A method, device, equipment and medium for horizon interpretation based on uncertainty quantification

Abstract

The application provides a horizon interpretation method and device based on uncertainty quantification, equipment and medium, belonging to the technical field of seismic data processing. The method comprises: acquiring a first seismic profile image, the first seismic profile image comprising seismic waves of multiple seismic traces; processing the first seismic profile image using any horizon tracking method to obtain a horizon tracking result of the first seismic profile image; determining an uncertainty parameter of each horizon based on the distribution of each horizon in the horizon tracking result in the first seismic profile image; and processing the horizon tracking result based on the uncertainty parameter of each horizon in the first seismic profile image. The scheme can more accurately understand the accuracy of the horizon tracking result, perform more accurate subsequent processing based on the horizon tracking result, and improve the accuracy of horizon interpretation.

Description

Technical Field

[0001] This application relates to the field of seismic data processing technology, and in particular to a method, apparatus, equipment and medium for horizon interpretation based on uncertainty quantification. Background Technology

[0002] Seismic data interpretation is a crucial part of seismic exploration, and horizon tracking is an important step in seismic data interpretation. The accuracy of horizon tracking results has a significant impact on subsequent structural interpretation and reservoir prediction. Summary of the Invention

[0003] This application provides a method, apparatus, device, and medium for stratigraphic interpretation based on uncertainty quantification. This method enables a more accurate understanding of the accuracy of stratigraphic tracking results, allowing for more precise subsequent processing and improving the accuracy of stratigraphic interpretation. The technical solution is as follows:

[0004] On the one hand, a method for interpreting hierarchical levels based on uncertainty quantification is provided, the method comprising:

[0005] Acquire a first seismic profile image, which includes seismic waves from multiple seismic traces;

[0006] The first seismic profile image is processed using any kind of horizon tracing method to obtain the horizon tracing result of the first seismic profile image, wherein the horizon tracing result indicates the position of at least one horizon in the first seismic profile image.

[0007] Based on the distribution of each layer in the first seismic profile image in the layer tracking results, an uncertainty parameter for each layer is determined. The uncertainty parameter is used to indicate the degree of uncertainty of the layer obtained by processing the first seismic profile image using the layer tracking method.

[0008] The layer tracking results are processed based on the uncertainty parameters of each layer in the first seismic profile image.

[0009] In one possible implementation, determining the uncertainty parameter for each layer based on the distribution of each layer in the first seismic profile image in the layer tracking results includes:

[0010] Based on the distribution of each layer in the first seismic profile image in the layer tracking results, the mean and variance of each layer are determined.

[0011] In one possible implementation, processing the layer tracking results based on the uncertainty parameters of each layer in the first seismic profile image includes:

[0012] Based on the mean and variance of each layer in the first seismic image, the confidence interval for each layer is determined;

[0013] For each layer in the layer tracking results, points that do not belong to the confidence interval of that layer are deleted.

[0014] In one possible implementation, determining the uncertainty parameter for each layer based on the distribution of each layer in the first seismic profile image in the layer tracking results includes:

[0015] The layer tracking results are sampled to obtain layer samples for each layer;

[0016] Based on the layer samples of each layer, Bayesian theory is used to obtain the first-order moment estimate and the second-order moment estimate of each layer sample;

[0017] The first moment estimate of the stratum sample is determined as the mean of the stratum, and the second moment estimate of the stratum sample is determined as the variance of the stratum.

[0018] In one possible implementation, the step of obtaining the first-order moment estimate and second-order moment estimate of each layer sample using Bayesian theory, based on the layer samples of each layer, includes:

[0019] Obtain the first relational data corresponding to the Monte Carlo integral, which is used to represent the relationship between the layer samples of each layer, the probability density function of each layer, and the mean of each layer;

[0020] Based on Bayesian estimation theory and the first assumption, the first relational data is transformed into second relational data. The first assumption is that the layers and artillery recording points in the first seismic profile image are independent and identically distributed. The second relational data is used to represent the relationship between the layer sample, conditional probability density function, layer function and mean of each layer.

[0021] Based on the second hypothesis, the second relational data is simplified to obtain the third relational data. The second hypothesis is that the conditional probability density function of the layer is a function.

[0022] Based on the aforementioned third relation data, Bayesian statistical theory is used to determine the first-order moment estimate and second-order moment estimate of the stratum samples for each stratum.

[0023] In one possible implementation, processing the layer tracking results based on the uncertainty parameters of each layer in the first seismic profile image includes:

[0024] When the uncertainty parameter of any layer in the first seismic profile is greater than the first threshold, the layer is deleted from the layer tracking results, or the layer tracking results are discarded.

[0025] In one possible implementation, the step of processing the first seismic profile image using any horizon tracing method to obtain the horizon tracing result of the first seismic profile image includes:

[0026] A horizon tracing model is used to perform horizon tracing on the first seismic profile image to obtain the horizon tracing result of the first seismic profile image; or,

[0027] Based on the first seismic profile image, a traditional dynamic time warping algorithm is used to process it, resulting in the layer tracking result of the first seismic profile image; or,

[0028] A layer-tracking model is used to extract features from the first seismic profile image. Based on the feature map of the first seismic profile image, a traditional dynamic time warping algorithm is used to process the feature map to obtain the layer-tracking result of the first seismic profile image.

[0029] In one possible implementation, a layer-tracking model is used to extract features from the first seismic profile image, wherein the feature map of the first seismic profile image includes:

[0030] Using the aforementioned layer tracing model, feature extraction is performed on the first seismic profile image to obtain a first feature map;

[0031] The first feature map is sampled to obtain the second feature map;

[0032] The process is repeated, inputting the currently obtained feature map into the layer tracking model, using the layer tracking model to extract features from the input feature map, outputting the feature map obtained from this feature extraction, and sampling the feature map obtained from this feature extraction until the termination condition is met.

[0033] In one possible implementation, the method further includes:

[0034] After obtaining the horizon tracking results of multiple consecutive seismic profile images, the horizon location distribution function is determined based on the horizon tracking results of the multiple consecutive seismic profile images.

[0035] Based on the layer location distribution function, the layers in the next seismic profile image of the plurality of consecutive seismic profile images are predicted.

[0036] On the other hand, a layer interpretation device based on uncertainty quantification is provided, the device comprising:

[0037] The acquisition module is used to acquire a first seismic profile image, which includes seismic waves from multiple seismic traces.

[0038] The tracking module is used to process the first seismic profile image using any layer tracking method to obtain the layer tracking result of the first seismic profile image, wherein the layer tracking result indicates the position of at least one layer in the first seismic profile image.

[0039] The determination module is used to determine the uncertainty parameter of each layer based on the distribution of each layer in the first seismic profile image in the layer tracking results. The uncertainty parameter is used to indicate the degree of uncertainty of the layer obtained by processing the first seismic profile image using the layer tracking method.

[0040] The processing module is used to process the layer tracking results based on the uncertainty parameters of each layer in the first seismic profile image.

[0041] In one possible implementation, the determining module is used to determine the mean and variance of each layer based on the distribution of each layer in the first seismic profile image in the layer tracking results.

[0042] In one possible implementation, the processing module is configured to determine a confidence interval for each layer based on the mean and variance of each layer in the first seismic image; and for each layer in the layer tracking result, delete points that do not belong to the confidence interval of that layer.

[0043] In one possible implementation, the determining module is used to sample the layer tracking results to obtain layer samples for each layer; based on the layer samples for each layer, Bayesian theory is used to obtain the first moment estimate and the second moment estimate for each layer sample; the first moment estimate of the layer samples for each layer is determined as the mean of the layer, and the second moment estimate of the layer samples for each layer is determined as the variance of the layer.

[0044] In one possible implementation, the determining module is configured to acquire first relational data corresponding to the Monte Carlo integral, wherein the first relational data represents the relationship between the layer samples of each layer, the probability density function of each layer, and the mean of each layer; based on Bayesian estimation theory and a first assumption, the first relational data is converted into second relational data, wherein the first assumption is that the layers and artillery recording points in the first seismic profile image are independently and identically distributed, and the second relational data represents the relationship between the layer samples, the conditional probability density function, the layer function, and the mean of each layer; based on a second assumption, the second relational data is simplified to obtain third relational data, wherein the second assumption is that the conditional probability density function of the layer is a function; based on the third relational data, Bayesian statistical theory is used to determine the first-order moment estimate and the second-order moment estimate of the layer samples of each layer.

[0045] In one possible implementation, the processing module is configured to delete the layer in the layer tracking result or discard the layer tracking result when the uncertainty parameter of any layer in the first seismic profile is greater than a first threshold.

[0046] In one possible implementation, the tracking module is used to perform layer tracking on the first seismic profile image using a layer tracking model to obtain the layer tracking result of the first seismic profile image; or...

[0047] The tracking module is used to process the first seismic profile image using a traditional dynamic time warping algorithm to obtain the layer tracking result of the first seismic profile image; or,

[0048] The tracking module is used to extract features from the first seismic profile image using a layer tracking model. Based on the feature map of the first seismic profile image, a traditional dynamic time warping algorithm is used to process the feature map to obtain the layer tracking result of the first seismic profile image.

[0049] In one possible implementation, the tracking module is used to extract features from the first seismic profile image using the layer tracking model to obtain a first feature map; sample the first feature map to obtain a second feature map; repeatedly input the currently obtained feature map into the layer tracking model, use the layer tracking model to extract features from the input feature map, output the feature map obtained by the current feature extraction, and sample the feature map obtained by the current feature extraction until a termination condition is met.

[0050] In one possible implementation, the device further includes:

[0051] The prediction module is used to determine the layer position distribution function based on the layer tracking results of multiple consecutive seismic profile images after obtaining the layer tracking results of the multiple consecutive seismic profile images; and to predict the layer in the next seismic profile image based on the layer position distribution function.

[0052] On the other hand, a computer device is provided, the computer device including a processor and a memory, the memory storing at least one piece of program code, the at least one piece of program code being loaded and executed by the processor to implement the layer interpretation method based on uncertainty quantization as described in any of the above implementations.

[0053] On the other hand, a computer-readable storage medium is provided, wherein at least one piece of program code is stored in the computer-readable storage medium, the at least one piece of program code being loaded and executed by a processor to implement the layer interpretation method based on uncertainty quantization as described in any of the above implementations.

[0054] On the other hand, a computer program product is provided, the computer program product comprising at least one piece of program code, the at least one piece of program code being loaded and executed by a processor to implement the layer interpretation method based on uncertainty quantization as described in any of the above implementations.

[0055] The beneficial effects of the technical solutions provided in this application include at least the following:

[0056] This application provides a method for interpreting stratigraphic levels based on uncertainty quantification. After obtaining the stratigraphic tracking result, the uncertainty parameter of the stratigraphic tracking result is determined in order to more accurately understand the accuracy of the stratigraphic tracking result. Based on the stratigraphic tracking result, more accurate next processing is performed to improve the accuracy of stratigraphic interpretation. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of this application, 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 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 a hierarchical interpretation method based on uncertainty quantification provided in an embodiment of this application;

[0059] Figure 2 This is a schematic diagram of a seismic profile image provided in an embodiment of this application;

[0060] Figure 3This is a schematic diagram of a stratigraphic tracing result provided in an embodiment of this application;

[0061] Figure 4 This is a flowchart of a hierarchical interpretation method based on uncertainty quantification provided in an embodiment of this application;

[0062] Figure 5 This is a flowchart of uncertainty quantification based on layer tracking results provided in an embodiment of this application;

[0063] Figure 6 This is a flowchart of a stratigraphic prediction method provided in an embodiment of this application;

[0064] Figure 7 This is a schematic diagram of a hierarchical interpretation device based on uncertainty quantification provided in an embodiment of this application;

[0065] Figure 8 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application;

[0066] Figure 9 This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0067] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0068] The terms "first," "second," "third," and "fourth," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. 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 apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0069] Figure 1 This is a flowchart illustrating a hierarchical interpretation method based on uncertainty quantification, provided in an embodiment of this application. This embodiment uses a computer device as an example for illustrative purposes. See also... Figure 1 The method includes:

[0070] 101. A computer device acquires a first seismic profile image, which includes seismic waves from multiple seismic traces.

[0071] The first seismic profile image includes seismic waves from multiple seismic traces. In some embodiments, the horizontal axis of the first seismic profile image represents the seismic trace, and the vertical axis represents time. The time corresponding to the seismic wave can be used to represent the formation depth. Therefore, marking formations in the first seismic profile image allows the determination of the corresponding formation depth based on the time. In other embodiments, the horizontal axis of the first seismic profile image represents time, and the vertical axis represents the seismic trace. This application does not limit the scope of the first seismic profile image. For example... Figure 2 A seismic profile image is shown, which includes seismic waves from multiple seismic traces.

[0072] 102. The computer equipment uses any kind of horizon tracing method to process the first seismic profile image to obtain the horizon tracing result of the first seismic profile image, which indicates the location of at least one horizon in the first seismic profile image.

[0073] The uncertainty-quantification-based stratigraphic interpretation provided in this application can employ any stratigraphic tracing method to process the first seismic profile image; this application does not limit the specific method used. In some embodiments, the computer device uses only one stratigraphic tracing method to process the first seismic profile image, obtaining one stratigraphic tracing result. In other embodiments, the computer device uses multiple stratigraphic tracing methods to process the first seismic profile image separately, obtaining multiple stratigraphic tracing results. Subsequently, the most accurate stratigraphic tracing result can be determined from the multiple results.

[0074] The horizon tracing method extracts phase axes from seismic profile images. Therefore, the position of the horizon in the horizon tracing result is the position of the phase axis. The horizon tracing result is as follows: Figure 3 As shown.

[0075] 103. The computer equipment determines the uncertainty parameter of each layer based on the distribution of each layer in the first seismic profile image in the layer tracking results. The uncertainty parameter is used to indicate the degree of uncertainty of the layers obtained by processing the first seismic profile image using the layer tracking method.

[0076] Stratification tracking technology is essentially the extraction of phase axes from seismic profile images. In other words, a layer is a phase axis in a seismic profile image. Therefore, the more concentrated the distribution of each layer in the first seismic profile image, the lower the uncertainty of the layer and the higher its accuracy. Conversely, the more dispersed the distribution of each layer in the first seismic profile image, the greater the uncertainty of the layer and the lower its accuracy.

[0077] 104. The computer equipment processes the layer tracking results based on the uncertainty parameters of each layer in the first seismic profile image.

[0078] Since the uncertainty parameter of a horizon indicates the degree of uncertainty of that horizon, the higher the uncertainty, the lower the accuracy of that horizon; and the lower the uncertainty, the higher the accuracy of that horizon. Therefore, the uncertainty parameter of a horizon can indicate the accuracy of the horizon, and this horizon tracking result can be referred to when performing further processing based on the horizon tracking result. This application does not limit the description of "the computer device processing the horizon tracking result based on the uncertainty parameter of each horizon in the first seismic profile image," but only provides illustrative examples using the following two embodiments.

[0079] In one possible implementation, the uncertainty parameters of the horizon include the mean and variance of the horizon. A confidence interval for the horizon can be determined based on the mean and variance, and the horizon tracking results can be corrected based on this confidence interval. The computer equipment processes the horizon tracking results based on the uncertainty parameters of each horizon in the first seismic profile image, including: determining a confidence interval for each horizon based on the mean and variance of each horizon in the first seismic image; and for each horizon in the horizon tracking results, deleting points that do not belong to the confidence interval of that horizon.

[0080] In another possible implementation, since the uncertainty parameter of the horizon can indicate the accuracy of the horizon, it can be used to determine whether to proceed with further processing based on the horizon tracking results. In some embodiments, the computer device processes the horizon tracking results based on the uncertainty parameter of each horizon in the first seismic profile image, including: deleting the horizon in the horizon tracking results when the uncertainty parameter of any horizon in the first seismic profile is greater than a first threshold, or discarding the horizon tracking results.

[0081] The first threshold can be any value, and this application embodiment does not limit the first threshold. Optionally, the first threshold is an empirical value.

[0082] This application's embodiments are merely examples of the two embodiments described above, illustrating the process of "processing the layer tracking results based on the uncertainty parameters of each layer in the first seismic profile image." Of course, other possible implementations can also be used to achieve this. For example, multiple layer tracking methods can be used to process the first seismic profile image, resulting in multiple layer tracking results. The layer tracking result with the lowest uncertainty level is then determined as the final layer tracking result.

[0083] The stratigraphic interpretation method based on uncertainty quantification provided in this application determines the uncertainty parameters of the stratigraphic tracking result after obtaining the result, so as to more accurately understand the accuracy of the result and perform more accurate further processing based on the result, thereby improving the accuracy of the stratigraphic interpretation.

[0084] In one possible implementation, the uncertainty parameters for each layer are determined based on the distribution of each layer in the first seismic profile image in the layer tracking results, including:

[0085] Based on the distribution of each layer in the first seismic profile image in the layer tracking results, the mean and variance of each layer are determined.

[0086] In one possible implementation, the horizon tracking results are processed based on the uncertainty parameters of each horizon in the first seismic profile image, including:

[0087] Based on the mean and variance of each layer in the first seismic image, the confidence interval for each layer is determined;

[0088] For each stratum in the stratum tracking results, points that do not belong to the confidence interval of the stratum will be deleted.

[0089] In one possible implementation, the uncertainty parameters for each layer are determined based on the distribution of each layer in the first seismic profile image in the layer tracking results, including:

[0090] The stratigraphic tracking results are sampled to obtain stratigraphic samples for each stratigraphic level;

[0091] Based on the stratum samples of each stratum, Bayesian theory is used to obtain the first-order moment estimate and the second-order moment estimate of each stratum sample;

[0092] The first moment estimate of the stratum sample is determined as the mean of the stratum, and the second moment estimate of the stratum sample is determined as the variance of the stratum.

[0093] In one possible implementation, based on the stratigraphic samples of each layer, Bayesian theory is used to obtain the first-order moment estimate and the second-order moment estimate of each stratigraphic sample, including:

[0094] Obtain the first relation data corresponding to the Monte Carlo integral. The first relation data is used to represent the relationship between the layer samples, the probability density function of each layer, and the mean of each layer.

[0095] Based on Bayesian estimation theory and the first assumption, the first relational data is transformed into second relational data. The first assumption is that the layers and artillery recording points in the first seismic profile image are independent and identically distributed. The second relational data is used to represent the relationship between the layer samples, conditional probability density function, layer function and mean of each layer.

[0096] Based on the second hypothesis, the second relation data is simplified to obtain the third relation data. The second hypothesis is that the conditional probability density function of the layer is a function.

[0097] Based on the third relation data, Bayesian statistical theory is used to determine the first moment estimate and second moment estimate of the stratum sample for each stratum.

[0098] In one possible implementation, the horizon tracking results are processed based on the uncertainty parameters of each horizon in the first seismic profile image, including:

[0099] When the uncertainty parameter of any layer in the first seismic profile exceeds the first threshold, the layer is deleted from the layer tracking results, or the layer tracking results are discarded.

[0100] In one possible implementation, any horizon tracing method is used to process the first seismic profile image to obtain the horizon tracing result of the first seismic profile image, including:

[0101] A horizon tracing model is used to perform horizon tracing on the first seismic profile image, yielding the horizon tracing results for the first seismic profile image; or,

[0102] Based on the first seismic profile image, a traditional dynamic time warping algorithm is used to process it, resulting in the layer tracking result of the first seismic profile image; or,

[0103] A layer-tracking model is used to extract features from the first seismic profile image. Based on the feature map of the first seismic profile image, a traditional dynamic time warping algorithm is used to process the image to obtain the layer-tracking result of the first seismic profile image.

[0104] In one possible implementation, a layer-tracing model is used to extract features from the first seismic profile image. The feature map of the first seismic profile image includes:

[0105] A layer-tracing model was used to extract features from the first seismic profile image to obtain the first feature map.

[0106] The first feature map is sampled to obtain the second feature map;

[0107] Repeatedly input the currently obtained feature map into the layer tracking model, use the layer tracking model to extract features from the input feature map, output the feature map obtained from this feature extraction, and sample the feature map obtained from this feature extraction until the termination condition is met.

[0108] In one possible implementation, the method also includes:

[0109] After obtaining the horizon tracking results of multiple consecutive seismic profile images, the horizon location distribution function is determined based on the horizon tracking results of multiple consecutive seismic profile images.

[0110] Based on the layer location distribution function, the layers in the next seismic profile image are predicted from multiple consecutive seismic profile images.

[0111] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0112] Figure 4 This is a flowchart illustrating a hierarchical interpretation method based on uncertainty quantification, provided in an embodiment of this application. This embodiment uses a computer device as the executing entity for illustrative purposes. See also... Figure 4 The method includes:

[0113] 401. The computer equipment acquires a first seismic profile image, which includes seismic waves from multiple seismic traces.

[0114] The first seismic profile image can be any seismic profile image; however, this application does not limit the first seismic profile image.

[0115] 402. The computer equipment uses any kind of horizon tracing method to process the first seismic profile image to obtain the horizon tracing result of the first seismic profile image. The horizon tracing result indicates the position of at least one horizon in the first seismic profile image.

[0116] In one possible implementation, the computer device employs a neural network model for horizon tracking. The computer device processes the first seismic profile image using any horizon tracking method to obtain the horizon tracking result of the first seismic profile image, including: using a horizon tracking model to perform horizon tracking on the first seismic profile image to obtain the horizon tracking result of the first seismic profile image.

[0117] In some embodiments, the neural network model is a convolutional neural network model. In some embodiments, the layer tracking model is trained using previous algorithms. In some embodiments, the layer tracking model is a prior model constructed based on a Bayesian prior method. The embodiments in this application are merely illustrative examples of layer tracking models and do not limit the scope of layer tracking models.

[0118] In another possible implementation, the computer device employs a conventional dynamic time warping algorithm for horizon tracking. The computer device processes the first seismic profile image using any horizon tracking method to obtain the horizon tracking result of the first seismic profile image, including: processing the first seismic profile image using a conventional dynamic time warping algorithm to obtain the horizon tracking result of the first seismic profile image.

[0119] In another possible implementation, the computer device uses a neural network model for feature extraction to obtain a feature map, and then uses a traditional dynamic time warping algorithm to perform horizon tracking on the feature map. The computer device processes the first seismic profile image using any horizon tracking method to obtain the horizon tracking result of the first seismic profile image, including: using a horizon tracking model to extract features from the first seismic profile image, obtaining the feature map of the first seismic profile image, and processing the feature map using a traditional dynamic time warping algorithm to obtain the horizon tracking result of the first seismic profile image.

[0120] In some embodiments, the neural network model is a convolutional neural network model. In some embodiments, the layer tracking model is trained using previous algorithms. In some embodiments, the layer tracking model is a prior model constructed based on a Bayesian prior method. The embodiments in this application are merely illustrative examples of layer tracking models and do not limit the scope of layer tracking models.

[0121] Specifically, the first seismic profile image is feature extracted using a layer tracking model, and the resulting feature map is the prior distribution of the layers in the first seismic profile image. Based on the feature map, a traditional dynamic time warping algorithm is used for processing, and the resulting layer tracking result of the first seismic profile image is the posterior distribution of the layers.

[0122] In determining the stratigraphic tracking results, feature extraction can be performed only once or multiple times to obtain the prior depth distribution of the stratigraphic layers. Optionally, a stratigraphic tracking model is used to extract features from the first seismic profile image. The feature map of the first seismic profile image includes: extracting features from the first seismic profile image using the stratigraphic tracking model to obtain a first feature map; sampling the first feature map to obtain a second feature map; repeatedly inputting the currently obtained feature map into the stratigraphic tracking model, extracting features from the input feature map using the stratigraphic tracking model, outputting the feature map obtained in this feature extraction, and sampling the feature map obtained in this feature extraction until a termination condition is met. The termination condition can be that the number of repetitions reaches a preset number.

[0123] In some embodiments, the layer tracking model is a convolutional neural network model. In some embodiments, the layer tracking model is trained using previous algorithms. In some embodiments, the layer tracking model is a prior model constructed based on a Bayesian prior method. The embodiments in this application are merely illustrative examples of layer tracking models and do not limit the scope of the layer tracking model.

[0124] The computer device can sample the feature map in any way. For example, it can use stochastic gradient Langevin dynamics to sample the feature map; it can also use the Markov chain Monte Carlo method to sample the feature map; it can also randomly sample the feature map; or it can sample the feature map at preset intervals, etc. This application does not limit the sampling method of the feature map.

[0125] For example, such as Figure 5 As shown, convolutional neural networks and Markov chain Monte Carlo sampling are used to process seismic profile images to obtain layer tracking results.

[0126] 403. The computer equipment determines the uncertainty parameters of each layer based on the distribution of each layer in the first seismic profile image in the layer tracking results. The uncertainty parameters of the layer include the mean and variance of the layer.

[0127] In one possible implementation, such as Figure 5 As shown, the computer equipment determines the mean and variance of the horizons based on Bayesian theory. Based on the distribution of each horizon in the first seismic profile image from the horizon tracking results, the computer equipment determines the uncertainty parameters of each horizon, including: sampling the horizon tracking results to obtain horizon samples for each horizon; using Bayesian theory to obtain the first-order moment estimate and second-order moment estimate for each horizon sample; determining the first-order moment estimate of the horizon sample as the horizon mean, and determining the second-order moment estimate of the horizon sample as the horizon variance.

[0128] Optionally, the computer equipment, based on the layer samples of each layer, uses Bayesian theory to obtain the first-order moment estimate and second-order moment estimate of each layer sample, including: obtaining the first relation data corresponding to the Monte Carlo integral, which represents the relationship between the layer samples, the probability density function, and the mean of each layer; based on Bayesian estimation theory and a first assumption, converting the first relation data into second relation data, where the first assumption is that the layers and artillery recording points in the first seismic profile image are independently and identically distributed, and the second relation data represents the relationship between the layer samples, the conditional probability density function, the layer function, and the mean of each layer; based on the second assumption, simplifying the second relation data to obtain third relation data, where the second assumption is that the conditional probability density function of the layer is a delta function; and based on the third relation data, using Bayesian statistical theory, determining the first-order moment estimate and second-order moment estimate of the layer samples of each layer.

[0129] In some embodiments, the first relation data corresponding to the Monte Carlo integral is obtained. The first relation data corresponding to the Monte Carlo integral is obtained as shown in the following formula (1):

[0130]

[0131] Where a and b are constants, d is the definite integral, f is the differential function, h is the stratum, f(h) is the stratum function of the stratum, which also represents the stratum sample of the stratum, f(h)>0, pdf(h) is the probability density function of the stratum, and E is the expectation, which also represents the mean of the stratum.

[0132] Before performing Bayesian estimation, it is necessary to assume that the layer h and the shot record point c in the seismic profile image are independent and identically distributed. Based on Bayesian estimation theory and the independent and identically distributed nature of the layer and shot record point, the above formula (1) is transformed into the following formula (2).

[0133]

[0134] Where is the definite integral, d is the differential, h is the layer, f(h) is the layer function of the layer, also representing the layer sample of the layer, represents the seismic profile image, represents the posterior distribution of layer h, that is, the layer sample of the layer. represents the posterior distribution of the seismic profile image. represents the conditional probability density function of the layer. Let represent the expectation of the posterior distribution of layer h in layer h. Let represent the expectation of the seismic profile image in the posterior distribution of the seismic profile image, and let represent the seismic profile image under the probability distribution of the artillery recording point c.

[0135] When performing multi-layer seismic tracing on a given seismic profile image, if the layers of the seismic profile image are determined, the conditional probability density function of the layers is the Dirac function, i.e. Then the above formula (2) can be simplified to the following formula (3).

[0136]

[0137] Where is the number of samples of the conditional probability density function, and is the number of samples of the posterior distribution of the seismic profile image. is the k-th sample obtained from the conditional probability density function, is the j-th sample obtained from the posterior distribution of the seismic profile image, and is the summation function.

[0138] Based on formulas (2) and (3), and combined with the Bayesian statistical principle, we can obtain the first moment estimate and the second moment estimate of the sample, that is, the mean and variance of the stratum sample.

[0139] The mean of the layer samples is

[0140] The variance of the stratum sample is

[0141] Therefore, the 99% confidence interval for the stratigraphic level is estimated to be (μ h -2.576σ h ,μ h +2.576σ h ).

[0142] 404. The computer equipment determines the confidence interval for each layer based on the mean and variance of each layer in the first seismic image. For each layer in the layer tracking results, points that do not belong to the confidence interval of that layer are deleted.

[0143] 405. After obtaining the horizon tracking results of multiple consecutive seismic profile images, the computer equipment determines the horizon location distribution function based on the horizon tracking results of multiple consecutive seismic profile images, and predicts the horizon in the next seismic profile image based on the horizon location distribution function.

[0144] In one possible implementation, the inter-frame differencing method is used to determine the layer position distribution function. For example, the inter-frame differencing method is used to obtain the layer contour positions of continuous seismic profile images, and the layer distribution function is determined based on the layer contour positions of continuous seismic profile images.

[0145] The inter-frame difference method obtains the layer contour position based on the difference between the layer positions of two adjacent seismic profile images. Assuming multiple consecutive seismic profile images with obtained layer tracking results are X, and the seismic profile image for which the layer to be predicted is Y, a bisection method is used to divide each seismic profile image X into two parts: layer and non-layer. The layer part is set to 1, and the non-layer part is set to 0. Then, the difference in layer position between two adjacent seismic profile images can be calculated. In some embodiments, the first seismic trace, intermediate seismic trace, final seismic trace, and special seismic traces of faults on the layer can be used as the basis for calculation of the difference D, as shown in the following formula:

[0146]

[0147] in, This represents the layer location corresponding to the i-th seismic trace in the n-th seismic profile image. This represents the layer location corresponding to the i-th seismic trace in the (n-1)-th seismic profile image. This represents the difference in the stratigraphic level corresponding to the i-th seismic trace between the n-th seismic profile image and the (n-1)-th seismic profile image, where n is any integer greater than 1 and m is any positive integer.

[0148] By analogy, we obtain the differences in seismic trace locations between multiple seismic profile images, fit the layer location distribution function, and thus predict the layer of seismic profile image Y.

[0149] It should be noted that the embodiments of this application are only exemplified by performing step 404 and then step 405 as an example. In fact, the computer device can use any layer tracking method to obtain the layer tracking results. After obtaining the layer tracking results of multiple consecutive seismic profile images, the inter-frame difference method is used to obtain the layer position distribution function. Based on the layer position distribution function, the layer in the next seismic profile image is predicted.

[0150] For example, such as Figure 6 As shown, after acquiring seismic data, the dynamic time warping algorithm is used to interpret the horizons, and then the inter-frame difference method is used to obtain the horizon location distribution function. Based on the horizon location distribution function, the horizons in the next seismic profile image are predicted.

[0151] The stratigraphic interpretation method based on uncertainty quantification provided in this application determines the uncertainty parameters of the stratigraphic tracking result after obtaining the result, so as to more accurately understand the accuracy of the result and perform more accurate further processing based on the result, thereby improving the accuracy of the stratigraphic interpretation.

[0152] Furthermore, the embodiments of this application can also predict the layer tracking results of subsequent seismic profile images based on the layer tracking results of multiple consecutive seismic profile images, thereby improving the layer tracking efficiency.

[0153] Figure 7 This is a schematic diagram of a hierarchical interpretation device based on uncertainty quantification provided in an embodiment of this application, as shown below. Figure 7 As shown, the device includes:

[0154] The acquisition module 701 is used to acquire a first seismic profile image, which includes seismic waves from multiple seismic traces.

[0155] The tracking module 702 is used to process the first seismic profile image using any kind of layer tracking method to obtain the layer tracking result of the first seismic profile image, wherein the layer tracking result indicates the position of at least one layer in the first seismic profile image.

[0156] The determination module 703 is used to determine the uncertainty parameter of each layer based on the distribution of each layer in the first seismic profile image in the layer tracking results. The uncertainty parameter is used to indicate the degree of uncertainty of the layer obtained by processing the first seismic profile image using the layer tracking method.

[0157] The processing module 704 is used to process the layer tracking results based on the uncertainty parameters of each layer in the first seismic profile image.

[0158] In one possible implementation, the determination module 703 is used to determine the mean and variance of each layer based on the distribution of each layer in the first seismic profile image in the layer tracking results.

[0159] In one possible implementation, the processing module 704 is used to determine the confidence interval for each layer based on the mean and variance of each layer in the first seismic image; and for each layer in the layer tracking results, points that do not belong to the confidence interval of the layer are deleted.

[0160] In one possible implementation, module 703 is used to sample the stratigraphic tracking results to obtain stratigraphic samples for each stratigraphic level; based on the stratigraphic samples for each stratigraphic level, Bayesian theory is used to obtain the first-moment estimate and the second-moment estimate for each stratigraphic sample; the first-moment estimate of the stratigraphic sample is determined as the mean of the stratigraphic level, and the second-moment estimate of the stratigraphic sample is determined as the variance of the stratigraphic level.

[0161] In one possible implementation, module 703 is used to obtain first relation data corresponding to the Monte Carlo integral. The first relation data represents the relationship between the layer samples, the probability density function, and the mean of each layer. Based on Bayesian estimation theory and a first assumption, the first relation data is transformed into second relation data. The first assumption is that the layers and artillery recording points in the first seismic profile image are independently and identically distributed. The second relation data represents the relationship between the layer samples, the conditional probability density function, the layer function, and the mean of each layer. Based on the second assumption, the second relation data is simplified to obtain third relation data. The second assumption is that the conditional probability density function of the layer is a delta function. Based on the third relation data, Bayesian statistical theory is used to determine the first-moment estimate and the second-moment estimate of the layer samples of each layer.

[0162] In one possible implementation, the processing module 704 is used to delete the layer in the layer tracking results or discard the layer tracking results when the uncertainty parameter of any layer in the first seismic profile is greater than a first threshold.

[0163] In one possible implementation, the tracking module 702 is used to perform layer tracking on the first seismic profile image using a layer tracking model to obtain the layer tracking result of the first seismic profile image; or,

[0164] The tracking module is used to process the first seismic profile image using a traditional dynamic time warping algorithm to obtain the layer tracking results of the first seismic profile image; or,

[0165] The tracking module is used to extract features from the first seismic profile image using a layer tracking model. Based on the feature map of the first seismic profile image, the traditional dynamic time warping algorithm is used to process the feature map to obtain the layer tracking result of the first seismic profile image.

[0166] In one possible implementation, the tracking module 702 is used to extract features from the first seismic profile image using a layer tracking model to obtain a first feature map; sample the first feature map to obtain a second feature map; repeatedly input the currently obtained feature map into the layer tracking model, extract features from the input feature map using the layer tracking model, output the feature map obtained by this feature extraction, and sample the feature map obtained by this feature extraction until the termination condition is met.

[0167] In one possible implementation, the device further includes:

[0168] The prediction module is used to determine the layer position distribution function based on the layer tracking results of multiple consecutive seismic profile images after obtaining the layer tracking results of multiple consecutive seismic profile images; and to predict the layer in the next seismic profile image based on the layer position distribution function.

[0169] It should be noted that the above-described hierarchical interpretation device based on uncertainty quantization is only illustrated by the division of the functional modules described above. In practical applications, the functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the hierarchical interpretation device based on uncertainty quantization and the hierarchical interpretation method embodiment provided above belong to the same concept, and their specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0170] In some embodiments, the computer device is provided as a terminal. Figure 8 This is a structural block diagram of a terminal provided in an embodiment of this application. The terminal 800 includes a processor 801 and a memory 802.

[0171] Processor 801 may include one or more processing cores, such as a quad-core processor or an octa-core processor. Processor 801 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 801 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 801 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 801 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0172] The memory 802 may include one or more computer-readable storage media, which may be non-transitory. The memory 802 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 802 are used to store at least one program code, which is executed by the processor 801 to implement the layer interpretation method based on uncertainty quantization provided in the method embodiments of this application.

[0173] In some embodiments, the terminal 800 may also optionally include a peripheral device interface 803 and at least one peripheral device. The processor 801, memory 802, and peripheral device interface 803 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 803 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: a radio frequency circuit 804, a display screen 805, a camera 806, an audio circuit 807, a positioning component 808, and a power supply 809.

[0174] Peripheral device interface 803 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 801 and memory 802. In some embodiments, processor 801, memory 802 and peripheral device interface 803 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 801, memory 802 and peripheral device interface 803 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0175] Display screen 805 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 805 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 801 for processing. In this case, display screen 805 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 805, which serves as the front panel of terminal 800; in other embodiments, there may be at least two display screens, respectively disposed on different surfaces of terminal 800 or in a folded design; in still other embodiments, display screen 805 may be a flexible display screen, disposed on a curved or folded surface of terminal 800. Furthermore, display screen 805 may be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. Display screen 805 may be made of materials such as LCD (Liquid Crystal Display) or OLED (Organic Light-Emitting Diode).

[0176] Power supply 809 is used to supply power to the various components in terminal 800. Power supply 809 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 809 includes a rechargeable battery, the rechargeable battery can support wired or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0177] Those skilled in the art will understand that Figure 8 The structure shown does not constitute a limitation on terminal 800 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0178] In some embodiments, the computer device is provided as a server. Figure 9 This is a schematic diagram of a server structure provided in an embodiment of this application. The server 900 can vary considerably due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 901 and one or more memories 902. The memory 902 stores at least one line of program code, which is loaded and executed by the processor 901 to implement the methods provided in the above-described method embodiments. Of course, the server may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server may also include other components for implementing device functions, which will not be elaborated here.

[0179] The server 900 is used to execute the steps performed by the server in the above method embodiments.

[0180] This application also provides a computer-readable storage medium storing at least one piece of program code, which is loaded and executed by a processor to implement the layer interpretation method based on uncertainty quantization as described in any of the above implementations.

[0181] This application also provides a computer program product, which includes at least one piece of program code, which is loaded and executed by a processor to implement the layer interpretation method based on uncertainty quantization as described in any of the above implementations.

[0182] In some embodiments, the computer program involved in the present application embodiments may be deployed and executed on a computer device, or executed on multiple computer devices located in one location, or executed on multiple computer devices distributed in multiple locations and interconnected through a communication network. Multiple computer devices distributed in multiple locations and interconnected through a communication network may constitute a blockchain system.

[0183] The above are merely optional embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for interpreting stratigraphic levels based on uncertainty quantification, characterized in that, The method includes: Acquire a first seismic profile image, which includes seismic waves from multiple seismic traces; The first seismic profile image is processed using a layer tracing method to obtain the layer tracing result of the first seismic profile image, wherein the layer tracing result indicates the position of at least one layer in the first seismic profile image; The layer tracking results are sampled to obtain layer samples for each layer; Obtain the first relational data corresponding to the Monte Carlo integral. The first relational data is used to represent the relationship between the layer samples of each layer, the probability density function of each layer, and the mean of each layer. The first relational data is shown in the following formula (1): （1） Where a and b are constants, Here, d is the definite integral, d is the differential, f is the stratum function, h is the stratum, f(h) is the stratum function of the stratum, f(h) > 0, pdf(h) is the probability density function of the stratum, and E is the expectation, which also represents the mean of the stratum. Based on Bayesian estimation theory and the first assumption, the first relational data is transformed into second relational data. The first assumption is that the layers and artillery recording points in the first seismic profile image are independently and identically distributed. The second relational data is used to represent the relationship between the layer sample, conditional probability density function, layer function and mean of each layer. The second relational data is shown in the following formula (2): （2） in, Represents a seismic profile image. This represents the posterior distribution of layer h, which is also the layer sample of that layer. This represents the posterior distribution of the seismic profile image. The conditional probability density function represents the layer. Let represent the expectation of the posterior distribution of layer h in layer h. This represents the expectation of the seismic profile image in the posterior distribution of the seismic profile image. This represents a seismic profile image showing the probability distribution at artillery recording point c. Based on the second assumption, the second relational data is simplified to obtain the third relational data. The second assumption is that the conditional probability density function of the layer is... The function, the third relational data is shown in the following formula (3): （3） in, It is the conditional probability density function The number of samples, It is the sample size of the posterior distribution of the seismic profile image. From the conditional probability density function The k-th sample obtained, It is the posterior distribution from the seismic profile image. The j-th sample obtained, For summation functions; Based on the aforementioned third relation data, Bayesian statistical theory is used to determine the first-order moment estimate and second-order moment estimate of the layer samples at each layer. The first moment estimate of the slice samples of the aforementioned stratum is determined as the mean of the stratum, and the second moment estimate of the slice samples of the aforementioned stratum is determined as the variance of the stratum; wherein, the mean of the slice samples of the aforementioned stratum is... The variance of the layer samples in the aforementioned layer is: ; Based on the uncertainty parameters of each layer in the first seismic profile image, the layer tracking results are processed. The uncertainty parameters include the mean and variance. The uncertainty parameters are used to indicate the degree of uncertainty of the layer. The higher the degree of uncertainty of the layer, the lower the accuracy of the layer. The lower the degree of uncertainty of the layer, the higher the accuracy of the layer. After obtaining the horizon tracking results of multiple consecutive seismic profile images, the horizon location distribution function is determined using the inter-frame differencing method based on the horizon tracking results of the multiple consecutive seismic profile images; wherein, the determination of the horizon location distribution function using the inter-frame differencing method based on the horizon tracking results of the multiple consecutive seismic profile images includes: Based on the layer tracking results of the multiple consecutive seismic profile images, the difference D between the layers of two adjacent seismic profile images is calculated using the following formula (4): （4） in, This represents the layer location corresponding to the i-th seismic trace in the n-th seismic profile image. This represents the layer location corresponding to the i-th seismic trace in the (n-1)-th seismic profile image. This represents the difference in the stratigraphic level corresponding to the i-th seismic trace between the n-th seismic profile image and the (n-1)-th seismic profile image, where n is any integer greater than 1 and m is any positive integer; The differences in the positions of the layers between the multiple consecutive seismic profile images are obtained, and the layer position distribution function is fitted. Based on the layer location distribution function, the layers in the next seismic profile image of the plurality of consecutive seismic profile images are predicted.

2. The method according to claim 1, characterized in that, The process of processing the layer tracking results based on the uncertainty parameters of each layer in the first seismic profile image includes: Based on the mean and variance of each layer in the first seismic profile image, the confidence interval of each layer is determined; For each layer in the layer tracking results, points that do not belong to the confidence interval of that layer are deleted.

3. The method according to claim 1, characterized in that, The process of processing the layer tracking results based on the uncertainty parameters of each layer in the first seismic profile image includes: When the uncertainty parameter of any layer in the first seismic profile is greater than the first threshold, the layer is deleted from the layer tracking results, or the layer tracking results are discarded.

4. The method according to claim 1, characterized in that, The step-tracking method is used to process the first seismic profile image to obtain the step-tracking result of the first seismic profile image, including: A horizon tracing model is used to perform horizon tracing on the first seismic profile image to obtain the horizon tracing result of the first seismic profile image; or, Based on the first seismic profile image, a traditional dynamic time warping algorithm is used to process it, resulting in the layer tracking result of the first seismic profile image; or, A layer-tracking model is used to extract features from the first seismic profile image to obtain a feature map of the first seismic profile image. Based on the feature map, a traditional dynamic time warping algorithm is used to process the image to obtain the layer-tracking result of the first seismic profile image.

5. The method according to claim 4, characterized in that, The layer tracing model is used to extract features from the first seismic profile image to obtain a feature map of the first seismic profile image, including: Using the aforementioned layer tracing model, feature extraction is performed on the first seismic profile image to obtain a first feature map; The first feature map is sampled to obtain the second feature map; The process is repeated, inputting the currently obtained feature map into the layer tracking model, using the layer tracking model to extract features from the input feature map, outputting the feature map obtained from this feature extraction, and sampling the feature map obtained from this feature extraction until the termination condition is met.

6. A strata interpretation device based on uncertainty quantification, characterized in that, The device includes: The acquisition module is used to acquire a first seismic profile image, which includes seismic waves from multiple seismic traces. The tracking module is used to process the first seismic profile image using a layer tracking method to obtain the layer tracking result of the first seismic profile image, wherein the layer tracking result indicates the position of at least one layer in the first seismic profile image. The determination module is used to sample the layer tracking results to obtain layer samples for each layer; and to obtain the first relation data corresponding to the Monte Carlo integral. The first relation data is used to represent the relationship between the layer samples of each layer, the probability density function of each layer, and the mean of each layer. The first relation data is shown in the following formula (1): （1） Where a and b are constants, For definite integral, d is the differential, f is the stratum function, h is the stratum, f(h) is the stratum function of the stratum, f(h) > 0, pdf(h) is the probability density function of the stratum, E is the expectation, which also represents the mean of the stratum; based on Bayesian estimation theory and the first assumption, the first relational data is converted into second relational data. The first assumption is that the stratum and the artillery record points in the first seismic profile image are independent and identically distributed. The second relational data is used to represent the relationship between the stratum sample, conditional probability density function, stratum function and mean of each stratum. The second relational data is shown in the following formula (2): （2） in, Represents a seismic profile image. This represents the posterior distribution of layer h, which is also the layer sample of that layer. This represents the posterior distribution of the seismic profile image. The conditional probability density function represents the layer. Let represent the expectation of the posterior distribution of layer h in layer h. This represents the expectation of the seismic profile image in the posterior distribution of the seismic profile image. The image represents the seismic profile under the probability distribution of the artillery recording point c. Based on the second assumption, the second relational data is simplified to obtain the third relational data. The second assumption is that the conditional probability density function of the layer is... The function, the third relation data is shown in the following formula (3): （3） in, It is the conditional probability density function The number of samples, It is the sample size of the posterior distribution of the seismic profile image. From the conditional probability density function The k-th sample obtained, It is the posterior distribution from the seismic profile image. The j-th sample obtained, To calculate the summation function; based on the third relation data, Bayesian statistical theory is used to determine the first-moment estimate and second-moment estimate of the stratum samples for each stratum; the first-moment estimate of the stratum samples is determined as the mean of the stratum, and the second-moment estimate of the stratum samples is determined as the variance of the stratum; wherein, the mean of the stratum samples is... The variance of the layer samples in the aforementioned layer is: ; The processing module is used to process the layer tracking results based on the uncertainty parameters of each layer in the first seismic profile image. The uncertainty parameters include the mean and variance. The uncertainty parameters are used to indicate the degree of uncertainty of the layer. The higher the degree of uncertainty of the layer, the lower the accuracy of the layer. The lower the degree of uncertainty of the layer, the higher the accuracy of the layer. The prediction module is used to determine the layer position distribution function based on the layer tracking results of multiple consecutive seismic profile images after obtaining the layer tracking results of the multiple consecutive seismic profile images, using the inter-frame difference method; wherein, the determination of the layer position distribution function based on the layer tracking results of the multiple consecutive seismic profile images using the inter-frame difference method includes: calculating the difference D between the layers of two adjacent seismic profile images using the following formula (4) based on the layer tracking results of the multiple consecutive seismic profile images: （4） in, This represents the layer location corresponding to the i-th seismic trace in the n-th seismic profile image. This represents the layer location corresponding to the i-th seismic trace in the (n-1)-th seismic profile image. This represents the difference in the stratigraphic level corresponding to the i-th seismic trace between the n-th seismic profile image and the (n-1)-th seismic profile image, where n is any integer greater than 1 and m is any positive integer; The differences in the positions of the layers between the multiple consecutive seismic profile images are obtained, and the layer position distribution function is fitted; based on the layer position distribution function, the layers in the next seismic profile image of the multiple consecutive seismic profile images are predicted.

7. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing at least one piece of program code, which is loaded and executed by the processor to implement the layer interpretation method based on uncertainty quantization as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one piece of program code, which is loaded and executed by a processor to implement the layer interpretation method based on uncertainty quantization as described in any one of claims 1 to 5.

Images