CN109492775B - Geological structure interpretation detection method, geological structure interpretation detection device and readable storage medium - Google Patents
Geological structure interpretation detection method, geological structure interpretation detection device and readable storage medium Download PDFInfo
- Publication number
- CN109492775B CN109492775B CN201811377579.8A CN201811377579A CN109492775B CN 109492775 B CN109492775 B CN 109492775B CN 201811377579 A CN201811377579 A CN 201811377579A CN 109492775 B CN109492775 B CN 109492775B
- Authority
- CN
- China
- Prior art keywords
- geological
- preset
- attribute
- geological structure
- sensitive
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The invention provides a detection method, a detection device and a readable storage medium for geological structure interpretation, and relates to the technical field of geological exploration. The detection method comprises the following steps: acquiring geological information of a target area to be detected; wherein the geological information comprises information of a plurality of seismic attributes; extracting sensitive information corresponding to the sensitive attribute from the geological information based on a plurality of predetermined sensitive attributes; and calculating the sensitive information based on a predetermined first learning algorithm to obtain a structural interpretation result of the target area to be detected. Therefore, the geological structure of the target area to be detected can be automatically identified, manual subjective interference on geological structure interpretation work is avoided, and a large amount of time consumed in the manual subjective judgment process can be reduced.
Description
Technical Field
The invention relates to the technical field of geological exploration, in particular to a detection method, a detection device and a readable storage medium for geological structure interpretation.
Background
Geologic structure interpretation is a task with multiple solutions and uncertainties. At present, the work of geological structure interpretation is mainly completed through artificial subjective judgment, and a great deal of time is consumed in the process of the artificial subjective judgment.
Disclosure of Invention
The invention provides a detection method, a detection device and a readable storage medium for geological structure interpretation, which aims to solve the problem of how to finish geological structure interpretation work through a machine learning algorithm.
In order to solve the above technical problem, the embodiment of the present invention is implemented as follows:
in a first aspect, an embodiment of the present invention provides a method for detecting a geological structure interpretation, including: acquiring geological information of a target area to be detected; wherein the geological information comprises information of a plurality of seismic attributes; extracting sensitive information corresponding to the sensitive attribute from the geological information based on a plurality of predetermined sensitive attributes; and calculating the sensitive information based on a predetermined first learning algorithm to obtain a construction interpretation result of the target area to be detected. Therefore, the geological structure of the target area to be detected can be automatically identified, manual subjective interference on geological structure interpretation work is avoided, and a large amount of time consumed in the manual subjective judgment process can be reduced.
With reference to the first aspect, an embodiment of the present invention provides a first possible implementation manner of the first aspect, where before extracting sensitive information corresponding to multiple predetermined sensitive attributes from the geological information, the method further includes: establishing a geological model based on the target area to be detected; forward modeling is carried out on the geological model to obtain seismic reflection data; determining a plurality of seismic attributes corresponding to the seismic reflection data; determining attribute values of the plurality of seismic attributes at a preset geological structure; and determining the seismic attribute of which the attribute value becomes maximum or minimum at the preset geological structure as the predetermined sensitive attribute. Sensitive seismic attributes for geological structure interpretation of the target area to be measured can be determined.
With reference to the first aspect or the first possible implementation manner of the first aspect, an embodiment of the present invention provides a second possible implementation manner of the first aspect, where determining attribute values of the plurality of seismic attributes at a preset geological structure includes: attribute values of the plurality of seismic attributes at the collapse column geological formation and at the fault geological formation are determined.
With reference to the first aspect, an embodiment of the present invention provides a third possible implementation manner of the first aspect, where before calculating the sensitive information based on a predetermined first learning algorithm to obtain a structural interpretation result of the target region to be measured, the method further includes: establishing a network model according to a plurality of preset learning algorithms; inputting data corresponding to the predetermined sensitivity attribute into the network model to obtain a detection result of each preset learning algorithm; comparing the detection result of each preset learning algorithm with a preset reference result to obtain the accuracy of each preset learning algorithm; and determining the preset learning algorithm with the highest accuracy as the first preset learning algorithm. Therefore, an intelligent learning algorithm can be reasonably selected, and the high-efficiency and high-precision geological structure explanation of the target area to be detected is realized.
With reference to the first aspect or the third possible implementation manner of the first aspect, an embodiment of the present invention provides a fourth possible implementation manner of the first aspect, where after the network model is built according to multiple preset learning algorithms, the method further includes: assigning a characteristic value to at least one predetermined geological structure; correspondingly, inputting the data corresponding to the predetermined sensitivity attribute into the network model to obtain the detection result of each preset learning algorithm, including: inputting the data corresponding to the characteristic value of each preset geological structure and the predetermined sensitive attribute into the network model to obtain a detection result of each preset geological structure by each preset learning algorithm; comparing the detection result of each preset learning algorithm with a preset reference result to obtain the accuracy of each preset learning algorithm, wherein the method comprises the following steps: and comparing the detection result of each preset geological structure with a preset reference result corresponding to each preset geological structure to obtain the detection accuracy of each preset learning algorithm on at least one preset geological structure. Therefore, the optimal preset learning algorithm of the target region to be detected can be confirmed according to the first geological structure.
With reference to the first aspect or the third possible implementation manner of the first aspect, an embodiment of the present invention provides a fifth possible implementation manner of the first aspect, where the multiple preset learning algorithms include: at least two algorithms of BP neural network algorithm, RBF neural network algorithm, support vector machine algorithm, decision tree algorithm and random forest algorithm. Therefore, the geological structure interpretation method provided by the embodiment of the invention can use various intelligent learning algorithms.
With reference to the first aspect, an embodiment of the present invention provides a sixth possible implementation manner of the first aspect, where the multiple predetermined sensitivity attributes include: at least two of an instantaneous frequency attribute, a dip angle attribute, a variance attribute, a chaos attribute, and a local flatness attribute. Therefore, the geological structure interpretation method provided by the embodiment of the invention can be used for confirming the sensitive seismic attribute of the target area to be detected.
In a second aspect, an embodiment of the present invention provides a detection apparatus for geological structure interpretation, including: the acquisition unit is used for acquiring geological information of a target area to be detected; wherein the geological information comprises information of a plurality of seismic attributes; the extracting unit is used for extracting sensitive information corresponding to the sensitive attribute from the geological information based on a plurality of predetermined sensitive attributes; and the calculating unit is used for calculating the sensitive information based on a predetermined first learning algorithm to obtain a structural interpretation result of the target area to be detected.
With reference to the second aspect, an embodiment of the present invention provides a first possible implementation manner of the second aspect, where the detection apparatus further includes: the forward modeling unit is used for establishing a geological model based on the target area to be detected; the forward modeling unit is also used for performing forward modeling on the geological model to obtain seismic reflection data; a processing unit for determining a plurality of seismic attributes corresponding to the seismic reflection data; the processing unit is further used for determining attribute values of the plurality of seismic attributes at a preset geological structure; the processing unit is further configured to determine that the seismic attribute at which the attribute value becomes a maximum or a minimum at the preset geological structure is the predetermined sensitive attribute.
With reference to the second aspect or the first possible implementation manner of the second aspect, the embodiment of the present invention provides a second possible implementation manner of the second aspect, and the processing unit is further configured to determine attribute values of the plurality of seismic attributes at the collapse column geological formation and the fault geological formation.
With reference to the second aspect, an embodiment of the present invention provides a third possible implementation manner of the second aspect, where the detection apparatus further includes: the modeling unit is used for establishing a network model according to a plurality of preset learning algorithms; the analysis unit is used for inputting the predetermined sensitivity attribute into the network model to obtain the detection result of each preset learning algorithm; the comparison unit is used for comparing the detection result of each preset learning algorithm with a preset reference result to obtain the accuracy of each preset learning algorithm; and the determining unit is used for determining the preset learning algorithm with the highest accuracy as the first preset learning algorithm.
With reference to the second aspect or the third possible implementation manner of the second aspect, an embodiment of the present invention provides a fourth possible implementation manner of the second aspect, and the detection apparatus further includes: an assigning unit for assigning a characteristic value to at least one preset geological structure; the analysis unit is further configured to input data corresponding to the feature value of each preset geological structure and the predetermined sensitivity attribute into the network model, and obtain a detection result of each preset geological structure by each preset learning algorithm; the comparison unit is further configured to compare the detection result of each preset geological structure with a preset reference result corresponding to each preset geological structure, so as to obtain the detection accuracy of each preset learning algorithm on the at least one preset geological structure.
In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, in which a computer program is stored, and when the computer program runs on a computer, the computer is caused to execute the method for detecting the geological structure interpretation according to the first aspect or any one of the embodiments of the first aspect.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments will be briefly described below. It is appreciated that the following drawings depict only some embodiments of the invention and are therefore not to be considered limiting of its scope, for those skilled in the art will be able to derive additional related drawings therefrom without the benefit of the inventive faculty.
Fig. 1 is a step diagram of a geological structure interpretation detection method provided by an embodiment of the present invention.
Fig. 2 is a result diagram obtained by forward modeling of the geological model according to the embodiment of the present invention.
Fig. 3 is a data profile obtained by forward modeling of a geological model according to an embodiment of the present invention.
Fig. 4 is a first sensitivity attribute map obtained after forward modeling is performed on a geological model according to an embodiment of the present invention.
Fig. 5 is a second sensitivity attribute map obtained after forward modeling of the geological model according to the embodiment of the present invention.
Fig. 6 is a first result graph obtained by calculating data corresponding to the sensitive attribute and a feature value of a preset geological structure by using the intelligent learning algorithm according to the embodiment of the present invention.
Fig. 7 is a second result graph obtained by calculating the data corresponding to the sensitive attribute and the feature value of the preset geological structure by the intelligent learning algorithm according to the embodiment of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the described embodiments are merely a few embodiments of the invention, and not all embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Furthermore, the terms "first," "second," and the like are used merely to distinguish one description from another, and are not to be construed as indicating or implying relative importance.
The geological structure interpretation is not only a coal field, but also a necessary means for understanding the development of underground structures of an oil and gas field, and the requirement on the structure interpretation precision is higher and higher as the exploitation environment is more severe. Geologic structure interpretation is a task with multiple solutions and uncertainties. At present, the work of geological structure interpretation is mainly completed through artificial subjective judgment, and a great deal of time is consumed in the process of the artificial subjective judgment.
In view of the above problems, the present inventors have conducted extensive research and research to provide the following embodiments to solve the above problems. The embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a step diagram of a detection method for geological structure explanation according to an embodiment of the present invention. The detection method comprises the following steps:
step S200, acquiring geological information of a target area to be detected; wherein the geological information comprises information of a plurality of seismic attributes.
And S400, extracting sensitive information corresponding to the sensitive attributes from the geological information based on the multiple predetermined sensitive attributes.
Step S600, sensitive information is calculated based on a predetermined first learning algorithm, and a structural interpretation result of the target area to be measured is obtained.
It can be understood that the geological information of the target region to be measured may be geological information of a certain region in M city, or geological information of a certain region in N city.
It is to be understood that, for the convenience of those skilled in the art to understand the embodiment of the present invention, the terms in step S200, step S400 and step S600 will be described first. Geological information comprises a variety of information in a multidimensional space, including geometric, kinematic, kinetic, and statistical features. Geological information also includes a variety of seismic attributes. Sensitive seismic attributes refer to seismic attributes that are sensitive to known geological formations in the target area to be measured. The first learning algorithm is an algorithm which is reasonably selected according to different geological tasks, different work area ranges and different geological structure interpretation targets.
It can be understood that, in the step S200, the step S400, and the step S600, the geological structure interpretation of the target region to be detected is performed by the detection method for geological structure interpretation provided by the embodiment of the present invention, so that the geological structure of the target region to be detected can be automatically identified, the geological structure interpretation work is prevented from being interfered by human subjectively, a large amount of time consumed in the process of human subjective judgment can be reduced, and the geological structure interpretation work can be objectively completed.
The following will describe a detection method for geological structure explanation provided by the embodiment of the present invention in detail. The detection method comprises the steps of carrying out forward modeling on geological information of a target area to be detected, establishing a relation between a geological structure of the target area to be detected and seismic reflection characteristics, and obtaining forward seismic data. Based on the forward seismic data, seismic attributes can be selected that are sensitive to the known geological structure of the target area to be measured. And then testing and analyzing the data of the sensitive earthquake attribute by adopting various intelligent learning algorithms, and selecting the intelligent learning algorithm with the highest accuracy to detect the actual data of the target area to be detected, thereby realizing the high-efficiency and high-precision geological structure interpretation of the target area to be detected.
Optionally, a geological model is established based on the target region to be detected; forward modeling is carried out on the geological model to obtain seismic reflection data; determining a plurality of seismic attributes corresponding to the seismic reflection data; determining attribute values of the plurality of seismic attributes at a preset geological structure; and determining the seismic attribute of which the attribute value becomes maximum or minimum at the preset geological structure as the predetermined sensitive attribute. Sensitive seismic attributes for geological structure interpretation of the target area to be measured can be determined.
Optionally, determining the attribute values of the plurality of seismic attributes at the preset geological structure includes: attribute values of the plurality of seismic attributes at the collapse column geological formation and at the fault geological formation are determined.
First, because forward modeling is an efficient way to obtain seismic reflection signals of known geological formations (e.g., collapse column features and fault features). Before the geological model is established, the geological basic structure of the target area to be detected needs to be known, such as the geological development scale, the development type and the geological hierarchical structure of the geology of the target area to be detected, whether the over-collapse column, the fault, the karst cave and the like appear. And then, a geological model is established for the target area to be detected, forward modeling is carried out on the geological model to obtain symbolic seismic reflection data, and theoretical data are provided for selection of sensitive seismic attributes and trial calculation of a network model, so that an intelligent learning algorithm with the highest accuracy is reasonably selected from the network model to carry out actual data detection on the target area to be detected, and high-efficiency and high-precision detection on the geological structure is realized.
Understandably, the target to be measured can be explained according to different geological tasks, different work area ranges and different geological structures, and corresponding geological models can be established, wherein the geological models are different. For example, when geological structure interpretation is performed on geological structures in a certain region of the M city, the geological basic structures of the M city need to be known, so that a geological model for the geological basic structures of the M city is built. For another example, when a geological structure of a certain region of the city N is interpreted, it is necessary to understand the geological basic structure of the city N, and to establish a geological model for the geological basic structure of the city N. Therefore, the geological model built for M city and the geological model built for N city may be different.
Referring to fig. 2, fig. 3, fig. 4 and fig. 5, fig. 2 is a diagram illustrating a result obtained by forward modeling of a geological model according to an embodiment of the present invention. Fig. 3 is a data profile obtained by forward modeling of a geological model according to an embodiment of the present invention. Fig. 4 is a first sensitivity attribute map obtained after forward modeling is performed on a geological model according to an embodiment of the present invention. Fig. 5 is a second sensitivity attribute map obtained after forward modeling of the geological model according to the embodiment of the present invention. Wherein, X1 in FIG. 4 and FIG. 5 represents a first trap column feature, X2 represents a second trap column feature, F1 represents a first fault feature, and F2 represents a second fault feature.
Next, from the foregoing seismic attribute contents, it is clear to those skilled in the art that the geological information of the target region to be measured can be described in terms of seismic attributes. Therefore, a plurality of seismic attributes can be widely extracted from the marked seismic reflection data. Understandably, due to the fact that the variety and the number of the seismic attributes are large, when the seismic attributes are widely extracted, the seismic attributes related to the geological model can be extracted aiming at the geological model. One or more sensitive seismic attributes are then selected from the extracted plurality of seismic attributes. Understandably, in order to meet the precision requirement of geological structure interpretation, the embodiment of the invention selects a plurality of sensitive seismic attributes from the extracted plurality of seismic attributes. And the selected data of the sensitive seismic attributes are used as input layer data of the network model.
Optionally, the plurality of predetermined sensitivity attributes includes: at least two of an instantaneous frequency attribute, a dip angle attribute, a variance attribute, a chaos attribute, and a local flatness attribute.
Specifically, from fig. 2 and 3, it can be known that the geological model subjected to forward modeling has a characteristic of a collapse column at an abscissa of 100 and an abscissa of 300. And it can also be known that fault features exist in the geologic model at 500 abscissa and 800 abscissa. Correspondingly, in fig. 4 and 5, the Instantaneous frequency attribute (Instantaneous frequency), the Dip angle attribute (Dip drilling), the Variance attribute (Variance), the Chaos attribute (Chaos) and the Local flatness attribute (Local flatness) have maximum or minimum values for the attribute values of the trapped column feature and the fault feature, and the attribute values have obvious variation trends. Thus, in the geological model, these five seismic attributes are determined to be sensitive seismic attributes.
In other words, the established geological model comprises the collapse column feature and the fault feature, and the sensitivity of the seismic attribute can be analyzed by analyzing the change of the seismic attribute at the structure of the collapse column feature and the structure of the fault feature, so as to determine whether the seismic attribute is the sensitive seismic attribute. Specifically, if the attribute value of the seismic attribute at the position without the trap column feature and/or the fault feature structure is normal, the attribute value at the position with the trap column feature and/or the fault feature structure has a maximum value or a minimum value, and the attribute value of the seismic attribute has obvious variation trend, so that the detection that the seismic attribute is suitable for the geological structure interpretation of the geological model is explained, that is, the seismic attribute is judged to be the sensitive seismic attribute, and vice versa. For another example, if the attribute value of a seismic attribute is not substantially changed or irregularly fluctuated in the geological model, and therefore the seismic attribute cannot identify or detect the collapse column feature and/or fault feature existing in the geological model, it indicates that the seismic attribute is not suitable for the geological model, i.e. the seismic attribute is considered to be less sensitive, and it is determined that the seismic attribute is not the sensitive seismic attribute of the geological model.
Next, with continuing reference to fig. 4 and 5, and with reference to fig. 6 and 7, fig. 6 is a first result graph obtained by calculating the data corresponding to the sensitive attribute and the feature value of the preset geological structure by the intelligent learning algorithm according to the embodiment of the present invention. Fig. 7 is a second result graph obtained by calculating the data corresponding to the sensitive attribute and the feature value of the preset geological structure by the intelligent learning algorithm according to the embodiment of the present invention. Where X1 in FIGS. 6 and 7 represents a first trap column feature, X2 represents a second trap column feature, and the trap column feature value is-5. F1 represents the first fault feature, F2 represents the second fault feature, and the fault feature value is 5.
Optionally, a network model is established according to a plurality of preset learning algorithms; inputting data corresponding to the predetermined sensitivity attribute into the network model to obtain a detection result of each preset learning algorithm; comparing the detection result of each preset learning algorithm with a preset reference result to obtain the accuracy of each preset learning algorithm; and determining the preset learning algorithm with the highest accuracy as the first preset learning algorithm.
Optionally, the plurality of preset learning algorithms include: at least two algorithms of BP neural network algorithm, RBF neural network algorithm, support vector machine algorithm, decision tree algorithm and random forest algorithm.
It is understood that the network model according to the embodiment of the present invention can include a plurality of smart learning algorithms, and the plurality of smart learning algorithms may include a BP (Back Propagation) neural network, an RBF (Radial basis function) neural network, a Support Vector Machine (SVM) (the Support Vector Machine adopted in the embodiment of the present invention is a GA-SVM, where GA is a Genetic Algorithm), a Decision Tree (Decision Tree) and a Random Forest (Random Forest) smart learning Algorithm, and the five smart learning algorithms are applied to the geological structure interpretation. The geological model after forward modeling is intelligently detected and identified through the five intelligent learning algorithms, and the accurate identification capability of each algorithm in geological structure interpretation is analyzed. It should be noted that the network model according to the embodiment of the present invention may further include other intelligent learning algorithms, and the manner of using the other intelligent learning algorithms is the same as the manner of using the above five intelligent learning algorithms.
Understandably, the BP neural network has the advantages of high classification accuracy, strong fault-tolerant capability and associative memory capability. The RBF neural network has the advantages of high computational efficiency and strong global myopia. The support vector machine has the advantages of solving high-dimensional problems, improving generalization capability and not depending on the whole data. Decision trees have the advantage of being both computationally easy and easy to understand and can handle samples of precise attributes. The random forest has the advantages of no over-fitting and strong anti-interference capability.
Specifically, the data of the multiple sensitive seismic attributes are selected to be used as input layer data of the network model. Thus, 100 sets of data of multiple sensitive seismic attributes may be selected from the data of multiple sensitive seismic attributes. The network model and the five intelligent learning algorithms can be detected by adopting a cross-checking method for the 100 groups of data, so that the detection precision of each intelligent learning algorithm is analyzed, or the accuracy of each intelligent algorithm can be analyzed, the intelligent learning algorithm with the highest accuracy is reasonably selected to detect the actual data of the target area to be detected, and the high-efficiency and high-precision detection of the geological structure is realized.
The method of cross-checking includes training the network model using 99 sets of data, and then checking the remaining 1 set of data. The checking mode can be that each intelligent learning algorithm is trained by using 99 groups of data, each intelligent learning algorithm respectively obtains a group of detection data, the detection data is compared with the remaining 1 group of data, and the similarity or the accuracy of the detection data and the remaining 1 group of data is checked. After the detection is carried out by adopting a cross-checking method, the detection result of each intelligent learning algorithm is obtained, and the detection results are compared with the preset reference result, so that the detection precision of each intelligent learning algorithm is analyzed, or the accuracy of each intelligent algorithm can be analyzed. Wherein, presetting the reference result comprises: and inputting the selected data of the multiple sensitive seismic attributes into the network model for calculation to obtain a detection result of the network model.
Understandably, the data of various sensitive seismic attributes are selected to be used as input layer data of the network model. And the data corresponding to the characteristic of the collapse column and the data corresponding to the characteristic of the fault exist in the data of the multiple sensitive seismic attributes. The network model is also capable of identifying both the trapping column features and the fault features. Meanwhile, the characteristics of the collapse column and the characteristics of the fault are identified, and the detection precision of each intelligent learning algorithm can be analyzed, or the accuracy of each intelligent algorithm can be analyzed.
Optionally, a characteristic value is assigned to at least one preset geological structure; correspondingly, inputting the data corresponding to the predetermined sensitivity attribute into the network model to obtain the detection result of each preset learning algorithm, including: inputting the data corresponding to the characteristic value of each preset geological structure and the predetermined sensitive attribute into the network model to obtain a detection result of each preset geological structure by each preset learning algorithm; comparing the detection result of each preset learning algorithm with a preset reference result to obtain the accuracy of each preset learning algorithm, wherein the method comprises the following steps: and comparing the detection result of each preset geological structure with a preset reference result corresponding to each preset geological structure to obtain the detection accuracy of each preset learning algorithm on at least one preset geological structure.
Specifically, the first predetermined geological structure may be a collapsed column feature to which a collapsed column feature value of-5 may be assigned. The second predetermined geological structure may be a fault signature to which a fault signature value of 5 may be assigned. And inputting the selected data of the multiple sensitive seismic attributes, the characteristic value of the trap column and the characteristic value of the fault into the network model to obtain the detection result of each intelligent learning algorithm. And comparing the detection result of each intelligent learning algorithm with a preset reference result (the preset reference result can be a characteristic value preset in the network model, for example, the characteristic value of a trap column can be-5, the characteristic value of a fault can be 5, and the characteristic value of a non-change geological structure can be 0) corresponding to each preset geological structure, so as to obtain the detection accuracy of each preset learning algorithm on the at least one preset geological structure. Therefore, the detection precision of each intelligent learning algorithm is analyzed, or the accuracy of each intelligent algorithm can be analyzed. And then reasonably selecting the intelligent learning algorithm with the highest accuracy to detect the actual data of the target area to be detected, thereby realizing the high-efficiency and high-precision detection of the geological structure.
In conclusion, by comprehensively comparing the accuracy of each intelligent learning algorithm, one intelligent learning algorithm can be reasonably selected for different geological tasks, different work area ranges and different geological structure interpretations of the target area to be detected, and high-efficiency and high-precision geological structure interpretation is realized.
Understandably, when the accuracy of each intelligent learning algorithm is not greatly different, the advantages of each intelligent learning algorithm can be comprehensively compared, so that one intelligent learning algorithm can be reasonably selected according to different geological tasks, different work area ranges and different geological structure interpretations of the target area to be tested, and high-efficiency and high-precision geological structure interpretation is realized.
The second aspect of the embodiments of the present invention also provides a detection apparatus for geological structure interpretation, including: the acquisition unit is used for acquiring geological information of a target area to be detected; wherein the geological information comprises information of a plurality of seismic attributes; the extracting unit is used for extracting sensitive information corresponding to the sensitive attribute from the geological information based on a plurality of predetermined sensitive attributes; and the calculating unit is used for calculating the sensitive information based on a predetermined first learning algorithm to obtain a structural interpretation result of the target area to be detected.
Optionally, the detection device further includes: the forward modeling unit is used for establishing a geological model based on the target area to be detected; the forward modeling unit is also used for performing forward modeling on the geological model to obtain seismic reflection data; a processing unit for determining a plurality of seismic attributes corresponding to the seismic reflection data; the processing unit is further used for determining attribute values of the plurality of seismic attributes at a preset geological structure; the processing unit is further configured to determine that the seismic attribute at which the attribute value becomes a maximum or a minimum at the preset geological structure is the predetermined sensitive attribute.
Optionally, the detection device further includes: the modeling unit is used for establishing a network model according to a plurality of preset learning algorithms; the analysis unit is used for inputting the predetermined sensitivity attribute into the network model to obtain the detection result of each preset learning algorithm; the comparison unit is used for comparing the detection result of each preset learning algorithm with a preset reference result to obtain the accuracy of each preset learning algorithm; and the determining unit is used for determining the preset learning algorithm with the highest accuracy as the first preset learning algorithm.
Optionally, the detection device further includes: an assigning unit for assigning a first feature value to the first geological structure; the analysis unit is further configured to input the first feature value into the network model; an obtaining unit, configured to obtain a first detection result of the network model, where the first detection result of the network model is a first reference result; the comparison unit is further configured to compare the detection result of each preset learning algorithm with the first reference result to obtain a first accuracy of each preset learning algorithm; the determining unit is further configured to determine the preset learning algorithm with the highest first accuracy as the predetermined first learning algorithm.
Optionally, the detection device further includes: the assigning unit is further used for assigning a second characteristic value to the second geological structure; wherein the second geological formation is different from the first geological formation and the second eigenvalue is different from the first eigenvalue; the analysis unit is further configured to input the second feature value into the network model; the obtaining unit is further configured to obtain a second detection result of the network model, where the second detection result of the network model is a second reference result; the comparison unit is further configured to compare the detection result of each preset learning algorithm with the second reference result to obtain a second accuracy of each preset learning algorithm; the determining unit is further configured to determine the predetermined first learning algorithm from the plurality of preset learning algorithms according to the first accuracy and the second accuracy.
The third aspect of the embodiments of the present invention further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program runs on a computer, the computer is caused to execute the method for detecting the geological structure interpretation according to the first aspect or any one of the embodiments of the first aspect.
From the above description of the embodiments, it is clear to those skilled in the art that the present invention can be implemented by hardware, or by software plus a necessary general hardware platform, and based on such understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.), and includes several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the method described in the embodiments of the present invention.
In summary, the present invention provides a method, an apparatus and a readable storage medium for detecting geological structure interpretation. The geological structure interpretation of the target area to be detected is carried out through multiple predetermined sensitive attributes and a predetermined first learning algorithm, so that the geological structure of the target area to be detected can be automatically identified, the geological structure interpretation work is prevented from being interfered by human subjectivity, a large amount of time consumed in the process of human subjective judgment can be reduced, and the geological structure interpretation work can be objectively completed.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, system, and method may be implemented in other ways. The apparatus, system, and method embodiments described above are illustrative only, as the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s).
It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part. Alternatively, all or part of the implementation may be in software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part.
The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. A method for detecting a geological structure interpretation, comprising:
acquiring geological information of a target area to be detected; wherein the geological information comprises information of a plurality of seismic attributes;
extracting sensitive information corresponding to the sensitive attribute from the geological information based on a plurality of predetermined sensitive attributes; the sensitive attribute is a seismic attribute which has a maximum value or a minimum value for the attribute values of the characteristic of the collapse column and the characteristic of the fault and has an obvious variation trend of the attribute values;
establishing a network model according to a plurality of preset learning algorithms;
assigning a characteristic value to at least one predetermined geological structure;
inputting the data corresponding to the characteristic value of each preset geological structure and the predetermined sensitive attribute into the network model to obtain a detection result of each preset geological structure by each preset learning algorithm;
comparing the detection result of each preset geological structure with a preset reference result corresponding to each preset geological structure to obtain the detection accuracy of each preset learning algorithm on at least one preset geological structure;
determining the preset learning algorithm with the highest accuracy as a first learning algorithm;
and calculating the sensitive information based on the first learning algorithm to obtain a construction interpretation result of the target area to be detected.
2. The detection method according to claim 1, wherein before the sensitive information corresponding to the sensitive attribute is extracted from the geological information based on a plurality of predetermined sensitive attributes, the method further comprises:
establishing a geological model based on the target area to be detected;
forward modeling is carried out on the geological model to obtain seismic reflection data;
determining a plurality of seismic attributes corresponding to the seismic reflection data;
determining attribute values of the plurality of seismic attributes at a preset geological structure;
and determining the seismic attribute of which the attribute value becomes maximum or minimum at the preset geological structure as the predetermined sensitive attribute.
3. The method of detecting according to claim 2, wherein determining the property values of the plurality of seismic properties at a predetermined geological formation comprises:
attribute values of the plurality of seismic attributes at the collapse column geological formation and at the fault geological formation are determined.
4. The detection method according to claim 1, wherein the plurality of preset learning algorithms comprises:
at least two algorithms of BP neural network algorithm, RBF neural network algorithm, support vector machine algorithm, decision tree algorithm and random forest algorithm.
5. The detection method according to claim 1, wherein the plurality of predetermined sensitivity attributes comprises:
at least two of an instantaneous frequency attribute, a dip angle attribute, a variance attribute, a chaos attribute, and a local flatness attribute.
6. A device for detecting geological structure interpretation, comprising:
the acquisition unit is used for acquiring geological information of a target area to be detected; wherein the geological information comprises information of a plurality of seismic attributes;
the extracting unit is used for extracting sensitive information corresponding to the sensitive attribute from the geological information based on a plurality of predetermined sensitive attributes; the sensitive attribute is a seismic attribute which has a maximum value or a minimum value for the attribute values of the characteristic of the collapse column and the characteristic of the fault and has an obvious variation trend of the attribute values;
the modeling unit is used for establishing a network model according to a plurality of preset learning algorithms;
an assigning unit for assigning a characteristic value to at least one preset geological structure;
the analysis unit is used for inputting the data corresponding to the characteristic value of each preset geological structure and the predetermined sensitive attribute into the network model to obtain the detection result of each preset geological structure by each preset learning algorithm;
the comparison unit is used for comparing the detection result of each preset geological structure with a preset reference result corresponding to each preset geological structure to obtain the detection accuracy of each preset learning algorithm on at least one preset geological structure;
the determining unit is used for determining the preset learning algorithm with the highest accuracy as a first learning algorithm;
and the calculating unit is used for calculating the sensitive information based on the first learning algorithm to obtain a construction interpretation result of the target area to be detected.
7. A computer-readable storage medium, in which a computer program is stored which, when run on a computer, causes the computer to carry out the method of detection of geological structure interpretations according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811377579.8A CN109492775B (en) | 2018-11-19 | 2018-11-19 | Geological structure interpretation detection method, geological structure interpretation detection device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811377579.8A CN109492775B (en) | 2018-11-19 | 2018-11-19 | Geological structure interpretation detection method, geological structure interpretation detection device and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109492775A CN109492775A (en) | 2019-03-19 |
| CN109492775B true CN109492775B (en) | 2020-05-12 |
Family
ID=65697118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811377579.8A Active CN109492775B (en) | 2018-11-19 | 2018-11-19 | Geological structure interpretation detection method, geological structure interpretation detection device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109492775B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110515117B (en) * | 2019-07-19 | 2020-11-17 | 广州市高速公路有限公司 | Underground karst cave detection method based on pile hammer shock and decision tree model |
| CN110441820B (en) * | 2019-08-21 | 2020-06-16 | 中国矿业大学(北京) | Intelligent interpretation method of geological structure |
| CN112578446B (en) * | 2019-09-30 | 2023-04-11 | 中国石油化工股份有限公司 | Method and system for depicting formation reflection disorder degree |
| CN110737021A (en) * | 2019-11-06 | 2020-01-31 | 中国矿业大学(北京) | Fault recognition method and model training method and device thereof |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104570083A (en) * | 2013-10-29 | 2015-04-29 | 中国石油天然气集团公司 | Multi-dimensional seismic attribute-based automatic geologic body identification method |
| CN105842732A (en) * | 2016-03-16 | 2016-08-10 | 中国石油大学(北京) | Inversion method of multichannel sparse reflection coefficient and system thereof |
| CN108318937A (en) * | 2017-12-29 | 2018-07-24 | 中国石油天然气集团公司 | Geologic interpretation method and apparatus |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201008993D0 (en) * | 2010-05-28 | 2010-07-14 | Arkex Ltd | Processing geophysical data |
-
2018
- 2018-11-19 CN CN201811377579.8A patent/CN109492775B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104570083A (en) * | 2013-10-29 | 2015-04-29 | 中国石油天然气集团公司 | Multi-dimensional seismic attribute-based automatic geologic body identification method |
| CN105842732A (en) * | 2016-03-16 | 2016-08-10 | 中国石油大学(北京) | Inversion method of multichannel sparse reflection coefficient and system thereof |
| CN108318937A (en) * | 2017-12-29 | 2018-07-24 | 中国石油天然气集团公司 | Geologic interpretation method and apparatus |
Non-Patent Citations (2)
| Title |
|---|
| 孙振宇，彭苏萍，邹冠贵.基于SVM 算法的地震小断层自动识别.《煤炭学报》.2017,第42卷(第11期),第2945-2952页. * |
| 谭锋奇，李洪奇，孟照旭，郭海峰，李雄炎.数据挖掘方法在石油勘探开发中的应用研究.《石油地球物理勘探》.2010,第45卷(第1期),第85-91页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109492775A (en) | 2019-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492775B (en) | Geological structure interpretation detection method, geological structure interpretation detection device and readable storage medium | |
| RU2601535C1 (en) | Identification of orientation clusters from microseismic data | |
| CN105760673B (en) | A kind of fluvial depositional reservoir seismic-sensitive parameterized template analysis method | |
| AU2007211291A1 (en) | Methods, systems, and computer-readable media for fast updating of oil and gas field production models with physical and proxy simulators | |
| CN113297272B (en) | Bridge monitoring data association rule mining and health early warning method and system | |
| CN110414723B (en) | Method, device and system for fracture hydrocarbon reservoir history fitting based on microseismic event | |
| CN113792936A (en) | Intelligent lithology while drilling identification method, system, equipment and storage medium | |
| CA2893812A1 (en) | System, method and program product for automatically matching new members of a population with analogous members | |
| GB2467852A (en) | Automated interpretation of a seismic structure | |
| US20140156192A1 (en) | Systems and methods for determining position of marker depth coordinates for construction of geological model of deposit | |
| US20140156246A1 (en) | System for automated identification of surfaces for building of geologic hydrodynamic model of oil and gas deposit by seismic data | |
| Carvalho et al. | Soil classification system from cone penetration test data applying distance-based machine learning algorithms | |
| KR20200058258A (en) | System and method for predicting ground layer information, and a recording medium having computer readable program for executing the method | |
| EP3948365A1 (en) | Automatic calibration of forward depositional models | |
| US10664635B2 (en) | Determining non-linear petrofacies using cross-plot partitioning | |
| CN111155986B (en) | Method, device, equipment and system for determining well spacing of multi-layer commingled production gas well | |
| CN111413731A (en) | Earthquake recognition method and device for carbonate rock fracture and cave body | |
| CN111475685B (en) | Oil gas exploration method and device, storage medium and electronic equipment | |
| CN114912703A (en) | Method, device and equipment for predicting rupture pressure and storage medium | |
| RU2530324C2 (en) | Method for determining position of marker depth coordinates when constructing geological model of deposit | |
| CN113946790A (en) | Method, system, equipment and terminal for predicting height of water flowing fractured zone | |
| Emelyanova et al. | Unsupervised identification of electrofacies employing machine learning | |
| Kurniadi et al. | Local mean imputation for handling missing value to provide more accurate facies classification | |
| US20220291405A1 (en) | System and method for storage and retrieval of subsurface rock physical property prediction models using seismic interpretation | |
| US20230141334A1 (en) | Systems and methods of modeling geological facies for well development |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |