A method and apparatus for while-drilling prediction of seismic drilling data of a target layer

Abstract

The application provides a method and device for predicting a target layer seismic drilling data while drilling, wherein the method comprises the following steps: generating geological layered depth domain data according to two-dimensional drilling data and two-dimensional logging data, so as to establish a time-depth dictionary; determining a first contribution degree of GST structure characteristic attribute data, a second contribution degree of amplitude energy attribute data and a third contribution degree of frequency absorption attenuation attribute data from three-dimensional seismic data, so as to establish initial seismic drilling data characterized by multiple and multiple types of composite attributes; obtaining real-time two-dimensional drilling data, so as to obtain updated first, second and third contribution degrees and obtain seismic drilling prediction data of the target layer characterized by multiple and multiple types of composite attributes. Through the above scheme, the technical problem of low accuracy in existing hole reservoir prediction by a single attribute is solved, and the technical effect of effectively improving reservoir prediction accuracy and reducing drilling risk is achieved.

Description

Technical Field

[0001] This application belongs to the field of geological exploration technology, and in particular relates to a method and apparatus for predicting seismic drilling data of a target layer while drilling. Background Technology

[0002] The reserves of carbonate oil and gas resources are very large. The carbonate reservoirs in the Tarim Basin are deep, with extremely high seismic wave velocities and complex storage spaces, mainly consisting of secondary dissolution pores or fractures. The development method of using one set of fractured cavities in one well cannot meet the needs of efficient development. A well needs to connect multiple fractured cavities as much as possible to achieve the needs of efficient development.

[0003] Underground karst caves and fissures are not isolated entities; they possess consistent water pressure conditions and form relatively independent cave-fractured systems, collectively known as cave-fractured bodies. On post-stack seismic profiles, cavities exhibit a "beaded" seismic characteristic with strong reflection amplitudes, a small lateral range, and significant longitudinal differences. This "beaded" seismic characteristic is often superimposed on underlying phase axes and noise, making it difficult to identify. In actual geological exploration, there are many types of "beaded anomalies." To study the formation mechanism of "beaded" anomalies in carbonate pore reservoirs, numerical and seismic physical models are generally used, employing wave equation numerical simulations and laboratory physical simulations for forward response studies. Currently, seismic interpretation of carbonate pore reservoirs is mostly divided into two categories: the first is the traditional identification method based on seismic data attributes and frequency variation intensity identification methods for "beaded" anomaly reflections; the second is the identification method that uses artificial intelligence to extract the "beaded" anomaly reflection characteristics of pore reservoirs. However, existing methods only consider identifying the "beaded" anomalous reflections formed by seismic diffraction waves, such as using root mean square amplitude, wave impedance inversion, and attribute-based "beaded" edge detection. They neglect the absorption and attenuation viscosity effect of fluids in carbonate pore reservoirs on seismic waves, failing to provide real-time updates of pore edge locations in drilling scenarios to guide drilling. Furthermore, existing identification methods describe reservoirs from kinematic characteristics using single seismic attributes, neglecting internal reservoir information, resulting in high uncertainty and inaccurate identification of pore reservoir boundaries, making it difficult to meet the safety requirements of "one well, multiple controls" during drilling.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] The purpose of this application is to provide a method and apparatus for predicting seismic drilling data of a target layer while drilling, which can solve the technical problem of low accuracy in existing methods for predicting pore reservoirs using a single attribute.

[0006] This application provides a method and apparatus for predicting seismic drilling data of a target layer while drilling, which is implemented as follows:

[0007] A method for predicting seismic drilling data of a target layer while drilling, the method comprising:

[0008] Two-dimensional drilling data and two-dimensional logging data are acquired, and geological stratification depth domain data are generated based on the two-dimensional drilling data and the two-dimensional logging data.

[0009] The geological stratification depth domain data is matched with the stratum time domain data to establish a time-depth dictionary;

[0010] Acquire three-dimensional seismic data, and extract gradient structure tensor (GST) structural characteristic attribute data, amplitude energy attribute data, and frequency absorption attenuation attribute data from the three-dimensional seismic data;

[0011] The first contribution of GST structural characteristic attribute data, the second contribution of amplitude energy attribute data, and the third contribution of frequency absorption attenuation attribute data were determined, and the initial seismic drilling data with multi-element and multi-type composite attribute characterization was established.

[0012] Acquire real-time two-dimensional drilling data, and map the two-dimensional drilling data to three-dimensional drilling seismic data according to the time-depth dictionary;

[0013] Based on the aforementioned three-dimensional seismic data while drilling, the first contribution, second contribution, and third contribution are updated;

[0014] Based on the updated first, second, and third contribution values, seismic drilling prediction data for the target layer with multi-variable and multi-type composite attribute representations are obtained.

[0015] In one implementation, the initial seismic drilling data characterized by the multi-variable and multi-type composite attributes is represented as follows:

[0016]

[0017] Among them, R 1 This is the initial data from seismic drilling. A represents GST structural characteristic attribute data, B represents amplitude energy attribute data, and C represents frequency absorption attenuation attribute data. Indicates the initial first contribution. Indicates the initial second contribution level. This indicates the initial third contribution level.

[0018] In one implementation, updating the first contribution, second contribution, and third contribution based on the three-dimensional seismic data while drilling includes:

[0019] Establish the following objective function:

[0020]

[0021] Among them, D n This represents the 3D seismic data after the nth update. The seismic drilling prediction data is characterized by multi-variable and multi-type composite attributes after the nth update;

[0022] The objective function is solved using the following formula:

[0023] l=(S T S) -1 S T D

[0024] Where l represents the first contribution, the second contribution, and the third contribution; S is an l×3 matrix composed of the feature parameters of the three types of attribute data; and D is an l×1 updated three-dimensional seismic data while drilling.

[0025] The first, second, and third contributions obtained from the solution are used as the updated first, second, and third contributions.

[0026] In one implementation, the geological stratification depth domain data is matched with the stratigraphic time domain data to establish a time-depth dictionary, including:

[0027] By using the stratigraphic depth domain data and the stratigraphic time domain data, the starting position of the medium stratification is matched to obtain the initial mapping relationship;

[0028] Based on well logging data from the adjacent target layer and the predicted average velocity of the target layer, time-depth conversion is performed to establish a time-depth dictionary.

[0029] In one implementation, GST structural characteristic attribute data is extracted from the three-dimensional seismic data, including:

[0030] For any point u in the three-dimensional seismic data, the gradient vector is obtained by taking the first-order partial derivatives in three directions:

[0031]

[0032] Where g represents the gradient vector of any point u in the three-dimensional seismic data, and g1, g2, g3 are the partial derivatives of any point u in the three-dimensional seismic data in the x, y, and z directions.

[0033] Construct a tensor matrix based on the gradient vector:

[0034]

[0035] Eigenvalue decomposition of the tensor matrix yields GST structural feature attribute data:

[0036] T = g1mmT +g2nn T +g3ww T

[0037] Where T represents the structural characteristic attribute data of GST, and g1, g2, and g3 represent T grad The three eigenvalues ​​are: m represents the unit cell in the horizontal x-direction, n represents the unit cell in the horizontal y-direction, and w represents the unit cell in the vertical z-direction.

[0038] In one implementation, amplitude energy attribute data is extracted from the three-dimensional seismic data, including:

[0039] The seismic arc length attribute is extracted from the three-dimensional seismic data as amplitude energy attribute data according to the following formula:

[0040]

[0041] Where S represents the arc length of a single seismic track extracted from the 3D seismic data, T represents the calculation time window, N represents the number of sampling points within the time window, and a(i) represents the amplitude value of the i-th sampling point within the time window.

[0042] In one implementation, frequency absorption attenuation attribute data is extracted from the three-dimensional seismic data, including:

[0043] Extract frequency absorption attenuation attribute data using the following formula:

[0044]

[0045] Where 'a' represents frequency absorption and attenuation attribute data, and 'u' is the current seismic trace amplitude. The total energy of the seismic traces in the 3D seismic data is represented by f, which represents the frequency, and y is the spectrum of the 3D seismic data determined based on the amplitude of the seismic traces. _85 and f _85 This represents the energy and frequency corresponding to 85% of the total energy, y _65 and f _65 This represents the energy and frequency corresponding to 65% of the total energy, where n is the number of sampling points and A is the amplitude value.

[0046] A drilling prediction device for seismic drilling data of a target layer, comprising:

[0047] The first acquisition module is used to acquire two-dimensional drilling data and two-dimensional logging data, and generate geological stratification depth domain data based on the two-dimensional drilling data and the two-dimensional logging data.

[0048] The matching module is used to match the geological stratification depth domain data with the stratum time domain data to establish a time-depth dictionary;

[0049] The second acquisition module is used to acquire three-dimensional seismic data and extract GST structural characteristic attribute data, amplitude energy attribute data and frequency absorption attenuation attribute data from the three-dimensional seismic data.

[0050] A module was established to determine the first contribution of GST structural characteristic attribute data, the second contribution of amplitude energy attribute data, and the third contribution of frequency absorption attenuation attribute data, thereby establishing initial seismic drilling data with multi-element and multi-type composite attribute characterization.

[0051] The third acquisition module is used to acquire real-time two-dimensional drilling data and map the two-dimensional drilling data into three-dimensional drilling seismic data according to the time-depth dictionary.

[0052] The update module is used to update the first contribution, the second contribution, and the third contribution based on the three-dimensional seismic data while drilling.

[0053] The generation module is used to obtain seismic drilling prediction data of the target layer with multi-variable and multi-type composite attribute representation based on the updated first contribution, second contribution, and third contribution.

[0054] An electronic device includes a processor and a memory for storing processor-executable instructions, wherein the processor, when executing the instructions, implements the steps of the method described above.

[0055] A computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0056] The target formation seismic drilling data prediction method provided in this application establishes a multi-element, multi-type composite attribute of seismic and drilling data. This composite attribute is obtained by weighted fusion of two seismic dynamic characteristic attributes and one seismic geometric characteristic attribute, which can provide accurate initial prediction results. Then, as the drilling process progresses, the weights are adjusted in real time according to the updated drilling data to obtain more refined porosity reservoir prediction results. The above scheme solves the technical problem of low accuracy in existing porosity reservoir prediction based on a single attribute, and achieves the technical effect of effectively improving reservoir prediction accuracy and reducing drilling risks. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 This is a flowchart of one embodiment of the method for predicting seismic drilling data of the target layer provided in this application;

[0059] Figure 2 This is a schematic diagram of the formation of the time-depth dictionary and the seismic data preprocessing provided in this application;

[0060] Figure 3 This is a flowchart illustrating the process for accurately predicting the distribution and properties of porous carbonate reservoirs provided in this application;

[0061] Figure 4 This is a schematic diagram of fine calibration of well trajectory using the average velocity of the target layer near the target well, provided in this application;

[0062] Figure 5 This is a schematic diagram of the predicted porosity reservoir provided in this application;

[0063] Figure 6 This is a schematic diagram of the "one well, multiple controls" technology scalp-scratching mode drilling provided in this application;

[0064] Figure 7 This is a schematic diagram of the drilling optimization scheme for the "one well, multiple controls" scalp rubbing mode provided in this application;

[0065] Figure 8 This is a hardware structure block diagram of an electronic device for a method of predicting seismic drilling data of a target layer provided in this application.

[0066] Figure 9 This is a schematic diagram of the module structure of one embodiment of the target layer seismic drilling data prediction module provided in this application. Detailed Implementation

[0067] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0068] As oil and gas exploration gradually moves towards deeper and more complex areas, the overpressure zone increases, and the development target in multi-round oilfield development shifts from "single well-single cavity" to "single well-multiple cavities," the need to avoid drilling accidents while achieving "one well, multiple controls" is becoming increasingly urgent. In carbonate rock drilling, it is necessary to update the plan based on data from the drilled section to predict the accurate reservoir morphology 100 meters ahead of the drill bit. This can prevent drilling accidents such as lost circulation, blowouts, and well collapse, and also provide a reference for drilling mud formulation. Therefore, accurate identification of cavities in the reservoir is required during drilling to connect multiple fractured cavities for simultaneous control and exploitation, thereby increasing the controlled reserves and productivity of a single well. For the "scalp-scraping" method of serially connecting fractured-cavitary formations, a segmented acid fracturing completion approach is adopted. This method involves scraping the surface of multiple fractured-cavitary formations in a "scalp-scraping" manner, modifying them one by one, and laterally connecting multiple fractured-cavitary formations for simultaneous production. This technology requires high accuracy in identifying the boundaries of fractured-cavitary formations. If the longitudinal distance from the fractured-cavitary formation boundary is too far, it will be difficult to connect the fractured-cavitary formations, increasing acid fracturing costs. If the longitudinal distance is too close, there is a risk of premature leakage. Therefore, high-precision identification of carbonate pore reservoirs is required to effectively connect multiple fractured-cavitary formations while avoiding drilling accidents, thereby achieving the goals of safe and economical drilling, reducing costs and increasing production capacity.

[0069] Based on this, this paper proposes a composite attribute based on multiple types of seismic and drilling data. This composite attribute fully utilizes drilling and seismic dynamics information, considers the superposition of diffraction wave energy and "beaded" reflection anomalies, and can finely describe reservoir morphology at different scales based on longitudinal and transverse constraints to improve the determinism of pore reservoir identification. This composite attribute is obtained by weighted fusion of two types of seismic dynamics characteristic attributes and one type of seismic geometry characteristic attribute, which can provide accurate initial prediction results. Then, as the drilling process progresses, the weights are adjusted in real time according to the updates of drilling data (e.g., drilling time, pressure, hydrocarbon detection) to obtain more refined pore reservoir prediction results (i.e., accurate prediction of pore boundaries in front of the drill bit). Based on the prediction results, drilling can be effectively guided to connect multiple fractured cavities by traversing surface reservoirs, effectively optimizing the drilling trajectory, reducing drilling risks, and thus achieving "one well, multiple controls".

[0070] Figure 1This is a flowchart of one embodiment of the method for predicting seismic drilling data of the target layer provided in this application. Although this application provides method operation steps or apparatus structures as shown in the following embodiments or figures, more or fewer operation steps or module units may be included in the method or apparatus based on conventional or non-inventive effort. In steps or structures where there is no logically necessary causal relationship, the execution order of these steps or the module structure of the apparatus is not limited to the execution order or module structure described in the embodiments and figures of this application. When the method or module structure is applied in actual devices or end products, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or figures (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed processing environment).

[0071] Specifically, such as Figure 1 As shown, the above-mentioned method for predicting seismic drilling data of the target layer while drilling may include the following steps:

[0072] Step 101: Obtain two-dimensional drilling data and two-dimensional logging data, and generate geological stratification depth domain data based on the two-dimensional drilling data and the two-dimensional logging data;

[0073] Step 102: Match the geological stratification depth domain data with the stratigraphic time domain data to establish a time-depth dictionary;

[0074] The process of matching the geological stratification depth domain data with the stratigraphic time domain data to establish a time-depth dictionary may include: matching the starting position of the medium stratification using the stratification depth domain data and the stratigraphic time domain data to obtain the initial mapping relationship; and performing time-depth conversion based on well logging data of the adjacent target layer and the predicted average velocity of the target layer to establish the time-depth dictionary.

[0075] Geological stratification refers to the division of lithology in a stratigraphic profile of a region, which can be used to guide corresponding geological prospecting work. Lithology is the main basis for geological stratification. It is very difficult to judge geological layers manually. Therefore, automatic stratification technology can be used to assist in rapid geological stratification. For example, BiLSTM networks can be used to obtain better geological stratification. Seismic horizons refer to the interfaces of geological media, which are represented as phase axes on seismic profiles. Therefore, they can be interpreted as the boundaries of geological structures and are stored in time-domain format in seismic data. Fine-grained horizon identification can reduce identification errors, provide accurate time-domain geological stratification data, and improve drill bit positioning accuracy. Horizon identification involves interpreters interpreting the target horizon based on geological sedimentary changes and physical characteristics such as seismic waveforms and phases. Then, based on waveform similarity interpolation and filling densification, fine-grained geological stratification and fine-grained horizon data are used to match the starting position of media stratification to obtain the initial mapping relationship. Then, based on the logging data and drilling time data of the target layer in nearby wells, the average velocity of the target layer is predicted. Finally, the velocity is used to perform time-depth conversion to establish a time-depth dictionary for the target layer.

[0076] Step 103: Acquire three-dimensional seismic data, and extract GST (Gradient Structure Tensor) structural characteristic attribute data, amplitude energy attribute data, and frequency absorption attenuation attribute data from the three-dimensional seismic data;

[0077] Among them, the GST structural gradient tensor property can identify the lateral boundary of the "beaded" abnormal reflection of post-stack data caused by seismic wave diffraction; amplitude energy properties (such as three-dimensional arc length properties) can characterize the amplitude energy anomaly caused by the strong impedance difference due to fluid in the pore reservoir; and absorption attenuation properties can analyze the degree of spectral distortion caused by the fluid viscosity effect in the pore reservoir.

[0078] Step 104: Determine the first contribution of GST structural characteristic attribute data, the second contribution of amplitude energy attribute data, and the third contribution of frequency absorption attenuation attribute data to establish initial seismic drilling data with multi-element and multi-type composite attribute characterization;

[0079] Specifically, in implementation, the initial seismic drilling data characterized by the aforementioned multi-dimensional and multi-type composite attributes can be represented as follows:

[0080]

[0081] Among them, R 1 This is the initial data from seismic drilling. A represents GST structural characteristic attribute data, B represents amplitude energy attribute data, and C represents frequency absorption attenuation attribute data. Indicates the initial first contribution. Indicates the initial second contribution level. This indicates the initial third contribution level.

[0082] Step 105: Obtain real-time two-dimensional drilling data, and map the two-dimensional drilling data to three-dimensional drilling seismic data according to the time-depth dictionary;

[0083] Step 106: Update the first contribution, second contribution, and third contribution based on the three-dimensional seismic data during drilling;

[0084] Step 107: Based on the updated first contribution, second contribution, and third contribution, obtain the seismic drilling prediction data of the target layer characterized by multivariate and multi-type composite attributes.

[0085] After obtaining seismic drilling prediction data of the target layer characterized by multiple types and composite attributes, the cavity boundary in front of the drill bit can be predicted, thereby accurately guiding drilling. Specifically, in the example above, based on big data analysis, considering cavity morphology, energy changes, and spectral changes caused by fluid viscosity, and updating the contribution of these three factors to the description of pore-bearing reservoirs in real time according to drilling data, a drilling prediction method for pore-bearing reservoirs in carbonate rocks based on seismic multi-attributes is proposed. This method can improve the accuracy and resolution of pore-bearing reservoir prediction, enabling drilling-scale prediction of pore-bearing reservoirs. Furthermore, based on the current drilling scheme, it can finely characterize the pore-bearing reservoirs of the target layer in adjacent wells, thus providing accurate guidance for future carbonate drilling design and the development of pore-bearing reservoir oil and gas.

[0086] When updating the first contribution, second contribution, and third contribution based on the three-dimensional seismic data while drilling, the following steps may be included:

[0087] S1: Establish the following objective function:

[0088]

[0089] Among them, D n This represents the 3D seismic data after the nth update. This refers to the seismic drilling prediction data characterized by multiple types and composite attributes after the nth update. A represents the GST structural characteristic attribute data, B represents the amplitude energy attribute data, and C represents the frequency absorption attenuation attribute data. Indicates the initial first contribution. Indicates the initial second contribution level. Indicates the initial third contribution level;

[0090] S2: The objective function is solved using the following formula:

[0091] l=(S T S) -1 S T D

[0092] Where l represents the first contribution, the second contribution, and the third contribution; S is an l×3 matrix composed of the feature parameters of the three types of attribute data; and D is an l×1 updated three-dimensional seismic data while drilling.

[0093] S3: Use the first, second, and third contributions obtained from the solution as the updated first, second, and third contributions.

[0094] The three types of attribute data mentioned above are explained as follows:

[0095] 1) Extracting GST structural characteristic attribute data from the three-dimensional seismic data can be achieved by:

[0096] Take the first-order partial derivatives in three directions for any point u in the three-dimensional seismic data:

[0097]

[0098] Where g represents the gradient vector of any point u in the three-dimensional seismic data, and g1, g2, g3 are the partial derivatives of any point u in the three-dimensional seismic data in the x, y, and z directions.

[0099] Construct a tensor matrix based on the gradient vector:

[0100]

[0101] Eigenvalue decomposition of the tensor matrix yields GST structural feature attribute data:

[0102] T = g1mm T +g2nn T +g3ww T

[0103] Where T represents the structural characteristic attribute data of GST, and g1, g2, and g3 represent T grad The three eigenvalues ​​are: m represents the unit cell in the horizontal x-direction, n represents the unit cell in the horizontal y-direction, and w represents the unit cell in the vertical z-direction. Where, when T... grad When none of the elements of T are zero, grad If at least one of the three eigenvalues ​​g1, g2, and g3 is not zero, then

[0104] 2) Extracting amplitude energy attribute data from the three-dimensional seismic data can be:

[0105] The seismic arc length attribute is extracted from the three-dimensional seismic data as amplitude energy attribute data according to the following formula:

[0106]

[0107] Where S represents the arc length of a single seismic track extracted from the 3D seismic data, T represents the calculation time window, N represents the number of sampling points within the time window, and a(i) represents the amplitude value of the i-th sampling point within the time window.

[0108] 3) Extracting frequency absorption and attenuation attribute data from the three-dimensional seismic data can be:

[0109] Extract frequency absorption attenuation attribute data using the following formula:

[0110]

[0111] Where 'a' represents frequency absorption and attenuation attribute data, and 'u' is the current seismic trace amplitude. The total energy of the seismic traces in the 3D seismic data is represented by f, which represents the frequency, and y is the spectrum of the 3D seismic data determined based on the amplitude of the seismic traces. _85 and f _85 This represents the energy and frequency corresponding to 85% of the total energy, y _65 and f _65 This represents the energy and frequency corresponding to 65% of the total energy, where n is the number of sampling points and A is the amplitude value.

[0112] The above method will be described below with reference to a specific embodiment. However, it is worth noting that this specific embodiment is only for better illustration of this application and does not constitute an improper limitation of this application.

[0113] Reservoir prediction is a crucial part of oil and gas resource exploration and development. However, due to the unique geological properties and complex pore structure of carbonate porous reservoirs, existing reservoir prediction methods have limitations in terms of accuracy and precision. In this case, to improve the accuracy and efficiency of drilling prediction for carbonate porous reservoirs, unlike existing methods that use single attributes to identify beaded reflections in post-stack data to characterize porous reservoirs, this approach combines the characteristics of seismic wave reflection and diffraction in porous reservoirs. Based on -90° phase shift seismic data or relative impedance attributes, it explores the geometric and dynamic sensitive attributes of reflection and diffraction data of porous reservoirs. Combining the drilling application scenario with domain knowledge and big data analysis, it determines that: 1) the GST structural gradient tensor attribute can identify the lateral boundary of the "beaded" abnormal reflections in post-stack data caused by seismic wave diffraction; 2) amplitude energy attributes, such as three-dimensional arc length attributes, can characterize the amplitude energy anomalies caused by strong impedance differences due to fluid in the porous reservoir; 3) absorption attenuation attributes can analyze the degree of spectral distortion caused by the fluid viscosity effect in the porous reservoir. Therefore, seismic composite attributes can be obtained by fusing the above attributes to accurately predict the borehole boundary in front of the drill bit, providing high-definition imaging results for the "one well, multiple boreholes" technology. Furthermore, during actual drilling, the fused attributes can be corrected in real time based on the drilling data updated during the drilling process. This provides new drilling trajectories for optimizing drilling, predicting drilling risks, achieving safe drilling, and laying the foundation for efficient production through acid fracturing in the later stages, thus achieving the goal of increasing production and reducing costs. Utilizing data processing and interpretation algorithms, combined with reservoir characteristic analysis and model building, a method for accurately predicting the distribution and properties of porous carbonate reservoirs is provided. This method can support drilling construction plans, effectively predict the construction risks of drilling at a depth of 100 meters before drilling, with a measured error of less than 15 meters, achieving the goal of efficient and safe drilling.

[0114] like Figure 2 As shown, firstly, the data is preprocessed and corrected appropriately based on drilling data, geological logging data, and well logging data. Then, a detailed depth-domain analysis of the geological strata is performed based on the drilling and well logging data. Next, the start time is precisely matched based on the time-domain stratigraphic data of the target layer. Finally, the average velocity of the target layer is estimated based on the drilling and well logging data of adjacent wells, and a time-depth relationship dictionary for the target layer is established accordingly. Simultaneously, the post-stack seismic data is denoised and shaped to obtain seismic data with a high signal-to-noise ratio and a wide bandwidth.

[0115] like Figure 3As shown, multiple attributes are calculated for the preprocessed seismic data, including: A) seismic amplitude and energy attribute, B) GST structural characteristic attribute, and C) absorption and attenuation attribute. Among these, the GST structural characteristic attribute can finely characterize the "beaded" anomaly morphology and the boundaries of geological anomalies; the seismic amplitude and energy attribute can identify amplitude anomalies such as "two peaks sandwiching one valley" or "three peaks sandwiching two valleys" caused by the superposition of diffracted wave energy; and the absorption and attenuation attribute can sensitively identify the spectral distortion characteristics of fluid-bearing pore reservoirs, revealing the reservoir's internal structure. Since the seismic response characteristics of different target pore reservoirs differ in the characteristics of these attributes, it is necessary to combine drilling data to analyze the predictive contribution of different attributes. The contribution of the seismic amplitude and energy attribute - A is... The contribution of GST structural characteristic attribute - B is: The contribution of fluid absorption attenuation attribute - C is: Where n is the sequence number of the contribution of the drilling data update. Among them, the seismic amplitude energy attribute-A is a seismic dynamic characteristic parameter, reflecting the energy anomalous concentration of diffraction superposition. This attribute is calculated in a single-channel open time window to ensure the vertical accuracy of the prediction results; the GST structural characteristic attribute-B is a seismic geometric characteristic parameter, which is the summation of the surface element characteristic values ​​in the normal lateral direction, providing lateral accuracy constraints for the prediction results; the fluid absorption attenuation attribute-C is a seismic dynamic characteristic parameter, reflecting the absorption and attenuation of seismic waves by the fluid, revealing the internal information of the reservoir, and l comes from the update of the drilling information data.

[0116] After normalization, the initial multi-element, multi-type composite attributes of seismic and drilling data can be expressed as:

[0117]

[0118] Drilling time data, hydrocarbon detection data, and pressure data obtained from drilling are standardized and preprocessed to obtain an l×1 dataset D. The initial drilling dataset is D. 0 The theoretical value after the nth drilling data update is D. n The predicted value is R n The goal is to find the optimal value of l that best fits the data: l = argmin l E(l), therefore, the objective function can be expressed as:

[0119]

[0120] Where E(l) is the objective function, D n Update data for n drilling operations.

[0121] f(l n )Right now, For n drilling data scenarios, there are multiple types of composite attributes. In these attributes, A represents standardized seismic dynamic characteristic amplitude and energy parameters, B represents standardized seismic geometric characteristic GST structural characteristic attributes, and C represents standardized seismic dynamic characteristic absorption and attenuation attributes. n For the parameters to be determined in the drilling data updated n times, the least squares fitting algorithm is used to solve the above equation to obtain the optimal l.

[0122] In the above algorithm, the seismic multi-type data and drilling data update information are two seismic dynamic characteristic parameters A and C, one seismic geometric characteristic parameter B, and drilling data D, respectively. The least squares optimization algorithm is used to update them in real time during drilling, which ensures the accuracy and efficiency of drilling prediction. It can effectively predict geological risks within 100 meters before drilling, so as to correctly select drilling fluid density and mud ratio for efficient, safe and economical drilling, and avoid the risk of drilling loss.

[0123] Specifically, geological stratification depth domain data is inferred from drilling and logging data, and a time-depth dictionary is established by matching stratigraphic time domain data. Geological stratification refers to the division of lithology in a stratigraphic profile of a region, which can be used to guide corresponding geological prospecting work. Lithology is the main basis for geological stratification. It is very difficult to determine geological strata manually. Therefore, automatic stratification technology can be used to assist in rapid geological stratification. For example, BiLSTM networks can be used to obtain better geological stratification results.

[0124] Seismic horizons refer to the interfaces between geological media, which are represented as phase axes on seismic profiles. Therefore, they can be interpreted as the boundaries of geological structures and are stored in time-domain format in seismic data. Fine-grained horizon identification can reduce identification errors, provide accurate time-domain geological stratification data, and improve drill bit positioning accuracy. Current horizon identification methods generally involve interpreters sparsely interpreting target horizons based on geological sedimentary changes and physical characteristics such as seismic waveforms and phases, and then interpolating and filling in the data based on waveform similarity. Specifically, fine-grained horizon data can be predicted using a U-Net network structure model.

[0125] By using fine geological stratification (Top) and fine stratigraphic data (Horizon) to match the starting positions of media stratification, the initial mapping relationship is obtained. Then, based on the logging data and drilling time data of the target layer in the adjacent well, the average velocity of the nth layer is predicted. Next, time-depth conversion is performed using speed. A time-depth dictionary for the target layer is established, where TVD represents vertical depth in meters (m); Time represents seismic sampling points in millimeters (ms); Top1 represents geological well stratification data updated from drilling in meters (m); and hor1 represents time-domain seismic horizon data in millimeters. For example... Figure 4 As shown, this is a time-depth dictionary built using neighboring wells. Figure 4 In the diagram, the thick gray line represents the original designed well trajectory, and the thick white line represents the well trajectory finely calibrated using a time-depth dictionary. Among them, checkshot dict For the time-deep dictionary, These are the time-domain layer set and the depth-domain well layer set, respectively.

[0126] By utilizing the low-frequency background trend of lateral changes in geological sedimentary relationships through the aforementioned time-depth dictionary, it can be determined that: under the same sedimentary environment, the stratigraphic framework is stable. After removing high-frequency disturbances caused by minor tectonic movements or oil and gas reservoir migration, the low-frequency background can be applied to adjacent areas of the same strata. Therefore, the average velocity obtained from adjacent wells can be used for the conversion of large-scale seismic data to small-scale drilling data.

[0127] Considering that the seismic reflection characteristics of carbonate porous reservoirs vary with porous size, surrounding rock differences, and fluid-bearing morphology, in order to accurately describe the porous reservoir and the "beaded" anomaly reflection characteristics and reduce interference from other geological isomorphisms, this example employs a multi-attribute comprehensive approach to finely describe the porous reservoir: A) GST structural characteristic attributes; B) Amplitude and energy attributes; C) Frequency absorption and attenuation attributes, where:

[0128] 1) The Gaussian Seismic Tensor (GST) is used to describe the local directional features of the structure of digital images. It was later used to extract discontinuities in 3D seismic data and describe fault development characteristics. The layered hierarchical structure of seismic data satisfies the GST linear structure definition; therefore, GST technology can be used to analyze the structural features of seismic data for seismic interpretation. Calculating GST structural features may include: obtaining the seismic data gradient; constructing the structural tensor matrix and smoothing it; and eigenvalue decomposition and sorting.

[0129] Specifically, the gradient vector can be obtained by taking the first-order partial derivatives of the seismic data in the Time, InLine, and CrossLine directions:

[0130] For any point u in the three-dimensional seismic data, the gradient vector is obtained by taking the first-order partial derivatives in three directions:

[0131]

[0132] Where g represents the gradient vector of any point u in the three-dimensional seismic data, and g1, g2, g3 are the partial derivatives of any point u in the three-dimensional seismic data in the x, y, and z directions.

[0133] The tensor matrix is ​​constructed as follows:

[0134]

[0135] When T gradWhen none of the elements are zero, T grad If at least one of the three eigenvalues ​​l1, l2, and l3 is not zero, then

[0136]

[0137] For any three-dimensional data structure tensor matrix, its eigendecomposition can be expressed as:

[0138] T = l1mm T +l2nn T +l3ww T (Formula 6)

[0139] Where T represents the structural characteristic attribute data of GST, and g1, g2, and g3 represent T grad The three eigenvalues ​​are: m represents the unit cell in the horizontal x-direction, n represents the unit cell in the horizontal y-direction, and w represents the unit cell in the vertical z-direction.

[0140] 2) Amplitude and energy attributes (e.g., seismic arc length) are defined as the length of the waveform received during an earthquake. They are a ratio measure of the range of variation across all seismic traces within a time window, used to differentiate between high-amplitude, high-frequency and high-amplitude, low-amplitude, high-frequency, and low-amplitude, low-frequency strata. They can be used to distinguish between shale sequence stratigraphy and sequences with high sand content. The calculation formula is as follows:

[0141]

[0142] Where S represents the arc length of a single seismic track extracted from the 3D seismic data, T represents the calculation time window, N represents the number of sampling points within the time window, and a(i) represents the amplitude value of the i-th sampling point within the time window.

[0143] 3) Spectral absorption and attenuation properties, such as energy half-decay, which calculates the relative time position when the energy reaches 1 / 2 within a given analysis window. If the analysis window is w, and there are N sampling points, the total energy for seismic data trace X is:

[0144]

[0145] The half-life energy is:

[0146]

[0147] The energy half-life reflects the relationship between seismic energy changes. In relatively calm sedimentary environments, seismic energy changes are small, and the half-life tends to be at the median value. If oil and gas are present, the reflected energy increases while the in-phase axis is pulled down, and the energy half-life increases. Therefore, the half-life energy can indicate the changes in sedimentary environment, lithology and lithofacies.

[0148] Alternatively, frequency absorption attenuation attribute data can be extracted using the following formula:

[0149]

[0150] Where 'a' represents frequency absorption and attenuation attribute data, and 'u' is the current seismic trace amplitude. The total energy of the seismic traces in the 3D seismic data is represented by f, which represents the frequency, and y is the spectrum of the 3D seismic data determined based on the amplitude of the seismic traces. _85 and f _85 This represents the energy and frequency corresponding to 85% of the total energy, y _65 and f _65 This represents the energy and frequency corresponding to 65% of the total energy, where n is the number of sampling points and A is the amplitude value.

[0151] In this example, multi-source, multi-type data from drilling and seismic analysis are used to determine the porosity reservoir and the contribution of each attribute is updated in real time during drilling to finely characterize the reservoir morphology and optimize drilling. Since the seismic response characteristics of different target porosity reservoirs differ in the aforementioned attributes, it is necessary to combine drilling data to analyze the predicted contribution of different attributes. The contribution of the seismic amplitude energy attribute - A is... The contribution of GST structural characteristic attribute - B is: The contribution of fluid absorption attenuation attribute - C is: Where n is the sequence number of the contribution of the drilling data update. Among them, the seismic amplitude energy attribute-A is a seismic dynamic characteristic parameter, reflecting the energy anomalous concentration of diffraction superposition. This attribute is calculated in a single-channel open time window to ensure the vertical accuracy of the prediction results; the GST structural characteristic attribute-B is a seismic geometric characteristic parameter, which is the summation of the characteristic values ​​of vertical surface elements, providing a lateral accuracy constraint for the prediction results; the fluid absorption attenuation attribute-C is a seismic dynamic characteristic parameter, reflecting the absorption and attenuation of seismic waves by the fluid, revealing the internal information of the reservoir, and l comes from the update of the drilling information data.

[0152] After normalization, the initial multi-element, multi-type composite attributes of seismic and drilling data are represented as follows:

[0153]

[0154] Drilling time, hydrocarbon detection, and pressure data obtained from drilling are standardized to obtain an l×1 dataset D. The initial drilling dataset is D. 0 The theoretical value after updating the drilling data is D. n The predicted value is R n Finding the optimal l best fits the data: l = argmin l E(l), the objective function is:

[0155]

[0156] Where E(l) is the objective function, Dn is the data from the nth drilling update, and f(l) n )Right now For the nth drilling data scenario, the predicted multivariate and multi-type composite attributes are defined, where A represents standardized seismic dynamic characteristic amplitude and energy parameters, B represents standardized seismic geometric characteristic GST structural characteristic attributes, and C represents standardized seismic dynamic characteristic absorption and attenuation attributes. n The parameters to be determined are for n updates of drilling data.

[0157] Using the least squares fitting algorithm to find the optimal solution for Equation 11, it can be rewritten as:

[0158] S·l=D (Formula 12)

[0159] The least squares solution is:

[0160] l=(S T S) -1 S T D (Formula 13)

[0161] Where l is the weight parameter to be determined. Taking single-track calculation as an example, S is an l×3 matrix composed of three feature parameters, and D is the theoretical value obtained from l×1 drilling update data.

[0162] like Figure 5 The diagram shown illustrates the drilling process using the "one well, multiple controls" technology in a scalp-scraping mode. This means the wellbore path passes along the edge of the fractured cavity, as shown below. Figure 6 The diagram illustrates the optimized drilling strategy for the "one well, multiple controls" scalping mode in this example. As drilling data is updated, the reservoir prediction results are continuously and precisely adjusted to forecast drilling risks. After each data update, the prediction boundaries are adjusted and the well trajectory is updated. That is, as shown... Figure 6 As shown in Figure a, the initial prediction results are as follows. Figure 6 As shown in b, this is the adjusted prediction scheme -1, as follows: Figure 6 As shown in c, the adjusted prediction scheme-2 is as follows. Figure 6 The diagram in 'd' shows the adjusted prediction scheme -3.

[0163] like Figure 7 The image shows a comparison diagram of earthquake physical simulation profiles, labels, and prediction results. Figure 7 In this diagram, 'a' represents the multi-well seismic physical simulation profile, 'b', 'c', and 'd' represent three attribute labels, 'e' represents the initial prediction result, and 'g' represents the prediction result updated while drilling. The initial multi-element, multi-type composite attribute... Based on drilling time and total hydrocarbon detection data, l was updated using least squares fitting to obtain l n= [0.41, 0.21, 0.38], thus obtaining the prediction results for drilling updates.

[0164] In the example above, multiple types of seismic data and updated information from drilling data were considered, including two seismic dynamic characteristic parameters A and C, one seismic geometric characteristic parameter B, and drilling data D. A least-squares optimization algorithm was used for real-time updates during drilling, ensuring the accuracy and efficiency of drilling predictions. This effectively predicted geological risks within 100 meters before drilling, allowing for the correct selection of drilling fluid density and mud ratio for efficient, safe, and economical drilling, avoiding the risk of lost drilling. By comprehensively and meticulously characterizing carbonate pore reservoirs using multiple data types, compared to existing single-attribute descriptions of pore reservoir "beaded" anomalies, this approach considers the combination of data from different scales of seismic and drilling data, the fusion of multiple types of data (seismic dynamic and seismic geometric characteristics), and the influence of diffraction superposition, "beaded" anomaly reflections, and reservoir internals on reservoir identification. Utilizing the seismic lateral constraints of GST structural characteristic attributes and the vertical constraints of amplitude and energy attributes, the determinism of small-scale pore reservoirs was strengthened, and the prediction error of large-scale pores was reduced. Least squares fitting is used to efficiently and dynamically process the drilling information obtained during drilling, and the weights of each attribute for describing the pore reservoir of carbonate rocks are updated in real time. During the exploration drilling period, the reservoir can be accurately predicted while drilling, so as to optimize drilling and achieve the goal of safe and economical drilling.

[0165] The methods and embodiments provided in the above-described embodiments of this application can be executed in a mobile terminal, computer terminal, or similar computing device. Taking operation on an electronic device as an example... Figure 8 This is a hardware block diagram of an electronic device for a method of predicting seismic drilling data of a target layer as provided in this application. Figure 8 As shown, the electronic device 10 may include one or more (only one is shown in the figure) processors 02 (processors 02 may include, but are not limited to, processing devices such as microprocessors (MCUs) or programmable logic devices (FPGAs), a memory 04 for storing data, and a transmission module 06 for communication functions. Those skilled in the art will understand that... Figure 8 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, electronic device 10 may also include... Figure 8 The more or fewer components shown, or having the same Figure 8 The different configurations shown.

[0166] The memory 04 can be used to store software programs and modules of application software, such as the program instructions / modules corresponding to the target layer seismic drilling data prediction method in this embodiment of the application. The processor 02 executes various functional applications and data processing by running the software programs and modules stored in the memory 04, thereby realizing the target layer seismic drilling data prediction method of the above-mentioned application. The memory 04 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 04 may further include memory remotely located relative to the processor 02, and these remote memories can be connected to the electronic device 10 via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0167] The transmission module 06 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the electronic device 10. In one example, the transmission module 06 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission module 06 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0168] At the software level, the aforementioned prediction-while-drilling device for seismic drilling data of the target layer can, as follows: Figure 9 As shown, it includes:

[0169] The first acquisition module 901 is used to acquire two-dimensional drilling data and two-dimensional logging data, and generate geological stratification depth domain data based on the two-dimensional drilling data and the two-dimensional logging data.

[0170] The matching module 902 is used to match the geological stratification depth domain data with the stratum time domain data to establish a time-depth dictionary;

[0171] The second acquisition module 903 is used to acquire three-dimensional seismic data and extract GST structural characteristic attribute data, amplitude energy attribute data and frequency absorption attenuation attribute data from the three-dimensional seismic data.

[0172] Module 904 is established to determine the first contribution of GST structural characteristic attribute data, the second contribution of amplitude energy attribute data, and the third contribution of frequency absorption attenuation attribute data, and to establish initial seismic drilling data with multi-element and multi-type composite attribute characterization.

[0173] The third acquisition module 905 is used to acquire real-time two-dimensional drilling data and map the two-dimensional drilling data into three-dimensional drilling seismic data according to the time-depth dictionary.

[0174] The update module 906 is used to update the first contribution, the second contribution, and the third contribution based on the three-dimensional seismic data while drilling.

[0175] The generation module 907 is used to obtain seismic drilling prediction data of the target layer with multi-variable and multi-type composite attributes based on the updated first contribution, second contribution and third contribution.

[0176] In one implementation, the initial seismic drilling data characterized by the multi-variable and multi-type composite attributes is represented as follows:

[0177]

[0178] Among them, R 1 This is the initial data from seismic drilling. A represents GST structural characteristic attribute data, B represents amplitude energy attribute data, and C represents frequency absorption attenuation attribute data. Indicates the initial first contribution. Indicates the initial second contribution level. This indicates the initial third contribution level.

[0179] In one implementation, the update module 906 can specifically establish the following objective function:

[0180]

[0181] Among them, D n This represents the 3D seismic data after the nth update. The seismic drilling prediction data is characterized by multi-variable and multi-type composite attributes after the nth update;

[0182] The objective function is solved using the following formula:

[0183] l=(S T S) -1 S T D

[0184] Where l represents the first contribution, the second contribution, and the third contribution; S is an l×3 matrix composed of the feature parameters of the three types of attribute data; and D is an l×1 updated three-dimensional seismic data while drilling.

[0185] The first, second, and third contributions obtained from the solution are used as the updated first, second, and third contributions.

[0186] In one implementation, the matching module 902 can specifically match the starting position of the medium layering using the formation layering depth domain data and the layer time domain data to obtain the initial mapping relationship; and perform time-depth conversion based on the well logging data of the adjacent target layer and the predicted average velocity of the target layer to establish a time-depth dictionary.

[0187] In one implementation, the second acquisition module 903 can specifically obtain the gradient vector by taking the first-order partial derivatives of any point u in the three-dimensional seismic data in three directions:

[0188]

[0189] Where g represents the gradient vector of any point u in the three-dimensional seismic data, and g1, g2, g3 are the partial derivatives of any point u in the three-dimensional seismic data in the x, y, and z directions.

[0190] Construct a tensor matrix based on the gradient vector:

[0191]

[0192] Eigenvalue decomposition of the tensor matrix yields GST structural feature attribute data:

[0193] T = g1mm T +g2nn T +g3ww T

[0194] Where T represents the structural characteristic attribute data of GST, and g1, g2, and g3 represent T grad The three eigenvalues ​​are: m represents the unit cell in the horizontal x-direction, n represents the unit cell in the horizontal y-direction, and w represents the unit cell in the vertical z-direction.

[0195] In one implementation, the second acquisition module 903 can specifically extract the seismic arc length attribute from the three-dimensional seismic data as amplitude energy attribute data according to the following formula:

[0196]

[0197] Where S represents the arc length of a single seismic track extracted from the 3D seismic data, T represents the calculation time window, N represents the number of sampling points within the time window, and a(i) represents the amplitude value of the i-th sampling point within the time window.

[0198] In one implementation, the second acquisition module 903 can specifically extract frequency absorption attenuation attribute data according to the following formula:

[0199]

[0200] Where 'a' represents frequency absorption and attenuation attribute data, and 'u' is the current seismic trace amplitude. The total energy of the seismic traces in the 3D seismic data is represented by f, which represents the frequency, and y is the spectrum of the 3D seismic data determined based on the amplitude of the seismic traces. _85 and f _85 This represents the energy and frequency corresponding to 85% of the total energy, y _65 and f _65 This represents the energy and frequency corresponding to 65% of the total energy, where n is the number of sampling points and A is the amplitude value.

[0201] This application also provides a specific implementation of an electronic device capable of implementing all steps in the target layer seismic drilling data prediction method described in the above embodiments. The electronic device specifically includes: a processor, a memory, a communication interface, and a bus; wherein the processor, memory, and communication interface communicate with each other via the bus; the processor is used to call a computer program in the memory, and when the processor executes the computer program, it implements all steps in the target layer seismic drilling data prediction method described in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0202] Step 1: Obtain two-dimensional drilling data and two-dimensional logging data, and generate geological stratification depth domain data based on the two-dimensional drilling data and the two-dimensional logging data;

[0203] Step 2: Match the geological stratification depth domain data with the stratigraphic time domain data to establish a time-depth dictionary;

[0204] Step 3: Acquire three-dimensional seismic data, and extract GST structural characteristic attribute data, amplitude energy attribute data, and frequency absorption attenuation attribute data from the three-dimensional seismic data;

[0205] Step 4: Determine the first contribution of GST structural characteristic attribute data, the second contribution of amplitude energy attribute data, and the third contribution of frequency absorption attenuation attribute data to establish initial seismic drilling data with multi-element and multi-type composite attribute characterization;

[0206] Step 5: Obtain real-time 2D drilling data, and map the 2D drilling data to 3D drilling seismic data according to the time-depth dictionary;

[0207] Step 6: Update the first contribution, second contribution, and third contribution based on the three-dimensional seismic data during drilling;

[0208] Step 7: Based on the updated first contribution, second contribution, and third contribution, obtain the seismic drilling prediction data of the target layer characterized by multivariate and multi-type composite attributes.

[0209] Embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the drilling prediction method for target layer seismic drilling data in the above embodiments. The computer-readable storage medium stores a computer program that, when executed by a processor, implements all steps of the drilling prediction method for target layer seismic drilling data in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0210] Step 1: Obtain two-dimensional drilling data and two-dimensional logging data, and generate geological stratification depth domain data based on the two-dimensional drilling data and the two-dimensional logging data;

[0211] Step 2: Match the geological stratification depth domain data with the stratigraphic time domain data to establish a time-depth dictionary;

[0212] Step 3: Acquire three-dimensional seismic data, and extract GST structural characteristic attribute data, amplitude energy attribute data, and frequency absorption attenuation attribute data from the three-dimensional seismic data;

[0213] Step 4: Determine the first contribution of GST structural characteristic attribute data, the second contribution of amplitude energy attribute data, and the third contribution of frequency absorption attenuation attribute data to establish initial seismic drilling data with multi-element and multi-type composite attribute characterization;

[0214] Step 5: Obtain real-time 2D drilling data, and map the 2D drilling data to 3D drilling seismic data according to the time-depth dictionary;

[0215] Step 6: Update the first contribution, second contribution, and third contribution based on the three-dimensional seismic data during drilling;

[0216] Step 7: Based on the updated first contribution, second contribution, and third contribution, obtain the seismic drilling prediction data of the target layer characterized by multivariate and multi-type composite attributes.

[0217] As described above, the embodiments of this application establish a composite attribute for earthquakes and drilling, which is obtained by weighted fusion of two seismic dynamic characteristic attributes and one seismic geometric characteristic attribute. This composite attribute can provide accurate initial prediction results. Then, as the drilling process progresses, the weights are adjusted in real time according to the updated drilling data to obtain more refined porosity reservoir prediction results. The above scheme solves the technical problem of low accuracy in existing porosity reservoir prediction based on a single attribute, and achieves the technical effect of effectively improving reservoir prediction accuracy and reducing drilling risks.

[0218] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, hardware + program embodiments are relatively simple in description because they are fundamentally similar to method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0219] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0220] While this application provides the method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or client product execution, the methods shown in the embodiments or drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0221] While this specification provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive means. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or end product execution, the methods shown in the embodiments or drawings may be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed data processing environment). The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitations, the presence of other identical or equivalent elements in the process, method, product, or apparatus that includes said elements is not excluded.

[0222] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing the embodiments of this specification, the functions of each module can be implemented in one or more software and / or hardware components, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0223] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0224] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0225] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0226] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of computer program products implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0227] The embodiments described in this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. The embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0228] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, system embodiments are basically similar to method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. In the description of this specification, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments in this specification. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0229] The above description is merely an embodiment of the present specification and is not intended to limit the embodiments of the present specification. Various modifications and variations can be made to the embodiments of the present specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of the present specification should be included within the scope of the claims of the embodiments of the present specification.

Claims

1. A method for predicting seismic drilling data of a target layer while drilling, characterized in that, The method includes: Two-dimensional drilling data and two-dimensional logging data are acquired, and geological stratification depth domain data are generated based on the two-dimensional drilling data and the two-dimensional logging data. The geological stratification depth domain data is matched with the stratum time domain data to establish a time-depth dictionary; Acquire three-dimensional seismic data, and extract gradient structure tensor (GST) structural characteristic attribute data, amplitude energy attribute data, and frequency absorption attenuation attribute data from the three-dimensional seismic data; The first contribution of GST structural characteristic attribute data, the second contribution of amplitude energy attribute data, and the third contribution of frequency absorption attenuation attribute data were determined, and the initial seismic drilling data with multi-element and multi-type composite attribute characterization was established. Acquire real-time two-dimensional drilling data, and map the two-dimensional drilling data to three-dimensional drilling seismic data according to the time-depth dictionary; Based on the aforementioned three-dimensional seismic data while drilling, the first contribution, second contribution, and third contribution are updated; Based on the updated first, second, and third contribution values, seismic drilling prediction data for the target layer with multi-variable and multi-type composite attribute representations are obtained.

2. The method according to claim 1, characterized in that, The initial seismic drilling data characterized by the multi-element, multi-type composite attributes are represented as follows: in, This is the initial data from the seismic drilling. Represents the structural characteristic attribute data of GST. This represents amplitude energy-related attribute data. This represents the frequency absorption attenuation attribute data. Indicates the highest level of contribution. Indicates the second degree of contribution. This indicates the third level of contribution.

3. The method according to claim 2, characterized in that, Based on the aforementioned three-dimensional seismic data while drilling, the first contribution, second contribution, and third contribution are updated, including: Establish the following objective function: in, Indicates the first The latest 3D seismic data while drilling. For the first The updated seismic drilling prediction data characterized by multiple types and composite attributes; The objective function is solved using the following formula: in, The first, second, and third contributions are respectively. It consists of feature parameters of three types of attribute data. The matrix, for The updated 3D seismic data while drilling; The first, second, and third contributions obtained from the solution are used as the updated first, second, and third contributions.

4. The method according to claim 1, characterized in that, The GST structural characteristic attribute data are extracted from the three-dimensional seismic data, including: For any point in the three-dimensional seismic data The gradient vector is obtained by taking the first-order partial derivatives in three directions: in, Represents any point in the three-dimensional seismic data gradient vector, For any point in the three-dimensional seismic data exist Partial derivatives in three directions; Construct a tensor matrix based on the gradient vector: Eigenvalue decomposition of the tensor matrix yields GST structural feature attribute data: in, Represents the structural characteristic attribute data of GST. express The three eigenvalues, Indicates horizontal Unit element in direction, Indicates horizontal Unit element in direction, express Unit face in the vertical direction.

5. The method according to claim 1, characterized in that, Amplitude and energy attribute data are extracted from the three-dimensional seismic data, including: The seismic arc length attribute is extracted from the three-dimensional seismic data as amplitude energy attribute data according to the following formula: in, This represents the arc length of a single seismic track extracted from 3D seismic data. Indicates the calculation window, Indicates the number of sampling points within the time window. Indicates the first time window The amplitude value of each sampling point.

6. The method according to claim 1, characterized in that, Frequency absorption attenuation attribute data are extracted from the three-dimensional seismic data, including: Extract frequency absorption attenuation attribute data using the following formula: in, This represents frequency absorption attenuation attribute data. This represents the current earthquake trace amplitude. This represents the total energy of the seismic traces in the three-dimensional seismic data. The frequency is represented by the spectrum of the three-dimensional seismic data determined based on the amplitude of the seismic trace. and This represents the energy and frequency corresponding to 85% of the total energy. and This represents the energy and frequency corresponding to 65% of the total energy. The number of sampling points. This represents the amplitude value.

7. A device for predicting seismic drilling data of a target layer while drilling, characterized in that, include: The first acquisition module is used to acquire two-dimensional drilling data and two-dimensional logging data, and generate geological stratification depth domain data based on the two-dimensional drilling data and the two-dimensional logging data. The matching module is used to match the geological stratification depth domain data with the stratum time domain data to establish a time-depth dictionary; The second acquisition module is used to acquire three-dimensional seismic data and extract GST structural characteristic attribute data, amplitude energy attribute data and frequency absorption attenuation attribute data from the three-dimensional seismic data. A module was established to determine the first contribution of GST structural characteristic attribute data, the second contribution of amplitude energy attribute data, and the third contribution of frequency absorption attenuation attribute data, thereby establishing initial seismic drilling data with multi-element and multi-type composite attribute characterization. The third acquisition module is used to acquire real-time two-dimensional drilling data and map the two-dimensional drilling data into three-dimensional drilling seismic data according to the time-depth dictionary. The update module is used to update the first contribution, the second contribution, and the third contribution based on the three-dimensional seismic data while drilling. The generation module is used to obtain seismic drilling prediction data of the target layer with multi-variable and multi-type composite attribute representation based on the updated first contribution, second contribution, and third contribution.

8. An electronic device comprising a processor and a memory for storing processor-executable instructions, characterized in that, When the processor executes the instructions, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1 to 6.

Images