A method for analyzing gemstone output and ore-forming conditions

Abstract

This application discloses a method for analyzing the occurrence and mineralization conditions of gemstones, relating to the fields of mineral exploration and mineral spectroscopic analysis. The method includes: graded sampling of primary and secondary ore deposits; high-pressure sealed digestion and elemental analysis to obtain the content of target elements; calculation of chemical mineralization indicators and establishment of a spectral and diffraction spectrum library, extracting characteristic peak area ratios as spectroscopic modeling variables; acquisition of cathodoluminescence images and spectra and determination of intensity ratios; integration of chemical mineralization indicators, spectroscopic modeling variables, cathodoluminescence intensity ratios, and regional geological variables into a target feature vector; modeling a mineralization analysis model based on machine learning models and interpretation algorithms; outputting a mineralization probability index and classifying it according to thresholds. This application improves the accuracy and efficiency of gemstone mineralization condition identification and prospective / target area determination by fusing multi-source geological, geochemical, and spectroscopic information and using machine learning modeling.

Description

Technical Field

[0001] This application relates to the field of mineral exploration and mineral spectroscopic analysis technology, and in particular to a method for analyzing the occurrence and mineralization conditions of gemstones. Background Technology

[0002] Gemstone mineralization is controlled by a combination of factors, including material sources, temperature and pressure conditions, fluid activity, and subsequent alteration, resulting in uneven spatial distribution and scattered indicators. Traditional prospecting relies mainly on regional geological surveys, mineralogical identification, and geochemical anomaly interpretation, but identification of concealed ore bodies, low-grade dispersed mineralization, and complex metamorphic-hydrothermal systems is challenging. While the development of high-throughput elemental analysis, Raman / infrared / XRD / catholuminescence spectroscopic techniques, and machine learning has provided a data and methodological foundation for mineralization prediction, key issues such as standardized fusion of multi-source data, quantitative feature extraction, and interpretable modeling urgently need to be addressed.

[0003] Existing methods include structural-lithofacies interpretation and target delineation, conventional geochemical measurements and anomaly threshold criteria, single spectroscopic / diffraction characterization for mineral facies and genetic indication, statistical discriminant mapping and principal component / discriminant analysis, and machine learning-based mineral exploration integrating multiple geological layers (such as RF, SVM, GBDT, etc.). Their main shortcomings are: fragmented sampling of primary and secondary mineralization leading to incomplete mineralization information; heterogeneity and dimensional inconsistencies among multi-source data making fusion difficult; and the lack of quantitative indicators in spectroscopic and diffraction methods, making coupling with chemical data challenging. These deficiencies limit the accurate identification and prospective evaluation of mineralization conditions in complex contexts.

[0004] The information disclosed in this background section is included only to enhance the understanding of the context of this disclosure, and therefore may contain information that does not constitute relevant technology currently known to those skilled in the art. Summary of the Invention

[0005] This application provides a method for analyzing the occurrence and mineralization conditions of gemstones, in order to solve the problems of inconsistent data standards, incomparable feature systems, difficulty in integrating regional and location information, and incomplete reconstruction of mineralization processes in existing technologies.

[0006] The technical solution adopted in this application is as follows:

[0007] Firstly, this application provides a method for analyzing the occurrence and mineralization conditions of gemstones, including:

[0008] Primary sampling of primary gemstone deposits and secondary sampling of secondary gemstone deposits were performed in the target area to obtain the target sample.

[0009] The target sample is subjected to high-pressure closed digestion and elemental analysis to determine the content of the target element in the target sample;

[0010] Chemical mineralization indicators were calculated based on the content of target elements, and a library of spectral and diffraction spectra was established.

[0011] Extract the ratio of characteristic peak areas from the spectral and diffraction spectrum library, and use the ratio of characteristic peak areas as a spectroscopic modeling variable;

[0012] Under preset conditions, acquire the cathodoluminescence image and cathodoluminescence spectrum of the target sample, and determine the cathodoluminescence intensity ratio based on the cathodoluminescence image and cathodoluminescence spectrum;

[0013] Chemical mineralization indicators, spectroscopic typographic variables, cathodoluminescence intensity ratio, and regional geological variables are integrated into a target feature vector with a preset dimension. The mineralization analysis model is then obtained by modeling based on a machine learning model, a preset interpretation algorithm, and the target feature vector. Among them, the regional geological variables are obtained by fusing regional geological surveys, geophysical exploration, well logging, and remote sensing inversion, and by combining mineral thermobarometer and fluid inclusion data.

[0014] The mineralization probability index is obtained based on the mineralization analysis model, and the classification is determined according to the mineralization probability index and the preset threshold.

[0015] This application establishes a mineralization probability evaluation system by standardizing and fusing multi-source data and using feature engineering, in conjunction with an interpretable machine learning model, thereby achieving quantitative assessment and grading of gemstone mineralization in the target area.

[0016] In conjunction with the first aspect, in one alternative implementation, primary sampling of the primary mineral deposits of gemstones is performed in the target area, including:

[0017] In the target area, primary mineral deposits of gemstones are sampled in a gridded manner according to structural-lithological units. The gridded sampling includes at least the surrounding rock sampling, alteration zone sampling, and ore body sampling.

[0018] In conjunction with the first aspect, in one alternative implementation, secondary sampling of the secondary minerals of gemstones includes:

[0019] Heavy sand samples were taken from the secondary mineral deposits of gemstones in the residual slope deposits and / or alluvial deposits, and environmental parameters were recorded, including at least elevation, landform type, and water system parameters.

[0020] In conjunction with the first aspect, in one optional implementation, the target sample is subjected to high-pressure sealed digestion and elemental analysis to determine the content of the target element in the target sample, including:

[0021] The target sample was subjected to high-pressure sealed digestion using a hydrofluoric acid-nitric acid system, and the content of the target elements was determined by inductively coupled plasma mass spectrometry and / or inductively coupled plasma emission spectroscopy. The content of the target elements included at least the content of major elements, trace elements, and rare earth elements.

[0022] In conjunction with the first aspect, in one alternative implementation, the chemical mineralization indicators include at least europium anomaly, the ratio of total light rare earth elements to total heavy rare earth elements, the ratio of chromium to gallium, and the ratio of iron to magnesium.

[0023] In conjunction with the first aspect, in one optional implementation, a library of spectra and diffraction patterns is established, including:

[0024] Establish a library of infrared spectral, Raman spectral shift, and X-ray diffraction spectra.

[0025] In conjunction with the first aspect, in one alternative implementation, the spectroscopic modeling variables include at least the area ratio of the two main peaks in the infrared hydroxyl stretching region and the area ratio of the characteristic peaks in the Si-O bending region.

[0026] In conjunction with the first aspect, in one optional implementation, under preset conditions, acquiring the cathodoluminescence image and cathodoluminescence spectrum of the target sample, and determining the cathodoluminescence intensity ratio based on the cathodoluminescence image and cathodoluminescence spectrum, including:

[0027] Under preset accelerating voltage and preset current conditions, acquire cathodoluminescence images and cathodoluminescence spectra of the target sample;

[0028] The intensity of blue, green and red light emission is quantified and their intensity ratio is calculated as the cathodic emission intensity ratio to characterize the superimposed history of pressure, temperature and metamorphic fluid.

[0029] The cathode luminescence intensity ratio includes at least one of the following: blue / green, blue / red, and green / red, and is used to distinguish the differences between high-pressure-high-temperature conditions and the superposition process of metamorphic fluids.

[0030] In conjunction with the first aspect, in one optional implementation, chemical mineralization indicators, spectroscopic typological variables, cathodoluminescence intensity ratios, and regional geological variables are integrated into a target feature vector of preset dimensions. Based on a machine learning model, a preset interpretation algorithm, and the target feature vector, a model is created to obtain a mineralization analysis model, including:

[0031] The chemical mineralization indicators, spectroscopic typological variables, cathodoluminescence intensity ratio, and regional geological variables are combined to form an eight-dimensional target feature vector; among which, the regional geological variables include at least temperature, pressure, intrusive distance, and marble thickness.

[0032] A random forest model is used to model the mineralization probability of the target feature vector, resulting in a mineralization analysis model.

[0033] In conjunction with the first aspect, in one optional implementation, a grading determination is made based on the mineralization probability index and a preset threshold, including:

[0034] When the mineralization probability index is greater than or equal to the first preset threshold, the target area is classified as a prospective area.

[0035] When the mineralization probability index is greater than or equal to the second preset threshold and less than the first preset threshold, the target area is divided into the target area.

[0036] When the mineralization probability index is less than the second preset threshold, the target area is classified as a low-potential area.

[0037] Other advantages, objectives and features of this application will be partly apparent from the description below, and partly understood by those skilled in the art through study and practice of this application. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0039] Figure 1 This is one of the flowcharts of the gemstone occurrence and mineralization condition analysis method provided in the embodiments of this application;

[0040] Figure 2 This is a schematic diagram of a sub-step of step S101 provided in the embodiments of this application;

[0041] Figure 3 This is the second flowchart of the gemstone production and mineralization condition analysis method provided in the embodiments of this application;

[0042] Figure 4 This is a schematic diagram of a sub-step of step S105 provided in an embodiment of this application;

[0043] Figure 5 This is a schematic diagram of a sub-step of step S106 provided in the embodiments of this application. Detailed Implementation

[0044] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0045] The term "and / or" as used in this application includes any and all combinations of one or more of the associated listed items. In this application, "at least one" means one or more, and "more than one" means two or more. The terms "first," "second," and other ordinal terms used in this application may be used to describe various constituent elements, but these constituent elements are not limited by these terms. The purpose of using these terms is solely to distinguish one constituent element from others and should not be construed as indicating or implying relative importance. For example, without departing from the scope of this application, a first constituent element may be named a second constituent element, and similarly, a second constituent element may be named a first constituent element.

[0046] Before introducing the embodiments of this application, the background technology involved in this application will be introduced first.

[0047] Gemstone mineralization is influenced by multi-stage geological processes, resulting in significant differences in composition and structural characteristics between primary and secondary deposits. Existing studies often focus on single sources or single scales, making it difficult to fully reconstruct the mineralization process and easily leading to missing key information and interpretation biases. At the testing level, multi-source data such as geochemical, spectral, and X-ray diffraction data suffer from inconsistencies in dimensions, noise, and acquisition conditions, as well as a lack of unified standards, resulting in insufficient comparability across laboratories and batches. Meanwhile, regional-scale geological factors such as tectonic frameworks, lithofacies assemblages, and geophysical / remote sensing inversions significantly constrain gemstone enrichment, but scale mismatches and information heterogeneity exist between these factors and the samples from specific sites, making it difficult to effectively integrate and quantify multi-source information.

[0048] In summary, existing solutions in related technologies suffer from problems such as inconsistent data standards, incomparable feature systems, difficulty in integrating regional and location information, and incomplete reconstruction of mineralization processes.

[0049] To address the aforementioned problems, this application provides a method for analyzing the occurrence and mineralization conditions of gemstones. (Reference) Figure 1 , Figure 1 This is one of the flowcharts for the gemstone production and mineralization condition analysis method provided in the embodiments of this application.

[0050] like Figure 1 As shown, the method for analyzing the occurrence and mineralization conditions of this gemstone includes at least the following steps:

[0051] S101: Perform primary sampling of the primary mineral deposits of gemstones in the target area and secondary sampling of the secondary mineral deposits of gemstones to obtain the target sample;

[0052] S102: The target sample is subjected to high-pressure closed digestion and elemental analysis to determine the content of the target element in the target sample;

[0053] S103: Calculate chemical mineralization indicators based on the content of target elements and establish a library of spectral and diffraction spectra;

[0054] S104: Extract the ratio of characteristic peak areas from the spectral and diffraction spectrum library, and use the ratio of characteristic peak areas as a spectroscopic modeling variable;

[0055] S105: Under preset conditions, acquire the cathodoluminescence image and cathodoluminescence spectrum of the target sample, and determine the cathodoluminescence intensity ratio based on the cathodoluminescence image and cathodoluminescence spectrum;

[0056] S106: Integrate chemical mineralization indicators, spectroscopic typographic variables, cathodoluminescence intensity ratio, and regional geological variables into a target feature vector with preset dimensions, and model it based on machine learning model, preset interpretation algorithm, and target feature vector to obtain mineralization analysis model; among them, regional geological variables are obtained by fusing regional geological survey, geophysical exploration, well logging and remote sensing inversion, and combined with mineral thermobarometer and fluid inclusion data inversion.

[0057] S107: Obtain the mineralization probability index based on the mineralization analysis model, and classify and determine the mineralization probability index and preset threshold.

[0058] Specifically, the process begins with sampling within the target area, conducted in two stages: primary sampling obtains samples from direct primary deposits, while secondary sampling obtains samples from secondary deposits. This comprehensive approach allows for a thorough understanding of the ore's origin and evolution. Next, these target samples undergo high-pressure, closed-system digestion. This step aims to completely decompose the samples, enabling subsequent elemental analysis to more accurately measure the content of target elements, such as the concentrations of key trace and rare elements.

[0059] Then, based on the content of these elements, chemical mineralization indicators are calculated, which can help identify the genesis and enrichment processes of minerals. Simultaneously, a spectral and diffraction spectrum library is established. By analyzing the spectral and diffraction characteristics of samples, the area ratios of characteristic peaks are extracted. These ratios serve as spectroscopic modeling variables, reflecting the physicochemical properties of the minerals. Furthermore, cathodoluminescence technology is used to acquire cathodoluminescence images and spectra of the samples, determining the cathodoluminescence intensity ratio, which can reveal the crystal structure and impurity distribution of the minerals.

[0060] All these analytical results, combined with regional geological information (such as geological surveys, geophysical exploration, well logging, and remote sensing data), are used to construct a multi-dimensional target feature vector. Machine learning models and pre-defined interpretation algorithms are then used to model these features, constructing a mineralization analysis model. This model calculates a mineralization probability index and uses set thresholds for grading, helping to identify which areas are more likely to be rich in gemstones, thus providing a scientific basis for exploration and mining activities.

[0061] It should be noted that the implementers of this plan may include, but are not limited to, automated exploration equipment, laboratory automation systems, data processing and analysis software, spectral analysis instruments, cathodoluminescence microscopes and spectrometers, geological data integration systems, machine learning platforms, automated decision support systems, etc.

[0062] For example, suppose a potentially gem-bearing area is discovered in a mountainous region. The research team analyzes the area following the steps outlined above. First, they conduct detailed sampling in the area, including samples collected directly from primary deposits and those from secondary deposits. Through high-pressure closed digestion and elemental analysis, the team determines the content of elements such as magnesium, iron, and silicon in the samples. Next, the team extracts the characteristic peak area ratios from the spectra and diffraction patterns as spectroscopic modeling variables. Simultaneously, they collect cathodoluminescence data from the samples to determine the cathodoluminescence intensity ratio. Combining this with geological survey data of the region, the team trains a machine learning model using all these variables. Ultimately, the mineralization analysis model calculates a mineralization probability index, indicating that the area has high gem-bearing potential, thus guiding further exploration and development activities.

[0063] In some embodiments, reference Figure 2 , Figure 2 This is a schematic diagram of the sub-steps of step S101 provided in an embodiment of this application. For example... Figure 2 As shown, the process of graded sampling of primary and secondary ore can include at least the following steps:

[0064] S201: In the target area, the primary mineral deposits of gemstones are sampled in a gridded manner according to the structural-lithological units. The gridded sampling includes at least the surrounding rock sampling, alteration zone sampling, and ore body sampling.

[0065] S202: Heavy sand samples shall be taken from the secondary mineral deposits of gemstones in the residual slope deposits and / or alluvial deposits, and environmental parameters shall be recorded, including at least elevation, landform type and water system parameters.

[0066] Specifically, in geological exploration, primary sampling refers to the initial collection of samples within the target area to obtain basic geological information. Grid-based sampling according to structural-lithological units involves dividing the sampling area into different units based on geological structures and rock types, and then systematically sampling within each unit according to a pre-defined grid. This method ensures that the sampling covers the geological diversity of the entire area.

[0067] Grid-based sampling typically includes three types of sampling: surrounding rock sampling, alteration zone sampling, and orebody sampling. Surrounding rock sampling involves collecting samples from the common rock surrounding the orebody to understand the background geological environment. Alteration zone sampling focuses on areas of rock that have undergone chemical changes; these areas are usually close to the orebody and may contain important mineralization information. Orebody sampling focuses on obtaining samples directly from the orebody to assess the ore grade and mineral composition.

[0068] For example, suppose we are exploring for jadeite in a target area. The geological report for this area shows the presence of several different tectonic-lithological units, including metamorphic rocks, granites, and basalts. During primary sampling, geologists would lay out grids (e.g., 20×20m grids) within these units. For instance, within a metamorphic rock unit, the grid might be configured to take a sample point every 50 meters.

[0069] In practice, geologists collect samples from the metamorphic host rocks surrounding the jadeite ore body to analyze the background geological conditions. Simultaneously, they sample from alteration zones near the ore body, as these areas may reveal useful information related to mineralization, such as the jadeite's formation environment and chemical changes. Finally, they collect samples directly from the jadeite ore body to assess ore quality and commercial mining value. Through this systematic and multi-layered sampling, the exploration team gains a comprehensive understanding of the geological characteristics and mineralization potential of the mining area.

[0070] Furthermore, secondary sampling refers to a more detailed and targeted sample collection process conducted after preliminary sampling. In gemstone exploration, secondary minerals typically refer to minerals released from primary deposits due to geological processes such as weathering, erosion, and transportation. These minerals are often concentrated in colluvial and alluvial deposits. Colluvial deposits are loose material accumulated on slopes due to gravity, while alluvial deposits are loose sediments transported and deposited by flowing water.

[0071] Heavy mineral sampling is a method focused on collecting heavier minerals from sediments in order to find potentially enriched gemstone grains. During sampling, the sampler also records environmental parameters to account for their impact on mineral distribution during data analysis. Elevation refers to the altitude of the sampling point, geomorphology describes the terrain features of the sampling point (river system, mountains, plains, etc.), and river system parameters relate to the characteristics of water flow near the sampling point (such as river width and flow velocity). This information helps in understanding mineral transport and deposition processes.

[0072] For example, in an exploration area targeting rubies, geologists have already identified potential secondary mineral deposits during preliminary exploration. During secondary sampling, they focus on heavy minerals from colluvial and alluvial deposits within that area. For instance, in alluvial deposits near a stream, they might use metal basins or sieves to separate heavier minerals from the sediment, searching for heavy minerals that may contain rubies.

[0073] During the sampling process, geologists recorded the elevation of the sampling points, such as finding that this point was located at an altitude of 200 meters. They also noted that the location was in a plain, and that the nearby stream was 15 meters wide with a slow current. These environmental parameters will be used to analyze the distribution patterns of rubies in the area and help determine further exploration directions. This detailed secondary sampling helps improve the accuracy and effectiveness of exploration.

[0074] In some embodiments, reference Figure 3 , Figure 3 This is the second flowchart of the method for analyzing the occurrence and mineralization conditions of gemstones provided in this application. Figure 3 As shown, the process of performing high-pressure sealed digestion and elemental analysis on the target sample to determine the content of the target element in the target sample includes at least step S301:

[0075] The target sample was subjected to high-pressure sealed digestion using a hydrofluoric acid-nitric acid system, and the content of the target elements was determined by inductively coupled plasma mass spectrometry and / or inductively coupled plasma emission spectroscopy. The content of the target elements included at least the content of major elements, trace elements, and rare earth elements.

[0076] Specifically, when performing elemental analysis on gemstone samples, the samples must first be processed to accurately determine their composition. High-pressure, closed-system digestion using a hydrofluoric acid-nitric acid system is a commonly used method. The mixture of hydrofluoric acid (HF) and nitric acid (HNO3) has strong corrosive and dissolving properties, effectively dissolving hard mineral samples into a liquid state. This step is typically carried out in a sealed, high-pressure digestion vessel to ensure complete digestion and prevent the loss of any volatile components.

[0077] After digestion, elemental analysis was performed using inductively coupled plasma mass spectrometry (ICP-MS) or inductively coupled plasma optical emission spectrometry (ICP-OES). These techniques can sensitively detect and quantify various elements in the sample, including major elements (such as silicon, aluminum, and iron), trace elements (such as zinc, lead, and copper), and rare earth elements (such as lanthanum, cerium, and praseodymium). Determining the content of these elements helps in understanding the compositional characteristics and mineralization conditions of gemstones.

[0078] For example, suppose we are analyzing a turquoise sample. First, the turquoise sample is ground into powder and then placed in a high-pressure digestion vessel, where a mixture of hydrofluoric acid and nitric acid is added. After high-pressure, sealed digestion, the sample is completely dissolved. Next, the digested solution is transferred to an analytical instrument. Using ICP-MS technology, we can accurately measure the major elements in the sample, such as phosphorus (P) and copper (Cu), which are the main components of turquoise. Simultaneously, ICP-MS can also detect trace elements and rare earth elements, such as zinc (Zn) and cerium (Ce). The presence and content of these elements help determine the geological origin and mineralization environment of the turquoise. Through this detailed analytical process, we can obtain comprehensive chemical composition information of the sample, thus providing important data support for gemstone mineralization research.

[0079] In some embodiments, the chemical mineralization indicators include at least europium anomaly, the ratio of total light rare earth elements to total heavy rare earth elements, the ratio of chromium to gallium, and the ratio of iron to magnesium.

[0080] Specifically, in geological and mineralogy research, chemical mineralization indicators are important tools for assessing and understanding the genesis and formation environment of ore deposits. These indicators reveal the formation conditions and evolutionary processes of ore deposits by analyzing the content and ratios of specific elements in mineral samples. The europium anomaly is a commonly used indicator that measures the degree of deviation of europium (Eu) from other rare earth elements (REEs) in the REE distribution pattern, and is usually associated with redox conditions and magmatic crystallization processes. A positive anomaly (Eu / Eu*>1) usually indicates a reducing environment or the fractional crystallization of plagioclase, while a negative anomaly (Eu / Eu*<1) may be related to an oxidizing environment or the assimilation of plagioclase. The ratio of total light rare earth elements (LREE) to total heavy rare earth elements (HREE) (LREE / HREE) reflects the degree of rare earth element differentiation and the mineralization environment of the deposit; a high ratio usually indicates enrichment in light rare earth elements. The chromium to gallium (Cr / Ga) ratio is used to distinguish ore deposits of different genetic types; a low ratio may suggest that the deposit is related to sedimentary processes. The iron-to-magnesium ratio (Fe / Mg) is used to determine the evolution of rocks and helps to identify the mineralization process and redox environment of ore deposits.

[0081] For example, in analyzing a potential rare earth element (REE) deposit, geologists used ICP-MS to detect a significant negative europium anomaly (Eu / Eu* = 0.7), which may indicate that the deposit formed in an oxidizing environment. The sample's LREE / HREE ratio of 10 indicates enrichment of light rare earth elements, related to magmatic differentiation. The low Cr / Ga ratio (2) suggests that the deposit may be related to sedimentary processes, while the Fe / Mg ratio of 5 indicates that the deposit formed in an iron-rich environment. The comprehensive analysis of these chemical mineralization indicators provides important clues to the genesis and formation environment of the deposit.

[0082] In some embodiments, establishing a spectral and diffraction spectrum library is for the purpose of better analyzing and identifying the composition and structure of substances. This includes establishing a 400–7500 cm⁻¹ library. -1 This database comprises infrared spectroscopy, Raman spectral shifts, and X-ray diffraction (XRD) libraries. Infrared spectral libraries, by identifying chemical bonds and functional groups in molecules, can rapidly match and identify the chemical composition of samples, and are widely used in the analysis of organic compounds. Raman spectral shift libraries, by measuring light scattering caused by molecular vibrations and rotations, provide information on the molecular structure of substances, and are particularly important in mineralogy and materials science. XRD libraries utilize X-ray diffraction techniques to rapidly identify the crystal structure and phase composition of samples, and are of great value in mineral analysis, materials science, and chemical engineering. By integrating these spectral and diffraction libraries, researchers can perform material identification and analysis more efficiently, thereby supporting material characterization analysis in scientific research and industrial applications.

[0083] In some embodiments, spectroscopic modeling variables include at least the area ratio of the two main peaks in the hydroxyl stretching region and the area ratio of the characteristic peaks in the Si-O bending region in the infrared spectrum. These variables can provide important information about the chemical structure of materials. The area ratio of the main peaks in the hydroxyl stretching region is commonly used to analyze the hydroxyl content and relative concentration in a sample, which is crucial for studying the water content and hydrogen bonding in hydrates, minerals, and polymer materials. On the other hand, the area ratio of the characteristic peaks in the Si-O bending region can reveal structural information in silicon oxide materials, such as the arrangement of silicon-oxygen bonds and crystal structure. These spectroscopic modeling variables have wide applications in materials science, geology, and chemical engineering, contributing to a deeper understanding and characterization of the chemical properties and structural features of materials.

[0084] In some embodiments, reference Figure 4 , Figure 4 This is a schematic diagram of a sub-step of step S105 provided in an embodiment of this application. For example... Figure 4 As shown, under preset conditions, the process of acquiring the cathodoluminescence image and cathodoluminescence spectrum of the target sample, and determining the cathodoluminescence intensity ratio based on the cathodoluminescence image and cathodoluminescence spectrum, may include at least the following steps:

[0085] S401: Under the conditions of preset accelerating voltage and preset current, acquire the cathodoluminescence image and cathodoluminescence spectrum of the target sample;

[0086] S402: The intensity of blue, green and red light emission is quantified and their intensity ratio is calculated as the cathode luminescence intensity ratio to characterize the superimposed history of pressure, temperature and deteriorated fluid.

[0087] S403: The cathode luminescence intensity ratio includes at least one of the following: blue / green, blue / red, and green / red, and is used to distinguish the differences between high-pressure-high-temperature conditions and the superposition process of metamorphic fluids.

[0088] Specifically, by acquiring cathodoluminescence images and spectra of the target sample, the characteristics of the sample under different environmental conditions can be analyzed. The process involves acquiring cathodoluminescence images and spectra of the sample under specific accelerating voltages (e.g., 10 kV) and current conditions (e.g., 0.5 mA). Then, the emission of blue, green, and red colors in the cathodoluminescence spectrum is quantified, and their intensity ratios are calculated as cathodoluminescence intensity ratios. These intensity ratios provide information about the sample under different pressure and temperature conditions and its history of undergoing metamorphic fluid superposition. Finally, by analyzing these ratios (e.g., blue / green, blue / red, green / red), it is possible to distinguish whether the sample has undergone high-pressure-high-temperature conditions or a metamorphic fluid superposition process.

[0089] For example, suppose a rock sample needs to be analyzed to determine its geological history. Using cathodoluminescence (CFL) technology under specific laboratory conditions, researchers obtain cathodoluminescence images and spectra of the rock sample. By comparing and analyzing the intensities of blue, green, and red light, researchers calculate the blue / green, blue / red, and green / red intensity ratios. If the blue / green intensity ratio is significantly high, it may indicate that the sample was exposed to a high-temperature, high-pressure environment. A high green / red ratio may indicate that the sample underwent specific fluid interactions. This information provides important reference for understanding the rock's formation and evolutionary history.

[0090] In some embodiments, reference Figure 5 , Figure 5 This is a schematic diagram of the sub-steps of step S106 provided in an embodiment of this application. For example... Figure 5 As shown, the process of integrating chemical mineralization indicators, spectroscopic typological variables, cathodoluminescence intensity ratio, and regional geological variables into a target feature vector of preset dimensions, and then modeling based on a machine learning model, a preset interpretation algorithm, and the target feature vector to obtain a mineralization analysis model, can include at least the following steps:

[0091] S501: Combine chemical mineralization indicators, spectroscopic modeling variables, cathodoluminescence intensity ratio, and regional geological variables to form an eight-dimensional target feature vector; among which, regional geological variables include at least temperature, pressure, intrusive distance, and marble thickness.

[0092] S502: The random forest model is used to model the mineralization probability of the target feature vector, and the mineralization analysis model is obtained.

[0093] Specifically, the development of mineralization analysis models involves integrating various types of geological and chemical information into a multi-dimensional feature vector for more complex modeling and analysis. First, chemical mineralization indicators, spectroscopic typographic variables, cathodoluminescence intensity ratios, and regional geological variables can be combined to form an eight-dimensional target feature vector. Among these, regional geological variables include important factors influencing mineralization processes, such as temperature, pressure, intrusive distance, and marble thickness. These variables provide comprehensive information about the geological and chemical environments, helping to better understand mineralization conditions.

[0094] Subsequently, these feature vectors can be used to model the mineralization probability using a random forest model and the SHAP interpretation algorithm. Random forest is a powerful machine learning algorithm suitable for handling complex multidimensional data because it improves the accuracy and stability of predictions by constructing multiple decision trees and averaging them. The resulting mineralization analysis model can effectively predict the mineralization potential of a specific area, helping geologists and mining companies to better conduct mineral exploration and development.

[0095] For example, suppose researchers collect a series of sample data from a mining area, including chemical composition, spectral characteristics, cathodoluminescence features, and geological background information of the region. They integrate this information into an eight-dimensional feature vector and input it into a pre-trained random forest model. After analysis, the model outputs the mineralization probability of the area, helping them determine which areas are more likely to contain abundant mineral resources, thereby optimizing exploration and mining strategies. In this way, researchers can effectively narrow down the exploration scope, save costs, and increase the success rate.

[0096] In some embodiments, to effectively assess and classify mineral exploration areas, a mineralization probability index and preset thresholds can be used for grading. This process divides target areas into different potential levels by setting two key thresholds. Specifically, when the mineralization probability index is greater than or equal to a first preset threshold, the target area is identified as a prospective area, meaning that the area has high mineralization potential and may be the preferred area for exploration. When the mineralization probability index is between a second preset threshold and the first preset threshold, the area is classified as a target area, indicating that it has medium mineralization potential and is worth further investigation and evaluation. When the mineralization probability index is below the second preset threshold, the area is marked as a low-potential area, and it is generally not recommended to invest too many exploration resources in this area.

[0097] For example, suppose a mining area has a mineralization probability index of 0.75, with a first preset threshold of 0.7 and a second preset threshold of 0.4. In this case, because the mineralization probability index of 0.75 is greater than the first preset threshold of 0.7, the mining area will be classified as a Class A prospective area, indicating that the area has high mineral resource potential and is a key target for exploration. Conversely, if the mineralization probability index of an area is 0.55, it will be classified as a Class B target area because its index is between 0.4 and 0.7. This means that further investigation is needed to confirm its mineral value. Furthermore, if the mineralization probability index of another area is only 0.35, which is below the second preset threshold of 0.4, it will be classified as a Class C low-potential area, and large-scale exploration investment is generally not recommended in this area. In this way, resource allocation can be optimized, and the efficiency and success rate of exploration work can be improved.

[0098] The above description involves various modules and units. It should be noted that the division of these modules and units in the description is for clarity. However, in actual implementation, the boundaries between various modules and units may be blurred. For example, any or all functional modules and units in this application may share various hardware and / or software elements. As another example, any and / or all functional modules in this application may be wholly or partially implemented by a shared processor executing software instructions. Furthermore, various software sub-modules executed by one or more processors may be shared among various software modules. Accordingly, unless expressly required, the scope of this application is not limited by mandatory boundaries between various hardware and / or software elements.

[0099] It should be noted that the order of description of the embodiments in this application is not intended to limit the priority of the embodiments.

[0100] Unless otherwise defined, all technical and scientific terms used in this application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in this application and in its specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0101] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many forms under the guidance of this application without departing from the spirit and scope of protection of the claims. All equivalent transformations made based on the technical concept of this application and the content of the description and drawings of this application, or direct / indirect applications in other related technical fields, are included within the scope of patent protection of this application.

Claims

1. A method for analyzing the occurrence and mineralization conditions of gemstones, characterized in that, include: Primary sampling of the primary mineral deposits of the gemstones in the target area and secondary sampling of the secondary mineral deposits of the gemstones are performed to obtain the target sample; The target sample is subjected to high-pressure sealed digestion and elemental analysis to determine the content of the target element in the target sample; Chemical mineralization indicators were calculated based on the content of the target elements, and a library of spectral and diffraction spectra was established. Extract the ratio of the area of ​​characteristic peaks in the spectrum and the diffraction spectrum library, and use the ratio of the area of ​​characteristic peaks as a spectroscopic model variable; Under preset conditions, acquire the cathodoluminescence image and cathodoluminescence spectrum of the target sample, and determine the cathodoluminescence intensity ratio based on the cathodoluminescence image and the cathodoluminescence spectrum; The chemical mineralization indicators, the spectroscopic typological variables, the cathodoluminescence intensity ratio, and the regional geological variables are integrated into a target feature vector of a preset dimension. A mineralization analysis model is obtained by modeling based on a machine learning model, a preset interpretation algorithm, and the target feature vector. The regional geological variables include at least temperature, pressure, intrusive distance, and marble thickness. The mineralization probability index is obtained based on the mineralization analysis model, and a classification judgment is made according to the mineralization probability index and a preset threshold.

2. The method according to claim 1, characterized in that, The primary sampling of the primary mineral deposits of gemstones in the target area includes: In the target area, primary mineral deposits of gemstones are sampled in a gridded manner according to structural-lithological units. The gridded sampling includes at least the sampling of surrounding rocks, alteration zones, and ore bodies.

3. The method according to claim 1, characterized in that, The secondary sampling of the secondary minerals of the gemstone includes: Heavy sand samples were taken from the secondary minerals of the gemstones in the residual slope deposits and / or alluvial deposits, and environmental parameters were recorded. The environmental parameters included at least elevation, landform type, and water system parameters.

4. The method according to claim 1, characterized in that, The step of performing high-pressure sealed digestion and elemental analysis on the target sample to determine the content of the target element in the target sample includes: The target sample was subjected to high-pressure sealed digestion using a hydrofluoric acid-nitric acid system, and the content of target elements was determined by inductively coupled plasma mass spectrometry and / or inductively coupled plasma emission spectroscopy. The content of target elements included at least the content of major elements, trace elements, and rare earth elements.

5. The method according to claim 1, characterized in that, The chemical mineralization indicators include at least europium anomaly, the ratio of total light rare earth elements to total heavy rare earth elements, the ratio of chromium to gallium, and the ratio of iron to magnesium.

6. The method according to claim 1, characterized in that, The establishment of the spectral and diffraction spectrum library includes: Establish a library of infrared spectral, Raman spectral shift, and X-ray diffraction spectra.

7. The method according to claim 1, characterized in that, The spectroscopic modeling variables include at least the area ratio of the two main peaks in the hydroxyl stretching region of the infrared spectrum and the area ratio of the characteristic peaks in the Si-O bending region.

8. The method according to claim 1, characterized in that, The step of acquiring the cathodoluminescence image and cathodoluminescence spectrum of the target sample under preset conditions, and determining the cathodoluminescence intensity ratio based on the cathodoluminescence image and the cathodoluminescence spectrum, includes: Under preset accelerating voltage and preset current conditions, acquire the cathodoluminescence image and cathodoluminescence spectrum of the target sample; The intensity of blue, green and red light emission is quantified and their intensity ratio is calculated as the cathodic emission intensity ratio to characterize the superimposed history of pressure, temperature and metamorphic fluid. The cathode luminescence intensity ratio includes at least one of the following: blue / green, blue / red, and green / red, and is used to distinguish the differences between high-pressure-high-temperature conditions and the superposition process of metamorphic fluids.

9. The method according to claim 1, characterized in that, The process involves integrating the chemical mineralization indicators, the spectroscopic modeling variables, the cathodoluminescence intensity ratio, and regional geological variables into a target feature vector of preset dimensions. A mineralization analysis model is then derived based on a machine learning model, a preset interpretation algorithm, and the target feature vector, including: The chemical mineralization index, the spectroscopic modeling variable, the cathodoluminescence intensity ratio, and the regional geological variable are combined to form an eight-dimensional target feature vector. A random forest model is used to model the mineralization probability of the target feature vector, resulting in a mineralization analysis model.

10. The method according to claim 1, characterized in that, The step of classifying and determining based on the mineralization probability index and a preset threshold includes: When the mineralization probability index is greater than or equal to a first preset threshold, the target area is divided into a prospective area. When the mineralization probability index is greater than or equal to the second preset threshold and less than the first preset threshold, the target area is divided into a target area. When the mineralization probability index is less than the second preset threshold, the target area is classified as a low-potential area.

Images