CN113326784A - Mineral resource detection method, system and equipment - Google Patents
Mineral resource detection method, system and equipment Download PDFInfo
- Publication number
- CN113326784A CN113326784A CN202110607608.0A CN202110607608A CN113326784A CN 113326784 A CN113326784 A CN 113326784A CN 202110607608 A CN202110607608 A CN 202110607608A CN 113326784 A CN113326784 A CN 113326784A
- Authority
- CN
- China
- Prior art keywords
- grid
- geophysical data
- meshes
- detected
- mesh
- 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.)
- Pending
Links
- 229910052500 inorganic mineral Inorganic materials 0.000 title claims abstract description 79
- 239000011707 mineral Substances 0.000 title claims abstract description 79
- 238000001514 detection method Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 65
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 27
- 230000015654 memory Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 5
- 238000011176 pooling Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000002372 labelling Methods 0.000 claims description 4
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 238000013508 migration Methods 0.000 claims description 3
- 230000005012 migration Effects 0.000 claims description 3
- 230000010287 polarization Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 4
- 239000007789 gas Substances 0.000 description 13
- 238000004458 analytical method Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000011160 research Methods 0.000 description 8
- 239000003921 oil Substances 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 239000002184 metal Substances 0.000 description 6
- 239000011435 rock Substances 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 238000005553 drilling Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 241000894007 species Species 0.000 description 4
- 241000282414 Homo sapiens Species 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000005484 gravity Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000010291 electrical method Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000005389 magnetism Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention provides a method, a system and equipment for detecting mineral resources, wherein the method comprises the following steps: acquiring geophysical data of a known region and geophysical data of a region to be detected; carrying out picture mesh generation on the geophysical data of the region to be detected to obtain a plurality of first meshes, and carrying out picture mesh generation on the geophysical data of the known region to obtain a plurality of second meshes; pairing the first mesh with the second mesh to construct a mesh pair; and inputting the grid pair into a deep convolutional neural network to obtain a mineral resource detection result of the area to be detected. The method is based on a large amount of geophysical data and based on a deep convolutional neural network in computer vision, and is used for processing various geophysical data of a known area and an area to be detected, and finally, intelligent detection and identification of mineral resources of the area to be detected are achieved.
Description
Technical Field
The invention relates to the technical field of geophysical, in particular to a method, a system and equipment for detecting mineral resources.
Background
Deep mineral resources are strategic successor areas of mineral resources. At present, the main methods applied to deep mineral resource exploration include seismic exploration, electromagnetic exploration, gravity and magnetic exploration and the like. However, the methods are independent of each other and have respective adaptability. The seismic exploration is a main method, the detection precision of the underground density interface is high, but the lithology of the stratum and the oil and gas in the reservoir are difficult to accurately identify. The gravity magnetic electric exploration method is classified as non-earthquake in oil and gas exploration, and also belongs to indirect exploration. In metal ore exploration, heavy magnetism and electricity are the main methods, but the method has low resolution and also has the problem of multi-resolution. Moreover, the methods are relatively independent in data interpretation at present, and depend on the understanding of geological interpreters on different methods to carry out comprehensive interpretation by themselves.
Therefore, the detection and identification of mineral products by the existing geophysical exploration method are mainly based on the comprehensive analysis and explanation of geophysical and geological experts on various geological data, the workload is high, and the identification accuracy is influenced by human subjective factors. In addition, the problems of serious geophysical inversion and multiple solution of geological interpretation caused by effective geophysical exploration data existing in deep resource exploration in China are difficult to solve by a single geophysical method.
Disclosure of Invention
In view of the above-mentioned problems of low accuracy of mineral detection and identification by conventional geophysical prospecting methods due to subjective factors, the present invention has been developed to provide a method, system and apparatus for detecting mineral resources that overcome or at least partially solve the above-mentioned problems.
According to one aspect of the present invention, there is provided a method of detecting mineral resources, the method comprising:
acquiring geophysical data of a known region and geophysical data of a region to be detected;
carrying out picture mesh generation on the geophysical data of the region to be detected to obtain a plurality of first meshes, and carrying out picture mesh generation on the geophysical data of the known region to obtain a plurality of second meshes;
pairing the first mesh with the second mesh to construct a mesh pair;
and inputting the grid pair into a deep convolutional neural network to obtain a mineral resource detection result of the area to be detected.
Preferably, the geophysical data of the known region and the geophysical data of the region to be detected each include at least one interpretation profile, and the interpretation profile includes at least one of the following attribute parameters: density, magnetic susceptibility, resistivity, velocity, polarizability, time constant, frequency dependent coefficient.
Preferably, the interpretation profile comprises: seismic migration imaging profiles, wave impedance profiles, resistivity profiles, induced polarization profiles.
Preferably, the performing picture mesh division on the geophysical data of the region to be detected to obtain a plurality of first meshes, and the performing picture mesh division on the geophysical data of the known region to obtain a plurality of second meshes includes:
and performing picture mesh division on each interpretation section contained in the geophysical data of the region to be detected to obtain a plurality of first meshes, and performing picture mesh division on each interpretation section contained in the geophysical data of the known region to obtain a plurality of second meshes, wherein the first meshes and the second meshes are the same in size, the first meshes have a first attribute, the second meshes have a second attribute, and the first attribute and the second attribute respectively correspond to at least one attribute parameter.
Preferably, pairing the first mesh with the second mesh to construct a mesh pair comprises:
respectively determining a first attribute corresponding to any one first grid and a second attribute corresponding to any one second grid;
comparing whether the first attribute and the second attribute meet a first association condition;
if yes, the first grid and the second grid are paired into a grid pair.
Preferably, after performing picture mesh division on the geophysical data of the region to be detected to obtain a plurality of first meshes and performing picture mesh division on the geophysical data of the known region to obtain a plurality of second meshes, the method further comprises:
determining one or more labels for each of the first grid and the second grid by well calibration;
and labeling each first grid and each second grid respectively.
Preferably, the inputting the grid pair into a deep convolutional neural network to obtain a mineral resource detection result of the area to be detected includes:
inputting the grid pair into a deep convolution neural network, and outputting the probability of each label corresponding to the first grid after convolution, nonlinear activation and pooling;
and comparing the probability of each label and selecting the label corresponding to the maximum probability to determine the mineral resource detection result.
Preferably, each interpretation profile is an input channel of the deep convolutional neural network.
According to one aspect of the present invention, there is provided a system for detecting mineral resources, the system comprising:
the device comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring the geophysical data of a known region and the geophysical data of a region to be detected;
the mesh generation unit is used for carrying out picture mesh generation on the geophysical data of the region to be detected so as to obtain a plurality of first meshes and carrying out picture mesh generation on the geophysical data of the known region so as to obtain a plurality of second meshes;
a mesh pairing unit configured to pair the first mesh with the second mesh to construct a mesh pair;
and the prediction unit is used for inputting the grid pair into a deep convolutional neural network to obtain a mineral resource detection result of the area to be detected.
According to an aspect of the present invention, there is provided a computing device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of detecting mineral resources as described in any one of the above when executing the computer program.
The method of the invention processes various geophysical data of a known area and an area to be detected based on a deep convolutional neural network in computer vision on the basis of a large amount of geophysical data, and finally realizes intelligent detection and identification of mineral resources of the area to be detected. Compared with the prior art, the embodiment of the invention can efficiently carry out intelligent identification on the mineral resources of the geophysical profile and the reservoir attribute interpretation profile, reduce the workload of data interpreter personnel and reduce errors caused by human beings.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for detecting mineral resources according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a deep convolutional neural network structure in the embodiment of the present method;
FIG. 3 is a schematic structural diagram of a system for detecting mineral resources according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computing device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
An embodiment of the present invention provides a method for detecting mineral resources, as shown in fig. 1, the method includes:
Since the area to be detected is not processed by drilling, development, sample analysis and the like, the geophysical data of the area to be detected are usually calculated by the existing analysis means, for example, measurement work such as gravity, magnetic force, electrical method, earthquake and the like is performed, the corresponding geophysical data are processed to obtain the geophysical data, and then the types, the abundance, the grade and the like of mineral resources are predicted. However, the above analysis methods are all self-organized systems, and only limited data analysis can be performed under the analysis method, and the methods are not compatible, so that the obtained geophysical data cannot directly determine the types of mineral resources. Different attribute parameters can be obtained through different measurement works, so that different modes can be selected for analysis according to different required attribute parameters to obtain corresponding required geophysical data in the embodiment of the invention.
102, carrying out picture mesh generation on the geophysical data of the region to be detected to obtain a plurality of first meshes, and carrying out picture mesh generation on the geophysical data of the known region to obtain a plurality of second meshes. In the step, the geophysical data of the area to be detected is subjected to image mesh division, namely the geophysical data of the area to be detected is divided into a plurality of first meshes. For example, the division is 256 × 256 first meshes. And (3) carrying out picture mesh subdivision on the geophysical data of the known region in the same way, namely dividing the geophysical data of the known region into a plurality of second meshes, wherein the size of each second mesh is the same as that of each first mesh so as to ensure that the geophysical data are input into the deep convolutional neural network for further calculation. Preferably, the sizes of the first grid and the second grid are determined according to the calculation precision and the calculation speed of the deep convolutional neural network, the accuracy and the calculation efficiency of the comparison result can be respectively tested according to the first grid and the second grid which are divided into different sizes, and finally, the proper grid size is selected.
And 104, inputting the grid pair into a deep convolutional neural network to obtain a mineral resource detection result of the area to be detected. Specifically, the geophysical data of the known area is used as an input channel of the deep convolutional neural network, the paired grid pairs are input into the deep convolutional neural network, and a mineral resource detection result of the area to be detected is finally output, so that intelligent detection and identification of the mineral resources can be realized. The mineral resource detection result comprises the types, the abundance, the grade and the like of mineral resources, namely the types, the abundance, the grade and the like of the mineral resources with the same or similar geophysical data of the region to be detected can be directly obtained through the direct association relationship between the geophysical data of the known region and the types, the abundance and the grade of the mineral resources.
The method of the embodiment of the invention processes various geophysical data of the known area and the area to be detected based on a deep convolutional neural network in computer vision on the basis of a large amount of geophysical data, and finally realizes intelligent detection and identification of mineral resources of the area to be detected. Compared with the prior art, the embodiment of the invention can efficiently carry out intelligent identification on the mineral resources of the geophysical profile and the reservoir attribute interpretation profile, reduce the workload of data interpreter personnel and reduce errors caused by human beings.
In the method for detecting mineral resources according to the embodiment of the present invention, preferably, the geophysical data of the known area and the geophysical data of the area to be detected both include at least one interpretation profile, and the interpretation profile includes at least one of the following attribute parameters: density, magnetic susceptibility, resistivity, velocity, polarizability, time constant, frequency dependent coefficient. In a specific embodiment, the attribute parameters corresponding to the interpretation profile included in the geophysical data of the known region may be one or more of density, magnetic susceptibility, resistivity, velocity, polarizability, time constant and frequency correlation coefficient, and the attribute parameters corresponding to the interpretation profile included in the geophysical data of the region to be detected may also be one or more of density, magnetic susceptibility, resistivity, velocity, polarizability, time constant and frequency correlation coefficient, which are all determined according to the actual situation of the region under study. And different attribute parameters are obtained in different modes, for example, the magnetic method can obtain magnetic susceptibility, the electric method can obtain resistivity and the like, and each method is self-systematic, and fusion analysis cannot be carried out under the condition of manual analysis.
Preferably, the interpretation profile includes: seismic migration imaging profiles, wave impedance profiles, resistivity profiles, induced polarization profiles. The interpretation profile according to the embodiment of the present invention may analyze the attribute parameters corresponding to the interpretation profile, and when other attribute parameters need to be analyzed, more types of interpretation profiles may be obtained, so the interpretation profiles are not limited to the ones described in the embodiment of the present invention.
In the method for detecting mineral resources according to the embodiment of the present invention, preferably, the performing picture mesh division on the geophysical data of the region to be detected to obtain a plurality of first meshes, and performing picture mesh division on the geophysical data of the known region to obtain a plurality of second meshes includes:
and performing picture mesh division on each interpretation section contained in the geophysical data of the region to be detected to obtain a plurality of first meshes, and performing picture mesh division on each interpretation section contained in the geophysical data of the known region to obtain a plurality of second meshes, wherein the first meshes and the second meshes are the same in size, the first meshes have a first attribute, the second meshes have a second attribute, and the first attribute and the second attribute respectively correspond to at least one attribute parameter.
In the specific embodiment of the present invention, since the geophysical data of the known region and the geophysical data of the region to be detected are both unique, the mesh division with the same size is performed on the known region and the to-be-detected region, and the first attribute corresponding to each first mesh may be the same as or different from the second attribute corresponding to the second mesh. For example, the first property of the first mesh corresponds to the property parameter being the first density, the first magnetic susceptibility, the first electrical resistivity, and the second property of the second mesh corresponds to the property parameter being the first density, the second magnetic susceptibility, the second electrical resistivity. In this case, the first and second meshes have the same density but different magnetic susceptibility and resistivity. Further, the first mesh and the second mesh cannot be a pair of mesh pairs.
In the method for detecting mineral resources according to the embodiment of the present invention, preferably, the pairing the first grid and the second grid to construct a grid pair includes:
respectively determining a first attribute corresponding to any one first grid and a second attribute corresponding to any one second grid;
comparing whether the first attribute and the second attribute meet a first association condition;
if yes, the first grid and the second grid are paired into a grid pair.
Specifically, the first association condition is that the first attribute is identical to the second attribute or the similarity between the first attribute and the second attribute. For example, when the first association condition is completely the same, it means that the first attribute corresponding to the first grid and the second attribute corresponding to the second grid can be paired into a grid pair only when they are completely the same. In another embodiment, when the first association condition is a similarity degree between the first attribute and the second attribute, the first attribute corresponding to the first grid and the second attribute corresponding to the second grid may be considered to be similar when the first attribute and the second attribute meet the corresponding similarity degree, and may be configured as a grid pair. The selection of the first association condition is determined according to the actual situation.
In the method for detecting mineral resources according to the embodiment of the present invention, preferably, after the geophysical data of the region to be detected is subjected to picture mesh generation to obtain a plurality of first meshes, and the geophysical data of the known region is subjected to picture mesh generation to obtain a plurality of second meshes, the method further includes:
determining one or more labels for each of the first grid and the second grid by well calibration;
and labeling each first grid and each second grid respectively.
The tag can be a mineral product type, and can include oil, gas, water, metal ore or other components, or the abundance or grade of any mineral product. And each of the first grid and the second grid is provided with one or more labels, namely the possible mineral types of the area to be detected are determined according to drilling calibration and are provided with corresponding labels, and then labeling processing is carried out on the first grid and the second grid according to the determined labels.
Preferably, the method for detecting mineral resources according to the embodiment of the present invention, wherein inputting the grid pair to a deep convolutional neural network to obtain a detection result of the mineral resources of the area to be detected includes:
and inputting the grid pair into a deep convolution neural network, and outputting the probability of each label corresponding to the first grid after convolution, nonlinear activation and pooling. After the grid pair is subjected to convolution, nonlinear activation and pooling operations of the deep convolution neural network, the probability of each tag corresponding to the first grid in the grid pair is output, the probability of each tag represents the probability of each tag corresponding to the first grid, and when the tags are of mineral types, the probability of the tags is also the probability of the mineral types, for example, when the tags corresponding to the first grid are oil, gas, water and metal ores, the output information is the probability of the oil, gas, water and metal ores, which means that the mineral resources corresponding to the first grid may be the probability of the oil, gas, water and metal ores respectively.
And comparing the probability of each label and selecting the label corresponding to the maximum probability to determine the mineral resource detection result. When the probability of a certain label in the probabilities of the labels corresponding to the first grid is the maximum, the probability that the mineral resource corresponding to the first grid is the label is the maximum, and then the content corresponding to the label is used as the detection result of the mineral resource.
Specifically, as shown in fig. 2, the deep convolutional neural network is a deep convolutional neural network, a reasonable deep convolutional neural network is constructed, the influence of different network layer numbers, convolutional kernel sizes and the like on the deep convolutional neural network is tested, the optimal deep learning network related parameters are optimized and obtained, the deep learning network of the research area is formed, the grid pairs are input into the deep convolutional neural network to perform convolution, nonlinear activation and pooling operation for at least one time, so that the optimal deep learning network parameters which accord with the area are obtained, the related data of mineral resources at any position of the whole research area are obtained, and the purpose of popularizing the known area to the whole research area is achieved.
In the method for detecting mineral resources according to the embodiment of the present invention, preferably, each interpretation profile is an input channel of the deep convolutional neural network. The plurality of interpretation profiles form a deep neural convolutional network with multiple input channels.
An embodiment of the present invention further provides a system for detecting mineral resources, as shown in fig. 3, the system includes:
a first acquiring unit 301, configured to acquire geophysical data of a known region and geophysical data of a region to be detected;
the mesh generation unit 302 is configured to perform picture mesh generation on the geophysical data of the region to be detected to obtain a plurality of first meshes, and perform picture mesh generation on the geophysical data of the known region to obtain a plurality of second meshes;
a mesh pairing unit 303, configured to pair the first mesh and the second mesh to construct a mesh pair;
and the prediction unit 304 is configured to input the grid pair to a deep convolutional neural network to obtain a mineral resource detection result of the area to be detected.
The embodiment of the present invention further provides a computing device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and when the processor executes the computer program, the method for detecting a mineral resource according to any one of the above embodiments is implemented.
In an embodiment herein, as shown in fig. 4, there is also provided a computing device, which computing device 402 may include one or more processors 404, such as one or more Central Processing Units (CPUs), each of which may implement one or more hardware threads. The computing device 402 may also include any storage resources 406 for storing any kind of information, such as code, settings, data, and the like. For example, and without limitation, storage resources 406 may include any one or more of the following in combination: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any memory may use any technology to store information. Further, any memory may provide volatile or non-volatile reservation of information, and the storage resource 406 stores a computer program operable on the processor 404, and the processor 404 executes the computer program to implement the electric vehicle charging and discharging control method according to any of the foregoing embodiments. Further, any memory may represent fixed or removable components of computing device 402. In one case, when the processor 404 executes the associated instructions, which are stored in any memory or combination of memories, the computing device 402 can perform any of the operations of the associated instructions. The computing device 402 also includes one or more drive mechanisms 408, such as a hard disk drive mechanism, an optical disk drive mechanism, and so forth, for interacting with any memory.
It should be understood that, in various embodiments of the present invention, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
It should also be understood that, in the embodiment of the present invention, the term "and/or" is only one kind of association relation describing an associated object, and means that three kinds of relations may exist. For example, a and/or B, may represent: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method of detecting mineral resources, the method comprising:
acquiring geophysical data of a known region and geophysical data of a region to be detected;
carrying out picture mesh generation on the geophysical data of the region to be detected to obtain a plurality of first meshes, and carrying out picture mesh generation on the geophysical data of the known region to obtain a plurality of second meshes;
pairing the first mesh with the second mesh to construct a mesh pair;
and inputting the grid pair into a deep convolutional neural network to obtain a mineral resource detection result of the area to be detected.
2. The method according to claim 1, wherein the geophysical data of the known area and the geophysical data of the area to be detected each comprise at least one interpretation profile, and the interpretation profile comprises at least one of the following attribute parameters: density, magnetic susceptibility, resistivity, velocity, polarizability, time constant, frequency dependent coefficient.
3. The method according to claim 2, wherein the interpretation profile comprises: seismic migration imaging profiles, wave impedance profiles, resistivity profiles, induced polarization profiles.
4. The method of claim 2, wherein the step of performing a picture meshing on the geophysical data of the area to be detected to obtain a plurality of first meshes, and the step of performing a picture meshing on the geophysical data of the known area to obtain a plurality of second meshes comprises:
and performing picture mesh division on each interpretation section contained in the geophysical data of the region to be detected to obtain a plurality of first meshes, and performing picture mesh division on each interpretation section contained in the geophysical data of the known region to obtain a plurality of second meshes, wherein the first meshes and the second meshes are the same in size, the first meshes have a first attribute, the second meshes have a second attribute, and the first attribute and the second attribute respectively correspond to at least one attribute parameter.
5. The method of claim 4, wherein pairing the first grid with the second grid to construct a grid pair comprises:
respectively determining a first attribute corresponding to any one first grid and a second attribute corresponding to any one second grid;
comparing whether the first attribute and the second attribute meet a first association condition;
if yes, the first grid and the second grid are paired into a grid pair.
6. The method according to claim 4, wherein after the geophysical data of the area to be detected is subjected to the picture meshing so as to obtain a plurality of first meshes, and the geophysical data of the known area is subjected to the picture meshing so as to obtain a plurality of second meshes, the method further comprises:
determining one or more labels for each of the first grid and the second grid by well calibration;
and labeling each first grid and each second grid respectively.
7. The method for detecting mineral resources according to claim 6, wherein inputting the grid pair to a deep convolutional neural network to obtain a mineral resource detection result of the area to be detected comprises:
inputting the grid pair into a deep convolution neural network, and outputting the probability of each label corresponding to the first grid after convolution, nonlinear activation and pooling;
and comparing the probability of each label and selecting the label corresponding to the maximum probability to determine the mineral resource detection result.
8. The method according to claim 3, wherein each interpretation profile is an input channel of the deep convolutional neural network.
9. A system for detecting mineral resources, the system comprising:
the device comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring the geophysical data of a known region and the geophysical data of a region to be detected;
the mesh generation unit is used for carrying out picture mesh generation on the geophysical data of the region to be detected so as to obtain a plurality of first meshes and carrying out picture mesh generation on the geophysical data of the known region so as to obtain a plurality of second meshes;
a mesh pairing unit configured to pair the first mesh with the second mesh to construct a mesh pair;
and the prediction unit is used for inputting the grid pair into a deep convolutional neural network to obtain a mineral resource detection result of the area to be detected.
10. A computing device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of detecting mineral resources of any one of claims 1 to 8 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110607608.0A CN113326784A (en) | 2021-06-01 | 2021-06-01 | Mineral resource detection method, system and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110607608.0A CN113326784A (en) | 2021-06-01 | 2021-06-01 | Mineral resource detection method, system and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113326784A true CN113326784A (en) | 2021-08-31 |
Family
ID=77423001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110607608.0A Pending CN113326784A (en) | 2021-06-01 | 2021-06-01 | Mineral resource detection method, system and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113326784A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140180593A1 (en) * | 2011-06-02 | 2014-06-26 | Jan Schmedes | Joint Inversion with Unknown Lithology |
| CN106250676A (en) * | 2016-07-20 | 2016-12-21 | 中国地质大学（北京） | Element geochemistry survey data method for optimizing based on information gain-ratio |
| US20170285221A1 (en) * | 2016-01-22 | 2017-10-05 | Saudi Arabian Oil Company | Generating dynamically calibrated geo-models in green fields |
| CN107480175A (en) * | 2017-06-30 | 2017-12-15 | 广州数鹏通科技有限公司 | A kind of geographic information data screening technique, electronic equipment, storage medium and system based on gridding |
| CN110362949A (en) * | 2019-07-23 | 2019-10-22 | 电子科技大学 | A kind of landslide sensitivity assessment method neural network based |
| CN110442666A (en) * | 2019-08-02 | 2019-11-12 | 中国地质调查局发展研究中心 | A kind of mineral resource prediction method and system based on neural network model |
| CN111080021A (en) * | 2019-12-24 | 2020-04-28 | 中国海洋石油集团有限公司 | Sand body configuration CMM neural network prediction method based on geological information base |
| CN111222541A (en) * | 2019-12-02 | 2020-06-02 | 国网浙江省电力有限公司 | Appearance box type identification method based on deep convolutional neural network |
| CN112613525A (en) * | 2020-11-26 | 2021-04-06 | 北京迈格威科技有限公司 | Target frame prediction method, device, equipment and medium |
| CN112836897A (en) * | 2021-03-04 | 2021-05-25 | 云南电网有限责任公司电力科学研究院 | Power grid geological settlement hidden danger risk prediction method based on machine learning |
-
2021
- 2021-06-01 CN CN202110607608.0A patent/CN113326784A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140180593A1 (en) * | 2011-06-02 | 2014-06-26 | Jan Schmedes | Joint Inversion with Unknown Lithology |
| US20170285221A1 (en) * | 2016-01-22 | 2017-10-05 | Saudi Arabian Oil Company | Generating dynamically calibrated geo-models in green fields |
| CN106250676A (en) * | 2016-07-20 | 2016-12-21 | 中国地质大学（北京） | Element geochemistry survey data method for optimizing based on information gain-ratio |
| CN107480175A (en) * | 2017-06-30 | 2017-12-15 | 广州数鹏通科技有限公司 | A kind of geographic information data screening technique, electronic equipment, storage medium and system based on gridding |
| CN110362949A (en) * | 2019-07-23 | 2019-10-22 | 电子科技大学 | A kind of landslide sensitivity assessment method neural network based |
| CN110442666A (en) * | 2019-08-02 | 2019-11-12 | 中国地质调查局发展研究中心 | A kind of mineral resource prediction method and system based on neural network model |
| CN111222541A (en) * | 2019-12-02 | 2020-06-02 | 国网浙江省电力有限公司 | Appearance box type identification method based on deep convolutional neural network |
| CN111080021A (en) * | 2019-12-24 | 2020-04-28 | 中国海洋石油集团有限公司 | Sand body configuration CMM neural network prediction method based on geological information base |
| CN112613525A (en) * | 2020-11-26 | 2021-04-06 | 北京迈格威科技有限公司 | Target frame prediction method, device, equipment and medium |
| CN112836897A (en) * | 2021-03-04 | 2021-05-25 | 云南电网有限责任公司电力科学研究院 | Power grid geological settlement hidden danger risk prediction method based on machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 胡泊 等: ""人工神经网络岩性识别在地质建模中的应用"", 《石油化工应用》, vol. 39, no. 11, 30 November 2020 (2020-11-30), pages 94 - 96 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A segmentation approach for stochastic geological modeling using hidden Markov random fields | |
| Witter et al. | Uncertainty and risk evaluation during the exploration stage of geothermal development: A review | |
| Eidsvik et al. | Value of information in the earth sciences: Integrating spatial modeling and decision analysis | |
| US9070049B2 (en) | Systems and methods for improving direct numerical simulation of material properties from rock samples and determining uncertainty in the material properties | |
| Rubo et al. | Digital petrography: Mineralogy and porosity identification using machine learning algorithms in petrographic thin section images | |
| Shaheen et al. | Data mining applications in hydrocarbon exploration | |
| CN114207550A (en) | System and method for supervised learning of permeability of a formation | |
| Male et al. | Lessons for machine learning from the analysis of porosity-permeability transforms for carbonate reservoirs | |
| Konaté et al. | Application of dimensionality reduction technique to improve geophysical log data classification performance in crystalline rocks | |
| CA3109021C (en) | Facilitating hydrocarbon exploration by applying a machine-learning model to basin data | |
| US11893495B2 (en) | Dual neural network architecture for determining epistemic and aleatoric uncertainties | |
| US20140270393A1 (en) | Systems and methods for improving direct numerical simulation of material properties from rock samples and determining uncertainty in the material properties | |
| Gu et al. | Data-driven lithology prediction for tight sandstone reservoirs based on new ensemble learning of conventional logs: A demonstration of a Yanchang member, Ordos Basin | |
| Bhattacharya | A primer on machine learning in subsurface geosciences | |
| Zhihong et al. | Evaluation of granular particle roundness using digital image processing and computational geometry | |
| Castafio et al. | Rover traverse science for increased mission science return | |
| Leung et al. | Sample truncation strategies for outlier removal in geochemical data: the MCD robust distance approach versus t-SNE ensemble clustering | |
| CN117576335B (en) | Three-dimensional space model data processing method and system for mineral area investigation | |
| Zhao et al. | Fast stratification of geological cross-section from CPT results with missing data using multitask and modified Bayesian compressive sensing | |
| CN114548299A (en) | Earthquake phase identification method and device, computer equipment and storage medium | |
| WO2022087332A1 (en) | Reservoir characterization using rock geochemistry for lithostratigraphic interpretation of a subterranean formation | |
| Diaz et al. | Variogram-based descriptors for comparison and classification of rock texture images | |
| CN113326784A (en) | Mineral resource detection method, system and equipment | |
| CN115101135A (en) | Rock physical parameter sensitivity analysis method and device | |
| US11208886B2 (en) | Direct hydrocarbon indicators analysis informed by machine learning processes |
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 |