Hot dry rock distribution identification method, device, electronic equipment and storage medium

Abstract

The present application discloses a method, device, electronic device and storage medium for identifying the distribution of hot dry rocks, which belongs to the field of geological exploration technology. The method includes: obtaining geophysical data of the target area; determining the characteristic vector related to the target area according to the geophysical data; inputting the characteristic vector into the hot dry rock distribution identification model to obtain the hot dry rock distribution result of the target area output by the hot dry rock distribution identification model; wherein the hot dry rock distribution identification model is constructed based on the gradient boosting tree model. The present application constructs a hot dry rock distribution identification model through the gradient boosting tree model, and utilizes the nonlinear fitting ability of the gradient boosting tree algorithm, combined with geophysical data, to realize accurate prediction and identification of the distribution of hot dry rocks on the seabed, and provide data support for subsequent exploration and development operations.

Description

Technical Field

[0001] The present application relates to the field of geological exploration technology, and in particular to a method, device, electronic equipment and storage medium for identifying hot dry rock distribution. Background Art

[0002] At present, with the development and utilization of deep geothermal energy, seabed hot dry rocks are increasingly valued as potential marine clean energy.

[0003] In related technologies, the detection of hot dry rocks on the seabed usually relies on gravity and magnetic measurements, magnetotelluric profiles, and seismic profile surveys. However, in actual applications, it is found that this survey method relies heavily on expert experience to process and interpret data, and it is difficult to meet the needs of accurate identification of hot dry rocks in complex marine environments.

[0004] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the invention

[0005] The embodiments of the present application provide a method, device, electronic device and storage medium for identifying the distribution of hot dry rocks, which can accurately predict and identify the distribution of hot dry rocks on the seabed and provide data support for subsequent exploration and development operations.

[0006] On the one hand, an embodiment of the present application provides a method for identifying hot dry rock distribution, comprising the following steps:

[0007] Acquire geophysical data of the target area;

[0008] Determining a feature vector associated with the target area based on the geophysical data;

[0009] Inputting the feature vector into a hot dry rock distribution recognition model to obtain a hot dry rock distribution result of the target area output by the hot dry rock distribution recognition model;

[0010] Among them, the hot dry rock distribution identification model is constructed based on the gradient boosting tree model.

[0011] Optionally, the geophysical data include lithology, fracture conditions, regional gravity anomalies, Bouguer gravity anomalies, magnetic anomalies and oblique magnetic susceptibility.

[0012] Optionally, the characteristic vectors related to the target area include lithology category frequency distribution, fracture density, regional gravity anomaly frequency characteristics, Bouguer gravity anomaly frequency characteristics, magnetic anomaly wavelet transform characteristics and oblique magnetic susceptibility spatial gradient characteristics.

[0013] Optionally, determining a feature vector related to the target area according to the geophysical data includes:

[0014] Obtain the frequency of occurrence of each lithology category, and then calculate the frequency distribution of each lithology category;

[0015] Obtain the number of occurrences of fractures in the target area, and then calculate the fracture density;

[0016] Obtaining the value of the regional gravity anomaly and the value of the Bouguer gravity anomaly, and then calculating the frequency characteristics of the regional gravity anomaly and the frequency characteristics of the Bouguer gravity anomaly by fast Fourier transform;

[0017] The numerical value of magnetic anomaly is obtained, and then the wavelet transform characteristics of magnetic anomaly are obtained through wavelet transform calculation;

[0018] Obtain the oblique magnetic susceptibility, and then calculate and extract the spatial gradient characteristics of the oblique magnetic susceptibility in three directions in three-dimensional space.

[0019] Optionally, the hot dry rock distribution identification model is trained based on the following steps:

[0020] Obtaining feature vectors of multiple regions and obtaining hot dry rock distribution results of multiple regions;

[0021] Taking the feature vectors of each of the regions as samples and the hot dry rock distribution results of each of the regions as sample labels corresponding to the samples, a training data set is constructed;

[0022] The hot dry rock distribution recognition model is pre-trained using the training data set.

[0023] Optionally, after acquiring the geophysical data of the target area, the method further comprises:

[0024] The geophysical data is preprocessed; wherein the preprocessing includes filling blank values, screening out abnormal values, and deleting duplicate values.

[0025] Optionally, after determining the feature vector related to the target area according to the geophysical data, the method further comprises:

[0026] A normalization operation is performed on the feature vector.

[0027] On the other hand, an embodiment of the present application provides a device for identifying hot dry rock distribution, the device comprising:

[0028] A data acquisition module, used to acquire geophysical data of a target area;

[0029] A feature extraction module, used to determine a feature vector related to the target area based on the geophysical data;

[0030] a distribution recognition module, used for inputting the feature vector into a hot dry rock distribution recognition model to obtain a hot dry rock distribution result of the target area output by the hot dry rock distribution recognition model;

[0031] Among them, the hot dry rock distribution identification model is constructed based on the gradient boosting tree model.

[0032] On the other hand, an embodiment of the present application provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned hot dry rock distribution identification method when executing the computer program.

[0033] On the other hand, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned hot dry rock distribution identification method is implemented.

[0034] The embodiment of the present application constructs a hot dry rock distribution identification model through a gradient boosting tree model. By utilizing the nonlinear fitting capability of the gradient boosting tree algorithm and combining it with geophysical data, it is possible to accurately predict and identify the distribution of hot dry rocks on the seabed and provide data support for subsequent exploration and development operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of an implementation environment of a hot dry rock distribution identification method provided in an embodiment of the present application;

[0036] Figure 2 It is a flow chart of a method for identifying hot dry rock distribution provided in an embodiment of the present application;

[0037] Figure 3 It is a schematic diagram of a process of extracting feature vectors from geophysical data provided in an embodiment of the present application;

[0038] Figure 4 It is a schematic diagram of a flow chart of training a hot dry rock distribution recognition model provided in an embodiment of the present application;

[0039] Figure 5 It is a schematic diagram of a flow chart of geophysical data preprocessing provided in an embodiment of the present application;

[0040] Figure 6 It is a flowchart of a feature vector normalization operation provided in an embodiment of the present application;

[0041] Figure 7 It is a structural schematic diagram of a hot dry rock distribution identification device provided in an embodiment of the present application;

[0042] Figure 8 It is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0044] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0045] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0047] At present, with the development and utilization of deep geothermal energy, seabed hot dry rocks are increasingly valued as potential marine clean energy. Hot dry rocks refer to high-temperature rock masses buried 3 to 10 kilometers underground, with temperatures ranging from 150 to 650°C, with no fluid or only a small amount of underground fluid (dense and impermeable) inside.

[0048] In the relevant technologies, the detection of hot dry rocks on the seabed usually relies on gravity and magnetic measurements, magnetotelluric profiles and seismic profile surveys. Among them, gravity and magnetic measurements are the collective name for gravity measurements and magnetic measurements. The underground geological structure is inferred by observing the density and magnetic differences of underground rocks; magnetotelluric method is a geophysical exploration method that studies the underground electrical structure by measuring the changes in the natural electromagnetic field of the earth. It uses the way electromagnetic waves propagate inside the earth to detect the conductivity at different depths; seismic exploration is to understand the physical properties of underground structures by analyzing the speed and path of seismic waves propagating inside the earth.

[0049] However, in actual applications, it was found that this exploration method relies heavily on expert experience to process and interpret data, and it is difficult to meet the needs of accurate identification of hot dry rocks in complex marine environments.

[0050] In view of this, a method, device, electronic device and storage medium for identifying the distribution of hot dry rocks are provided in the embodiments of the present application. A hot dry rock distribution identification model is constructed through a gradient boosting tree model. The nonlinear fitting ability of the gradient boosting tree algorithm is utilized, combined with geophysical data, to achieve accurate prediction and identification of the distribution of hot dry rocks on the seabed, thereby providing data support for subsequent exploration and development operations.

[0051] The specific implementation of the embodiment of the present application is described in detail below in conjunction with the accompanying drawings. First, a method for identifying hot dry rock distribution provided in the embodiment of the present application is described in conjunction with the accompanying drawings.

[0052] Please refer to Figure 1 , Figure 1 The schematic diagram of the implementation environment of a method for identifying hot dry rock distribution provided by an embodiment of the present application is shown. In the implementation environment, the main software and hardware entities involved include a terminal processor 110 and a server 120.

[0053] Specifically, the terminal processor 110 may be installed with a relevant hot dry rock distribution identification control program, and the server 120 is a background server of the control program. The terminal processor 110 and the background server 120 are connected in communication. The hot dry rock distribution identification method provided in the embodiment of the present application may be executed on the terminal processor 110 side.

[0054] Server 120 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0055] In addition, the server 120 may also be a node server in the blockchain network.

[0056] The terminal processor 110 and the server 120 may establish a communication connection through a wireless network. The wireless network uses standard communication technology and / or protocols, and the network may be set to the Internet, or any other network, such as but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, or any combination of a wireless network, a private network, or a virtual private network. Moreover, the above-mentioned software and hardware entities may use the same communication connection mode or different communication connection modes, and this application does not impose any specific restrictions on this.

[0057] Of course, it is understandable that Figure 1 The implementation environment in the embodiment of the present application is only some optional application scenarios of the hot dry rock distribution identification method provided in the embodiment of the present application, and the actual application is not fixed. Figure 1 The software and hardware environment shown is not specifically limited in this application.

[0058] like Figure 2 As shown, Figure 2 It is a flow chart of a method for identifying hot dry rock distribution provided in an embodiment of the present application, which specifically includes but is not limited to steps S100 to S300.

[0059] Step S100: Acquire geophysical data of the target area.

[0060] In the embodiment of the present application, after determining the target area for hot dry rock resource development, various geophysical data in the target area can be further collected. Among them, geophysical data refers to data on the internal structure of the earth, geological structure, mineral resources, hydrogeology, etc. obtained through various geophysical exploration methods.

[0061] For example, geophysical data can be obtained from various public documents and databases. In addition, it is also possible to cooperate with scientific research institutions, geological survey units, university research teams and energy companies that conduct geological exploration to obtain high-quality original data provided by these institutions.

[0062] Of course, it is understandable that the above-mentioned optional implementation methods for obtaining geophysical data are only used for illustrative purposes and are not meant to limit the actual implementation methods for obtaining geophysical data. They can be selected independently according to the actual usage scenario.

[0063] Specifically, as an optional implementation, the geophysical data include lithology, fracture conditions, regional gravity anomalies, Bouguer gravity anomalies, magnetic anomalies, and oblique magnetic susceptibility.

[0064] In an embodiment of the present application, when acquiring geophysical data of a target area, six types of geophysical data may be selected, including lithology, fracture conditions, regional gravity anomalies, Bouguer gravity anomalies, magnetic anomalies, and oblique magnetic susceptibility at multiple locations in the target area.

[0065] Among them, lithology (L) refers to the type or composition of rock. Lithology describes the physical properties of rock, such as mineral composition, structure, color and grain size. Fracture (F) refers to whether there are cracks or faults in the crust. These fractures are usually caused by geological stress and may be the result of seismic activity, volcanic activity or crustal movement. Regional Gravity Anomaly (RGA) refers to the change in gravity field caused by differences in geological structure in a large area. Regional gravity anomaly can reflect large-scale density changes in the crust and upper mantle. Bouguer Gravity Anomaly (BGA) is a specific gravity anomaly. It is the residual gravity difference after eliminating the influence of topography, elevation and earth shape when measuring gravity data. This anomaly is mainly used to detect underground density changes. Magnetic Anomaly (MA) refers to the local deviation of the earth's magnetic field. Magnetic anomaly is usually caused by magnetic differences in underground rocks and can be used to detect the distribution of underground ferromagnetic minerals. Inclined Magnetic Susceptibility (IMS) refers to the magnetization ability of a material when subjected to a non-horizontal magnetic field. Inclined Magnetic Susceptibility is used to interpret the magnetic characteristics of underground rocks in magnetic exploration.

[0066] Optionally, the data format of the geophysical data collected above can be in the form of x, y, z, where x and y represent the longitude and latitude of the sampling point respectively, and z represents the value of the data. It should be noted that when it is data on lithology and fracture conditions, z can represent the classification, that is, the specific lithology category and whether there is a fracture (for example, 1 can be used to indicate the presence of a fracture, and 0 can be used to indicate the absence of a fracture), and when it is data on regional gravity anomalies, Bouguer gravity anomalies, magnetic anomalies, and oblique magnetic susceptibility, z can represent a specific discrete value.

[0067] Of course, it is understandable that the data format of the above-mentioned geophysical data is only used for illustrative purposes and does not mean to limit the actual data format for obtaining geophysical data. It can be independently defined according to the actual usage scenario requirements.

[0068] In practical applications, the geophysical data obtained at any sampling point i, including lithology, fracture conditions, regional gravity anomaly, Bouguer gravity anomaly, magnetic anomaly, and oblique magnetic susceptibility, can be expressed as , , , , , , and customize a vector Represents all geophysical parameters at the sampling point i, namely:

[0069] ;

[0070] Furthermore, after geophysical data are collected at n different locations in the target area, these vectors can be integrated into a matrix X ,Right now:

[0071] ;

[0072] That is, the matrix X All geophysical data acquired in the target area will be uniformly identified as a data set to facilitate further data preprocessing of the data set.

[0073] Specifically, as an optional implementation, Figure 5 As shown, Figure 5 1 is a schematic diagram of a flow chart of geophysical data preprocessing provided by an embodiment of the present application. After obtaining geophysical data of the target area in step S100, the method further includes:

[0074] Step S700, preprocessing the geophysical data; wherein the preprocessing includes filling blank values, screening out abnormal values, and deleting duplicate values.

[0075] In the embodiment of the present application, in the process of acquiring geophysical data of the target area, the quality of the geophysical data will inevitably be affected by various factors. In order to ensure the accuracy and effectiveness of the geophysical data, the geophysical data can be preprocessed. The preprocessing mainly includes three methods: filling blank values, screening out abnormal values, and deleting duplicate values.

[0076] Filling blank values ​​means using interpolation or surrounding numerical mean method to fill blank values ​​in geophysical data to ensure the continuity of geophysical data.

[0077] For example, in the dataset matrix X Medium To represent the data parameters of the i-th row and j-th column in the data set, if If it is a blank value (NaN), the value can be filled by interpolation, which can be calculated by the following formula (1):

[0078] (1)

[0079] Screening and eliminating outliers means using statistical methods (such as calculating standard deviation and box plot method) to screen, identify and propose outliers, thereby reducing the interference of data noise on the model.

[0080] For example, for the dataset matrix X Each row vector in Calculate its mean and standard deviation ,like satisfy , it is considered as an outlier and removed, where k The value can be 2 or 3, which can be defined according to the actual application scenario.

[0081] Deleting duplicate values ​​means deleting duplicate records in a data set to ensure that each data point is independent and unique, thereby better improving the representativeness of the data and the generalization ability of the model.

[0082] It should be noted that in the process of screening out outliers and deleting duplicate values, if any parameter If a value is confirmed to be an outlier or duplicate value, other geophysical data at the location of this parameter need to be deleted simultaneously when performing the removal or deletion operation.

[0083] Step S200: Determine a feature vector related to the target area according to the geophysical data.

[0084] In an embodiment of the present application, after completing the step of acquiring the geophysical data of the target area, feature vectors related to the target area can be further extracted and determined from the geophysical data of the target area, thereby making full use of the potential information of these data to improve the recognition ability of the model.

[0085] Specifically, as an optional implementation, the characteristic vector related to the target area includes lithology category frequency distribution, fracture density, regional gravity anomaly frequency characteristics, Bouguer gravity anomaly frequency characteristics, magnetic anomaly wavelet transform characteristics and oblique magnetic susceptibility spatial gradient characteristics.

[0086] In the embodiments of the present application, the frequency distribution of lithology categories refers to the distribution characteristics of the occurrence frequency of each type of lithology; the fracture density refers to the number of fractures within a certain area; the frequency characteristics of regional gravity anomalies and the frequency characteristics of Bouguer gravity anomalies refer to the main frequency components of gravity anomalies extracted after converting spatial data into the frequency domain; the wavelet transform characteristics of magnetic anomalies refer to the extraction of magnetic anomaly characteristics at different scales through wavelet transform; the spatial gradient characteristics of oblique magnetic susceptibility refer to the spatial distribution characteristics of oblique magnetic susceptibility data, and its spatial characteristics, namely the spatial gradient, can be extracted.

[0087] Specifically, as an optional implementation, Figure 3 As shown, Figure 3 : is a schematic diagram of a flow chart of extracting a feature vector from geophysical data provided in an embodiment of the present application, wherein determining a feature vector related to the target area based on the geophysical data includes:

[0088] Step S210, obtaining the occurrence frequency of each lithology category, and then calculating the frequency distribution of each lithology category;

[0089] Step S220, obtaining the number of occurrences of fractures in the target area, and then calculating the fracture density;

[0090] Step S230, obtaining the value of the regional gravity anomaly and the value of the Bouguer gravity anomaly, and then calculating the frequency characteristics of the regional gravity anomaly and the frequency characteristics of the Bouguer gravity anomaly by fast Fourier transform;

[0091] Step S240, obtaining the value of the magnetic anomaly, and then obtaining the wavelet transform characteristics of the magnetic anomaly through wavelet transform calculation;

[0092] Step S250: Obtain the oblique magnetic susceptibility, and then calculate and extract the oblique magnetic susceptibility spatial gradient characteristics in three directions in the three-dimensional space.

[0093] In the embodiment of the present application, when determining the frequency distribution of lithology categories, the frequency of occurrence of each lithology category that has been classified can be counted, and the frequency distribution of each lithology category can be calculated based on the total number, which can be expressed as a category distribution vector, that is, ,in, L represents the frequency distribution of different lithology categories, j Indicates the lithology category.

[0094] Furthermore, the fracture density refers to the number of fractures within a certain area. The size of the area can be defined by the user. For example, the number of fractures in the target area can be obtained to calculate the fracture density of the target area. The target area can also be divided into multiple different areas, and the fracture density in each area can be calculated separately and expressed as a vector ,Right now ,in, represents the fracture density of region n.

[0095] Alternatively, if directional data are available, the principal directions of the fracture can be extracted and their angular distribution can be extracted and represented as a vector using statistical analysis (e.g., rose diagram analysis).

[0096] Furthermore, for the discrete values ​​of regional gravity anomaly and Bouguer gravity anomaly, the spatial data can be converted to the frequency domain, the main frequency component of the gravity anomaly can be extracted, and the characteristics of the frequency domain can be expressed as a frequency factor vector f, that is, ,in, is the fast Fourier transform, are the discrete values ​​of regional gravity anomaly and Bouguer gravity anomaly.

[0097] Furthermore, the numerical value of magnetic anomaly is obtained, and the magnetic anomaly features at different scales are extracted through wavelet transform. These features can be expressed as the wavelet transform features of magnetic anomaly at different scales. ,Right now ,in, is the wavelet transform, is the value of the magnetic anomaly.

[0098] Furthermore, the oblique magnetic susceptibility is obtained, and because the oblique magnetic susceptibility data has a spatial distribution characteristic, its spatial characteristics, namely the spatial gradient, can be extracted therefrom. Finally, the oblique magnetic susceptibility spatial gradient characteristics in three directions in three-dimensional space are extracted, and can point to the direction where the scalar field changes most dramatically.

[0099] Specifically, in an optional implementation manner, as Figure 6 As shown, Figure 6 is a flow chart of a feature vector normalization operation provided by an embodiment of the present application. After determining the feature vector related to the target area according to the geophysical data in step S200, the method further includes:

[0100] Step S800: normalize the feature vector.

[0101] In an embodiment of the present application, after extracting and determining the feature vectors related to the target area, all vectors can be normalized to scale the data to a specific range (eg, between 0 and 1), which can effectively reduce the scale differences between features.

[0102] For example, for the matrix X The normalization operation for each value in any row vector in can be calculated by the following formula (2):

[0103] (2)

[0104] in, is the normalized data value, is the data value before normalization, is the minimum value in the corresponding row vector, is the maximum value in the corresponding row vector.

[0105] When each data in the data set is normalized, a normalized data set matrix is ​​obtained.

[0106] Step S300, inputting the feature vector into a hot dry rock distribution recognition model to obtain a hot dry rock distribution result of the target area output by the hot dry rock distribution recognition model;

[0107] Among them, the hot dry rock distribution identification model is constructed based on the gradient boosting tree model.

[0108] In the embodiment of the present application, the hot dry rock distribution identification model is constructed based on the gradient boosting tree model, wherein the gradient boosting tree (GBDT) is an integrated learning method. Its advantage in processing nonlinear data is that it fits complex nonlinear relationships by combining multiple decision trees, and ultimately improves the prediction performance of the model. Each decision tree model is divided into multiple sub-regions in the feature space, and only simple linear fitting is performed in these sub-regions, which further enhances the speed of model operation.

[0109] The identification of hot dry rocks on the seabed usually involves the comprehensive analysis of a variety of geophysical data, which have a highly nonlinear relationship. The hot dry rock distribution identification model built on the basis of the gradient boosting tree model can effectively combine geophysical data through nonlinear fitting capabilities to achieve accurate identification of the distribution of hot dry rocks on the seabed.

[0110] Specifically, in an optional implementation manner, as Figure 4 As shown, Figure 4 : is a flow chart of a training hot dry rock distribution recognition model provided in an embodiment of the present application, wherein the hot dry rock distribution recognition model is trained based on the following steps:

[0111] Step S400, obtaining feature vectors of multiple regions, and obtaining hot dry rock distribution results of multiple regions;

[0112] Step S500, taking the feature vectors of each of the regions as samples, and taking the hot dry rock distribution results of each of the regions as sample labels corresponding to the samples, to construct a training data set;

[0113] Step S600: pre-training the hot dry rock distribution recognition model using the training data set.

[0114] In an embodiment of the present application, characteristic vectors of multiple explored areas and hot dry rock distribution results of multiple areas in the historical exploration and development process can be obtained, and then the characteristic vector of any area is used as a sample and the hot dry rock distribution result of any area is used as a sample label corresponding to the sample to form a group of training samples. A training data set is constructed by obtaining multiple training samples, and then the training data set is input into the hot dry rock distribution recognition model. The model parameters in the hot dry rock distribution recognition model are adjusted according to each output result of the hot dry rock distribution recognition model, and finally the pre-training process of the hot dry rock distribution recognition model is completed.

[0115] The pre-training process of the hot dry rock distribution recognition model may be considered completed after reaching a preset number of pre-training times; or the pre-training process of the hot dry rock distribution recognition model may be considered completed when the training output results of the hot dry rock distribution recognition model converge.

[0116] Exemplarily, the gradient boosting tree model has multiple hyperparameters that need to be adjusted, such as learning rate, number of trees, maximum depth, etc. These hyperparameters can be initialized before model training. For example, the learning rate can be set to 0.1, the number of trees to 100, the maximum depth of the tree to 4, the subsample ratio to 1.0, the minimum number of sample splits to 2, and the minimum number of sample leaves to 1.

[0117] The objective function of the hot dry rock distribution identification model for predicting the distribution of hot dry rocks is: , which can be expressed as follows:

[0118]

[0119] in, is the output of the sth decision tree, which represents the partial nonlinear pattern that can capture the input feature x. The model forms the final prediction result by combining the c outputs of all trees, which can approximate complex nonlinear relationships. is the weight coefficient of the sth decision tree, which is determined through the optimization process and is used to adjust the influence of each tree on the final hot dry rock distribution identification model; Identify the model values ​​for the initial hot dry rock distribution.

[0120] Furthermore, during the pre-training process of the hot dry rock distribution recognition model, the hot dry rock distribution recognition model can also be evaluated by a cross-validation method, and the hyperparameters can be adjusted according to the evaluation results to optimize the performance of the hot dry rock distribution recognition model.

[0121] In practical applications, after constructing the training data set, it can be divided into a training set and a test set, with the training set accounting for 80% of the training data set and the test set accounting for 20% of the training data set. The training set is used for model training and the test set is used for model verification. When the test set is used to verify the hot dry rock distribution recognition model, the performance indicators such as the accuracy and F1 score of the hot dry rock distribution recognition model can be calculated. For example, when the accuracy and F1 score are above 0.6-0.8, the model can be considered to be more reliable and have better performance.

[0122] Below, in combination with a specific application implementation process, the hot dry rock distribution identification method provided in the present invention is introduced and described in detail:

[0123] In an embodiment of the present application, a method for identifying the distribution of hot dry rocks is provided. The method can be applied to the scene of identifying the distribution of hot dry rocks on the seabed. A hot dry rock distribution identification model is constructed through a gradient boosting tree model. The nonlinear fitting ability of the gradient boosting tree algorithm is utilized in combination with geophysical data to achieve accurate prediction and identification of the distribution of hot dry rocks on the seabed, thereby providing data support for subsequent exploration and development operations.

[0124] Specifically, before performing hot dry rock distribution identification, the hot dry rock distribution identification model can be pre-trained, that is, by obtaining the feature vectors of multiple explored areas and the hot dry rock distribution results of multiple areas in the historical exploration and development process, and then taking the feature vector of any area as a sample and the hot dry rock distribution result of any area as the sample label corresponding to the sample, a group of training samples are formed, and a training data set is constructed by obtaining multiple training samples, and then the training data set is input into the hot dry rock distribution identification model, and the model parameters in the hot dry rock distribution identification model are adjusted according to each output result of the hot dry rock distribution identification model, and finally the pre-training process of the hot dry rock distribution identification model is completed.

[0125] Furthermore, geophysical data of the target area to be identified are obtained, and feature vectors related to the target area are extracted to determine the geophysical data, wherein the geophysical data can be divided into lithology, fracture conditions, regional gravity anomalies, Bouguer gravity anomalies, magnetic anomalies, and oblique magnetic susceptibility; the feature vectors related to the target area can be divided into lithology category frequency distribution, fracture density, regional gravity anomaly frequency characteristics, Bouguer gravity anomaly frequency characteristics, magnetic anomaly wavelet transform characteristics, and oblique magnetic susceptibility spatial gradient characteristics.

[0126] Furthermore, all the extracted and determined feature vectors are input into the trained hot dry rock distribution recognition model to perform hot dry rock distribution recognition prediction. The hot dry rock distribution result of the target area output by the hot dry rock distribution recognition model is whether there is hot dry rock distributed at the position corresponding to each set of geophysical data. If there is hot dry rock, the result 1 is returned, and if there is no hot dry rock, the result 0 is returned.

[0127] Finally, based on the hot dry rock distribution results of the target area output by the hot dry rock distribution identification model, the kriging difference can be used to generate a hot dry rock distribution map to provide data support for subsequent exploration and development operations.

[0128] See also Figure 7 The embodiment of the present application also provides a hot dry rock distribution identification device, which can implement the above hot dry rock distribution identification method, and the device includes:

[0129] A data acquisition module 710 is used to acquire geophysical data of a target area;

[0130] A feature extraction module 720, for determining a feature vector associated with the target area based on the geophysical data;

[0131] A distribution identification module 730 is used to input the feature vector into a hot dry rock distribution identification model to obtain a hot dry rock distribution result of the target area output by the hot dry rock distribution identification model;

[0132] Among them, the hot dry rock distribution identification model is constructed based on the gradient boosting tree model.

[0133] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0134] Please refer to Figure 8 , Figure 8 The hardware structure of the electronic device provided in the embodiment of the present application is illustrated, and the electronic device includes:

[0135] The processor 801 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0136] The memory 802 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 802 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 802, and the processor 801 calls and executes the hot dry rock distribution identification method of the embodiment of this application;

[0137] Input / output interface 803, used to implement information input and output;

[0138] The communication interface 804 is used to realize the communication interaction between the device and other devices. The communication can be realized through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.);

[0139] A bus 805 that transmits information between various components of the device (e.g., the processor 801, the memory 802, the input / output interface 803, and the communication interface 804);

[0140] The processor 801 , the memory 802 , the input / output interface 803 and the communication interface 804 are connected to each other in communication within the device via a bus 805 .

[0141] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned hot dry rock distribution identification method is implemented.

[0142] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0143] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0144] The embodiments of the present application provide a method, device, electronic device and storage medium for identifying the distribution of hot dry rocks. The method constructs a hot dry rock distribution identification model through a gradient boosting tree model, utilizes the nonlinear fitting ability of the gradient boosting tree algorithm, and combines geophysical data to achieve accurate prediction and identification of the distribution of hot dry rocks on the seabed, thereby providing data support for subsequent exploration and development operations.

[0145] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0146] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0147] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0148] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0149] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0150] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0151] In the several embodiments provided in the present application, it should be understood that the disclosed 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 above 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. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0152] The units described above 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 solution of this embodiment.

[0153] In addition, each functional unit in each embodiment of the present application 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.

[0154] 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 application, 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 multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0155] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for identifying hot dry rock distribution, characterized in that: The method comprises the following steps: Acquire geophysical data of the target area; Determining a feature vector associated with the target area based on the geophysical data; Inputting the feature vector into a hot dry rock distribution recognition model to obtain a hot dry rock distribution result of the target area output by the hot dry rock distribution recognition model; Wherein, the hot dry rock distribution identification model is constructed based on the gradient boosting tree model; The geophysical data include lithology, fracture conditions, regional gravity anomaly, Bouguer gravity anomaly, magnetic anomaly and oblique magnetic susceptibility; The characteristic vectors related to the target area include lithology category frequency distribution, fracture density, regional gravity anomaly frequency characteristics, Bouguer gravity anomaly frequency characteristics, magnetic anomaly wavelet transform characteristics and oblique magnetic susceptibility spatial gradient characteristics; Determining a feature vector related to the target area according to the geophysical data includes: Obtain the frequency of occurrence of each lithology category, and then calculate the frequency distribution of each lithology category; Obtain the number of occurrences of fractures in the target area, and then calculate the fracture density; Obtaining the value of the regional gravity anomaly and the value of the Bouguer gravity anomaly, and then calculating the frequency characteristics of the regional gravity anomaly and the frequency characteristics of the Bouguer gravity anomaly by fast Fourier transform; The numerical value of magnetic anomaly is obtained, and then the wavelet transform characteristics of magnetic anomaly are obtained through wavelet transform calculation; Obtain the oblique magnetic susceptibility, and then calculate and extract the spatial gradient characteristics of the oblique magnetic susceptibility in three directions in three-dimensional space; The expression of the objective function of the hot dry rock distribution identification model for hot dry rock distribution prediction is for: ； in, is the output of the sth decision tree; is the weight coefficient of the sth decision tree; Identify the model values ​​for the initial hot dry rock distribution.

2. The method for identifying hot dry rock distribution according to claim 1, characterized in that: The hot dry rock distribution identification model is trained based on the following steps: Obtaining feature vectors of multiple regions and obtaining hot dry rock distribution results of multiple regions; Taking the feature vectors of each of the regions as samples and the hot dry rock distribution results of each of the regions as sample labels corresponding to the samples, a training data set is constructed; The hot dry rock distribution recognition model is pre-trained using the training data set.

3. The method for identifying hot dry rock distribution according to claim 1, characterized in that: After acquiring the geophysical data of the target area, the method further includes: The geophysical data is preprocessed; wherein the preprocessing includes filling blank values, screening out abnormal values, and deleting duplicate values.

4. The method for identifying hot dry rock distribution according to claim 1, characterized in that: After determining the feature vector associated with the target area according to the geophysical data, the method further includes: A normalization operation is performed on the feature vector.

5. A hot dry rock distribution identification device, characterized in that: The device comprises: A data acquisition module, used to acquire geophysical data of a target area; A feature extraction module, used to determine a feature vector related to the target area based on the geophysical data; a distribution recognition module, used for inputting the feature vector into a hot dry rock distribution recognition model to obtain a hot dry rock distribution result of the target area output by the hot dry rock distribution recognition model; Wherein, the hot dry rock distribution identification model is constructed based on the gradient boosting tree model; The geophysical data include lithology, fracture conditions, regional gravity anomaly, Bouguer gravity anomaly, magnetic anomaly and oblique magnetic susceptibility; The characteristic vectors related to the target area include lithology category frequency distribution, fracture density, regional gravity anomaly frequency characteristics, Bouguer gravity anomaly frequency characteristics, magnetic anomaly wavelet transform characteristics and oblique magnetic susceptibility spatial gradient characteristics; Determining a feature vector related to the target area according to the geophysical data includes: Obtain the frequency of occurrence of each lithology category, and then calculate the frequency distribution of each lithology category; Obtain the number of occurrences of fractures in the target area, and then calculate the fracture density; Obtaining the value of the regional gravity anomaly and the value of the Bouguer gravity anomaly, and then calculating the frequency characteristics of the regional gravity anomaly and the frequency characteristics of the Bouguer gravity anomaly by fast Fourier transform; The numerical value of magnetic anomaly is obtained, and then the wavelet transform characteristics of magnetic anomaly are obtained through wavelet transform calculation; Obtain the oblique magnetic susceptibility, and then calculate and extract the spatial gradient characteristics of the oblique magnetic susceptibility in three directions in three-dimensional space; The expression of the objective function of the hot dry rock distribution identification model for hot dry rock distribution prediction is for: ； in, is the output of the sth decision tree; is the weight coefficient of the sth decision tree; Identify the model values ​​for the initial hot dry rock distribution.

6. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the hot dry rock distribution identification method according to any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the hot dry rock distribution identification method according to any one of claims 1 to 4 is implemented.

Images