CN118395223A - Environment investigation data processing method for geological mineral exploration - Google Patents
Environment investigation data processing method for geological mineral exploration Download PDFInfo
- Publication number
- CN118395223A CN118395223A CN202410267760.2A CN202410267760A CN118395223A CN 118395223 A CN118395223 A CN 118395223A CN 202410267760 A CN202410267760 A CN 202410267760A CN 118395223 A CN118395223 A CN 118395223A
- Authority
- CN
- China
- Prior art keywords
- environmental
- parameter
- matrix
- environment
- collaborative
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Business, Economics & Management (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Mining & Mineral Resources (AREA)
- Agronomy & Crop Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses an environmental survey data processing method for geological mineral exploration, and relates to the field of geological mineral exploration. Firstly, arranging environmental investigation parameters of all sampling points into an environmental multi-parameter collaborative input matrix according to environmental parameter sample dimensions, extracting environmental multi-parameter association characteristics to obtain a plurality of environmental multi-parameter collaborative association characterization characteristic matrixes, then respectively carrying out characteristic reinforcement on the plurality of environmental multi-parameter collaborative association characterization characteristic matrixes by using a characteristic expression enhancer based on a re-parameterization layer to obtain a plurality of reinforced environmental multi-parameter collaborative association characterization characteristic matrixes, then carrying out joint cluster analysis on the plurality of reinforced environmental multi-parameter collaborative association characterization characteristic matrixes by using a joint cluster network to obtain sampling point global environmental parameter collaborative characterization characteristics, and finally, determining whether a geological mineral exploration area is a sensitive area or not based on the sampling point global environmental parameter collaborative characterization characteristics. Thus, the efficiency and the accuracy of geological mineral exploration can be improved.
Description
Technical Field
The present application relates to the field of geological mineral exploration, and more particularly to an environmental survey data processing method for geological mineral exploration.
Background
Geological mineral exploration refers to the process of investigation, evaluation and development of underground mineral resources. Geological mineral exploration is an important activity, but it also has a certain impact on the environment. In order to protect the environment, it is necessary to evaluate the environmental conditions of geological mineral exploration areas to determine whether sensitive areas, such as ecologically vulnerable areas, water source protection areas, natural protection areas, etc., are present. However, conventional environmental survey data processing methods typically consider only a single environmental parameter, such as soil, water quality, vegetation, or gas, and ignore the synergistic relationship between different environmental parameters, which may lead to inaccurate or incomplete assessment results.
Accordingly, an optimized environmental survey data processing scheme for geological mineral exploration is desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The application provides an environmental survey data processing method for geological mineral exploration, which can comprehensively consider a plurality of environmental survey parameters in a geological mineral exploration area, and carry out collaborative analysis among the environmental survey parameters by utilizing a data processing and analysis algorithm based on a deep learning technology and artificial intelligence so as to more comprehensively evaluate the environmental condition of the geological mineral exploration area and judge whether the geological mineral exploration area is a sensitive area.
According to one aspect of the present application there is provided an environmental survey data processing method for geological mineral exploration, comprising:
Acquiring environmental investigation parameters of a plurality of sampling points in a geological mineral exploration area, wherein the environmental investigation parameters comprise soil data, water quality data, vegetation data and gas data;
after the environmental investigation parameters of each sampling point are arranged into an environmental multi-parameter collaborative input matrix according to the dimension of an environmental parameter sample, respectively extracting environmental multi-parameter association characteristics of the environmental multi-parameter collaborative input matrix of each sampling point to obtain a plurality of environmental multi-parameter collaborative association characterization characteristic matrixes;
Respectively carrying out characteristic reinforcement on the multiple environment multi-parameter collaborative association characteristic matrixes by using a characteristic expression enhancer based on a re-parameterization layer so as to obtain the multiple reinforced environment multi-parameter collaborative association characteristic matrixes;
Performing joint cluster analysis on the multiple reinforced environment multi-parameter collaborative association characterization feature matrixes by using a joint cluster network to obtain a sampling point global environment parameter collaborative characterization feature matrix serving as a sampling point global environment parameter collaborative characterization feature;
And determining whether the geological mineral exploration area is a sensitive area based on the global environmental parameter collaborative characterization characteristics of the sampling points.
Further, after the environmental investigation parameters of each sampling point are arranged into an environmental multi-parameter collaborative input matrix according to the dimension of the environmental parameter sample, respectively extracting environmental multi-parameter association characteristics of the environmental multi-parameter collaborative input matrix of each sampling point to obtain a plurality of environmental multi-parameter collaborative association characteristic matrixes, including:
And arranging the environmental investigation parameters of each sampling point into an environmental multi-parameter collaborative input matrix according to the dimension of an environmental parameter sample, and then obtaining a plurality of environmental multi-parameter collaborative association characterization feature matrixes through an environmental parameter feature extractor based on a convolutional neural network model.
Further, the feature expression enhancer based on the re-parameterization layer is used for respectively carrying out feature enhancement on the multiple environment multi-parameter collaborative association characterization feature matrixes to obtain the multiple enhanced environment multi-parameter collaborative association characterization feature matrixes, and the method comprises the following steps:
Respectively carrying out characteristic enhancement on the multiple environment multi-parameter collaborative association characterization characteristic matrixes by using a characteristic expression enhancer based on a re-parameterization layer according to the following enhancement formula so as to obtain the multiple enhanced environment multi-parameter collaborative association characterization characteristic matrixes; wherein, the strengthening formula is:
Wherein, For each of a plurality of environmental multi-parameter collaborative association characterization feature matrices a global average of the environmental multi-parameter collaborative association characterization feature matrices,Characterizing the variance of the feature matrix for each environmental multi-parameter collaborative association,Is obtained by randomly sampling Gaussian distribution of each environment multi-parameter collaborative association characteristic matrixThe value of the one of the values,Is the characteristic value of each position in the multi-parameter collaborative association characteristic matrix of each strengthened environment in the multi-parameter collaborative association characteristic matrix of the strengthened environment,Representing multiplication by location.
Further, performing joint cluster analysis on the multiple reinforced environment multi-parameter collaborative association characterization feature matrices by using a joint cluster network to obtain a sampling point global environment parameter collaborative characterization feature matrix as a sampling point global environment parameter collaborative characterization feature, including:
Constructing adjacent matrixes and degree matrixes of a plurality of reinforced environment multi-parameter collaborative association characterization feature matrixes;
calculating a Laplace matrix based on the adjacency matrix and the degree matrix;
carrying out standardization processing on the Laplace matrix to obtain a standardized Laplace matrix;
Arranging the characteristic values of the standardized Laplace matrix from large to small, extracting the first K characteristic values, and calculating the characteristic vectors of the first K characteristic values;
and normalizing the feature vectors of the first K feature values and forming a feature vector matrix by the feature vectors of the first K normalized feature values to obtain the feature matrix of the global environmental parameter collaborative characterization of the sampling points.
Further, constructing a plurality of adjacency matrices and degree matrices of the enhanced environment multi-parameter collaborative association characterization feature matrix, including:
calculating association weight values among the reinforced environment multi-parameter collaborative association characterization feature matrixes in the reinforced environment multi-parameter collaborative association characterization feature matrixes according to the following weight formula to obtain an adjacent matrix; wherein, the weight formula is:
Wherein, AndCharacterizing the first characteristic matrix of the multi-parameter collaborative association of the plurality of enhanced environmentsAnd (b)The characteristic matrix is characterized by the multi-parameter cooperative association of the environment after strengthening,Is the firstCharacterization feature matrix and first feature matrix of multi-parameter collaborative association of environment after strengtheningThe multi-parameter collaborative association of the environment after strengthening characterizes the variance among the feature matrices,Representing the square of the two norms,For the purpose of the exponential operation,Is the first in the adjacency matrixCharacteristic values of the location.
Further, constructing a plurality of adjacency matrices and degree matrices of the enhanced environment multi-parameter collaborative association characterization feature matrix, including:
The characteristic value of each position in the degree matrix is the sum of the associated weight values of all the rest of the strengthened environment multi-parameter collaborative association characteristic feature matrices connected with each strengthened environment multi-parameter collaborative association characteristic feature matrix in the strengthened environment multi-parameter collaborative association characteristic feature matrices.
Further, calculating the laplacian matrix based on the adjacency matrix and the degree matrix, comprising:
Calculating a Laplace matrix by the following Laplace formula based on the adjacency matrix and the degree matrix; wherein, the Laplace formula is:
Wherein, In order to be a contiguous matrix,In the form of a degree matrix,Is a laplace matrix.
Further, the normalization processing is performed on the laplace matrix to obtain a normalized laplace matrix, which includes:
Carrying out standardization processing on the Laplace matrix by using the following standardization formula to obtain a standardized Laplace matrix; wherein, the standardized formula is:
Wherein, In order to be a contiguous matrix,In the form of a degree matrix,Is a matrix of units which is a matrix of units,Is a normalized laplacian matrix.
Further, determining whether the geological mineral exploration area is a sensitive area based on the collaborative characterization feature of the global environmental parameter of the sampling point comprises:
And the sampling point global environment parameter collaborative characterization feature matrix is passed through a classifier to obtain a classification result, and the classification result is used for indicating whether the geological mineral exploration area is a sensitive area or not.
Further, the training method also comprises the following training steps: the method is used for training an environment parameter feature extractor, a joint clustering network and a classifier based on a convolutional neural network model;
Wherein, training step includes:
The method comprises the steps of training data acquisition, wherein the training data comprise training environment investigation parameters of a plurality of sampling points in a geological mineral exploration area and whether the geological mineral exploration area is a true value of a sensitive area, and the training environment investigation parameters comprise training soil data, training water quality data, training vegetation data and training gas data;
Training environment investigation parameters of all sampling points are arranged into a training environment multi-parameter collaborative input matrix according to the dimension of an environment parameter sample, and then a plurality of training environment multi-parameter collaborative association characterization feature matrixes are obtained through an environment parameter feature extractor based on a convolutional neural network model;
respectively carrying out feature enhancement on the multi-parameter collaborative association characteristic matrixes of the training environments by using a feature expression enhancer based on a re-parameterization layer so as to obtain the multi-parameter collaborative association characteristic matrixes of the environment after the training enhancement;
performing joint cluster analysis on the multiple training-reinforced environment multi-parameter collaborative association characterization feature matrixes by using a joint cluster network to obtain a training sampling point global environment parameter collaborative characterization feature matrix;
expanding the training sampling point global environment parameter collaborative characterization feature matrix to obtain a training sampling point global environment parameter collaborative characterization feature vector;
the global environmental parameter collaborative characterization feature vector of the training sampling point passes through a classifier to obtain a classification loss function value;
And training the environmental parameter feature extractor, the joint clustering network and the classifier based on the convolutional neural network model by using the classification loss function value, wherein the training sampling point global environmental parameter collaborative characterization feature vector obtained by developing the training sampling point global environmental parameter collaborative characterization feature matrix is optimized during each iteration training of the classifier.
Compared with the prior art, the environmental investigation data processing method for geological mineral exploration is characterized in that firstly, environmental investigation parameters of all sampling points are arranged into an environmental multi-parameter collaborative input matrix according to the dimensions of environmental parameter samples, then environmental multi-parameter association characteristic extraction is carried out to obtain a plurality of environmental multi-parameter collaborative association characteristic matrixes, then, a characteristic expression enhancer based on a re-parameterization layer is used for carrying out characteristic enhancement on the plurality of environmental multi-parameter collaborative association characteristic matrixes to obtain a plurality of enhanced environmental multi-parameter collaborative association characteristic matrixes, then, a joint clustering network is used for carrying out joint clustering analysis on the plurality of enhanced environmental multi-parameter collaborative association characteristic matrixes to obtain sampling point global environmental parameter collaborative characteristic characteristics, and finally, whether a geological mineral exploration area is a sensitive area is determined based on the sampling point global environmental parameter collaborative characteristic characteristics. Thus, the efficiency and accuracy of geological mineral exploration can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly introduced below, the following drawings not being drawn to scale with respect to actual dimensions, emphasis instead being placed upon illustrating the gist of the present application.
FIG. 1 is a flow chart of an environmental survey data processing method for geological mineral exploration, according to an embodiment of the present application;
FIG. 2 is a schematic architecture diagram of an environmental survey data processing method for geological mineral exploration, according to an embodiment of the present application;
FIG. 3 is a block diagram of an environmental survey data processing system for geological mineral exploration, in accordance with an embodiment of the present application;
Fig. 4 is an application scenario diagram of an environmental survey data processing method for geological mineral exploration according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are also within the scope of the application.
As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
In geological mineral exploration, environmental survey data typically includes a number of parameters, such as soil data, water quality data, vegetation data, and gas data, which may reflect the environmental conditions of the exploration area. By processing and analyzing the environmental survey data, the environmental characteristics of the survey area can be obtained, and whether a sensitive area exists or not, such as an ecologically vulnerable area, a water source protection area, a natural protection area and the like, is judged.
Based on this, in the technical scheme of the application, an environmental survey data processing method for geological mineral exploration is provided, which can comprehensively consider a plurality of environmental survey parameters in a geological mineral exploration area, such as soil data, water quality data, vegetation data and gas data, and perform collaborative analysis between the environmental survey parameters by utilizing a data processing and analyzing algorithm based on a deep learning technology and artificial intelligence, so as to more comprehensively evaluate the environmental condition of the geological mineral exploration area and judge whether the geological mineral exploration area is a sensitive area. Therefore, the efficiency and the accuracy of geological mineral exploration can be improved, and scientific basis and decision support are provided for environmental protection.
FIG. 1 is a flow chart of an environmental survey data processing method for geological mineral exploration, in accordance with an embodiment of the present application. Fig. 2 is a schematic architecture diagram of an environmental survey data processing method for geological mineral exploration according to an embodiment of the present application. As shown in fig. 1 and 2, the environmental survey data processing method for geological mineral exploration according to an embodiment of the present application includes the steps of: s110, acquiring environmental investigation parameters of a plurality of sampling points in a geological mineral investigation region, wherein the environmental investigation parameters comprise soil data, water quality data, vegetation data and gas data; s120, after the environmental investigation parameters of the sampling points are arranged into an environmental multi-parameter collaborative input matrix according to the dimensions of environmental parameter samples, respectively extracting environmental multi-parameter association characteristics of the environmental multi-parameter collaborative input matrix of the sampling points to obtain a plurality of environmental multi-parameter collaborative association characterization characteristic matrixes; s130, respectively carrying out characteristic enhancement on the environment multi-parameter collaborative association characteristic matrixes by using a characteristic expression enhancer based on a re-parameterization layer so as to obtain the enhanced environment multi-parameter collaborative association characteristic matrixes; s140, performing joint cluster analysis on the multiple reinforced environment multi-parameter collaborative association characterization feature matrixes by using a joint cluster network to obtain a sampling point global environment parameter collaborative characterization feature matrix serving as a sampling point global environment parameter collaborative characterization feature; and S150, determining whether the geological mineral exploration area is a sensitive area or not based on the global environmental parameter collaborative characterization characteristics of the sampling points.
Specifically, in the technical scheme of the application, firstly, environment investigation parameters of a plurality of sampling points in a geological mineral exploration area are obtained, wherein the environment investigation parameters comprise soil data, water quality data, vegetation data and gas data. Next, consider that for each sample point, each sample point contains different environmental survey data, such as soil data, water quality data, vegetation data, and gas data, with certain correlations and interactions between these environmental parameters. Therefore, in order to better utilize the cooperative relationship between different environmental parameters so as to extract the characteristics with more representativeness and distinguishing degree, in the technical scheme of the application, the environmental investigation parameters of each sampling point are required to be arranged into an environmental multi-parameter cooperative input matrix according to the dimension of an environmental parameter sample, and then the characteristic mining is carried out in an environmental parameter characteristic extractor based on a convolutional neural network model so as to extract the cooperative association characteristic information between different environmental parameters in the environmental investigation parameters of each sampling point, thereby obtaining a plurality of environmental multi-parameter cooperative association characteristic matrixes. In this way, the mutual relation and information interaction among different environmental parameters of the sampling points can be fully utilized, and more representative and differentiated environmental state characteristics can be extracted. Compared with a single environmental parameter processing method, the environmental multi-parameter collaborative analysis can more comprehensively consider the environmental condition of the investigation region, and improve the accuracy and reliability of the environmental condition assessment result.
Correspondingly, in step S120, after the environmental survey parameters of the sampling points are arranged into an environmental multi-parameter collaborative input matrix according to the environmental parameter sample dimension, the environmental multi-parameter collaborative input matrix of each sampling point is respectively subjected to environmental multi-parameter association feature extraction to obtain a plurality of environmental multi-parameter collaborative association characterization feature matrices, including: and arranging the environmental investigation parameters of the sampling points into an environmental multi-parameter collaborative input matrix according to the dimension of the environmental parameter sample, and obtaining the environmental multi-parameter collaborative association characterization feature matrix through an environmental parameter feature extractor based on a convolutional neural network model.
Then, it is contemplated that in geological mineral exploration, the environmental survey data typically includes a plurality of environmental parameters, which may have certain correlations and complex interactions between them. The feature extractor based on the convolutional neural network is used for processing, although some preliminary feature representations can be extracted from the environment multi-parameter collaborative association characterization feature matrix. However, these features may not be adequate and accurate enough to fully capture subtle changes and differences in environmental features. In order to enhance and enrich the expression capability of the environment parameter collaborative association characteristic, so that different environment states are more differentiated and robust, in the technical scheme of the application, a characteristic expression enhancer based on a heavy parameterization layer is further used for carrying out characteristic enhancement on the environment multi-parameter collaborative association characteristic matrixes respectively so as to obtain the enhanced environment multi-parameter collaborative association characteristic matrixes. Through the processing of the feature expression enhancer based on the re-parameterization layer, randomness can be introduced, and the original characterization feature matrix is re-parameterized into richer feature representation, so that the expression capability of the environment multi-parameter cooperative association characterization feature is enhanced. In this process, the mean and variance of each of the environmental multi-parameter collaborative associations characterizing feature matrices are extracted and used to generate new feature matrices. This form of re-parameterization can be seen as a way of data enhancement in the semantic feature space, which helps to improve the environmental feature expression capability of the geological mineral investigation region, and to improve the perception and recognition capability of the classifier for different environmental state features, thereby more accurately assessing the environmental condition of the geological mineral investigation region.
Accordingly, in step S130, the feature enhancement is performed on the multiple environmental multi-parameter collaborative association characterization feature matrices by using a feature expression enhancer based on the re-parameterization layer to obtain multiple enhanced environmental multi-parameter collaborative association characterization feature matrices, including: respectively carrying out characteristic reinforcement on the plurality of environment multi-parameter collaborative association characteristic matrixes by using the characteristic expression enhancer based on the re-parameterization layer according to the following reinforcement formula so as to obtain the plurality of reinforced environment multi-parameter collaborative association characteristic matrixes; wherein, the strengthening formula is:
Wherein, For each of the plurality of environmental multi-parameter collaborative association characterization feature matrices a global average of the environmental multi-parameter collaborative association characterization feature matrices,Characterizing the variance of the feature matrix for each of the environmental multi-parameter collaborative associations,Is obtained by randomly sampling the Gaussian distribution of each environment multi-parameter cooperative association characteristic matrixThe value of the one of the values,Is the characteristic value of each position in each reinforced environment multi-parameter cooperative association characteristic matrix in the reinforced environment multi-parameter cooperative association characteristic matrices,Representing multiplication by location.
In geological mineral exploration, through the steps of feature extraction and feature reinforcement, the characteristic matrixes of the environmental multi-parameter collaborative association characterization after the reinforcement can be obtained, wherein each characteristic matrix represents the environmental state feature expression of one sampling point. Furthermore, in order to more accurately and comprehensively detect the environmental state of the geological mineral exploration area by considering that the environmental state characteristics of different sampling points have correlation relations, in the technical scheme of the application, a joint clustering network is further used for carrying out joint clustering analysis on the plurality of reinforced environmental multi-parameter collaborative correlation characterization characteristic matrixes so as to obtain a sampling point global environmental parameter collaborative characterization characteristic matrix. The method can comprehensively utilize the similarity and the association relation between the environmental state characterization features of different sampling points in the geological mineral exploration area by using the combined clustering network for processing, and screen and fuse important semantic association features relevant to environmental condition evaluation of the geological mineral exploration area. Therefore, the reinforced environment multi-parameter collaborative association characteristic matrixes with different sampling points can be subjected to global analysis, so that the environment conditions of a geological mineral exploration area can be more comprehensively described, and the detection and analysis of the basin bottom function conditions can be more accurately carried out.
Accordingly, in step S140, performing a joint cluster analysis on the multiple reinforced environmental multi-parameter collaborative association characterization feature matrices by using a joint cluster network to obtain a sampling point global environmental parameter collaborative characterization feature matrix as a sampling point global environmental parameter collaborative characterization feature, including: constructing an adjacency matrix and a degree matrix of the characteristic matrix of the multi-parameter collaborative association characterization of the plurality of reinforced environments; calculating a laplace matrix based on the adjacency matrix and the degree matrix; carrying out standardization processing on the Laplace matrix to obtain a standardized Laplace matrix; arranging the characteristic values of the standardized Laplace matrix from large to small, extracting the first K characteristic values, and calculating the characteristic vectors of the first K characteristic values; and normalizing the feature vectors of the first K feature values and forming a feature vector matrix by the feature vectors of the first K normalized feature values to obtain the feature matrix of the global environmental parameter collaborative characterization of the sampling points.
Wherein in one example, constructing the adjacency matrix and the degree matrix of the plurality of post-reinforcement environmental multi-parameter collaborative association characterization feature matrices comprises: calculating association weight values among the reinforced environment multi-parameter collaborative association characterization feature matrixes in the reinforced environment multi-parameter collaborative association characterization feature matrixes according to the following weight formula to obtain the adjacent matrix; wherein, the weight formula is:
Wherein, AndRespectively representing the first characteristic matrix in the multi-parameter collaborative association of the plurality of enhanced environmentsAnd (b)The characteristic matrix is characterized by the multi-parameter cooperative association of the environment after strengthening,Is the firstThe characteristic matrix and the first characteristic matrix are characterized by the multi-parameter collaborative association of the environment after strengtheningThe multi-parameter collaborative association of the environment after strengthening characterizes the variance among the feature matrices,Representing the square of the two norms,For the purpose of the exponential operation,Is the first in the adjacency matrixCharacteristic values of the location.
Wherein in one example, constructing the adjacency matrix and the degree matrix of the plurality of post-reinforcement environmental multi-parameter collaborative association characterization feature matrices comprises: the characteristic value of each position in the degree matrix is the sum of the associated weight values of all the rest of the reinforced environment multi-parameter collaborative association characteristic matrixes connected with each reinforced environment multi-parameter collaborative association characteristic matrix in the reinforced environment multi-parameter collaborative association characteristic matrixes.
Wherein, in one example, calculating a laplace matrix based on the adjacency matrix and the degree matrix comprises: calculating the laplace matrix in the following laplace formula based on the adjacency matrix and the degree matrix; wherein, the Laplace formula is:
Wherein, For the said adjacency matrix,For the degree matrix to be a function of the degree matrix,Is the laplace matrix.
Wherein in one example, the normalization processing is performed on the laplace matrix to obtain a normalized laplace matrix, which includes: carrying out standardization processing on the Laplace matrix by using the following standardization formula to obtain the standardized Laplace matrix; wherein, the standardized formula is:
Wherein, For the said adjacency matrix,For the degree matrix to be a function of the degree matrix,Is a matrix of units which is a matrix of units,And (3) the normalized Laplace matrix.
And then, the sampling point global environment parameter collaborative characterization feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the geological mineral exploration area is a sensitive area or not. That is, the global environmental state characterization features among the plurality of sampling points in the geological mineral exploration area are utilized to conduct classification processing, so that the environmental condition of the geological mineral exploration area is more comprehensively estimated, and whether the geological mineral exploration area is a sensitive area or not is judged. Therefore, the efficiency and the accuracy of geological mineral exploration can be improved, and scientific basis and decision support are provided for environmental protection.
Accordingly, in step S150, determining whether the geological mineral exploration area is a sensitive area based on the collaborative characterization feature of the global environmental parameter of the sampling point includes: and the sampling point global environment parameter collaborative characterization feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether a geological mineral exploration area is a sensitive area or not.
It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.
Further, in the technical scheme of the application, the environmental survey data processing method for geological mineral exploration further comprises a training step: the environment parameter feature extractor is used for training the environment parameter feature extractor, the joint clustering network and the classifier based on the convolutional neural network model.
Wherein, in one example, the training step comprises: training data are acquired, wherein the training data comprise training environment investigation parameters of a plurality of sampling points in a geological mineral exploration area and whether the geological mineral exploration area is a true value of a sensitive area, and the training environment investigation parameters comprise training soil data, training water quality data, training vegetation data and training gas data; training environment investigation parameters of all the sampling points are arranged into a training environment multi-parameter collaborative input matrix according to the dimension of the environment parameter sample, and then a plurality of training environment multi-parameter collaborative association characterization feature matrixes are obtained through the environment parameter feature extractor based on the convolutional neural network model; respectively carrying out feature enhancement on the multi-parameter collaborative association characteristic matrixes of the training environments by using the feature expression enhancer based on the re-parameterization layer so as to obtain multi-parameter collaborative association characteristic matrixes of the environment after the training enhancement; performing joint cluster analysis on the multiple training and strengthening environment multi-parameter collaborative association characteristic matrixes by using the joint cluster network to obtain a training sampling point global environment parameter collaborative association characteristic matrix; expanding the training sampling point global environment parameter collaborative characterization feature matrix to obtain a training sampling point global environment parameter collaborative characterization feature vector; the training sampling point global environment parameter collaborative characterization feature vector passes through the classifier to obtain a classification loss function value; and training the environmental parameter feature extractor, the joint clustering network and the classifier based on the convolutional neural network model by using the classification loss function value, wherein the training sampling point global environmental parameter collaborative characterization feature vector obtained by developing the training sampling point global environmental parameter collaborative characterization feature matrix is optimized during each iteration training of the classifier.
In the technical scheme of the application, each of the plurality of training-enhanced environment multi-parameter collaborative association characteristic matrixes expresses the re-parameterized enhancement expression of local high-order association characteristics among parameter sample dimensions of environment investigation parameters of each sampling point in the geological mineral exploration area. When the multi-parameter collaborative association characteristic matrix of the environment after training and strengthening is subjected to the joint cluster analysis based on the joint cluster network, the global environment parameter collaborative association characteristic matrix of the training and sampling points can be obtained based on joint cluster distribution of local high-order association strengthening characteristics among parameter sample dimensions of environment investigation parameters among all sampling points.
However, considering that the environmental survey parameters of the plurality of sampling points have distribution differences in a data source domain, when the global environmental parameter collaborative characterization feature matrix of the sampling points is obtained based on joint clustering of local high-order correlation enhancement features among parameter sample dimensions of the environmental survey parameters among the sampling points, the feature distribution information significance of the local high-order correlation features among the parameter sample dimensions of the local high-order correlation feature matrix after the training enhancement is affected, so that the global environmental parameter collaborative characterization feature matrix of the training sampling points has the problem of insufficient feature distribution aggregation, and the expression effect of the global environmental parameter collaborative characterization feature matrix of the training sampling points and the training speed of a model are affected. Therefore, the application optimizes the training sampling point global environment parameter collaborative characterization feature vector obtained by developing the training sampling point global environment parameter collaborative characterization feature matrix preferably during each iteration training of the classifier.
Correspondingly, in one example, during each iterative training of the classifier, the training sampling point global environment parameter collaborative characterization feature vector obtained by expanding the training sampling point global environment parameter collaborative characterization feature matrix is optimized by the following optimization formula to obtain an optimized training sampling point global environment parameter collaborative characterization feature vector; wherein, the optimization formula is:
Wherein, Is the feature vector of the global environment parameter collaborative characterization of the training sampling points,Is the first feature vector of the training sampling point global environment parameter collaborative characterization feature vectorThe characteristic value of the individual position is used,Is the feature vector of the global environmental parameter collaborative characterization of the training sampling pointsIs the square of the 1-norm of (c),Is the feature vector of the global environmental parameter collaborative characterization of the training sampling pointsThe inverse of the square root of the 2 norms of (c),Is the feature vector of the global environmental parameter collaborative characterization of the training sampling pointsAnd (2) length ofIs a scaling parameter that is used to scale the super-parameters,The logarithmic function value is represented with a base of 2,Is the third feature vector of the global environmental parameter collaborative characterization of the optimized training sampling pointCharacteristic values of the individual positions.
Here, feature vectors are characterized in synergy based on the training sample points global environmental parametersIs expressed as a feature vector cooperatively characterizing global environmental parameters of the training sampling pointsVoting clusters aggregated by feature value sets of the training sampling points and cooperatively characterizing feature vectors of global environmental parametersNormalized voting relative to the information-aware framework is performed to map feature values attributed to the same regression class to similar local normalized coordinate sets by aggregating the regression representations of the direction and scale of feature distribution, thereby promoting the training sample point global environmental parameter collaborative characterization feature vectorImproving the feature vector of the training sampling point global environment parameter collaborative characterization feature vectorAnd the classification convergence effect of the classifier is achieved, namely the classification training speed and the accuracy of classification results are improved. Therefore, the environmental conditions of the geological mineral exploration area can be comprehensively evaluated based on the collaborative association of the characteristic features of the environmental parameters of different sampling points in the geological mineral exploration area, and whether the geological mineral exploration area is a sensitive area or not is judged, so that the efficiency and the accuracy of geological mineral exploration can be improved, and scientific basis and decision support are provided for environmental protection.
In summary, the environmental survey data processing method for geological mineral exploration according to the embodiment of the application is explained, which can improve the efficiency and accuracy of geological mineral exploration.
FIG. 3 is a block diagram of an environmental survey data processing system 100 for geological mineral exploration, in accordance with an embodiment of the present application. As shown in fig. 3, an environmental survey data processing system 100 for geological mineral exploration according to an embodiment of the present application includes: a data acquisition module 110, configured to acquire environmental survey parameters of a plurality of sampling points in a geological mineral exploration area, where the environmental survey parameters include soil data, water quality data, vegetation data, and gas data; the environmental multi-parameter associated feature extraction module 120 is configured to, after arranging the environmental survey parameters of the sampling points into environmental multi-parameter collaborative input matrices according to the environmental parameter sample dimensions, respectively performing environmental multi-parameter associated feature extraction on the environmental multi-parameter collaborative input matrices of the sampling points to obtain a plurality of environmental multi-parameter collaborative associated characterization feature matrices; the feature enhancement module 130 is configured to perform feature enhancement on the multiple environmental multi-parameter collaborative association characterization feature matrices by using a feature expression enhancer based on a re-parameterization layer, so as to obtain multiple enhanced environmental multi-parameter collaborative association characterization feature matrices; the joint cluster analysis module 140 is configured to perform joint cluster analysis on the multiple enhanced environment multi-parameter collaborative association characterization feature matrices by using a joint cluster network to obtain a sampling point global environment parameter collaborative characterization feature matrix as a sampling point global environment parameter collaborative characterization feature; and a sensitivity analysis module 150, configured to determine whether the geological mineral exploration area is a sensitive area based on the collaborative characterization feature of the sampling point global environmental parameter.
Here, it will be understood by those skilled in the art that the specific functions and operations of the respective modules in the above-described environmental survey data processing system 100 for geological mineral exploration have been described in detail in the above description of the environmental survey data processing method for geological mineral exploration with reference to fig. 1 to 2, and thus, repetitive descriptions thereof will be omitted.
As described above, the environmental survey data processing system 100 for geological mineral exploration according to an embodiment of the present application may be implemented in various wireless terminals, such as a server or the like having an environmental survey data processing algorithm for geological mineral exploration. In one example, the environmental survey data processing system 100 for geological mineral exploration according to embodiments of the present application may be integrated into a wireless terminal as a software module and/or hardware module. For example, the environmental survey data processing system 100 for geological mineral exploration may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the environmental survey data processing system 100 for geological mineral exploration may equally be one of the many hardware modules of the wireless terminal.
Alternatively, in another example, the environmental survey data processing system 100 for geological mineral exploration and the wireless terminal may be separate devices, and the environmental survey data processing system 100 for geological mineral exploration may be connected to the wireless terminal through a wired and/or wireless network and communicate interactive information in accordance with agreed data formats.
Fig. 4 is an application scenario diagram of an environmental survey data processing method for geological mineral exploration according to an embodiment of the present application. As shown in fig. 4, in this application scenario, first, environmental survey parameters (e.g., D illustrated in fig. 4) of a plurality of sampling points within a geological mineral survey area are acquired, wherein the environmental survey parameters include soil data, water quality data, vegetation data, and gas data, and then, the environmental survey parameters of the respective sampling points are input to a server (e.g., S illustrated in fig. 4) where an environmental survey data processing algorithm for geological mineral survey is deployed, wherein the server can process the environmental survey parameters of the respective sampling points using the environmental survey data processing algorithm for geological mineral survey to obtain a classification result for indicating whether the geological mineral survey area is a sensitive area.
According to another aspect of the present application there is also provided a non-volatile computer readable storage medium having stored thereon computer readable instructions which when executed by a computer can perform a method as described above.
Program portions of the technology may be considered to be "products" or "articles of manufacture" in the form of executable code and/or associated data, embodied or carried out by a computer readable medium. A tangible, persistent storage medium may include any memory or storage used by a computer, processor, or similar device or related module. Such as various semiconductor memories, tape drives, disk drives, or the like, capable of providing storage functionality for software.
Furthermore, those skilled in the art will appreciate that the various aspects of the application are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The foregoing is illustrative of the present application and is not to be construed as limiting thereof. Although a few exemplary embodiments of this application have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this application. Accordingly, all such modifications are intended to be included within the scope of this application as defined in the following claims. It is to be understood that the foregoing is illustrative of the present application and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The application is defined by the claims and their equivalents.
Claims (10)
1. An environmental survey data processing method for geological mineral exploration, comprising:
Acquiring environmental investigation parameters of a plurality of sampling points in a geological mineral exploration area, wherein the environmental investigation parameters comprise soil data, water quality data, vegetation data and gas data;
After the environmental investigation parameters of the sampling points are arranged into an environmental multi-parameter collaborative input matrix according to the dimension of the environmental parameter sample, respectively extracting environmental multi-parameter association characteristics of the environmental multi-parameter collaborative input matrix of the sampling points to obtain a plurality of environmental multi-parameter collaborative association characterization characteristic matrixes;
Respectively carrying out characteristic reinforcement on the environment multi-parameter collaborative association characteristic matrixes by using a characteristic expression enhancer based on a re-parameterization layer so as to obtain the environment multi-parameter collaborative association characteristic matrixes after reinforcement;
Performing joint cluster analysis on the multiple enhanced environment multi-parameter collaborative association characterization feature matrixes by using a joint cluster network to obtain a sampling point global environment parameter collaborative characterization feature matrix serving as a sampling point global environment parameter collaborative characterization feature;
and determining whether the geological mineral exploration area is a sensitive area or not based on the global environmental parameter collaborative characterization characteristics of the sampling points.
2. The method for processing environmental survey data for geological mineral exploration according to claim 1, wherein after arranging the environmental survey parameters of the sampling points into an environmental multi-parameter collaborative input matrix according to the environmental parameter sample dimension, respectively extracting environmental multi-parameter associated features of the environmental multi-parameter collaborative input matrix of the sampling points to obtain a plurality of environmental multi-parameter collaborative associated characterization feature matrices, comprising:
And arranging the environmental investigation parameters of the sampling points into an environmental multi-parameter collaborative input matrix according to the dimension of the environmental parameter sample, and obtaining the environmental multi-parameter collaborative association characterization feature matrix through an environmental parameter feature extractor based on a convolutional neural network model.
3. The environmental survey data processing method for geological mineral exploration of claim 2, wherein the feature enhancement is performed on the plurality of environmental multi-parameter collaborative association characterization feature matrices using a feature expression enhancer based on a re-parameterized layer, respectively, to obtain a plurality of enhanced environmental multi-parameter collaborative association characterization feature matrices, comprising:
Respectively carrying out characteristic reinforcement on the plurality of environment multi-parameter collaborative association characteristic matrixes by using the characteristic expression enhancer based on the re-parameterization layer according to the following reinforcement formula so as to obtain the plurality of reinforced environment multi-parameter collaborative association characteristic matrixes; wherein, the strengthening formula is:
Wherein, For each of the plurality of environmental multi-parameter collaborative association characterization feature matrices a global average of the environmental multi-parameter collaborative association characterization feature matrices,Characterizing the variance of the feature matrix for each of the environmental multi-parameter collaborative associations,Is obtained by randomly sampling the Gaussian distribution of each environment multi-parameter cooperative association characteristic matrixThe value of the one of the values,Is the characteristic value of each position in each reinforced environment multi-parameter cooperative association characteristic matrix in the reinforced environment multi-parameter cooperative association characteristic matrices,Representing multiplication by location.
4. The environmental survey data processing method for geological mineral exploration of claim 3, wherein performing joint cluster analysis on the plurality of enhanced environmental multi-parameter collaborative correlation characterization feature matrices using a joint cluster network to obtain a sampling point global environmental parameter collaborative characterization feature matrix as a sampling point global environmental parameter collaborative characterization feature comprises:
Constructing an adjacency matrix and a degree matrix of the characteristic matrix of the multi-parameter collaborative association characterization of the plurality of reinforced environments;
calculating a laplace matrix based on the adjacency matrix and the degree matrix;
Carrying out standardization processing on the Laplace matrix to obtain a standardized Laplace matrix;
Arranging the characteristic values of the standardized Laplace matrix from large to small, extracting the first K characteristic values, and calculating the characteristic vectors of the first K characteristic values;
And normalizing the feature vectors of the first K feature values and forming a feature vector matrix by the feature vectors of the first K normalized feature values to obtain the feature matrix of the global environmental parameter collaborative characterization of the sampling point.
5. The environmental survey data processing method for geological mineral exploration of claim 4, wherein constructing the adjacency matrix and the degree matrix of the plurality of post-reinforcement environmental multi-parameter collaborative correlation characterization feature matrices comprises:
Calculating association weight values among the reinforced environment multi-parameter collaborative association characterization feature matrixes in the reinforced environment multi-parameter collaborative association characterization feature matrixes according to the following weight formula to obtain the adjacent matrix; wherein, the weight formula is:
Wherein, AndRespectively representing the first characteristic matrix in the multi-parameter collaborative association of the plurality of enhanced environmentsAnd (b)The characteristic matrix is characterized by the multi-parameter cooperative association of the environment after strengthening,Is the firstThe characteristic matrix and the first characteristic matrix are characterized by the multi-parameter collaborative association of the environment after strengtheningThe multi-parameter collaborative association of the environment after strengthening characterizes the variance among the feature matrices,Representing the square of the two norms,For the purpose of the exponential operation,Is the first in the adjacency matrixCharacteristic values of the location.
6. The environmental survey data processing method for geological mineral exploration of claim 5, wherein constructing the adjacency matrix and the degree matrix of the plurality of post-reinforcement environmental multi-parameter collaborative correlation characterization feature matrices comprises:
The characteristic value of each position in the degree matrix is the sum of the associated weight values of all the rest of the reinforced environment multi-parameter collaborative association characteristic matrixes connected with each reinforced environment multi-parameter collaborative association characteristic matrix in the reinforced environment multi-parameter collaborative association characteristic matrixes.
7. The environmental survey data processing method for geological mineral exploration of claim 6, wherein calculating a laplace matrix based on the adjacency matrix and the degree matrix comprises:
Calculating the laplace matrix in the following laplace formula based on the adjacency matrix and the degree matrix; wherein, the Laplace formula is:
Wherein, For the said adjacency matrix,For the degree matrix to be a function of the degree matrix,Is the laplace matrix.
8. The environmental survey data processing method for geological mineral exploration of claim 7, wherein normalizing the laplace matrix to obtain a normalized laplace matrix comprises:
Carrying out standardization processing on the Laplace matrix by using the following standardization formula to obtain the standardized Laplace matrix; wherein, the standardized formula is:
Wherein, For the said adjacency matrix,For the degree matrix to be a function of the degree matrix,Is a matrix of units which is a matrix of units,And (3) the normalized Laplace matrix.
9. The environmental survey data processing method for geological mineral exploration of claim 8, wherein determining whether a geological mineral exploration area is a sensitive area based on the sample point global environmental parameter collaborative characterization feature comprises:
and the sampling point global environment parameter collaborative characterization feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether a geological mineral exploration area is a sensitive area or not.
10. The environmental survey data processing method for geological mineral exploration of claim 9, further comprising the training step of: the environment parameter feature extractor is used for training the environment parameter feature extractor, the joint clustering network and the classifier based on the convolutional neural network model;
wherein the training step comprises:
Training data are acquired, wherein the training data comprise training environment investigation parameters of a plurality of sampling points in a geological mineral exploration area and whether the geological mineral exploration area is a true value of a sensitive area, and the training environment investigation parameters comprise training soil data, training water quality data, training vegetation data and training gas data;
Training environment investigation parameters of all the sampling points are arranged into a training environment multi-parameter collaborative input matrix according to the dimension of the environment parameter sample, and then a plurality of training environment multi-parameter collaborative association characterization feature matrixes are obtained through the environment parameter feature extractor based on the convolutional neural network model;
Respectively carrying out feature enhancement on the multi-parameter collaborative association characteristic matrixes of the training environments by using the feature expression enhancer based on the re-parameterization layer so as to obtain multi-parameter collaborative association characteristic matrixes of the environment after the training enhancement;
Performing joint cluster analysis on the multiple training and strengthening environment multi-parameter collaborative association characteristic matrixes by using the joint cluster network to obtain a training sampling point global environment parameter collaborative association characteristic matrix;
Expanding the training sampling point global environment parameter collaborative characterization feature matrix to obtain a training sampling point global environment parameter collaborative characterization feature vector;
the training sampling point global environment parameter collaborative characterization feature vector passes through the classifier to obtain a classification loss function value;
And training the environmental parameter feature extractor, the joint clustering network and the classifier based on the convolutional neural network model by using the classification loss function value, wherein the training sampling point global environmental parameter collaborative characterization feature vector obtained by expanding the training sampling point global environmental parameter collaborative characterization feature matrix is optimized during each iteration training of the classifier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410267760.2A CN118395223B (en) | 2024-03-08 | 2024-03-08 | Environment investigation data processing method for geological mineral exploration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410267760.2A CN118395223B (en) | 2024-03-08 | 2024-03-08 | Environment investigation data processing method for geological mineral exploration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118395223A true CN118395223A (en) | 2024-07-26 |
| CN118395223B CN118395223B (en) | 2024-10-01 |
Family
ID=91996819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410267760.2A Active CN118395223B (en) | 2024-03-08 | 2024-03-08 | Environment investigation data processing method for geological mineral exploration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118395223B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119029843A (en) * | 2024-07-31 | 2024-11-26 | 国网河南省电力公司漯河供电公司 | A method for planning intelligent power grid construction |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150006212A1 (en) * | 2010-04-01 | 2015-01-01 | Tony W. Covely | Soil Sample Tracking System and Method |
| CN117037432A (en) * | 2023-10-08 | 2023-11-10 | 四川省公路规划勘察设计研究院有限公司 | Risk evaluation geological disaster early warning method based on multi-method cooperation |
-
2024
- 2024-03-08 CN CN202410267760.2A patent/CN118395223B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150006212A1 (en) * | 2010-04-01 | 2015-01-01 | Tony W. Covely | Soil Sample Tracking System and Method |
| CN117037432A (en) * | 2023-10-08 | 2023-11-10 | 四川省公路规划勘察设计研究院有限公司 | Risk evaluation geological disaster early warning method based on multi-method cooperation |
Non-Patent Citations (2)
| Title |
|---|
| MARCO CONCIATORI 等: "Importance of multi-parameter approaches in the development of Machine Learning algorithms for landslide displacement forecasting", 《CONFERENCE: GEOENV 2022 - 14TH INTERNATIONAL CONFERENCE ON GEOSTATISTICS FOR ENVIRONMENTAL APPLICATIONS》, 30 June 2022 (2022-06-30), pages 1 - 2 * |
| 尹婧博: "生态脆弱区乡村聚落空间布局优化研究 ——以吉林省西部地区为例", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》, no. 12, 15 December 2023 (2023-12-15), pages 038 - 27 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119029843A (en) * | 2024-07-31 | 2024-11-26 | 国网河南省电力公司漯河供电公司 | A method for planning intelligent power grid construction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118395223B (en) | 2024-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109583468B (en) | Training sample acquisition method, sample prediction method and corresponding device | |
| CN117475236B (en) | Data processing system and method for mineral resource exploration | |
| González et al. | Validation methods for plankton image classification systems | |
| CN110472675A (en) | Image classification method, image classification device, storage medium and electronic equipment | |
| CN113988226B (en) | Data desensitization validity verification method and device, computer equipment and storage medium | |
| CN112115996B (en) | Image data processing method, device, equipment and storage medium | |
| CN118210664A (en) | Chip testing equipment and control method of chip testing equipment | |
| CN116451139A (en) | Live broadcast data rapid analysis method based on artificial intelligence | |
| US12066910B2 (en) | Reinforcement learning based group testing | |
| CN118395223B (en) | Environment investigation data processing method for geological mineral exploration | |
| CN117134958B (en) | Information processing method and system for network technology service | |
| Wiwaha et al. | Enhancing rainfall prediction accuracy through XGBoost model with data balancing techniques | |
| CN116707859B (en) | Feature rule extraction method and apparatus, network intrusion detection method and apparatus | |
| CN115567224B (en) | Method for detecting abnormal block chain transaction and related product | |
| CN116721441A (en) | Access control security management method and system based on blockchain | |
| CN112766387A (en) | Error correction method, device, equipment and storage medium for training data | |
| CN112348750A (en) | SAR image change detection method based on threshold fusion and neighborhood voting | |
| CN119442104B (en) | Causally driven counterfactual data generation and its application method, device and storage medium in anomaly detection | |
| CN119272055A (en) | Vehicle window anti-mis-pinch method, device, electronic equipment and storage medium | |
| CN113052604A (en) | Object detection method, device, equipment and storage medium | |
| CN119441059A (en) | Test case priority sorting method, device, electronic device and readable storage medium | |
| CN118333988A (en) | Defect detection method and system based on difference enhancement and adaptive meta-learning | |
| CN113743464B (en) | Continuous characteristic discretization loss information compensation method and application thereof | |
| CN117953200A (en) | A target detection method, device, equipment and medium | |
| US20230041338A1 (en) | Graph data processing method, device, and computer program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |