A method, system and device for detecting mineral resources

Abstract

The present invention provides a method, system and device for detecting mineral resources, the method comprising: obtaining geophysical data of a known area and geophysical data of an area to be detected; performing image grid division on the geophysical data of the area to be detected to obtain a plurality of first grids, and performing image grid division on the geophysical data of the known area to obtain a plurality of second grids; pairing the first grid with the second grid to construct a grid pair; inputting the grid pair into a deep convolutional neural network to obtain a mineral resource detection result of the area to be detected. The above method is based on a large amount of geophysical data, and based on the deep convolutional neural network in computer vision, processes various geophysical data of the known area and the area to be detected, and finally realizes intelligent detection and identification of mineral resources in the area to be detected.

Description

Technical Field

[0001] The present invention relates to the field of geophysical technology, and in particular to a method, system and equipment for detecting mineral resources. Background Art

[0002] Deep mineral resources are strategic successor areas for mineral resources. The main methods currently used for deep mineral resource exploration include seismic exploration, electromagnetic exploration, gravity and magnetic exploration, etc. However, the above methods are independent of each other and have their own adaptability. Among them, seismic exploration is the main method, which has high accuracy in detecting underground density interfaces, but it is difficult to accurately identify stratum lithology and reservoir oil and gas. Gravity, magnetism and electricity exploration methods are classified as non-seismic in oil and gas exploration and are also indirect exploration. In metal mine exploration, gravity, magnetism and electricity are the main methods, but the resolution of this method is not high and there is a problem of multiple solutions. Moreover, these methods are currently relatively independent in data interpretation, relying on the geological interpreters' understanding of different methods and their own comprehensive interpretation.

[0003] It can be seen that the detection and identification of minerals by existing geophysical exploration methods are mainly based on the comprehensive analysis and interpretation of various geological data by geophysical and geological experts. The workload is large, and human subjective factors will affect the accuracy of identification. In addition, the effective geophysical exploration data in my country's deep resource exploration currently leads to serious problems such as multiple solutions of geophysical inversion and geological interpretation, which are difficult to solve by relying on a single geophysical method. Summary of the invention

[0004] In view of the problem that the detection and identification of minerals by the above-mentioned traditional geophysical exploration methods may have low accuracy due to subjective factors, the present invention is proposed to provide a method, system and equipment for detecting mineral resources that overcome the above-mentioned problem or at least partially solve the above-mentioned problem.

[0005] According to one aspect of the present invention, a method for detecting mineral resources is provided, the method comprising:

[0006] Obtain geophysical data of known areas and geophysical data of areas to be inspected;

[0007] Performing image grid division on the geophysical data of the area to be detected to obtain a plurality of first grids, and performing image grid division on the geophysical data of the known area to obtain a plurality of second grids;

[0008] pairing the first grid with the second grid to construct a grid pair;

[0009] The grid pairs are input into a deep convolutional neural network to obtain the mineral resource detection results of the area to be detected.

[0010] 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, and frequency correlation coefficient.

[0011] Preferably, the interpretation profile includes: seismic migration imaging profile, wave impedance profile, resistivity profile, and induced polarization profile.

[0012] Preferably, performing image grid division on the geophysical data of the area to be detected to obtain a plurality of first grids, and performing image grid division on the geophysical data of the known area to obtain a plurality of second grids comprises:

[0013] Each interpretation section included in the geophysical data of the area to be detected is divided into a plurality of first grids by image grid division, and each interpretation section included in the geophysical data of the known area is divided into a plurality of second grids by image grid division, wherein the first grid and the second grid have the same size, and the first grid has a first attribute, and the second grid has a second attribute, and the first attribute and the second attribute respectively correspond to at least one attribute parameter.

[0014] Preferably, pairing the first grid with the second grid to construct a grid pair comprises:

[0015] respectively determining a first attribute corresponding to any of the first grids and a second attribute corresponding to any of the second grids;

[0016] Comparing whether the first attribute and the second attribute satisfy a first association condition;

[0017] If so, the first grid and the second grid are paired into a grid pair.

[0018] Preferably, after performing image grid division on the geophysical data of the area to be detected to obtain a plurality of first grids, and performing image grid division on the geophysical data of the known area to obtain a plurality of second grids, the method further comprises:

[0019] Determine one or more labels of each first grid and second grid by drilling calibration;

[0020] Labeling is performed on each first grid and each second grid.

[0021] Preferably, inputting the grid pairs into a deep convolutional neural network to obtain the mineral resource detection result of the area to be detected includes:

[0022] Input the grid pair into a deep convolutional neural network, and after convolution, nonlinear activation, and pooling operations, output the probability of each label corresponding to the first grid;

[0023] Compare the probabilities of each label and select the label corresponding to the largest probability to determine the mineral resource detection results.

[0024] Preferably, each interpretation profile is an input channel of the deep convolutional neural network.

[0025] According to one aspect of the present invention, a mineral resource detection system is provided, the system comprising:

[0026] A first acquisition unit, used to acquire geophysical data of a known area and geophysical data of an area to be detected;

[0027] A gridding unit, used for performing image gridding on the geophysical data of the area to be detected to obtain a plurality of first grids, and performing image gridding on the geophysical data of the known area to obtain a plurality of second grids;

[0028] a grid pairing unit, configured to pair the first grid with the second grid to construct a grid pair;

[0029] A prediction unit is used to input the grid pairs into a deep convolutional neural network to obtain the mineral resource detection results of the area to be detected.

[0030] According to one aspect of the present invention, there is provided a computing device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a method for detecting mineral resources as described in any one of the above items is implemented.

[0031] The above method of the present invention is based on a large amount of geophysical data and a deep convolutional neural network in computer vision to process various geophysical data of known areas and areas to be detected, and finally realizes intelligent detection and identification of mineral resources in the areas to be detected. Compared with the prior art, the embodiment of the present invention can efficiently perform intelligent identification of mineral resources on geophysical profiles and reservoir attribute interpretation profiles, reduce the workload of data interpreters, and reduce errors caused by human factors.

[0032] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 This is a flow chart of a method for detecting mineral resources in an embodiment of the present invention;

[0035] Figure 2 This is a schematic diagram of the structure of a deep convolutional neural network in this embodiment of the method;

[0036] Figure 3 A schematic diagram of the structure of a mineral resource detection system in an embodiment of the present invention;

[0037] Figure 4 The figure is a schematic diagram of the structure of a computing device in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] The present invention provides a method for detecting mineral resources. Figure 1 As shown, the method includes:

[0040] Step 101, obtain geophysical data of known areas and geophysical data of areas to be detected. Specifically, the known areas and areas to be detected are both located in the same study area, and have similar geological properties and mineral resources, which is convenient for expanding from a small-scale known area to a larger range of areas to be detected, and then obtaining the purpose of mineral resources in the entire study area. Among them, the method for obtaining geophysical data of known areas includes: directly conducting drilling work in the study area and collecting the obtained target body and surrounding surrounding rocks, mineral abundance, grade, or oil and gas content as an oil and gas reservoir, and other attribute parameters; collecting the target body of developed mineral deposits and surrounding surrounding rocks in the same study area. Abundance, grade, or oil and gas content of oil and gas reservoirs, and other attribute parameters; collecting typical strata, rocks, and mineral specimens from geological outcrops in and around the same study area, and collecting the target body and surrounding surrounding rocks. Abundance, grade, or oil and gas content as an oil and gas reservoir, and other attribute parameters. The data obtained above means that the geophysical data of the known area are all actual data directly obtained through drilling, development results or sample analysis, that is, geophysical data obtained by actual measurement, and the types, abundance and grade of mineral resources are also known, so the direct correlation between the attribute parameters and the types, abundance and grade of mineral resources can be directly obtained. For example, the mineral types of the target body are oil, gas, water, metal ore or igneous rock with different lithology and lithofacies, etc., with a certain abundance and grade of mineral deposits. The value of the attribute parameter corresponding to the mineral type and abundance and grade, then it can be considered that under the value of the attribute parameter, the target body has the characteristics of the mineral type, abundance and grade, then under the same or similar attribute parameters, the probability that other target bodies are also of the same mineral type is relatively large.

[0041] Since the area to be tested has not been drilled, developed, or subjected to sample analysis, its geophysical data is usually calculated using existing analytical methods. For example, through gravity, magnetism, electrical methods, seismic and other measurement work, the corresponding geophysical data is processed to obtain geophysical data, and then the type, abundance, and grade of mineral resources are predicted. However, the above-mentioned analysis methods are all self-contained systems, and only limited data analysis can be performed under the analysis method. The methods are not compatible with each other, so the geophysical data obtained cannot directly determine the type of mineral resources. Among them, different attribute parameters can be obtained through different measurement work. Therefore, in the embodiment of the present invention, different methods will be selected for analysis to obtain the corresponding required geophysical data according to the different required attribute parameters.

[0042] Step 102, the geophysical data of the area to be detected is subjected to image grid division to obtain a plurality of first grids, and the geophysical data of the known area is subjected to image grid division to obtain a plurality of second grids. In this step, the geophysical data of the area to be detected is subjected to image grid division, that is, the geophysical data of the area to be detected is divided into a plurality of first grids. For example, it is divided into 256*256 first grids. The geophysical data of the known area is also subjected to image grid division, that is, the geophysical data of the known area is divided into a plurality of second grids, wherein the size of the second grid is the same as the first grid, so as to ensure that it is subsequently input into the deep convolutional neural network for further calculation. Preferably, the size of the first grid and the second grid is determined according to the calculation accuracy and calculation speed of the deep convolutional neural network, and the accuracy and calculation efficiency of the comparison result can be tested respectively according to the first grid and the second grid divided into different sizes, and finally the appropriate grid size is selected.

[0043] Step 103, pairing the first grid with the second grid to construct a grid pair. In a specific embodiment, the process of pairing the first grid with the second grid is to compare any first grid with any second grid, and the same or similar first grid and second grid can be paired as a grid pair, so multiple first grids and second grids can construct multiple grid pairs. In a preferred embodiment, multiple test pairs can also be obtained by the same pairing method, where the number of grid pairs and test pairs can be determined according to the calculation speed of the deep convolutional neural network and the required calculation accuracy.

[0044] Step 104, input the grid pair into a deep convolutional neural network to obtain the mineral resource detection result of the area to be detected. Specifically, the geophysical data of the known area is used as the input channel of the deep convolutional neural network, and the paired grid pair is input into the deep convolutional neural network to finally output the mineral resource detection result of the area to be detected, so that intelligent detection and identification of mineral resources can be achieved. Among them, the mineral resource detection result includes the type, abundance, grade, etc. of mineral resources, that is, through the direct correlation between the geophysical data of the known area and the type, abundance, and grade of mineral resources, the type, abundance, and grade of mineral resources in the area to be detected with the same or similar geophysical data can be directly obtained.

[0045] The method described in the above embodiment of the present invention is based on a large amount of geophysical data and a deep convolutional neural network in computer vision to process various geophysical data of known areas and areas to be detected, and finally realize intelligent detection and identification of mineral resources in the areas to be detected. Compared with the prior art, the embodiment of the present invention can efficiently perform intelligent identification of mineral resources on geophysical profiles and reservoir attribute interpretation profiles, reduce the workload of data interpreters, and reduce errors caused by human factors.

[0046] A method for detecting mineral resources described in an 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, and frequency correlation coefficient. In a specific embodiment, the attribute parameter corresponding to the interpretation profile contained in the geophysical data of the known area can be one or more of density, magnetic susceptibility, resistivity, velocity, polarizability, time constant, and frequency correlation coefficient, and the attribute parameter corresponding to the interpretation profile contained in the geophysical data of the area to be detected can also be one or more of density, magnetic susceptibility, resistivity, velocity, polarizability, time constant, and frequency correlation coefficient, all of which are determined according to the actual situation of the study area. And different attribute parameters are obtained in different ways, for example, magnetic susceptibility can be obtained by magnetic method, resistivity can be obtained by electrical method, etc., and each method is self-contained, and fusion analysis cannot be performed in the case of manual analysis.

[0047] In a method for detecting mineral resources described in an embodiment of the present invention, preferably, the interpretation profile includes: a seismic migration imaging profile, a wave impedance profile, a resistivity profile, and an induced polarization profile. The interpretation profile described in the embodiment of the present invention can analyze the attribute parameters corresponding to the interpretation profile, and when other attribute parameters need to be analyzed, more types of interpretation profiles can also be obtained, so the interpretation profiles are not limited to the several types described in the embodiment of the present invention.

[0048] In a method for detecting mineral resources according to an embodiment of the present invention, preferably, performing image grid division on the geophysical data of the area to be detected to obtain a plurality of first grids, and performing image grid division on the geophysical data of the known area to obtain a plurality of second grids comprises:

[0049] Each interpretation section included in the geophysical data of the area to be detected is divided into a plurality of first grids by image grid division, and each interpretation section included in the geophysical data of the known area is divided into a plurality of second grids by image grid division, wherein the first grid and the second grid have the same size, and the first grid has a first attribute, and the second grid has a second attribute, and the first attribute and the second attribute respectively correspond to at least one attribute parameter.

[0050] In a specific embodiment of the present invention, since the geophysical data of the known area and the geophysical data of the area to be detected are unique, the two are divided into grids of the same size, and the first attribute corresponding to each first grid and the second attribute corresponding to the second grid may be the same or different. For example, the first attribute of the first grid corresponds to the attribute parameters of the first density, the first magnetic susceptibility, and the first resistivity, while the second attribute of the second grid corresponds to the attribute parameters of the first density, the second magnetic susceptibility, and the second resistivity. In this case, the density of the first grid is the same as that of the second grid, but the magnetic susceptibility and resistivity are different. Furthermore, the first grid and the second grid cannot become a grid pair.

[0051] In the method for detecting mineral resources described in an embodiment of the present invention, preferably, pairing the first grid with the second grid to construct a grid pair includes:

[0052] respectively determining a first attribute corresponding to any of the first grids and a second attribute corresponding to any of the second grids;

[0053] Comparing whether the first attribute and the second attribute satisfy a first association condition;

[0054] If so, the first grid and the second grid are paired into a grid pair.

[0055] Specifically, the first association condition is that the first attribute and the second attribute are completely identical or the similarity between the two. For example, when the first association condition is completely identical, it means that the first attribute corresponding to the first grid and the second attribute corresponding to the second grid can only be paired as a grid pair when they are completely identical. In another embodiment, when the first association condition is the similarity between the first attribute and the second attribute, then when the first attribute corresponding to the first grid and the second attribute corresponding to the second grid meet the corresponding similarity, they can be considered similar and can be paired as a grid pair. The specific selection of the first association condition is determined according to the actual situation.

[0056] In a method for detecting mineral resources according to an embodiment of the present invention, preferably, after performing image grid division on the geophysical data of the area to be detected to obtain a plurality of first grids, and performing image grid division on the geophysical data of the known area to obtain a plurality of second grids, the method further comprises:

[0057] Determine one or more labels of each first grid and second grid by drilling calibration;

[0058] Labeling is performed on each first grid and each second grid.

[0059] The label can be a mineral type, including oil, gas, water, metal ore or other components, or the abundance or grade of any mineral. Each first grid and second grid is set with one or more labels, that is, the possible mineral types of the area to be detected are determined according to the drilling calibration, and then the first grid and the second grid are labeled according to the determined labels.

[0060] In a method for detecting mineral resources according to an embodiment of the present invention, preferably, inputting the grid pair into a deep convolutional neural network to obtain a mineral resource detection result of the area to be detected includes:

[0061] The grid pair is input into a deep convolutional neural network, and after convolution, nonlinear activation, and pooling operations, the probability of each label corresponding to the first grid is output. Among them, when the grid pair is subjected to convolution, nonlinear activation, and pooling operations of the deep convolutional neural network, the probability of each label corresponding to the first grid in the grid pair is output, and the probability of each label represents the probability size of each label corresponding to the first grid. When the label is a mineral type, the probability of the label is also the possibility of the mineral type. For example, when the label corresponding to the first grid is oil, gas, water, and metal ore, the output information is the probability of oil, gas, water, and metal ore, which means that the mineral resources corresponding to the first grid may be the probability size of oil, gas, water, and metal ore, respectively.

[0062] Compare the probabilities of each label and select the label corresponding to the largest probability to determine the mineral resource detection result. When the probability of a label among the probabilities of the labels corresponding to the first grid is the largest, it means that the possibility that the mineral resource corresponding to the first grid is the label is the largest, and the content corresponding to the label is used as the mineral resource detection result.

[0063] Specifically, Figure 2As shown, a deep convolutional neural network is formed. By constructing a reasonable deep convolutional neural network and testing the effects of different numbers of network layers, convolution kernel sizes, etc. on the deep convolutional neural network, the best deep learning network related parameters are optimized and obtained to form a deep learning network for the study area. The grid pairs are input into the deep convolutional neural network for at least one convolution, nonlinear activation, and pooling operation to obtain the best deep learning network parameters that meet the needs of this area, and obtain relevant data on mineral resources at any location in the entire study area, thereby achieving the purpose of generalizing from known areas to the entire study area.

[0064] In the method for detecting mineral resources described in the embodiment of the present invention, preferably, each interpretation section is an input channel of the deep convolutional neural network. Then, multiple interpretation sections constitute a deep neural convolutional network with multiple input channels.

[0065] The embodiment of the present invention also provides a mineral resource detection system, such as Figure 3 As shown, the system comprises:

[0066] A first acquisition unit 301 is used to acquire geophysical data of a known area and geophysical data of an area to be detected;

[0067] A gridding unit 302 is used to perform image gridding on the geophysical data of the area to be detected to obtain a plurality of first grids, and to perform image gridding on the geophysical data of the known area to obtain a plurality of second grids;

[0068] A grid pairing unit 303, configured to pair the first grid with the second grid to construct a grid pair;

[0069] The prediction unit 304 is used to input the grid pair into a deep convolutional neural network to obtain the mineral resource detection result of the area to be detected.

[0070] An embodiment of the present invention also provides a computing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for detecting mineral resources as described in any one of the above specific embodiments is implemented.

[0071] In one embodiment of this invention, Figure 4As shown, a computing device is also provided, and the computing device 402 may include one or more processors 404, such as one or more central processing units (CPUs), and each processing unit may implement one or more hardware threads. The computing device 402 may also include any storage resource 406, which is used to store any kind of information such as code, settings, data, etc. Non-limitingly, for example, the storage resource 406 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any memory may use any technology to store information. Further, any memory may provide volatile or non-volatile retention of information, and a computer program that can be run on the processor 404 is stored on the storage resource 406, and the electric vehicle charging and discharging control method described in any of the aforementioned embodiments is implemented when the processor 404 executes the computer program. Further, any memory may represent a fixed or removable component of the computing device 402. In one case, when the processor 404 executes an associated instruction stored in any memory or a combination of memories, the computing device 402 may perform any operation of the associated instruction. The computing device 402 also includes one or more drive mechanisms 408 for interacting with any storage, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.

[0072] The computing device 402 may also include an input / output module 410 (I / O) for receiving various inputs (via input device 412) and for providing various outputs (via output device 414). A specific output mechanism may include a presentation device 416 and an associated graphical user interface (GUI) 418. In other embodiments, the input / output module 410 (I / O), input device 412, and output device 414 may not be included, and the computing device 402 may be used as only one computing device in the network. The computing device 402 may also include one or more network interfaces 420 for exchanging data with other devices via one or more communication links 422. One or more communication buses 424 couple the components described above together.

[0073] The communication link 422 may be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 422 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.

[0074] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0075] It should also be understood that in the embodiments of the present invention, the term "and / or" is only a description of the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0076] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0077] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0078] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0079] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0080] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0081] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0082] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for detecting mineral resources, characterized in that: The method comprises: Obtain geophysical data of known areas and geophysical data of areas to be inspected; Performing image grid division on the geophysical data of the area to be detected to obtain a plurality of first grids, and performing image grid division on the geophysical data of the known area to obtain a plurality of second grids; The step of performing image grid division on the geophysical data of the area to be detected to obtain a plurality of first grids, and performing image grid division on the geophysical data of the known area to obtain a plurality of second grids comprises: Performing image grid division on each interpretation section included in the geophysical data of the area to be detected to obtain a plurality of first grids, and performing image grid division on each interpretation section included in the geophysical data of the known area to obtain a plurality of second grids, wherein the first grid and the second grid have the same size, and the first grid has a first attribute, and the second grid has a second attribute, and the first attribute and the second attribute respectively correspond to at least one attribute parameter; Determine one or more labels of each first grid and second grid by drilling calibration; Labeling each first grid and each second grid respectively; pairing the first grid with the second grid to construct a grid pair; Pairing the first grid with the second grid to construct a grid pair includes: respectively determining a first attribute corresponding to any of the first grids and a second attribute corresponding to any of the second grids; Comparing whether the first attribute and the second attribute satisfy a first association condition; If yes, pairing the first grid and the second grid into a grid pair; Inputting the grid pairs into a deep convolutional neural network to obtain a mineral resource detection result of the area to be detected; Inputting the grid pair into a deep convolutional neural network to obtain the mineral resource detection result of the area to be detected includes: Input the grid pair into a deep convolutional neural network, and after convolution, nonlinear activation, and pooling operations, output the probability of each label corresponding to the first grid; Compare the probabilities of each label and select the label corresponding to the largest probability to determine the mineral resource detection results.

2. A method for detecting mineral resources according to claim 1, characterized in that: 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, and frequency correlation coefficient.

3. A method for detecting mineral resources according to claim 2, characterized in that: The interpretation profiles include: seismic migration imaging profile, wave impedance profile, resistivity profile, and induced polarization profile.

4. A method for detecting mineral resources according to claim 3, characterized in that: Each explanation profile is an input channel of the deep convolutional neural network.

5. A mineral resource detection system, characterized in that: The system comprises: A first acquisition unit, used to acquire geophysical data of a known area and geophysical data of an area to be detected; A gridding unit, used for performing image gridding on the geophysical data of the area to be detected to obtain a plurality of first grids, and performing image gridding on the geophysical data of the known area to obtain a plurality of second grids. Performing image gridding on the geophysical data of the area to be detected to obtain a plurality of first grids, and performing image gridding on the geophysical data of the known area to obtain a plurality of second grids comprises: performing image gridding on each interpretation section included in the geophysical data of the area to be detected to obtain a plurality of first grids, and performing image gridding on each interpretation section included in the geophysical data of the known area to obtain a plurality of second grids, wherein the first grid and the second grid are of the same size, and the first grid has a first attribute, and the second grid has a second attribute, and the first attribute and the second attribute respectively correspond to at least one attribute parameter; The grid generation unit is further used to determine one or more labels of each first grid and second grid through drilling calibration; and perform labeling processing on each first grid and second grid respectively; A grid pairing unit, used for pairing the first grid with the second grid to construct a grid pair, wherein pairing the first grid with the second grid to construct a grid pair comprises: respectively determining a first attribute corresponding to any of the first grids and a second attribute corresponding to any of the second grids; comparing whether the first attribute and the second attribute satisfy a first association condition; and if so, pairing the first grid with the second grid into a grid pair; A prediction unit is used to input the grid pair into a deep convolutional neural network to obtain the mineral resource detection result of the area to be detected. Inputting the grid pair into the deep convolutional neural network to obtain the mineral resource detection result of the area to be detected includes: inputting the grid pair into the deep convolutional neural network, and outputting the probability of each label corresponding to the first grid after convolution, nonlinear activation, and pooling operations; comparing the probabilities of each label and selecting the label corresponding to the largest probability to determine the mineral resource detection result.

6. A computing device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the mineral resource detection method described in any one of claims 1 to 4 is implemented.

Images