtain channel-divided integrated data; The frequency-division seismic trace data and channel-division integral data are input into the pre-trained coal seam thickness prediction model to obtain the coal seam thickness prediction results output by the coal seam thickness prediction model. The coal seam thickness prediction model is obtained by training a pre-set machine learning model based on the sample frequency-division seismic trace data and sample channel integral data corresponding to the sample well. During model training, the seismic trace matching the sample well is used as the feature vector, and the natural gamma logging curve of the sample well is used as the label of the sample well.

4. The method according to claim 1, characterized in that, Based on the 3D seismic pure wave data volume, the predicted results of gas source fractures are determined, including: Interpretive processing of 3D seismic pure wave data volumes is performed using guided filtering and low-frequency filtering. Based on the three-dimensional seismic pure wave data volume after interpretive processing, the seismic data elements, number of samples, and fault response characteristics are determined. The seismic data elements, number of samples, and fault response characteristics are input into the pre-trained gas source fracture prediction model to obtain the gas source fracture prediction results output by the gas source fracture prediction model. The gas source fracture prediction model is obtained by training a pre-set machine learning model based on the sample seismic data surface elements, sample sampling number, and sample fault response characteristics corresponding to the sample wells.

5. The method according to claim 1, characterized in that, Based on the 3D seismic pure wave data volume, the predicted hydrocarbon extent is determined, including: Based on the 3D seismic pure wave data volume, determine the pre-stack common reflection point gather; Perform at least one preprocessing step on the pre-stack common reflection point gather, including: denoising, gather flattening, and harmonic processing; Angle gather forward modeling was performed on the pre-processed pre-stack common reflection point gathers, and the sensitive attributes for hydrocarbon range prediction were determined based on the angle gather forward modeling results. Based on the sensitive attributes of oil and gas range prediction, oil and gas range prediction is performed by changing the pre-stack amplitude with offset, and the oil and gas range prediction results are obtained.

6. The method according to claim 1, characterized in that, Based on the trap type identification results, coal seam thickness prediction results, gas source fracture prediction results, and oil and gas range prediction results, the sweet spot region of the coalbed methane to be processed was determined, including: Determine the overlapping area of ​​the predicted coal seam thickness, gas source fracture, and oil and gas extent. If the trap type identification result of the overlapping region is determined to be a broken nose or a broken block, then the overlapping region is regarded as the sweet spot region of the coal and rock gas to be processed.

7. The method according to any one of claims 1-6, characterized in that, After identifying the sweet spot region of the coal shale gas to be processed, the following is also included: The trajectory of the designed horizontal well is adjusted based on the sweet spot region of the coal and rock gas to be processed.

8. A device for determining a sweet spot region of coal shale gas, characterized in that, include: The 3D seismic pure wave data volume determination module is used to determine the 3D seismic pure wave data volume of the coal and gas to be processed. The prediction module is used to determine the trap type identification result, coal seam thickness prediction result, gas source fracture prediction result, and oil and gas range prediction result of the coal and gas to be processed based on the three-dimensional seismic pure wave data volume. The sweet spot region determination module is used to determine the sweet spot region of the coalbed methane to be processed based on the trap type identification results, coal seam thickness prediction results, gas source fracture prediction results, and oil and gas range prediction results.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method for determining the sweet spot region of coal shale gas as described in any one of claims 1-7.

10. A storage medium for storing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the method for determining the sweet spot region of coal shale gas as described in any one of claims 1-7.

Images