Metallization prediction method and system fusing fractal representation engineering

Abstract

The invention belongs to the technical field of metallogenic prediction, and discloses a metallogenic prediction method fusing fractal representation engineering. The invention aims to provide a metallogenic prediction method fusing fractal representation engineering, which is characterized in that original data is processed through fractal analysis and feature selection, nonlinear metallogenic information of a data set is highlighted, an optimal feature subset is screened out, and an optimized data set is obtained. Through prediction of the data set, the prediction precision of the artificial intelligence model is improved, a prediction result which is more accurate than that of a traditional method is finally obtained, the labor and economic cost of exploration is reduced, the exploration risk is reduced, and then the metallogenic prediction method which is more scientific, more reliable and more efficient is provided. The method is suitable for metallogenic prediction work of various artificial intelligence models. The invention further provides an implementation method of the fractal representation engineering.

Description

Technical Field

[0001] The present invention belongs to the technical field of mineralization prediction, and in particular relates to a mineralization prediction method and system integrating fractal characterization engineering. Background Art

[0002] Mineral resources are an important material basis for economic and social development. With the advancement of urbanization and industrialization, the demand for mineral resources is increasing, and it is particularly important to find new mineral prospecting areas. In addition, mineral exploration is characterized by high costs and high risks. How to obtain more accurate mineral prospecting targets has become a problem that needs to be solved urgently. Mineral resource potential evaluation maps can quantify and draw the probability of discovering mineral deposits through exploration in the study area. At present, artificial intelligence-driven mineral resource potential evaluation has become an increasingly accepted important tool for delineating mineral exploration targets. However, due to the inherent complexity and noise of the geological characteristics used in mineral resource potential evaluation, the application of artificial intelligence models in actual exploration is subject to certain limitations.

[0003] The mineralization prediction method technology integrated with fractal characterization engineering can mine potential nonlinear mineralization information from the original features, search for the optimal feature subset of the input data set, and meet the current high-precision requirements in mineral resource exploration.

[0004] Limitations of traditional algorithms: Existing AI-driven mineral resource potential evaluation usually only performs simple preprocessing on the original data set, which will largely miss the potential nonlinear mineralization information in the original features and make it difficult to search for the optimal feature subset from the input data set, resulting in deviations in the final prediction results, missing potential mineralization areas or exaggerating areas with low mineralization potential, causing inconvenience to actual exploration work.

[0005] Through the above analysis, the problems and defects of the prior art are as follows:

[0006] Existing AI-driven mineral resource potential evaluation usually only performs simple preprocessing on the original data set, which will largely miss the potential nonlinear mineralization information in the original features and make it difficult to search for the optimal feature subset from the input data set, resulting in deviations in the final prediction results, missing potential mineralization areas or exaggerating areas with low mineralization potential, causing inconvenience to actual exploration work. Summary of the invention

[0007] In view of the problems existing in the prior art, the present invention provides a mineralization prediction method integrating fractal characterization engineering.

[0008] The present invention is implemented in this way: a mineralization prediction method integrating fractal characterization engineering comprises:

[0009] S1, obtain the mineralization prediction data set and perform preprocessing;

[0010] Obtain a mineralization prediction dataset; the dataset contains labels, sample point coordinates, and sample features, covering various favorable mineralization factors;

[0011] S2, fractal analysis and feature selection of the data set;

[0012] Construct a mineralization prediction framework integrating fractal characterization engineering;

[0013] S3, model training and optimization;

[0014] After completing fractal analysis and feature selection, select the prediction model, train the model, and find the optimal parameter combination to further improve the model's adaptability and prediction accuracy;

[0015] S4, model predictions;

[0016] The trained and optimized mineralization prediction model can be used to predict the mineralization probability in the study area and assist in delineating the prospecting target area;

[0017] S5, result output and evaluation.

[0018] Further, the mineralization prediction data set is obtained and preprocessed:

[0019] (a) Denoising: Geological features are inherently complex and noisy, so the collected data often contain some noisy data, and it is necessary to process missing values, duplicate items, etc. in the data;

[0020] (b) Data normalization: To ensure the subsequent prediction effect, the data is normalized.

[0021] Further, the data set is subjected to fractal analysis and feature selection:

[0022] (1) Fractal and multifractal analysis: The box dimension method is used to describe the fractal characteristics of the mineral points, and then the Fry analysis is used to interpret the fractal results to enhance the subtle morphology of the mineral occurrence; the spatial correlation between these occurrences and geological characteristics is characterized to mine the mineralization distribution pattern; the sliding window technology is used to process the evidence layer of the original features to assist in capturing the local features within the massive prediction units, and multifractal analysis is performed to obtain the fractal representation of the original features;

[0023] (2) Feature selection: Based on fractal processing, a variety of feature selection methods are used for analysis. The analysis results of various methods are combined to obtain the best combination of fractal indicator features and construct a fractal index feature data set for model prediction. The specific feature selection methods used are: prediction-area chart, K-means clustering, information gain, chi-square test and Pearson correlation coefficient.

[0024] Further, the model training and optimization:

[0025] (a) Select prediction model: With the rapid development of artificial intelligence algorithms, many excellent artificial intelligence algorithms have emerged. The models commonly used for mineralization prediction include artificial neural networks, random forests, support vector machines, and convolutional neural networks;

[0026] (b) Model training and optimization: The optimal parameter combination is found by using the random grid search method and the ten-fold cross-validation method to further improve the prediction ability of the model. In addition, in order to minimize the impact of randomness, the data set should be randomly selected multiple times to form different training sets for separate training, and the final average value is taken as the result.

[0027] Furthermore, the model predicts:

[0028] (a) Processing the prediction data set: The prediction data set should contain feature columns, coordinates and mineral point label information; by preprocessing the prediction data, the prediction data set is fractally characterized;

[0029] (b) Input prediction data: Input the processed data to be predicted into the prediction model trained with different training sets, and make predictions respectively. The model will make predictions based on the sample characteristics, and the final prediction results will be averaged;

[0030] (c) Quantitative analysis: The model outputs the mineralization probability of each sample point, and combines the success rate curve with the uncertainty scatter plot to screen out high-potential areas for mineralization and low-risk exploration areas.

[0031] Further, the result output and evaluation:

[0032] (a) Draw a mineral resource potential evaluation map: Combine the model prediction results with the delineated high-potential mineralization areas and low-risk exploration areas to obtain a mineral resource potential evaluation map and delineate the prospecting target areas;

[0033] (b) Result evaluation: The evaluation indicators and feature importance of the output model are combined with existing exploration experience and mineralization research to evaluate the prediction results of the model to facilitate subsequent geological research and mineral exploration work.

[0034] Another object of the present invention is to provide a mineralization prediction system integrating fractal characterization engineering, comprising:

[0035] A preprocessing module is used to obtain and preprocess the mineralization prediction data set; obtain the mineralization prediction data set; the data set contains labels, sample point coordinates and sample features, covering various favorable mineralization factors;

[0036] Feature selection module, used to perform fractal analysis and feature selection on data sets; to build a mineralization prediction framework integrating fractal characterization engineering;

[0037] The optimization module is used for model training and optimization. After completing fractal analysis and feature selection, the prediction model is selected, the model is trained, and the optimal parameter combination is found to further improve the model's adaptability and prediction accuracy.

[0038] Prediction module, used for model prediction; the trained and optimized mineralization prediction model can be used to predict the mineralization probability in the study area and assist in delineating the prospecting target area;

[0039] Evaluation module, used for result output and evaluation.

[0040] Another object of the present invention is to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the mineralization prediction method integrating fractal characterization engineering.

[0041] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to execute the steps of the mineralization prediction method integrating fractal characterization engineering.

[0042] Another object of the present invention is to provide an information data processing terminal, which is used to implement the mineralization prediction system that integrates fractal characterization engineering.

[0043] In combination with the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solutions to be protected by the present invention are as follows:

[0044] First, the purpose of the present invention is to provide a mineralization prediction method integrating fractal characterization engineering, which is characterized in that the original data is processed by fractal analysis and feature selection, the nonlinear mineralization information of the data set is highlighted, the optimal feature subset is screened out, and the optimized data set is obtained. Prediction is performed through this data set to improve the prediction accuracy of the artificial intelligence model, and ultimately obtain more accurate prediction results than traditional methods, reduce the manpower and economic costs of exploration, reduce exploration risks, and thus provide a more scientific, more reliable, and more efficient mineralization prediction method. It is suitable for mineralization prediction work of various artificial intelligence models. Further provide an implementation method of the fractal characterization engineering.

[0045] The present invention provides a mineralization prediction method integrating fractal characterization engineering, which is characterized in that original data are processed through fractal analysis and feature selection, nonlinear mineralization information of a data set is highlighted, an optimal feature subset is screened out, and an optimized data set is obtained.

[0046] Second, the technical solution of the present invention solves the technical problem that people have been eager to solve but have never succeeded: a lot of mineralization geological information is indirect information, that is, it is necessary to effectively extract and interpret the original data to obtain information that is beneficial to mineralization prediction. The effectiveness of information extraction and interpretation will directly affect the accuracy of mineralization prediction. The geological information related to mineralization is the product of the coupling of multiple fields and processes such as mechanical deformation, thermodynamics, fluid flow, temperature change, etc., and has undergone a long geological evolution with millions of years as the basic unit, so it has significant complexity and nonlinearity. Cracking the complexity and nonlinearity of mineralization geological information and improving the effectiveness of information extraction and interpretation has always been a difficult problem in the field of mineralization prediction, and it is also a prerequisite for efficient mineralization prediction. In response to this problem, the present invention uses fractal measurement as a tool to characterize the complexity and nonlinearity of mineralization geological information, accurately tracks and captures the trace feature information left by the mineralization process, and improves the interpretation accuracy of mineralization geological information and the accuracy of mineralization prediction.

[0047] Third, the mineralization prediction method of the present invention significantly improves the accuracy and efficiency of mineralization prediction in industrial applications by integrating fractal characterization engineering with mineralization prediction models, solves the limitations of prediction methods in the prior art, and achieves significant technological progress.

[0048] 1. Solved the problem of insufficient accuracy in mineralization prediction

[0049] In traditional mineralization prediction methods, it is often difficult to accurately describe the multi-scale characteristics of geological data, resulting in insufficient prediction accuracy. The present invention adopts fractal characterization engineering to identify the multi-scale characteristics of data and extract important favorable factors for mineralization. Fractal analysis improves the expression ability of data characteristics, optimizes the input data of the model, effectively enhances the accuracy of mineralization prediction, and makes the delineation of mineralization target areas more accurate.

[0050] 2. Improved the efficiency of data processing and feature selection

[0051] The present invention introduces feature selection technology in the data preprocessing stage, removes redundant information through fractal analysis, and extracts key mineralization factors. Compared with the existing technical methods, this technical means simplifies the data processing process, significantly reduces the computational complexity, improves the efficiency of the model, makes the prediction process faster and more efficient, and adapts to the needs of larger-scale mineralization data processing.

[0052] 3. Enhanced the adaptability and stability of the model

[0053] The present invention constructs a mineralization prediction model with high stability and adaptability through multiple training and parameter optimization of the model. Compared with the prediction model of the traditional single algorithm, the method of the present invention can maintain high prediction accuracy in a variety of geological environments, provide support for the diversity of mining areas, and significantly improve adaptability and stability.

[0054] 4. Reduced prospecting costs and exploration risks

[0055] Traditional prospecting usually requires a lot of manpower and material resources, and due to high uncertainty, it is easy to waste costs by blindly exploring. This invention helps the geological team to effectively delineate the mineralization target area through efficient prediction of mineralization probability, avoiding unnecessary waste of resources, thereby greatly reducing exploration costs and risks, and providing efficient auxiliary decision-making support for the mining industry.

[0056] 5. Provides visual mineralization prediction results

[0057] The present invention outputs the prediction results into a mineralization probability map, and provides users with intuitive mineralization distribution information in combination with prediction evaluation indicators. This visualization method not only facilitates the understanding and application of the results, but also provides a reliable reference for decision-makers, further improving the practicality of the prediction method in actual industrial applications.

[0058] In summary, the mineralization prediction method of the present invention solves the problems of low precision, complexity and high cost of traditional mineralization prediction. Through innovative means such as data feature extraction, model optimization and fractal analysis, it has achieved significant technological progress and provided efficient, accurate and practical technical support for mining exploration. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a flow chart of a mineralization prediction method integrating fractal characterization engineering provided by an embodiment of the present invention.

[0060] Figure 2 It is a flow chart of a method for fractal analysis and feature selection of a data set provided by an embodiment of the present invention.

[0061] Figure 3 It is a structural block diagram of a mineralization prediction system integrating fractal characterization engineering provided by an embodiment of the present invention.

[0062] Figure 4 It is a comparison chart of the comprehensive performance of the model of the fusion fractal characterization engineering and the traditional method provided by the embodiment of the present invention.

[0063] Figure 5 It is a comparison diagram of mineralization prospects of the fusion fractal characterization engineering and the traditional method provided by the embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0065] like Figure 1 As shown, a mineralization prediction method integrating fractal characterization engineering provided by an embodiment of the present invention comprises the following steps:

[0066] S1, obtain the mineralization prediction data set and perform preprocessing;

[0067] Obtain a mineralization prediction dataset; the dataset contains labels, sample point coordinates, and sample features, covering various favorable mineralization factors;

[0068] S2, fractal analysis and feature selection of the data set;

[0069] Construct a mineralization prediction framework integrating fractal characterization engineering;

[0070] S3, model training and optimization;

[0071] After completing fractal analysis and feature selection, select the prediction model, train the model, and find the optimal parameter combination to further improve the model's adaptability and prediction accuracy;

[0072] S4, model predictions;

[0073] The trained and optimized mineralization prediction model can be used to predict the mineralization probability in the study area and assist in delineating the prospecting target area;

[0074] S5, result output and evaluation.

[0075] In the process of mineralization prediction, data acquisition and preprocessing are important basic steps. The mineralization prediction data set includes labels, sample point coordinates, and sample characteristics of various mineralization favorable factors. First, relevant data are collected through geological exploration, remote sensing and other means to form a comprehensive data set containing mineralization conditions and characteristics. The preprocessing steps include data cleaning, normalization, and processing of missing values, so as to ensure the integrity and consistency of the data and provide high-quality data input for subsequent steps.

[0076] Fractal analysis is an effective method for describing complex geological phenomena and can identify multi-scale features in data sets. By constructing a fractal characterization project, important geological features in sample data are identified, and redundant information is removed through feature selection to extract the most favorable features for mineralization prediction. The combination of fractal analysis and feature selection enables the mineralization prediction framework to not only handle the complexity of data, but also improve the efficiency and accuracy of the prediction model.

[0077] After completing fractal analysis and feature selection, the next step is to build and train the model. Using the selected important features, select a suitable mineralization prediction model (such as neural network, random forest, etc.), and tune the model parameters. Through multiple training and testing, the model parameters are continuously adjusted to find the optimal parameter combination, so that the model can better adapt to the data characteristics and further improve the model's adaptability and prediction accuracy.

[0078] The trained and optimized model is used to predict the mineralization probability of the research area. New regional geological data is input into the model, and the model outputs the mineralization possibility of the area. This step helps geologists effectively delineate the prospecting target area, and to a certain extent reduces the blindness and cost of exploration, and provides a more accurate mineralization probability distribution map.

[0079] The prediction results are output as mineralization probability maps through visualization tools, and the results are evaluated. The actual prospecting data of the mineralization target area is compared with the model prediction results to evaluate the prediction effect of the model. The performance of the model is evaluated through indicators such as accuracy, recall rate and F1 score, and the degree of consistency between the analysis results and the actual situation is verified to verify the prediction reliability and stability of the model.

[0080] According to the evaluation feedback of the prediction results, the model is further improved, the details of fractal representation and feature selection are adjusted, or more complex algorithms are introduced to improve the adaptability of the model. Such a circular feedback mechanism makes the model closer to the real geological mineralization environment in the continuous optimization, and enhances the practical application effect of the mineralization prediction method.

[0081] The embodiment of the present invention provides obtaining a mineralization prediction data set and performing preprocessing:

[0082] Obtain a mineralization prediction data set; the data set contains labels, sample point coordinates, and sample characteristics (such as geological characteristics, geophysical characteristics, geochemical characteristics, etc.), covering various favorable mineralization factors; in order to improve the prediction accuracy of the model, the obtained mineralization prediction data needs to be preprocessed; the preprocessing operation includes the following:

[0083] (a) Denoising: Geological features are inherently complex and noisy, so the collected data often contain some noisy data. It is necessary to process missing values ​​and duplicates in the data to ensure the integrity and reliability of the data;

[0084] (b) Data normalization: To ensure the subsequent prediction effect, the data is normalized, which can improve the prediction efficiency and the prediction accuracy of the model to a certain extent;

[0085] The processed mineralization prediction data set is obtained through preprocessing, providing data guarantee for subsequent model training and prediction.

[0086] like Figure 2 As shown, the fractal analysis and feature selection of the data set provided by the embodiment of the present invention are as follows:

[0087] The core of the present invention is to construct a mineralization prediction framework integrating fractal characterization engineering; the specific steps are as follows:

[0088] S201, Fractal and Multifractal Analysis:

[0089] The box dimension method is used to describe the fractal characteristics of the mineral points, and then the Fry analysis is used to interpret the fractal results to enhance the subtle morphology of the mineral occurrence; the spatial correlation between these occurrences and geological characteristics is portrayed to mine the mineralization distribution pattern; the sliding window technology is used to process the evidence layer of the original features to assist in capturing the local features within the massive prediction units, and multiple fractal analysis is performed to obtain the fractal representation of the original features;

[0090] S202, feature selection:

[0091] On the basis of fractal processing, a variety of feature selection methods are used for analysis. Combining the analysis results of various methods, the best combination of fractal index features is obtained, and a fractal index feature data set is constructed for model prediction. The specific feature selection methods used are: prediction-area chart, K-means clustering, information gain, chi-square test and Pearson correlation coefficient, etc.

[0092] By combining fractal analysis with feature selection, potential nonlinear mineralization information in the original features of the data set is further mined, and the optimal feature subset of the input data set is constructed; through the fractal characterization method, the present invention can effectively improve the accuracy of mineralization prediction.

[0093] Model training and optimization provided by the embodiments of the present invention:

[0094] After completing fractal analysis and feature selection, select the prediction model, train the model, and find the optimal parameter combination to further improve the adaptability and prediction accuracy of the model. The specific process is as follows:

[0095] (a) Select prediction model: With the rapid development of artificial intelligence algorithms, many excellent artificial intelligence algorithms have emerged. The models commonly used for mineralization prediction include artificial neural networks, random forests, support vector machines, and convolutional neural networks;

[0096] (b) Model training and optimization: The optimal parameter combination is found by using the random grid search method and the ten-fold cross validation method to further improve the prediction ability of the model. In addition, in order to minimize the impact of randomness, the data set should be randomly selected multiple times to form different training sets for training respectively, and the average value is finally taken as the result to improve the credibility of the final prediction.

[0097] Through the above model training and optimization steps, a well-trained mineralization prediction model is obtained, and it is adapted to the mineralization prediction task of a given fractal characterization data set.

[0098] The model provided by the embodiment of the present invention predicts:

[0099] The trained and optimized mineralization prediction model can be used to predict the mineralization probability in the study area and assist in delineating the prospecting target area; the specific steps are as follows:

[0100] (a) Processing the prediction data set: The prediction data set should contain information such as feature columns, coordinates and mineral point labels (optional); preprocess the prediction data using the method in step 1 above, and perform fractal characterization on the prediction data set using the method in step 2 (1);

[0101] (b) Input prediction data: Input the processed data to be predicted into the prediction model trained with different training sets, and make predictions respectively. The model will make predictions based on the sample characteristics, and the final prediction results will be averaged;

[0102] (c) Quantitative analysis: The model outputs the mineralization probability of each sample point, and combines the success rate curve with the uncertainty scatter plot to screen out high potential areas for mineralization and low risk exploration areas;

[0103] Through the above steps, this technology can realize the mineralization prediction work in a certain area and finally output the mineralization probability distribution map in the area.

[0104] Result output and evaluation provided by the embodiment of the present invention:

[0105] (a) Draw a mineral resource potential evaluation map: Combine the model prediction results with the delineated high-potential mineralization areas and low-risk exploration areas to obtain a mineral resource potential evaluation map and delineate the prospecting target areas;

[0106] (b) Result evaluation: The evaluation indicators and feature importance of the output model are combined with existing exploration experience and mineralization research to evaluate the prediction results of the model to facilitate subsequent geological research and mineral exploration work.

[0107] like Figure 3 As shown, a mineralization prediction system integrating fractal characterization engineering provided by an embodiment of the present invention includes:

[0108] A preprocessing module is used to obtain and preprocess the mineralization prediction data set; obtain the mineralization prediction data set; the data set contains labels, sample point coordinates and sample features, covering various favorable mineralization factors;

[0109] Feature selection module, used to perform fractal analysis and feature selection on data sets; to build a mineralization prediction framework integrating fractal characterization engineering;

[0110] The optimization module is used for model training and optimization. After completing fractal analysis and feature selection, the prediction model is selected, the model is trained, and the optimal parameter combination is found to further improve the model's adaptability and prediction accuracy.

[0111] Prediction module, used for model prediction; the trained and optimized mineralization prediction model can be used to predict the mineralization probability in the study area and assist in delineating the prospecting target area;

[0112] Evaluation module, used for result output and evaluation.

[0113] Another object of the present invention is to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the mineralization prediction method integrating fractal characterization engineering.

[0114] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to execute the steps of the mineralization prediction method integrating fractal characterization engineering.

[0115] Another object of the present invention is to provide an information data processing terminal, which is used to implement the mineralization prediction system that integrates fractal characterization engineering.

[0116] The present invention is specifically implemented:

[0117] Example 1

[0118] (1) Obtain mineralization prediction dataset.

[0119] Obtain a mineralization prediction data set, which may include various favorable mineralization factors, such as geological features, geophysical features, and geochemical features that are favorable to mineralization. Samples include three types: mineral points, non-mineral points, and samples to be predicted.

[0120] Preprocessing steps: (a) Denoising: First, clean the data set and process the noisy data to ensure the accuracy of model training and prediction. (b) Data normalization: Normalize the data to accelerate the learning process of the model, improve accuracy, and weaken the impact of outliers.

[0121] (2) Perform fractal characterization on the data set.

[0122] The box dimension method is used to describe the fractal characteristics of mineral points and non-mineral points in the training set, and Fry analysis is used to interpret the fractal results, enhance the subtle morphology of mineral occurrences, and characterize the spatial correlation between these occurrences and geological characteristics. The sliding window is used to process the original evidence layer to better capture the local characteristics within the prediction unit.

[0123] The specific process of sliding window to obtain data is as follows: (a) Cover the feature under study with a grid with a side length of m, and slide a window with a side length of m from left to right and from bottom to top. (b) Set the lower left corner of the feature map as the starting position, and slide the window to the focus position in the upper right corner of the image.

[0124] After acquiring data through the sliding window, the multifractal spectrum is estimated by combining the moment method, and then the fractal dimension, singularity index and other parameters are obtained to perform fractal characterization on the original features.

[0125] The prediction-area chart, K-means clustering, information gain, chi-square test and Pearson correlation coefficient are used in turn for feature selection. The results obtained by different methods are ranked jointly to finally obtain the best combination of fractal indicator features and complete the fractal characterization of the data set.

[0126] (3) Model training and optimization.

[0127] (a) Training process:

[0128] The fractal representation data set is used to train the artificial intelligence model and find the optimal parameters to improve its accuracy and reliability in mineralization prediction. The specific steps of the training are as follows:

[0129] In the data set represented by fractals, negative samples with the same number as positive samples are randomly selected and divided into training set and test set in a ratio of 7:3, and positive and negative samples are evenly distributed in the training set and test set in a ratio of 1:1.

[0130] Set the corresponding hyperparameters according to the selected artificial intelligence model.

[0131] The random grid search method is combined with ten-fold cross validation to search for the optimal parameter combination and improve the prediction accuracy of the model.

[0132] (b) Model optimization:

[0133] In order to minimize the impact of randomness, the random splitting process of the data set was performed 10 times to generate ten training data sets. The model was trained on the ten data sets respectively to improve the reliability of the model.

[0134] (4) Model prediction

[0135] For model prediction, the prediction data should be input into different models trained by ten training data sets for prediction, and the final prediction results and model evaluation indicators are the average of the results of five models. The average mineralization probability distribution map in the study area was obtained, and the mineralization area was briefly divided.

[0136] (5) Evaluation of mineral resource potential.

[0137] (a) Differentiate different mineralization potential areas: draw a success rate curve of the prediction results, and divide the high potential area, medium potential area, low potential area and background area into different areas according to the slope of the curve.

[0138] (b) Delineation of prospecting target areas: By combining the uncertainty scatter plot with the high mineralization potential areas delineated in (a), high-potential, low-risk exploration areas are delineated as prospecting target areas.

[0139] (c) Result evaluation: Based on the existing mineralization theory and exploration experience, the model prediction results and various evaluation indicators are evaluated to determine the reliability of the prediction results.

[0140] The generated results include the target area mineralization prediction results and potential mineralization areas, and display the mineralization prediction distribution map of the target area. This technology is widely applicable to multiple fields such as mineral resource exploration and ore deposit evaluation, providing a more reliable, scientific and efficient mineralization prediction method. The above are only specific embodiments of the present invention, but the technical features of the present invention are not limited to this.

[0141] The present invention is specifically applied to the technical field of mineralization prediction, and in particular relates to a mineralization prediction method and system integrating fractal characterization engineering.

[0142] The following are relevant achievements obtained by the embodiments of the present invention.

[0143] The comprehensive performance of the model predicted by the fractal representation dataset and the original dataset is as follows Figure 4 As shown, Figure 4 The evaluation indicators of (a), (b), and (c) are the prediction efficiency, accuracy, and Kappa coefficient of the model, respectively. The prediction efficiency is used to evaluate the results from the perspective of actual exploration, and the accuracy and Kappa coefficient are used to measure the classification accuracy from the algorithm perspective. It can be seen intuitively that the prediction efficiency, prediction accuracy, and Kappa coefficient of all artificial intelligence models are higher in the same model when trained with the fractal representation dataset than in the model trained with the original dataset.

[0144] The final mineralization prospect map generated by each artificial intelligence model is shown in Figure 5 ,in Figure 5 (a), (c) 、 (e) 、(g) are the prediction results of the fractal representation data set in different artificial intelligence models (artificial neural network, random forest, decision tree, logistic regression), and (b), (d), (f), and (h) are the prediction results of the original data set in different artificial intelligence models. It can intuitively indicate the high potential mineralization areas in the study area.

[0145] Combination Figure 4 and Figure 5 , taking the prediction efficiency of the artificial neural network model as an example for analysis. The prediction efficiency of the artificial neural network model trained with the original data set is 8.6723, and 70.34% of the known mineral points are captured through the 9% high mineralization potential area, while the prediction efficiency of the artificial neural network model trained with fractal characterization is 9.3785, and 78.81% of the known mineral points are successfully captured in the 9% high mineralization potential area, achieving the highest prediction efficiency, which is significantly higher than the training effect of the original data set. Figure 4 (b) and (c) show that the artificial neural network model trained with the fractal representation data set is also higher than the artificial neural network model trained with the original data set in terms of accuracy and Kappa coefficient. This intuitively reflects the superiority of fractal representation engineering in improving exploration efficiency and model classification accuracy.

[0146] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. It can be understood by a person of ordinary skill in the art that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0147] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principle of the present invention should be covered by the protection scope of the present invention.

Claims

1. A mineralization prediction method integrating fractal characterization engineering, characterized in that: The following steps are involved: S1, obtain the mineralization prediction data set and perform preprocessing; Obtain a mineralization prediction dataset; the dataset contains labels, sample point coordinates, and sample features, covering various favorable mineralization factors; S2, fractal analysis and feature selection of the data set; Construct a mineralization prediction framework integrating fractal characterization engineering; S3, model training and optimization; After completing fractal analysis and feature selection, select the prediction model, train the model, and find the optimal parameter combination to further improve the model's adaptability and prediction accuracy; S4, model predictions; The trained and optimized mineralization prediction model can be used to predict the mineralization probability in the study area and assist in delineating the prospecting target area; S5, result output and evaluation.

2. The mineralization prediction method integrating fractal characterization engineering as claimed in claim 1, characterized in that: The mineralization prediction data set is obtained and preprocessed: (a) Denoising: Geological features are inherently complex and noisy, so the collected data often contain some noisy data, and it is necessary to process missing values, duplicate items, etc. in the data; (b) Data normalization: To ensure the subsequent prediction effect, the data is normalized.

3. The mineralization prediction method integrating fractal characterization engineering as claimed in claim 1, characterized in that: The fractal analysis and feature selection of the data set are as follows: (1) Fractal and multifractal analysis: The box dimension method is used to describe the fractal characteristics of the mineral points, and then the Fry analysis is used to interpret the fractal results to enhance the subtle morphology of the mineral occurrence; the spatial correlation between these occurrences and geological characteristics is characterized to mine the mineralization distribution pattern; the sliding window technology is used to process the evidence layer of the original features to assist in capturing the local features within the massive prediction units, and multifractal analysis is performed to obtain the fractal representation of the original features; (2) Feature selection: Based on fractal processing, a variety of feature selection methods are used for analysis. The analysis results of various methods are combined to obtain the best combination of fractal indicator features and construct a fractal index feature data set for model prediction. The specific feature selection methods used are: prediction-area chart, K-means clustering, information gain, chi-square test and Pearson correlation coefficient.

4. The mineralization prediction method integrating fractal characterization engineering as claimed in claim 1, characterized in that: The model training and optimization: (a) Select prediction model: With the rapid development of artificial intelligence algorithms, many excellent artificial intelligence algorithms have emerged. The models commonly used for mineralization prediction include artificial neural networks, random forests, support vector machines, and convolutional neural networks; (b) Model training and optimization: The optimal parameter combination is found by using the random grid search method and the ten-fold cross-validation method to further improve the prediction ability of the model. In addition, in order to minimize the impact of randomness, the data set should be randomly selected multiple times to form different training sets for separate training, and the final average value is taken as the result.

5. The mineralization prediction method integrating fractal characterization engineering as claimed in claim 1, characterized in that: The model predicts: (a) Processing the prediction data set: The prediction data set should contain feature columns, coordinates and mineral point label information; by preprocessing the prediction data, the prediction data set is fractally characterized; (b) Input prediction data: Input the processed data to be predicted into the prediction model trained with different training sets, and make predictions respectively. The model will make predictions based on the sample characteristics, and the final prediction results will be averaged; (c) Quantitative analysis: The model outputs the mineralization probability of each sample point, and combines the success rate curve with the uncertainty scatter plot to screen out high-potential areas for mineralization and low-risk exploration areas.

6. The mineralization prediction method integrating fractal characterization engineering as claimed in claim 1, characterized in that: The result output and evaluation: (a) Draw a mineral resource potential evaluation map: Combine the model prediction results with the delineated high-potential mineralization areas and low-risk exploration areas to obtain a mineral resource potential evaluation map and delineate the prospecting target areas; (b) Result evaluation: The evaluation indicators and feature importance of the output model are combined with existing exploration experience and mineralization research to evaluate the prediction results of the model to facilitate subsequent geological research and mineral exploration work.

7. A mineralization prediction system integrating fractal characterization engineering and implementing the mineralization prediction method integrating fractal characterization engineering as claimed in any one of claims 1 to 6, characterized in that: The mineralization prediction system integrating fractal characterization engineering includes: A preprocessing module is used to obtain and preprocess the mineralization prediction data set; obtain the mineralization prediction data set; the data set contains labels, sample point coordinates and sample features, covering various favorable mineralization factors; Feature selection module, used to perform fractal analysis and feature selection on data sets; to build a mineralization prediction framework integrating fractal characterization engineering; The optimization module is used for model training and optimization. After completing fractal analysis and feature selection, the prediction model is selected, the model is trained, and the optimal parameter combination is found to further improve the model's adaptability and prediction accuracy. Prediction module, used for model prediction; the trained and optimized mineralization prediction model can be used to predict the mineralization probability in the study area and assist in delineating the prospecting target area; Evaluation module, used for result output and evaluation.

8. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the mineralization prediction method integrating fractal characterization engineering as described in any one of claims 1-6.

9. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the mineralization prediction method integrating fractal characterization engineering as described in any one of claims 1 to 6.

10. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the mineralization prediction system integrating fractal characterization engineering as described in claim 7.

Images