Metal resource evaluation method and system based on geological exploration

Abstract

The invention discloses a metal resource assessment method and system based on geological exploration, relates to the technical field of mineral data processing, and effectively solves key problems in geological resource assessment through multi-module collaboration. A data fusion module integrates drilling data Zk, geophysical data Dw and remote sensing data Yg; the confidence Rx is calculated by using an adaptive weighting algorithm and probability filling is carried out, so that the data sparsity error is remarkably reduced; the boundary optimization module is used for calculating a mineralization continuity index Lx and generating a boundary optimization coefficient Ly in combination with the temperature dynamic factor Tx so as to realize intelligent correction of the boundary of the ore body; the depth correction module constructs a depth compensation model through the signal intensity M, the stability V and the noise level N, the deep data credibility Sx is improved, Monte Carlo simulation and dynamic parameter adjustment are matched, the system overcomes the defects of a traditional method in the aspects of data uncertainty, boundary ambiguity and deep precision, and the method has the advantages of being high in accuracy and high in reliability. And full-process automation and high-precision resource evaluation and early warning are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of mineral data processing, and particularly to a metal resource evaluation method and system based on geological exploration. Background Art

[0002] The metal resource evaluation system originated in the mid - to late 20th century. With the progress of mineral exploration technology and the development of computer science, traditional manual evaluation has gradually shifted towards digitization and modeling. Early systems relied on geostatistics and simple databases, and later incorporated GIS, remote sensing, and machine learning technologies, achieving the intelligence of resource quantity prediction, grade evaluation, and mining optimization, and becoming one of the core tools in modern mining.

[0003] However, when the metal resource evaluation system is applied to mineral exploration, it often has the following technical drawbacks:

[0004] 1. High data uncertainty: Geological data (such as borehole samples, geophysical data) are often sparse or incomplete, resulting in large errors in the evaluation model.

[0005] 2. Ambiguity of ore - body boundaries: The morphology of ore - bodies is complex. Traditional interpolation algorithms (such as Kriging method) may underestimate or overestimate the mineralized range, affecting the calculation of resource quantity.

[0006] 3. Low accuracy in deep exploration: As the depth increases, geophysical signals attenuate, making it difficult to identify deep - seated ore - bodies and reducing the reliability of evaluation. Summary of the Invention

[0007] In view of the deficiencies of the prior art, the present invention provides a metal resource evaluation method and system based on geological exploration, which solves the technical drawbacks mentioned in the technical background.

[0008] To achieve the above - mentioned objectives, the present invention is realized through the following technical solutions: A metal resource evaluation system based on geological exploration includes a data fusion module, a boundary optimization module, a depth correction module, a resource calculation module, and a dynamic feedback module;

[0009] The data fusion module is used to collect and integrate multi - source geological data, including data related to boreholes, data related to geophysics, and data related to remote sensing. Then, through an adaptive weighted algorithm, it calculates the confidence level Rx of the evaluation data and fills in the sparse data with probabilities.

[0010] The boundary optimization module, based on three - dimensional geological modeling and machine learning algorithms, uses multi - source geological data to analyze the spatial distribution characteristics of the ore - body morphology, calculates and evaluates the mineralization continuity index Lx, and dynamically corrects the ore - body boundary;

[0011] The depth correction module is used to construct a depth-signal compensation model by combining the attenuation law of deep geophysical signals. Then, it extracts multi-source geological data to calculate the reliability Sx of deep data, and improves the recognition accuracy of deep ore bodies through inversion optimization.

[0012] The resource calculation module is used to comprehensively utilize the corrected ore body boundary and deep data, and adopt Monte Carlo simulation to calculate the resource quantity Qz and grade distribution Pz, and generate a resource evaluation report.

[0013] The dynamic feedback module is used to monitor the update of exploration data in real time, including the resource quantity Qz and grade distribution Pz, automatically optimize the model parameters, and feedback the resource evaluation results and uncertainty warnings through a visualization interface.

[0014] Preferably, the data fusion module includes a data acquisition unit, a confidence calculation unit, and a data optimization unit.

[0015] The data acquisition unit is used to collect and integrate multi-source geological data, including the benchmark value Zk of borehole data, the benchmark value Dw of geophysical data, and the benchmark value Yg of remote sensing data.

[0016] The confidence calculation unit calculates the confidence Rx of the evaluation data through an adaptive weighting algorithm, and its specific calculation method is as follows:

[0017]

[0018] In the formula, Zmax, Dmax, and Ymax respectively represent the maximum confidence benchmark values of borehole data, geophysical data, and remote sensing data; α, β, and γ are dynamically adjusted weight coefficients, and satisfy α + β + γ = 1.

[0019] Preferably, the confidence calculation unit compares and evaluates the preset confidence threshold R with the calculated data confidence Rx, and its specific evaluation scheme is as follows:

[0020] If the current data confidence Rx ≥ the confidence threshold R, a first confidence result is generated, indicating that the current data reliability is normal and can be directly used for resource evaluation.

[0021] If the current data confidence Rx < the confidence threshold R, a second confidence result is generated, indicating that the current data reliability is abnormal, and probability filling is performed at this time.

[0022] According to the confidence evaluation result and the data confidence Rx, probability filling is performed on the sparse data, and a data reliability report is generated, including the confidence values of each data source, the optimization processing records, and the recommended correction measures, and finally feedback to the user through a visualization interface.

[0023] Preferably, the boundary optimization module includes a morphology analysis unit and a boundary correction unit.

[0024] The morphological analysis unit is used to construct a spatial distribution feature model of the ore body morphology based on multi-source geological data and calculate the mineralization continuity index Lx. The specific calculation formula is as follows:

[0025] Lx = f(D, C, S);

[0026] Where D represents the distance variability parameter of the ore body morphology, C represents the spatial correlation parameter of the ore body mineralization degree, and S represents the boundary change trend parameter of the mineralized body;

[0027] Then, in combination with the geological environment change information, the dynamic adjustment factor Tx of the ore body boundary is obtained. The specific calculation formula is as follows:

[0028]

[0029] In the formula, k represents the monitoring period, i = 1, 2, 3......, k, Ti represents the temperature value at the i-th time node within the monitoring period, and Tavg represents the average temperature within the monitoring period.

[0030] Preferably, the boundary correction unit is used to calculate the change trend of the mineralization continuity index Lx under different geological environment conditions, and based on its influence degree on the dynamic adjustment factor Tx of the ore body boundary, the boundary optimization coefficient Ly is obtained. The specific calculation formula is as follows:

[0031] Ly = g(Lx, Tx)

[0032] Then, a boundary stability threshold L is preset and compared with the boundary optimization coefficient Ly to evaluate the applicability of the ore body boundary correction strategy. The specific content is as follows:

[0033] If the boundary optimization coefficient Ly ≥ the boundary stability threshold L, it is determined that the current ore body boundary needs to be dynamically corrected, and an optimization instruction is triggered;

[0034] If the boundary optimization coefficient Ly < the boundary stability threshold L, it is determined that the current ore body boundary does not need to be corrected, and the original boundary morphology is maintained.

[0035] Preferably, the depth correction module includes a signal compensation unit and a data credibility calculation unit;

[0036] The signal compensation unit constructs a depth-signal compensation model based on the attenuation law of deep geophysical signals and corrects the deep detection signals to improve the integrity and accuracy of the data;

[0037] The data credibility calculation unit is used to extract multi-source geological data and calculate the deep data credibility Sx. The deep data credibility Sx is obtained through the following formula:

[0038]

[0039] Among them, M represents the signal intensity of the deep exploration data, V represents the structural stability of the deep exploration data, N represents the noise level of the deep exploration data, and Wm, Wv, and Wn are the weight coefficients of each parameter respectively.

[0040] Preferably, the data credibility calculation unit evaluates the credibility Sx of the deep data within different depth ranges by setting a credibility threshold Q. The specific evaluation scheme is as follows:

[0041] If the current deep data credibility Sx > credibility threshold Q, a first credibility result is generated at this time, indicating that the data credibility within this depth range is normal and is used for ore body identification;

[0042] If the current deep data credibility Sx < credibility threshold Q, a second credibility result is generated at this time, indicating that the data credibility within this depth range is abnormal, and further optimization processing is performed at this time;

[0043] Finally, according to the depth-signal compensation model, the data with abnormal credibility is optimized and inverted, and the optimized deep ore body identification result is displayed based on the interactive interface.

[0044] Preferably, the resource calculation module calculates the resource quantity Qz based on the comprehensively corrected ore body boundary data and deep exploration data by the Monte Carlo simulation method through the following formula:

[0045]

[0046] Among them, Qa i represents the volume of the i-th simulated sampling unit, Qb i represents the density of the i-th simulated sampling unit, and z is the number of Monte Carlo simulation samplings.

[0047] Secondly, based on the calculation result of the resource quantity Qz, the ore body grade information is extracted, and the grade distribution Pz is calculated by the statistical analysis method; further combining the resource quantity Qz and grade distribution Pz in different regions, a resource evaluation report is generated; among them, the resource evaluation report includes the resource quantity calculation result, grade distribution situation and its spatial variability analysis, and the evaluation result is displayed through the interactive interface.

[0048] Preferably, the dynamic feedback module obtains and updates the exploration data in real time, including the resource quantity Qz and grade distribution Pz, and dynamically stores and processes the newly obtained data;

[0049] Then, based on the real-time updated exploration data, the parameters of the resource calculation model are adaptively adjusted to optimize the calculation accuracy of the resource quantity Qz and grade distribution Pz. The specific optimization process is as follows:

[0050] Extract the currently updated dataset and calculate the data change rate Rd;

[0051] If the data change rate Rd exceeds the preset threshold, trigger the recalculation of model parameters and compare the errors of the model outputs before and after adjustment;

[0052] Based on the error analysis results, adaptively optimize the model parameters;

[0053] Finally, based on the optimized resource calculation results, generate a resource assessment report, and display the change trends of the resource quantity Qz and the grade distribution Pz through an interactive visualization interface. At the same time, provide uncertainty warning information; when the uncertainty assessment result exceeds the preset threshold, generate a warning signal and prompt the user to perform further data verification or model adjustment.

[0054] A metal resource assessment method based on geological exploration, comprising the following steps:

[0055] Step 1: Collect and integrate multi-source geological data, including drilling-related data, geophysical-related data, and remote sensing-related data. Then, through an adaptive weighting algorithm, calculate the evaluation data confidence Rx and perform probability filling on sparse data;

[0056] Step 2: Based on 3D geological modeling and machine learning algorithms, use multi-source geological data to analyze the spatial distribution characteristics of the ore body morphology, calculate and evaluate the mineralization continuity index Lx, and dynamically correct the ore body boundary;

[0057] Step 3: Combine the attenuation law of deep geophysical signals to construct a depth-signal compensation model. Then, extract multi-source geological data to calculate the deep data credibility Sx, and improve the deep ore body identification accuracy through inversion optimization;

[0058] Step 4: Based on the comprehensively corrected ore body boundary and deep data, use Monte Carlo simulation to calculate the resource quantity Qz and the grade distribution Pz, and generate a resource assessment report;

[0059] Step 5: Real-time monitor the update of exploration data, including the resource quantity Qz and the grade distribution Pz, automatically optimize the model parameters, and feedback the resource assessment results and uncertainty warnings through a visualization interface.

[0060] The present invention provides a metal resource assessment method and system based on geological exploration. It has the following beneficial effects:

[0061] (1) The metal resource assessment method and system based on geological exploration, aiming at the problem of high data uncertainty, integrates multi-source geological data (drilling data reference value Zk, geophysical data reference value Dw, remote sensing data reference value Yg) through the data fusion module, and calculates the confidence level Rx of the assessment data by using the adaptive weighted algorithm; conducts comparative evaluation by presetting the confidence threshold R, fills in the sparse data probabilistically, effectively improves the data integrity and credibility; at the same time, generates a data credibility report (including the confidence level values of each data source, optimization processing records and recommended corrective measures), significantly reducing the model error caused by sparse or incomplete data

[0062] (2) The metal resource assessment method and system based on geological exploration, aiming at the problem of ambiguous ore body boundaries, constructs a spatial distribution feature model of the ore body morphology through the boundary optimization module, and calculates the mineralization continuity index Lx (based on the distance variability parameter D of the ore body morphology, the spatial correlation parameter C of the mineralization degree, and the ore body boundary change trend parameter S); obtains the dynamic adjustment factor Tx of the ore body boundary by combining the geological environment change information (based on the temperature value Ti and the average temperature Tavg at the time nodes within the monitoring period k); further calculates the boundary optimization coefficient Ly and compares it with the boundary stability threshold L to dynamically correct the ore body boundary, overcoming the underestimation or overestimation problems of the mineralization range by traditional interpolation algorithms

[0063] (3) The metal resource assessment method and system based on geological exploration, aiming at the problem of low deep exploration accuracy, constructs a depth-signal compensation model through the depth correction module, and calculates the credibility Sx of the deep data (evaluates the data credibility by setting the credibility threshold Q and optimally inverses the abnormal data; combines the Monte Carlo simulation of the resource calculation module (based on the simulated sampling unit volume Vi, density ρi and the number of sampling times z) and the adaptive parameter adjustment of the dynamic feedback module (based on the data change rate Rd), significantly improving the recognition accuracy of deep ore bodies and the reliability of resource assessment Description of the Drawings

[0064] Figure 1 It is a schematic diagram of the framework structure of a metal resource assessment system based on geological exploration according to the present invention;

[0065] Figure 2 It is a schematic diagram of the step flow of a metal resource assessment method based on geological exploration according to the present invention. Detailed Embodiments

[0066] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0067] Embodiment 1

[0068] Please refer to Figure 1 , the present invention provides a metal resource evaluation system based on geological exploration, including a data fusion module, a boundary optimization module, a depth correction module, a resource calculation module, and a dynamic feedback module;

[0069] The data fusion module is used to collect and integrate multi-source geological data, including drilling-related data, geophysical-related data, and remote sensing-related data, and then calculate the confidence level Rx of the evaluation data through an adaptive weighted algorithm to perform probability filling on sparse data;

[0070] The boundary optimization module is based on three-dimensional geological modeling and machine learning algorithms, uses multi-source geological data, analyzes the spatial distribution characteristics of the ore body morphology, calculates and evaluates the mineralization continuity index Lx, and dynamically corrects the ore body boundary;

[0071] The depth correction module is used to construct a depth-signal compensation model in combination with the attenuation law of deep geophysical signals, then extract multi-source geological data to calculate the credibility Sx of deep data, and improve the recognition accuracy of deep ore bodies through inversion optimization;

[0072] The resource calculation module is used to comprehensively consider the corrected ore body boundary and deep data, use Monte Carlo simulation to calculate the resource volume Qz and grade distribution Pz, and generate a resource evaluation report;

[0073] The dynamic feedback module is used to monitor the update of exploration data in real time, including the resource volume Qz and grade distribution Pz, automatically optimize the model parameters, and feedback the resource evaluation results and uncertainty warnings through a visual interface.

[0074] In this embodiment, the data fusion module significantly improves the accuracy of multi-source data fusion and reduces uncertainty by integrating drilling data Zk, geophysical data Dw, and remote sensing data Yg and calculating the confidence level Rx; the boundary optimization module calculates the mineralization continuity index Lx based on the ore body shape parameters D, C, and S and combines it with the temperature dynamic factor Tx to achieve intelligent dynamic correction of the ore body boundary; the depth correction module constructs a depth compensation model through the signal strength M, stability V, and noise level N and calculates the credibility Sx to effectively improve the ability to identify deep ore bodies; the resource calculation module accurately calculates the resource quantity Qz and grade distribution Pz using Monte Carlo simulation (volume Vi, density ρi) and generates a highly reliable resource assessment report; the dynamic feedback module continuously improves the system assessment accuracy and provides a visualization warning function by real-time monitoring the data change rate Rd and adaptively optimizing parameters.

[0075] Embodiment 2

[0076] The data fusion module includes a data acquisition unit, a confidence level calculation unit, and a data optimization unit;

[0077] The data acquisition unit is used to collect and integrate multi-source geological data, including the drilling data reference value Zk, the geophysical data reference value Dw, and the remote sensing data reference value Yg;

[0078] The confidence level calculation unit calculates the evaluation data confidence level Rx through an adaptive weighting algorithm, and its specific calculation method is as follows:

[0079]

[0080] In the formula, Zmax, Dmax, and Ymax respectively represent the maximum credibility reference values of drilling data, geophysical data, and remote sensing data; α, β, and γ are dynamically adjusted weight coefficients, and α + β + γ = 1.

[0081] The confidence level calculation unit compares and evaluates the preset confidence level threshold R with the calculated data confidence level Rx, and its specific evaluation scheme is as follows:

[0082] If the current data confidence level Rx ≥ the confidence level threshold R, a first confidence result is generated, indicating that the current data credibility is normal and it is directly used for resource assessment;

[0083] If the current data confidence level Rx < the confidence level threshold R, a second confidence result is generated, indicating that the current data credibility is abnormal, and at this time probability filling is performed;

[0084] According to the confidence level evaluation result and the data confidence level Rx, probability filling is performed on the sparse data, and a data credibility report is generated, including the confidence level values of each data source, the optimization processing records, and the recommended correction measures, and finally it is fed back to the user through a visualization interface.

[0085] The boundary optimization module includes a morphological analysis unit and a boundary correction unit;

[0086] The morphological analysis unit is used to construct a spatial distribution feature model of the ore body morphology based on multi-source geological data and calculate the mineralization continuity index Lx. The specific calculation formula is as follows:

[0087] Lx = f(D, C, S);

[0088] Where D represents the distance variability parameter of the ore body morphology, C represents the spatial correlation parameter of the ore body mineralization degree, and S represents the boundary change trend parameter of the mineralized body;

[0089] Then, combined with the geological environment change information, the dynamic adjustment factor Tx of the ore body boundary is obtained. The specific calculation formula is as follows:

[0090]

[0091] In the formula, k represents the monitoring period, i = 1, 2, 3......, k, Ti represents the temperature value at the i-th time node within the monitoring period, and Tavg represents the average temperature within the monitoring period.

[0092] The boundary correction unit is used to calculate the change trend of the mineralization continuity index Lx under different geological environment conditions and obtain the boundary optimization coefficient Ly based on its influence degree on the dynamic adjustment factor Tx of the ore body boundary. The specific calculation formula is as follows:

[0093] Ly = g(Lx, Tx)

[0094] Then, a boundary stability threshold L is preset and compared with the boundary optimization coefficient Ly to evaluate the applicability of the ore body boundary correction strategy. The specific content is as follows:

[0095] If the boundary optimization coefficient Ly ≥ the boundary stability threshold L, it is determined that the current ore body boundary needs to be dynamically corrected and an optimization instruction is triggered;

[0096] If the boundary optimization coefficient Ly < the boundary stability threshold L, it is determined that the current ore body boundary does not need to be corrected and the original boundary morphology is maintained.

[0097] In this embodiment, the data fusion module collects the benchmark value Zk of drilling data, the benchmark value Dw of geophysical data, and the benchmark value Yg of remote sensing data, and calculates the confidence level Rx by using the maximum credibility benchmark values Zmax, Dmax, Ymax and the dynamic weight coefficients α, β, γ. By comparing with the threshold R, the data quality grading management is realized to ensure the reliability of multi-source data fusion; the boundary optimization module constructs the mineralization continuity index Lx through the distance variability parameter D, the spatial correlation parameter C, and the boundary change trend parameter S, and combines the temperature node Ti and the mean value Tavg within the monitoring period k to calculate the dynamic adjustment factor Tx. Finally, the boundary optimization coefficient Ly is generated and compared with the stability threshold L to realize the intelligent dynamic correction of the ore body boundary; the depth correction module calculates the credibility Sx of the deep data based on the signal intensity M, the stability V, and the noise level N, and evaluates the data quality and optimizes the inversion through the credibility threshold Q; the resource calculation module uses Monte Carlo simulation to calculate the resource quantity Qz and the grade distribution Pz based on the sampling unit volume Vi and the density ρi; the dynamic feedback module realizes the adaptive optimization of parameters through the monitoring data change rate Rd; the entire system realizes the closed-loop management from data collection, quality evaluation, boundary optimization, depth correction to resource quantity calculation through the collaborative work of each module, significantly improving the accuracy and reliability of metal resource evaluation

[0098] Embodiment 3

[0099] The depth correction module includes a signal compensation unit and a data credibility calculation unit;

[0100] Based on the attenuation law of deep geophysical signals, the signal compensation unit constructs a depth-signal compensation model and corrects the deep detection signals to improve the integrity and accuracy of the data;

[0101] The data credibility calculation unit is used to extract multi-source geological data and calculate the credibility Sx of the deep data. The credibility Sx of the deep data is obtained through the following formula:

[0102]

[0103] where M represents the signal intensity of the deep detection data, V represents the structural stability of the deep detection data, N represents the noise level of the deep detection data, and Wm, Wv, and Wn are the weight coefficients of each parameter respectively.

[0104] The data credibility calculation unit evaluates the credibility Sx of the deep data within different depth ranges by setting a credibility threshold Q. The specific evaluation scheme is as follows:

[0105] If the current credibility Sx of the deep data > the credibility threshold Q, a first credibility result is generated at this time, indicating that the data credibility within this depth range is normal and is used for ore body identification;

[0106] If the current deep data credibility Sx < credibility threshold Q, a second credibility result is generated at this time, indicating that the data credibility within this depth range is abnormal. Further optimization processing is performed at this time;

[0107] Finally, based on the depth-signal compensation model, the data with abnormal credibility is optimized and inverted, and the optimized deep ore body identification results are displayed based on the interactive interface.

[0108] Based on the comprehensively corrected ore body boundary data and deep exploration data, the resource calculation module calculates the resource quantity Qz through the following formula based on the Monte Carlo simulation method:

[0109]

[0110] where Qa i represents the volume of the i-th simulation sampling unit, Qb i represents the density of the i-th simulation sampling unit, and z is the number of Monte Carlo simulation samplings.

[0111] Secondly, based on the calculation results of the resource quantity Qz, the ore body grade information is extracted, and the grade distribution Pz is calculated through statistical analysis methods; further combining the resource quantity Qz and grade distribution Pz in different regions, a resource evaluation report is generated; among them, the resource evaluation report includes the resource quantity calculation results, grade distribution conditions and their spatial variability analysis, and the evaluation results are displayed through the interactive interface.

[0112] The dynamic feedback module obtains and updates the exploration data in real time, including the resource quantity Qz and grade distribution Pz, and dynamically stores and processes the newly obtained data;

[0113] Then, based on the real-time updated exploration data, the parameters of the resource calculation model are adaptively adjusted to optimize the calculation accuracy of the resource quantity Qz and grade distribution Pz. The optimization process is as follows:

[0114] Extract the currently updated data set and calculate the data change rate Rd;

[0115] If the data change rate Rd exceeds the preset threshold, trigger the recalculation of the model parameters and compare the errors of the model outputs before and after adjustment;

[0116] Based on the error analysis results, adaptively optimize the model parameters;

[0117] Finally, based on the optimized resource calculation results, a resource evaluation report is generated, and the change trends of the resource quantity Qz and grade distribution Pz are displayed through an interactive visualization interface, and at the same time, uncertainty warning information is provided; when the uncertainty evaluation result exceeds the preset threshold, a warning signal is generated and the user is prompted to perform further data verification or model adjustment.

[0118] In this embodiment, the deep data credibility Sx is calculated by the depth correction module based on the signal strength M, the structural stability V, and the noise level N. By combining the weight coefficients Wm, Wv, Wn, and the credibility threshold Q, the deep data quality grading evaluation and optimization inversion are realized, significantly improving the recognition accuracy of deep ore bodies. The resource calculation module uses the Monte Carlo simulation method to accurately calculate the resource quantity Qz through the sampling unit volume Vi, density ρi, and the number of samplings z, and generates a resource evaluation report including spatial variability analysis in combination with the grade distribution Pz. The dynamic feedback module monitors the changes in the resource quantity Qz and the grade distribution Pz in real time, realizes parameter adaptive optimization by calculating the data change rate Rd, automatically triggers model recalculation and error analysis when the data fluctuation exceeds the threshold, and continuously improves the evaluation accuracy. The system intuitively displays the optimized deep ore body recognition results, resource evaluation data, and warning information through an interactive visualization interface, realizes the full-process intelligent management from data acquisition, depth correction, resource calculation to dynamic optimization, and provides high-precision and high-reliability decision support for metal resource evaluation.

[0119] Embodiment 4

[0120] A metal resource evaluation method based on geological exploration, comprising the following steps:

[0121] Step 1: Collect and integrate multi-source geological data, including borehole-related data, geophysical-related data, and remote sensing-related data. Then, through the adaptive weighted algorithm, calculate the evaluation data confidence Rx and perform probability filling on sparse data.

[0122] Step 2: Based on 3D geological modeling and machine learning algorithms, use multi-source geological data to analyze the spatial distribution characteristics of the ore body morphology, calculate and evaluate the mineralization continuity index Lx, and dynamically correct the ore body boundary.

[0123] Step 3: Combine the attenuation law of deep geophysical signals to construct a depth-signal compensation model. Then, extract multi-source geological data to calculate the deep data credibility Sx, and improve the recognition accuracy of deep ore bodies through inversion optimization.

[0124] Step 4: Based on the comprehensively corrected ore body boundary and deep data, use the Monte Carlo simulation to calculate the resource quantity Qz and the grade distribution Pz, and generate a resource evaluation report.

[0125] Step 5: Monitor the update of exploration data in real time, including the resource quantity Qz and the grade distribution Pz, automatically optimize the model parameters, and feedback the resource evaluation results and uncertainty warnings through a visualization interface.

[0126] Although embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A metal resource evaluation system based on geological exploration, characterized in that: It includes a data fusion module, a boundary optimization module, a depth correction module, a resource calculation module, and a dynamic feedback module; The data fusion module is used to collect and integrate multi-source geological data, including borehole-related data, geophysical-related data, and remote sensing-related data. Then, through an adaptive weighted algorithm, it calculates and evaluates the data confidence level Rx, and performs probabilistic filling on sparse data; Based on 3D geological modeling and machine learning algorithms, the boundary optimization module uses multi-source geological data to analyze the spatial distribution characteristics of the ore body morphology, calculates and evaluates the mineralization continuity index Lx, and dynamically corrects the ore body boundary; The depth correction module is used to combine the attenuation law of deep geophysical signals to construct a depth-signal compensation model. Then, it extracts multi-source geological data to calculate the credibility Sx of deep data, and improves the recognition accuracy of deep ore bodies through inversion optimization; The resource calculation module is used to comprehensively consider the corrected ore body boundary and deep data, and uses Monte Carlo simulation to calculate the resource quantity Qz and grade distribution Pz, and generates a resource evaluation report; The dynamic feedback module is used to monitor the update of exploration data in real time, including the resource quantity Qz and grade distribution Pz, automatically optimize the model parameters, and feedback the resource evaluation results and uncertainty warnings through a visualization interface.

2. A metal resource evaluation system based on geological exploration according to claim 1, characterized in that: The data fusion module includes a data acquisition unit, a confidence calculation unit, and a data optimization unit; The data acquisition unit is used to collect and integrate multi-source geological data, including the borehole data reference value Zk, the geophysical data reference value Dw, and the remote sensing data reference value Yg; The confidence calculation unit calculates and evaluates the data confidence level Rx through an adaptive weighted algorithm. The specific calculation method is as follows: In the formula, Zmax, Dmax, and Ymax respectively represent the maximum credibility reference values of borehole data, geophysical data, and remote sensing data; α, β, and γ are dynamically adjustable weight coefficients, and α + β + γ = 1.

3. A metal resource evaluation system based on geological exploration according to claim 1, characterized in that: The confidence calculation unit compares and evaluates the calculated data confidence level Rx with a preset confidence threshold R. The specific evaluation scheme is as follows: If the current data confidence level Rx ≥ the confidence threshold R, a first confidence result is generated, indicating that the current data credibility is normal and it is directly used for resource evaluation; If the current data confidence level Rx < the confidence threshold R, a second confidence result is generated, indicating that the current data credibility is abnormal, and at this time, probabilistic filling is performed; According to the confidence evaluation result and the data confidence level Rx, probabilistic filling is performed on sparse data, and a data credibility report is generated, including the confidence values of each data source, the optimization processing records, and the recommended correction measures. Finally, it is fed back to the user through a visualization interface.

4. A metal resource evaluation system based on geological exploration according to claim 1, characterized in that: The boundary optimization module includes a morphology analysis unit and a boundary correction unit; The morphology analysis unit is used to construct a spatial distribution characteristic model of the ore body morphology based on multi-source geological data, and calculate the mineralization continuity index Lx. The specific calculation formula is as follows: Lx = f(D, C, S); Among them, D represents the distance variability parameter of the ore body morphology, C represents the spatial correlation parameter of the ore body mineralization degree, and S represents the boundary change trend parameter of the mineralized body; Then, combined with the geological environment change information, the dynamic adjustment factor Tx of the ore body boundary is obtained. The specific calculation formula is as follows: Wherein, k represents the monitoring period, i = 1, 2, 3......, k, Ti represents the temperature value at the i-th time node within the monitoring period, and Tavg represents the average temperature within the monitoring period.

5. A metal resource evaluation system based on geological exploration according to claim 1, characterized in that: The boundary correction unit is used to calculate the change trend of the mineralization continuity index Lx under different geological environment conditions, and obtain the boundary optimization coefficient Ly based on its influence degree on the ore body boundary dynamic adjustment factor Tx. The specific calculation formula is as follows: Ly = g(Lx, Tx) Then, a boundary stability threshold L is preset and compared with the boundary optimization coefficient Ly to evaluate the applicability of the ore body boundary correction strategy. The specific content is as follows: If the boundary optimization coefficient Ly ≥ the boundary stability threshold L, it is determined that the current ore body boundary needs to be dynamically corrected, and an optimization instruction is triggered; If the boundary optimization coefficient Ly < the boundary stability threshold L, it is determined that the current ore body boundary does not need to be corrected, and the original boundary form is maintained.

6. A metal resource evaluation system based on geological exploration according to claim 1, characterized in that: The depth correction module includes a signal compensation unit and a data credibility calculation unit; The signal compensation unit constructs a depth-signal compensation model based on the attenuation law of deep geophysical signals, and corrects the deep detection signals to improve the integrity and accuracy of the data; The data credibility calculation unit is used to extract multi-source geological data and calculate the deep data credibility Sx. The deep data credibility Sx is obtained through the following formula: Wherein, M represents the signal intensity of the deep detection data, V represents the structural stability of the deep detection data, N represents the noise level of the deep detection data, and Wm, Wv, and Wn are the weight coefficients of each parameter respectively.

7. A metal resource evaluation system based on geological exploration according to claim 1, characterized in that: The data credibility calculation unit evaluates the deep data credibility Sx within different depth ranges by setting a credibility threshold Q. The specific evaluation scheme is as follows: If the current deep data credibility Sx > the credibility threshold Q, a first credibility result is generated at this time, indicating that the data credibility within this depth range is normal and is used for ore body identification; If the current deep data credibility Sx < the credibility threshold Q, a second credibility result is generated at this time, indicating that the data credibility within this depth range is abnormal, and further optimization processing is performed at this time; Finally, based on the depth-signal compensation model, the data with abnormal credibility is optimized and inverted, and the optimized deep ore body identification result is displayed based on the interactive interface.

8. A metal resource evaluation system based on geological exploration according to claim 1, characterized in that: The resource calculation module calculates the resource amount Qz through the following formula based on the comprehensively corrected ore body boundary data and deep detection data, using the Monte Carlo simulation method: Among them, Qa i represents the volume of the ith simulated sampling unit, Qb i represents the density of the ith simulation sampling unit, and z is the number of Monte Carlo simulation samplings. Secondly, based on the calculation result of the resource amount Qz, the ore body grade information is extracted, and the grade distribution Pz is calculated through statistical analysis methods; further combining the resource amount Qz and grade distribution Pz in different regions, a resource evaluation report is generated; wherein, the resource evaluation report includes the resource amount calculation result, grade distribution situation, and its spatial variability analysis, and the evaluation result is displayed through the interactive interface.

9. A metal resource assessment system based on geological exploration according to claim 1, characterized in that: The dynamic feedback module obtains and updates exploration data in real time, including the resource amount Qz and grade distribution Pz, and dynamically stores and processes the newly obtained data; Next, based on the real-time updated exploration data, the parameters of the resource calculation model are adaptively adjusted to optimize the calculation accuracy of the resource quantity Qz and the grade distribution Pz. The optimization process is as follows: Extract the currently updated dataset and calculate the data change rate Rd; If the data change rate Rd exceeds the preset threshold, trigger the recalculation of the model parameters and compare the errors of the model output before and after adjustment; Based on the error analysis results, adaptively optimize the model parameters; Finally, based on the optimized resource calculation results, generate a resource assessment report and display the change trends of the resource quantity Qz and the grade distribution Pz through an interactive visualization interface, and at the same time provide uncertainty warning information; When the uncertainty assessment result exceeds the preset threshold, generate a warning signal and prompt the user to conduct further data verification or model adjustment.

10. A metal resource assessment method based on geological exploration, and a metal resource assessment system based on geological exploration according to any one of claims 1-9, characterized in that: Including the following steps: Step 1: Collect and integrate multi-source geological data, including borehole-related data, geophysical-related data, and remote sensing-related data. Then, through an adaptive weighted algorithm, calculate the confidence level Rx of the evaluation data and perform probability filling on sparse data; Step 2: Based on 3D geological modeling and machine learning algorithms, use multi-source geological data to analyze the spatial distribution characteristics of the ore body morphology, calculate and evaluate the mineralization continuity index Lx, and dynamically correct the ore body boundary; Step 3: Combine the attenuation law of deep geophysical signals to construct a depth-signal compensation model. Then, extract multi-source geological data to calculate the credibility Sx of deep data, and improve the recognition accuracy of deep ore bodies through inversion optimization; Step 4: Based on the comprehensively corrected ore body boundary and deep data, use Monte Carlo simulation to calculate the resource quantity Qz and the grade distribution Pz, and generate a resource assessment report; Step 5: Real-time monitor the update of exploration data, including the resource quantity Qz and the grade distribution Pz, automatically optimize the model parameters, and feedback the resource assessment results and uncertainty warnings through a visualization interface.

Images