CN118759600A - A prospecting prediction method suitable for tectonic altered rock type gold deposits - Google Patents

Abstract

The invention relates to the technical field of mining area detection, in particular to a prospecting prediction method suitable for constructing a changed rock-type gold mine, which comprises the steps of determining a mineral forming condition based on a mineral forming geological body and construction characteristics; constructing a three-dimensional space model of the mining area based on the fused data; positioning a mineralized area by utilizing a three-dimensional space model; calculating the ore content of the body by using a trend extrapolation method, and finishing quantitative estimation of the positioned mining area; according to the invention, geological, geophysical and geochemical data are integrated into the three-dimensional space model, so that the positioning accuracy of the mineralized area is improved; the mineral reserve can be estimated quantitatively by utilizing trend extrapolation and bulk ore content calculation, and reliable prediction is provided for ore distribution; and the rich ore section and the lean ore section are identified in a sectional manner along the tilting direction, so that the exploration target area is effectively determined, and the resource allocation is optimized.

Description

A prospecting prediction method suitable for tectonic altered rock type gold deposits

Technical Field

The invention relates to the technical field of mining area detection, and in particular to a prospecting prediction method suitable for tectonic altered rock type gold deposits.

Background Art

Gold mines are important mineral resources, and their mining is of great significance to the national and local economies. Accurately predicting the location and scale of gold mines can improve the efficiency and success rate of resource development. By predicting the distribution of gold mines, mineral resources can be better planned and managed, reducing blind mining and resource waste. Understanding the location and scale of ore bodies helps to formulate scientific mining plans, reduce the impact on the environment, and reduce environmental pollution and damage risks;

At present, prospecting and prediction of tectonic altered rock type gold deposits faces the following challenges:

Data may be insufficient in some areas, particularly remote or inaccessible areas, which can affect accurate predictions of ore bodies;

It is a challenge to effectively integrate geological, geophysical, chemical and remote sensing data, and data from different techniques may need to be converted and corrected;

The geological structure may be very complex. For example, the overlap of faults and folds increases the difficulty of ore body prediction. Tectonic activity and deformation may change the location and morphology of the original mineralized body, and the impact of tectonic evolution needs to be considered.

Summary of the invention

In view of the above-mentioned problems, the present invention is proposed.

In order to solve the above technical problems, the present invention provides the following technical solutions: a prospecting prediction method applicable to tectonic altered rock type gold deposits, comprising the following steps:

Determine the mineralization conditions based on the mineralization geological bodies and structural characteristics, including:

The multi-source data fusion algorithm is used to realize the fusion of ore body data and to perform feature analysis on the fused data information, specifically:

Analyze the fused data layer by layer, calculate the reduced dimension feature matrix, and perform weighted combination based on the calculated reduced dimension feature matrix;

Construct a 3D spatial model of the mining area based on the fused data, including:

The fused data is converted into three-dimensional geographic coordinates using a geographic transformation algorithm, and a spatial network is generated based on the three-dimensional geographic coordinates, specifically:

The clustering algorithm is used to intelligently identify data density, dynamically adjust spatial network nodes, calculate the Euclidean distance between nodes to determine the edges of the network space, and finally construct weighted edges based on the differences in node characteristics;

Use 3D spatial models to locate areas where mineralization exists, including:

The current mineralized area is segmented and the mining area is located by analyzing the extension of the ore body along the dip direction, specifically:

Calculate the thickness T and gold grade G of the current mining area, and use the thickness and strike data of the ore body to analyze the changes in the ore body along the dip direction. Finally, use the GIS tool to draw a target area map, predict the prospecting location, and use the actual exploration data to complete the determination of the target area.

By applying the trend extrapolation method to calculate the body mineral content, a quantitative estimate of the located mining area can be completed.

As a preferred solution of the prospecting prediction method for tectonic altered rock type gold deposits described in the present invention, the fusion of ore body data is achieved by using a multi-source data fusion algorithm, which is specifically as follows:

By integrating remote sensing data, seismic data and geological data, we can obtain:

F＝ _w1 ·R+ _w2 ·S+ _w3 ·G

Among them, w ₁ , w ₂ , and w ₃ represent the weight coefficients of remote sensing data, seismic data, and geological data, respectively, and satisfy the formula w ₁ +w ₂ +w ₃ =1. R represents the collected remote sensing data, which is collected through satellite remote sensing technology. S represents seismic data, which is collected based on the database. G represents geological data, which is collected through on-site rock and mineral sampling by geologists.

As a preferred solution of the prospecting prediction method for tectonic altered rock type gold deposits described in the present invention, wherein: the feature analysis of the fused data information is performed, then,

According to the fused data F, it is divided into three layers based on remote sensing data, seismic data and geological data. The principal component analysis is performed on each layer of data, and then,

_Zi ＝ _Fi ′· _Wi

Fi _′ ＝ _Fi -μ

Wherein, Fi _′ represents the centralized data in the i-th layer data, _Wi represents the eigenvector matrix of the i-th layer, _Fi represents the i-th layer data of the fused data F, i＝1,2,...,n represents the index layer number of the fused data, representing remote sensing data, seismic data and geological data respectively, μ represents the mean of the fused data, and _Zi represents the dimension reduction feature matrix of the i-th layer;

According to the calculated dimensionality reduction feature matrix, the data is weighted and combined to complete the feature analysis of the data information, then we have:

Among them, w _i represents the weight coefficient of the i-th layer of data, and satisfies the formula w ₁ +w ₂ +w ₃ +....+ _wn =1, _Zi represents the dimensionality reduction feature matrix of the i-th layer, and Z represents the feature matrix after weighted combination, which is used to complete the feature analysis of data information and then determine the mineralization conditions.

As a preferred solution of the prospecting prediction method for tectonic altered rock type gold deposits described in the present invention, the geographic conversion algorithm is specifically implemented as follows:

The fused data F is converted into the corresponding three-dimensional geographic coordinates F(x, y, z) using the geographic conversion algorithm, and then a spatial network is generated based on the converted three-dimensional geographic coordinates. Then,

Using data points in three-dimensional geographic coordinates as network nodes (x _i , y _i , z _i ) of the spatial network;

Before the spatial network nodes are generated, clustering algorithms are used to automatically identify potential threats in dense data areas.

C _k ={F(x _i ,y _i ,z _i )|argmin _j ||F(x _i ,y _i ,z _i )-μ _j }

Among them, F( _xi , _yi , _zi ) represents the three-dimensional geographic coordinates of the i-th data point, _μj represents the j-th cluster center, and _Ck represents the k-th cluster center. By calculating the cluster center, the dense area of the data is automatically identified and the node connection is dynamically adjusted.

As a preferred solution of the prospecting prediction method for tectonic altered rock type gold deposits described in the present invention, the spatial network generated according to the three-dimensional geographic coordinates is specifically constructed as follows:

Once the network nodes are determined, the Euclidean distance between the nodes is calculated, and then,

Among them, (x _i ,y _i , _zi ) and (x _j ,y _j ,z _j ) represent the coordinates of the i-th and j-th nodes respectively, and d _ij represents the Euclidean distance between two nodes;

According to the calculated Euclidean distance, the edges of the spatial network are determined, then,

When the calculated Euclidean distance satisfies the formula d _ij ≥ α·std(d _ij ), it means that an edge needs to be established between the current two nodes;

Among them, α represents the adjustment coefficient, which is set by the implementer according to the actual application conditions, and std(d _ij ) represents the standard deviation of the Euclidean distance between two nodes;

Using the difference in node features to construct weighted edges, we have:

w _ij (t) = w _ij × (1 + f (t))

d＝d _ij ·wi _ij (t)

Among them, _fi and _fj represent the node eigenvalues, which are determined by the feature matrix in the fused data, β represents the characteristic coefficient, which is set by the implementers according to the actual application scenario, f(t) represents the time function, which is used to reflect the changing trend of data with time series, w _ij represents the edge weight between two nodes, w _ij (t) represents the edge weight between two nodes under the action of the time function, _dij represents the Euclidean distance between two nodes, d represents the edge length between two nodes in the spatial network, and when the edges between all nodes are constructed, it means that the spatial network of the current mining area is generated, and then the generated spatial networks are combined to form a three-dimensional spatial model.

As a preferred solution of the prospecting prediction method for tectonic altered rock type gold deposits described in the present invention, the regional segmentation of the current mineralized area is specifically implemented as follows:

The mining area data is applied to the three-dimensional spatial model to calculate the thickness T, gold grade G and the product T×G of the current mining area. At the same time, the rich ore section threshold K _F , the poor ore section threshold K _P and the mineralized section threshold K are set as follows:

When the product of the thickness of the mining area and the gold grade satisfies the formula T× _G≥KF , it means that the current mineralized area is a rich ore section;

When the product of the thickness of the mining area and the gold grade satisfies the formula T× _G≤KP , it means that the current mineralized area is a lean ore section.

When the product of the thickness and gold grade of the mining area satisfies the formula _KP <T×G< _KF , it means that the current mineralized area is a mineralized area.

As a preferred solution of the prospecting prediction method for tectonic altered rock type gold deposits described in the present invention, wherein: the calculation of the body ore content by applying the trend extrapolation method is to calculate the body ore content by constructing a trend line equation, and the specific calculation is as follows:

Using the thickness T and gold grade G data of the current mining area, we can construct a trend line equation:

y＝k·X+b

Among them, X represents the location variable of the current mining area, k and b represent the slope and intercept of the trend line equation respectively, and y represents the predicted mineralization parameters, including the thickness and gold grade of the mining area;

Using the predicted mineralization parameters, the body ore content of the mining area is calculated, and then,

Where R represents the calculated volume mineralization rate, _Ti represents the thickness of the ith block, _Gi represents the gold grade of the ith block, and _Vi represents the volume of the ith block.

Beneficial effects of the present invention: The present invention improves the accuracy of mineralized area positioning by integrating geological, geophysical and geochemical data into a three-dimensional spatial model; utilizes trend extrapolation and volume ore content calculation to quantitatively estimate mineral reserves and provide reliable predictions for ore distribution; identifies rich ore sections and poor ore sections in sections along the inclination direction, effectively determines exploration targets, and optimizes resource allocation.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

FIG1 is a schematic diagram of the overall method steps of a prospecting prediction method applicable to tectonic altered rock type gold deposits of the present invention.

FIG2 is a schematic diagram of the overall composition structure of a prospecting prediction system suitable for tectonic altered rock type gold deposits according to the present invention.

DETAILED DESCRIPTION

In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

Meanwhile, in the description of the present invention, it should be noted that the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

Example 1

1, which is a first embodiment of the present invention, provides a prospecting prediction method applicable to tectonic altered rock type gold deposits, comprising the following steps:

S1: Determine the mineralization conditions based on the mineralization geological bodies and structural characteristics.

Specifically, the determination of mineralization conditions based on mineralization geological bodies and structural characteristics is achieved by integrating multi-source data information, analyzing the mineralization geological bodies and structural characteristics, and then determining the mineralization conditions. The integration of multi-source data information is achieved by integrating remote sensing data, seismic data and geological data, and analyzing the characteristics of the integrated data to achieve the determination of mineralization conditions.

Furthermore, the integration of multi-source data information is to use the multi-source data fusion algorithm to fuse remote sensing data, seismic data and geological data, and to determine the mineralization conditions by performing feature analysis on the fused data information, as follows:

By integrating remote sensing data, seismic data and geological data, we can obtain:

F＝ _w1 ·R+ _w2 ·S+ _w3 ·G

Among them, w ₁ , w ₂ , w ₃ represent the weight coefficients of remote sensing data, seismic data and geological data respectively, and satisfy the formula w ₁ +w ₂ +w ₃ =1, R represents the collected remote sensing data, which is collected through satellite remote sensing technology, S represents seismic data, which is collected based on the database, and G represents geological data, which is collected through on-site rock and mineral sampling by geologists;

Performing feature analysis on the fused data information, we have:

According to the fused data F, it is divided into three layers based on remote sensing data, seismic data and geological data. The principal component analysis is performed on each layer of data, and then,

_Zi ＝ _Fi ′· _Wi

Fi _′ ＝ _Fi -μ

Wherein, Fi _′ represents the centralized data in the i-th layer data, _Wi represents the eigenvector matrix of the i-th layer, _Fi represents the i-th layer data of the fused data F, i＝1,2,...,n represents the index layer number of the fused data, representing remote sensing data, seismic data and geological data respectively, μ represents the mean of the fused data, and _Zi represents the dimension reduction feature matrix of the i-th layer;

According to the calculated dimensionality reduction feature matrix, the data is weighted and combined to complete the feature analysis of the data information, then we have:

Among them, w _i represents the weight coefficient of the i-th layer of data, and satisfies the formula w ₁ +w ₂ +w ₃ +....+ _wn =1, _Zi represents the dimensionality reduction feature matrix of the i-th layer, and Z represents the feature matrix after weighted combination, which is used to complete the feature analysis of data information and then determine the mineralization conditions.

S2: Construct a three-dimensional spatial model of the mining area based on the fused data.

Specifically, constructing a three-dimensional spatial model of the mining area based on the fused data is to convert the data into a three-dimensional spatial model data format, generate a spatial network, and construct a three-dimensional spatial model based on the generated spatial network to determine the spatial distribution and morphology of the ore body, thereby extracting data for the subsequent positioning of the mining area.

Furthermore, the data is converted into a three-dimensional spatial model data format by using a geographic conversion algorithm to convert the fused data F into corresponding three-dimensional geographic coordinates F (x, y, z), and then a spatial network is generated based on the converted three-dimensional geographic coordinates. Then,

Using data points in three-dimensional geographic coordinates as network nodes (x _i , y _i , z _i ) of the spatial network;

Before the spatial network nodes are generated, clustering algorithms are used to automatically identify potential threats in dense data areas to improve the intelligence of the network structure.

C _k ={F(x _i ,y _i ,z _i )|argmin _j ||F(x _i ,y _i ,z _i )-μ _j }

Among them, F( _xi , _yi , _zi ) represents the three-dimensional geographic coordinates of the i-th data point, _μj represents the j-th cluster center, and _Ck represents the k-th cluster center. Through the calculated cluster centers, the dense areas of data are automatically identified and the node connections are dynamically adjusted;

Once the network nodes are determined, the Euclidean distance between the nodes is calculated, and then,

Among them, (x _i ,y _i , _zi ) and (x _j ,y _j ,z _j ) represent the coordinates of the i-th and j-th nodes respectively, and d _ij represents the Euclidean distance between two nodes;

According to the calculated Euclidean distance, the edges of the spatial network are determined, then,

When the calculated Euclidean distance satisfies the formula d _ij ≥ α·std(d _ij ), it means that an edge needs to be established between the current two nodes;

Among them, α represents the adjustment coefficient, which is set by the implementer according to the actual application conditions, and std(d _ij ) represents the standard deviation of the Euclidean distance between two nodes;

Using the difference in node features to construct weighted edges, we have:

w _ij (t) = w _ij × (1 + f (t))

d＝d _ij ·wi _ij (t)

Among them, _fi and _fj represent the node eigenvalues, which are determined by the feature matrix in the fused data, β represents the characteristic coefficient, which is set by the implementers according to the actual application scenario, f(t) represents the time function, which is used to reflect the changing trend of data with time series, w _ij represents the edge weight between two nodes, w _ij (t) represents the edge weight between two nodes under the action of the time function, _dij represents the Euclidean distance between two nodes, d represents the edge length between two nodes in the spatial network, and when the edges between all nodes are constructed, it means that the spatial network of the current mining area is generated, and then the generated spatial networks are combined to form a three-dimensional spatial model.

Furthermore, the spatial distribution and morphology of the ore body are determined by using the generated three-dimensional spatial model, as follows:

Using the generated three-dimensional spatial model, the three-dimensional shape of the ore body is displayed on the terminal device through volume rendering technology;

At the same time, the boundary of the current ore body is identified using isosurface technology;

Based on the determined boundaries and ore body morphology, and according to the current application scenario, the implementer selects the cross section of the ore body for feature analysis, and then completes the distribution of the ore body at different levels;

Finally, the model parameters are adjusted to improve accuracy, and historical data are used to verify the model to ensure the accuracy of the analyzed ore body distribution.

S3: Use three-dimensional spatial models to locate areas where mineralization exists.

Specifically, the use of a three-dimensional space model to locate a mineralized area is to use the three-dimensional space model to analyze the geological features related to the mineralization in the model, and to accurately locate the mineralized area based on the comparison between the geological features and the mineralization threshold.

Furthermore, the use of the three-dimensional spatial model to analyze the geological characteristics related to mineralization in the model is to apply the mining area data to the three-dimensional spatial model, calculate the thickness T, gold grade G and the product T×G of the current mining area, and set the rich ore section threshold K _F , the poor ore section threshold K _P and the mineralized section threshold K, as follows:

When the product of the thickness of the mining area and the gold grade satisfies the formula T× _G≥KF , it means that the current mineralized area is a rich ore section;

When the product of the thickness of the mining area and the gold grade satisfies the formula T× _G≤KP , it means that the current mineralized area is a lean ore section.

When the product of the thickness and gold grade of the mining area satisfies the formula _KP <T×G< _KF , it means that the current mineralized area is a mineralized area.

It should be noted that the thickness of the current mining area is calculated using the drill hole spacing and core length in the exploration data, as follows:

Where L represents the vertical length of the core and θ represents the inclination angle;

The current gold grade of the mine is calculated based on the gold content analysis of ore samples, as follows:

Among them, _Wore represents the total weight of the ore sample, and _Wgold represents the weight of gold in the sample.

Furthermore, accurate positioning of the mineralized area is achieved by analyzing the changes in the ore body along the inclination direction, and using the geological model to perform inclination analysis to determine the extension of the ore body along the inclination direction. According to the mineralized area and the inclination direction, the prospecting target area is determined, and the exploration data is combined to optimize the positioning of the mining area.

Specifically, the extension of the ore body along the inclination direction is determined by using the thickness and strike data of the ore body to analyze the changes of the ore body along the inclination direction, as follows:

D＝(x,y)＝(L·cos(φ),L·sin(φ))

L＝T·cos(θ)

Among them, (x, y) represents the horizontal coordinate, D represents the displacement of the ore body on the horizontal plane, L represents the vertical length of the core, θ represents the dip angle, φ represents the strike data, and T represents the thickness of the current mining area;

The positioning of the target area is based on the calculated extension of the ore body along the inclination direction, and the mineralized area and inclination direction are mapped using GIS tools to predict the prospecting location. At the same time, the actual exploration data is used to complete the determination of the target area, thereby achieving accurate positioning of the mining area.

S4: Calculate the volume mineralization rate by applying the trend extrapolation method to complete the quantitative estimation of the located mining area.

Specifically, the calculation of the body mineralization rate by applying the trend extrapolation method is to calculate the body mineralization rate by constructing a trend line equation, and the specific calculation is as follows:

Using the thickness T and gold grade G data of the current mining area, we can construct a trend line equation:

y＝k·X+b

Among them, X represents the location variable of the current mining area, k and b represent the slope and intercept of the trend line equation respectively, and y represents the predicted mineralization parameters, including the thickness and gold grade of the mining area;

Using the predicted mineralization parameters, the body ore content of the mining area is calculated, and then,

Where R represents the calculated volume mineralization rate, _Ti represents the thickness of the ith block, _Gi represents the gold grade of the ith block, and _Vi represents the volume of the ith block.

It should be noted that in order to further improve the accuracy of the trend line equation, the trend line equation is optimized and verified by using the historical data of the mining area. The slope and intercept of the linear equation are adjusted through the input historical data to ensure the accuracy of the calculated volume ore content of the mining area.

Example 2

2 , which is a second embodiment of the present invention, provides a prospecting prediction system suitable for tectonic altered rock type gold deposits, including a mineralization condition determination module, a three-dimensional space model construction module, a mineralized area positioning module and a mining area quantitative estimation module;

Specifically, the mineralization condition determination module is used to determine the mineralization conditions based on the mineralization geological body and structural characteristics; the three-dimensional space model construction module is used to construct a three-dimensional space model of the mining area based on the fused data; the mineralized area positioning module is used to use the three-dimensional space model to locate the area where mineralization exists; the mining area quantitative estimation module calculates the body ore content by applying the trend extrapolation method to complete the quantitative estimation of the located mining area.

Furthermore, the mineralization condition determination module is the foundation of the system. It first collects and analyzes multi-source information such as geological exploration data, remote sensing images, geophysical exploration data, and historical mining records in the target area. This information is comprehensively analyzed through advanced data processing algorithms (such as machine learning, data mining, etc.) to identify potential mineralization geological bodies (such as lithology, structural belts, magmatic activity, etc.) and mineralization structural features (such as faults, folds, alteration zones, etc.). By comparing the geological characteristics of known gold mining areas, the module can determine whether the target area has similar mineralization conditions, and then screen out high-potential mineralization areas;

The three-dimensional spatial model construction module, based on the output results of the mineralization condition determination module, will integrate geological exploration data, topographic data, groundwater level data and other multi-dimensional information, and use three-dimensional modeling software (such as ArcG I S, GOCAD, etc.) to construct a detailed three-dimensional spatial model of the mining area. This model not only includes the morphological characteristics of the surface, but also goes deep underground to show the three-dimensional distribution of key geological elements such as rock structure, fracture system, and alteration zone. Through visualization technology, researchers can intuitively view and analyze the geological structure of the mining area, providing an accurate spatial framework for the subsequent positioning of the mineralized area;

The mineralized area positioning module uses a three-dimensional spatial model, combined with geostatistical methods and geophysical inversion technology, to accurately locate potential mineralized areas. By simulating the migration, precipitation and enrichment of ore fluids, this module can predict the spatial distribution of ore bodies. At the same time, remote sensing technology and ground survey data are used to identify information such as altered mineral assemblages and geochemical anomalies related to mineralization, further narrowing the scope of the mineralized area. Finally, through comprehensive analysis and multi-source information fusion, the specific location and scale of the mineralized area are determined;

The mining area quantitative estimation module uses trend extrapolation and other statistical prediction methods (such as Kriging interpolation, geostatistical simulation, etc.) to make quantitative estimates of the located mining areas based on the positioning of the mineralized areas. This module first collects parameter data such as grade, thickness, and morphology of known ore bodies in the mining area to establish a mathematical model of the ore body characteristics. Then, the model is extrapolated to the entire mineralized area, the body mineral content (that is, the content of useful minerals in a unit volume of rock) is calculated, and the total resources of the mining area are estimated accordingly. In addition, this module also takes into account geological uncertainty factors and conducts a probabilistic assessment of resource quantities, providing a reliable basis for resource assessment for mine development.

It should be noted that through the close cooperation and mutual influence of the above four modules, the system can realize the comprehensive prospecting prediction of altered rock type gold deposits and provide strong technical support for gold mine exploration and development.

Furthermore, if the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

The logic and/or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

It should be understood that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but for those of ordinary skill having the benefit of this disclosure, the development effort will be a routine task of design, fabrication, and production without undue experimentation.

It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims (7)

1. A prospecting prediction method applicable to tectonic altered rock type gold deposits, characterized in that it comprises the following steps: Determine the mineralization conditions based on the mineralization geological bodies and structural characteristics, including: The multi-source data fusion algorithm is used to realize the fusion of ore body data and to perform feature analysis on the fused data information, specifically: Analyze the fused data layer by layer, calculate the reduced dimension feature matrix, and perform weighted combination based on the calculated reduced dimension feature matrix; Construct a 3D spatial model of the mining area based on the fused data, including: The fused data is converted into three-dimensional geographic coordinates, and a spatial network is generated according to the three-dimensional geographic coordinates, specifically: The clustering algorithm is used to intelligently identify data density, dynamically adjust spatial network nodes, calculate the Euclidean distance between nodes to determine the edges of the network space, and finally construct weighted edges based on the differences in node characteristics; Use 3D spatial models to locate areas where mineralization exists, including: The current mineralized area is segmented and the mining area is located by analyzing the extension of the ore body along the dip direction, specifically: Calculate the thickness T and gold grade G of the current mining area, and use the thickness and strike data of the ore body to analyze the changes in the ore body along the inclination direction, draw a target area map, predict the prospecting location, and use the actual exploration data to complete the determination of the target area; By applying the trend extrapolation method to calculate the body mineral content, a quantitative estimate of the located mining area can be completed. 2. A prospecting prediction method for tectonic altered rock type gold deposits as claimed in claim 1, characterized in that: the fusion of ore body data is achieved by using a multi-source data fusion algorithm, specifically as follows: By integrating remote sensing data, seismic data and geological data, we can obtain: F＝ _w1 ·R+ _w2 ·S+ _w3 ·G Among them, w ₁ , w ₂ , and w ₃ represent the weight coefficients of remote sensing data, seismic data, and geological data, respectively, and satisfy the formula w ₁ +w ₂ +w ₃ =1. R represents the collected remote sensing data, which is collected through satellite remote sensing technology. S represents seismic data, which is collected based on the database. G represents geological data, which is collected through on-site rock and mineral sampling by geologists. 3. A prospecting prediction method for tectonic altered rock type gold deposits as claimed in claim 2, characterized in that: the feature analysis of the fused data information is performed, and then, According to the fused data F, it is divided into three layers based on remote sensing data, seismic data and geological data. The principal component analysis is performed on each layer of data, and then, _Zi ＝ _Fi ′· _Wi Fi _′ ＝ _Fi -μ Wherein, Fi _′ represents the centralized data in the i-th layer data, _Wi represents the eigenvector matrix of the i-th layer, _Fi represents the i-th layer data of the fused data F, i＝1,2,...,n represents the index layer number of the fused data, representing remote sensing data, seismic data and geological data respectively, μ represents the mean of the fused data, and _Zi represents the dimension reduction feature matrix of the i-th layer; According to the calculated dimensionality reduction feature matrix, the data is weighted and combined to complete the feature analysis of the data information, then we have: Among them, w _i represents the weight coefficient of the i-th layer of data, and satisfies the formula w ₁ +w ₂ +w ₃ +....+ _wn =1, _Zi represents the dimensionality reduction feature matrix of the i-th layer, and Z represents the feature matrix after weighted combination, which is used to complete the feature analysis of data information and then determine the mineralization conditions. 4. A prospecting prediction method for tectonic altered rock type gold deposits as claimed in claim 3, characterized in that: the conversion of the fused data into three-dimensional geographic coordinates is specifically implemented as follows: The fused data F is converted into the corresponding three-dimensional geographic coordinates F(x, y, z) using the geographic conversion algorithm, and then a spatial network is generated based on the converted three-dimensional geographic coordinates. Then, Using data points in three-dimensional geographic coordinates as network nodes (x _i , y _i , z _i ) of the spatial network; Before the spatial network nodes are generated, clustering algorithms are used to automatically identify potential threats in dense data areas. C _k ={F(x _i ,y _i ,z _i )|argmin _j ||F(x _i ,y _i ,z _i )-μ _j } Among them, F( _xi , _yi , _zi ) represents the three-dimensional geographic coordinates of the i-th data point, _μj represents the j-th cluster center, and _Ck represents the k-th cluster center. By calculating the cluster center, the dense area of the data is automatically identified and the node connection is dynamically adjusted. 5. A prospecting prediction method for tectonic altered rock type gold deposits as claimed in claim 4, characterized in that: the spatial network generated according to the three-dimensional geographic coordinates is specifically constructed as follows: Once the network nodes are determined, the Euclidean distance between the nodes is calculated, and then, Among them, (x _i ,y _i , _zi ) and (x _j ,y _j ,z _j ) represent the coordinates of the i-th and j-th nodes respectively, and d _ij represents the Euclidean distance between two nodes; According to the calculated Euclidean distance, the edges of the spatial network are determined, then, When the calculated Euclidean distance satisfies the formula d _ij ≥ α·std(d _ij ), it means that an edge needs to be established between the current two nodes; Among them, α represents the adjustment coefficient, which is set by the implementer according to the actual application conditions, and std(d _ij ) represents the standard deviation of the Euclidean distance between two nodes; Using the difference in node features to construct weighted edges, we have: w _ij (t) = w _ij × (1 + f (t)) d＝d _ij ·wi _ij (t) Among them, _fi and _fj represent the node eigenvalues, which are determined by the feature matrix in the fused data, β represents the characteristic coefficient, which is set by the implementers according to the actual application scenario, f(t) represents the time function, which is used to reflect the changing trend of data with time series, w _ij represents the edge weight between two nodes, w _ij (t) represents the edge weight between two nodes under the action of the time function, _dij represents the Euclidean distance between two nodes, d represents the edge length between two nodes in the spatial network, and when the edges between all nodes are constructed, it means that the spatial network of the current mining area is generated, and then the generated spatial networks are combined to form a three-dimensional spatial model. 6. A prospecting prediction method applicable to tectonic altered rock type gold deposits as claimed in claim 5, characterized in that: the regional segmentation of the current mineralized area is specifically implemented as follows: The mining area data is applied to the three-dimensional spatial model to calculate the thickness T, gold grade G and the product T×G of the current mining area. At the same time, the rich ore section threshold K _F , the poor ore section threshold K _P and the mineralized section threshold K are set as follows: When the product of the thickness of the mining area and the gold grade satisfies the formula T× _G≥KF , it means that the current mineralized area is a rich ore section; When the product of the thickness of the mining area and the gold grade satisfies the formula T× _G≤KP , it means that the current mineralized area is a lean ore section. When the product of the thickness and gold grade of the mining area satisfies the formula _KP <T×G< _KF , it means that the current mineralized area is a mineralized area. 7. A prospecting prediction method applicable to tectonic altered rock type gold deposits as claimed in claim 6, characterized in that: the calculation of the body ore content by applying the trend extrapolation method is to calculate the body ore content by constructing a trend line equation, and the specific calculation is as follows: Using the thickness T and gold grade G data of the current mining area, we can construct a trend line equation: y＝k·X+b Among them, X represents the location variable of the current mining area, k and b represent the slope and intercept of the trend line equation respectively, and y represents the predicted mineralization parameters, including the thickness and gold grade of the mining area; Using the predicted mineralization parameters, the body ore content of the mining area is calculated, and then, Where R represents the calculated volume mineralization rate, _Ti represents the thickness of the ith block, _Gi represents the gold grade of the ith block, and _Vi represents the volume of the ith block.