Mineral resource intelligent identification method based on multi-source remote sensing data

Abstract

The invention relates to the technical field of mineral exploration, and discloses a mineral resource intelligent identification method based on multi-source remote sensing data, and the method constructs an intelligent identification model based on a deviation analysis and correction mechanism through integrating the multi-source remote sensing data, geological data and mineral reaction characteristic signals, can dynamically adapt to different environmental conditions, and improves the identification efficiency. According to the method, the mineral resource exploration precision and reliability are remarkably improved, through dynamic correction and multi-coefficient integration, the misjudgment rate is effectively reduced, the recognition accuracy and precision ratio of the mineral target area are improved, potential mining areas can be rapidly screened out in a large-range area, manual intervention is reduced, the exploration efficiency is remarkably improved, and the method is suitable for popularization and application. By generating a plurality of mineral marker guidance coefficients KWX, the mineral resource potential is comprehensively evaluated from multiple angles, and the accuracy and stability of mineral recognition are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mineral exploration, and specifically to an intelligent identification method for mineral resources based on multi-source remote sensing data. Background Technique

[0002] Mineral resource exploration is an important application direction of remote sensing technology, especially the identification and detection of the distribution of mineral resources through remote sensing data. Specifically in the field of mineral resource exploration, the intelligent identification of iron ore is a key task. By using multi-source remote sensing data and combining image processing and data fusion technologies, potential iron ore resource areas can be accurately identified, significantly improving the efficiency and accuracy of resource exploration.

[0003] Although the intelligent identification method for mineral resources based on multi-source remote sensing data has made certain progress in iron ore exploration, it still faces some key problems. First, the resolution of remote sensing data still has limitations in large-scale iron ore exploration, resulting in the inability to accurately identify the tiny features of the mining area, affecting the accuracy of identification. Second, optical remote sensing data is greatly affected by atmospheric interference and shadow effects, especially in complex terrain areas, which may cause the surface features of the mining area to be blocked, thereby reducing the effective identification ability of mineral resources. In addition, in areas where the ore body is deeply buried or the terrain is complex, traditional remote sensing means may be difficult to identify the hidden mineral distribution, resulting in omissions or errors in the identification results. Moreover, although multi-source data fusion technology helps to improve the identification accuracy, due to the differences in resolution, quality, etc. of different data sources, how to effectively fuse these data is still a technical problem, affecting the application scope and accuracy of the mineral resource exploration method.

[0004] Therefore, we propose an intelligent identification method for mineral resources based on multi-source remote sensing data to solve the above-mentioned problems. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent identification method for mineral resources based on multi-source remote sensing data to solve the problems of mineral exploration proposed in the above background technique.

[0006] To achieve the above purpose, the present invention provides the following technical solution: An intelligent identification method for mineral resources based on multi-source remote sensing data, characterized in that the specific steps are as follows: S1. Data collection, collect multi-source data in the process of mineral identification and perform preprocessing to generate the first data set, the second data set, and the third data set; S2. Remote sensing analysis, perform computational analysis on the first data set to generate the remote sensing deviation analysis coefficient YGF, the remote sensing correction coefficient YGJ, and the first analysis result; S3. Geological analysis: perform computational analysis on the second dataset to generate a geological deviation analysis coefficient DZF, a geological correction coefficient DZJ, and a second analysis result; S4. Mineral characteristic signal analysis: perform computational analysis on the third dataset to generate a mineral reaction deviation analysis coefficient KWF, a mineral reaction correction coefficient KWJ, and a third analysis result; S5. Integrate and calculate the remote sensing deviation analysis coefficient YGF, the remote sensing correction coefficient YGJ, the geological deviation analysis coefficient DZF, the geological correction coefficient DZJ, the mineral reaction deviation analysis coefficient KWF, and the mineral reaction correction coefficient KWJ to generate multiple mineral marking guidance coefficients KWX. Analyze the multiple mineral marking guidance coefficients KWX respectively to generate a fourth analysis result. According to the fourth analysis result, execute a mineral marking instruction for the target.

[0007] Preferably, step S1 completes data collection and preprocessing through the following steps; Step S1.1: Identify and extract remote sensing data, geomorphic environment data collected by remote sensing, and mineral reaction data during the mineral identification process; The remote sensing data includes a spectral reflectance index, a terrain deformation rate, and a lidar canopy height; The geomorphic environment data includes a terrain complexity index, a vegetation coverage, and a rainfall erosivity index; The mineral reaction data includes a short-wave infrared absorption depth, a thermal infrared emissivity anomaly index, and a radar polarization scattering entropy; The spectral reflectance index, the terrain deformation rate, the lidar canopy height, the terrain complexity index, the vegetation coverage, the rainfall erosivity index, the short-wave infrared absorption depth, the thermal infrared emissivity anomaly index, and the radar polarization scattering entropy constitute a multi-source dataset; Step S1.2: Preprocess and dimensionlessize the multi-source dataset, and reorganize the preprocessed multi-source data into a first dataset, a second dataset, and a third dataset; The first dataset includes a spectral reflectance index A, a terrain deformation rate B, and a lidar canopy height C; The second dataset includes a terrain complexity index D, a vegetation coverage E, and a rainfall erosivity index F; The third dataset includes a short-wave infrared absorption depth G, a thermal infrared emissivity anomaly index H, and a radar polarization scattering entropy I.

[0008] Preferably, the step S2 completes the calculation and analysis of the first dataset through the following steps; Step S2.1: Integrate and calculate the first dataset to generate a remote sensing deviation analysis coefficient YGF and a remote sensing correction coefficient YGJ; Step S2.2: Analyze the remotely sensed deviation analysis coefficient YGF obtained through calculation to generate a first analysis result, specifically as follows: When it indicates that the current remotely sensed data is normal, and the remotely sensed correction coefficient YGJ is not required in subsequent model analysis; When it indicates that the current remotely sensed data has fluctuations, and the remotely sensed correction coefficient YGJ is required in subsequent model analysis.

[0009] Preferably, in step S2.1, the remotely sensed deviation analysis coefficient YGF and the remotely sensed correction coefficient YGJ are obtained through calculation using the following formula;

[0010]

[0011] In the formula: A is the spectral reflectance index, B is the terrain deformation rate, C is the lidar canopy height, a1 and a2 are weight values, and the values of a1 and a2 are adjusted and set by the user, exp is the exponential function, max is the maximum value function, and ln is the natural logarithm function.

[0012] Preferably, step S3 is completed by performing the following steps for the calculation and analysis of the second data set; Step S3.1: Integrate and calculate the second data set to generate a geological deviation analysis coefficient DZF and a geological correction coefficient DZJ; Step S3.2: Analyze the geological deviation analysis coefficient DZF obtained through calculation to generate a second analysis result, specifically as follows: When it indicates that the current geological data is normal, and the geological correction coefficient DZJ is not required in subsequent model analysis; When it indicates that the current geological data has fluctuations, and the geological correction coefficient DZJ is required in subsequent model analysis.

[0013] Preferably, in step S3.1, the geological deviation analysis coefficient DZF and the geological correction coefficient DZJ are obtained through calculation using the following formula;

[0014]

[0015] In the formula: D is the terrain complexity index, E is the vegetation coverage, F is the rainfall erosion force index water, b1, b2, and b3 are proportionality coefficients, and b1≠b2≠b3≠0, b1≠b2≠b3≠1, a3 and a4 are weight values, and the values of b1, b2, b3, a3, and a4 are adjusted and set by the user.

[0016] Preferably, in step S4, the calculation and analysis of the third data set are completed through the following steps; Step S4.1: Integrate and calculate the third data set to generate a mineral reaction deviation analysis coefficient KWF and a mineral reaction correction coefficient KWJ; Step S4.2: Analyze the calculated mineral reaction deviation analysis coefficient KWF to generate a third analysis result, specifically as follows: When it represents that the current mineral data is normal and the mineral reaction correction coefficient KWJ does not need to be used in subsequent model analysis; When it represents that the current mineral data fluctuates and the mineral reaction correction coefficient KWJ needs to be used in subsequent model analysis.

[0017] Preferably, in step S4.1, the mineral reaction deviation analysis coefficient KWF and the mineral reaction correction coefficient KWJ are calculated through the following formula;

[0018]

[0019] In the formula: G is the short-wave infrared absorption depth, H is the thermal infrared emissivity anomaly index, I is the radar polarization scattering entropy, exp is the exponential function, max is the maximum value function, a5 is the weight value, K is the correction attenuation coefficient, and the values of a5 and K are adjusted and set by the user.

[0020] Preferably, in step S5, the calculation and analysis of the third data set are completed through the following steps; Step S4.1: Integrate and calculate the remote sensing deviation analysis coefficient YGF, the remote sensing correction coefficient YGJ, the geological deviation analysis coefficient DZF, the geological correction coefficient DZJ, the mineral reaction deviation analysis coefficient KWF, and the mineral reaction correction coefficient KWJ to generate multiple mineral marking guidance coefficients KWX; Step S4.2: Analyze the calculated ones to generate a first analysis result, specifically as follows: When it represents that the current mineral data is abnormal and no guidance marking is performed; When it represents that the current mineral data is normal and guidance marking is performed; When it represents that the current mineral data is abnormal and no guidance marking is performed; When it represents that the current mineral data is normal and guidance marking is performed; When When it is, it represents that the current mineral data is abnormal and no guidance mark is made; When it is, it represents that the current mineral data is normal and a guidance mark is made; When it is, it represents that the current mineral data is abnormal and no guidance mark is made; When it is, it represents that the current mineral data is normal and a guidance mark is made.

[0021] Preferably, in step S5.1, multiple mineral marking guidance coefficients KWX are calculated and obtained through the following formula;

[0022]

[0023]

[0024]

[0025]

[0026] In the formula: YGJ is the remote sensing deviation analysis coefficient, YGJ is the remote sensing correction coefficient, DZF is the geological deviation analysis coefficient, DZJ is the geological correction coefficient, KWF is the mineral reaction deviation analysis coefficient, KWJ is the mineral reaction correction coefficient, exp is the exponential function, and K is the correction attenuation coefficient.

[0027] Compared with the prior art, the beneficial effects of the present invention are: 1. By comprehensively integrating multi-source remote sensing data, geological data, and mineral reaction characteristic signals, the present method constructs an intelligent recognition model based on a deviation analysis and correction mechanism, which can dynamically adapt to different environmental conditions, significantly improving the accuracy and reliability of mineral resource exploration. Through dynamic correction and multi-coefficient integration, the present method effectively reduces the misjudgment rate, improves the recognition accuracy and precision of mineral target areas, and can quickly screen out potential mining areas within a large range of areas, reducing manual intervention and significantly enhancing the exploration efficiency.

[0028] 2. By integrating and calculating the remote sensing deviation analysis coefficient YGF, the remote sensing correction coefficient YGJ, the geological deviation analysis coefficient DZF, the geological correction coefficient DZJ, the mineral reaction deviation analysis coefficient KWF, and the mineral reaction correction coefficient KWJ, multiple mineral marking guidance coefficients KWX are generated. Through the weighted calculation of multiple parameters, the present method can comprehensively consider remote sensing, geology, and mineral reaction characteristics, comprehensively evaluate the potential of mineral resources from multiple perspectives, and significantly improve the accuracy and stability of mineral recognition. Description of the Drawings

[0029] Figure 1This is the method step diagram of the present invention. Detailed implementation manners

[0030] 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. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0031] Embodiment 1: Please refer to Figure 1 , an intelligent mineral resource identification method based on multi-source remote sensing data, the specific steps are as follows: S1. Data collection, collect multi-source data in the process of mineral identification and perform preprocessing to generate the first data set, the second data set, and the third data set; S2. Remote sensing analysis, perform computational analysis on the first data set to generate a remote sensing deviation analysis coefficient YGF, a remote sensing correction coefficient YGJ, and a first analysis result; S3. Geological analysis, perform computational analysis on the second data set to generate a geological deviation analysis coefficient DZF, a geological correction coefficient DZJ, and a second analysis result; S4. Mineral characteristic signal analysis, perform computational analysis on the third data set to generate a mineral reaction deviation analysis coefficient KWF, a mineral reaction correction coefficient KWJ, and a third analysis result; S5. Integrate and calculate the remote sensing deviation analysis coefficient YGF, the remote sensing correction coefficient YGJ, the geological deviation analysis coefficient DZF, the geological correction coefficient DZJ, the mineral reaction deviation analysis coefficient KWF, and the mineral reaction correction coefficient KWJ to generate multiple mineral marking guiding coefficients KWX. Analyze the multiple mineral marking guiding coefficients KWX respectively to generate a fourth analysis result. According to the fourth analysis result, execute a mineral marking instruction on the target.

[0032] In this embodiment: In step S1, during the process of mineral resource identification, the collection of multi-source data is first carried out, including optical remote sensing data, radar remote sensing data, and lidar data. The collected data undergoes necessary preprocessing, specifically including operations such as radiometric correction, geometric registration, and noise filtering, so as to generate the first data set, the second data set, and the third data set. Through the preprocessing and standardization of multi-source data, the spatio-temporal inconsistency and dimensional differences between data can be eliminated, ensuring the high quality of the data and providing a reliable basis for subsequent analysis. This step effectively reduces the noise and errors that may exist in the original data, improves the overall data quality, and lays a foundation for subsequent accurate analysis.

[0033] In step S2, in the remote sensing analysis step, by performing computational analysis on the first data set, a remote sensing deviation analysis coefficient YGF and a remote sensing correction coefficient YGJ are generated. YGF reflects the deviation between remote sensing data and actual observed values and can reveal data quality problems. If YGF exceeds the set threshold, the data is corrected according to the remote sensing correction coefficient YGJ. Through this step, noise reduction and correction of remote sensing data can be performed to eliminate interferences such as atmosphere and sensor errors. This step significantly improves the reliability and accuracy of remote sensing data by dynamically adjusting the deviation correction of remote sensing data. The corrected remote sensing data can more accurately reflect the actual surface conditions, providing more accurate input data for the intelligent identification of mineral resources, thereby effectively reducing the risk of misidentification.

[0034] In step S3, in the geological analysis step, computational analysis is performed on the second data set to generate a geological deviation analysis coefficient DZF and a geological correction coefficient DZJ. DZF quantifies the impact of the geological environment on mineral identification by analyzing geological parameters such as terrain complexity, vegetation coverage, and rainfall erosivity. When the value of DZF exceeds the set threshold, the system generates the corresponding geological correction coefficient DZJ to optimize the model's identification ability. Through geological analysis, areas with complex geological environments, such as landslides and karsts, can be accurately identified, avoiding misjudgment. In a complex geological environment, this step can effectively eliminate the interference of adverse factors, making the mineral identification process more accurate and stable.

[0035] In step S4, the mineral characteristic signal analysis is performed by computational analysis of the third data set to generate a mineral reaction deviation analysis coefficient KWF and a mineral reaction correction coefficient KWJ. KWF mainly measures the intensity of the mineral characteristic signal and quantitatively analyzes the reaction of the mineral. If the value of KWF exceeds the set threshold, KWJ will be corrected according to the specific situation. Through this step, the characteristic signal of the mineral can be more accurately identified, eliminating the interference of surface noise. This step can help accurately identify the mineral characteristic signal, exclude the interference of surface coverings, climate factors, etc., and improve the accuracy of mineral classification and identification. Especially in an environment with a low signal-to-noise ratio, efficient identification can still be achieved.

[0036] In step S5, in this step, the aforementioned remote sensing deviation analysis coefficient YGF, remote sensing correction coefficient YGJ, geological deviation analysis coefficient DZF, geological correction coefficient DZJ, mineral reaction deviation analysis coefficient KWF, and mineral reaction correction coefficient KWJ are integrated and calculated to generate multiple mineral marking guidance coefficients KWX. According to these mineral marking guidance coefficients, the target area is analyzed to generate the final mineral marking instruction. This step integrates multi-source data and correction information, providing efficient and accurate decision-making support for the intelligent identification of mineral resources. Through the fusion and analysis of multiple coefficients, it can synthesize the information of each data source and improve the identification accuracy of the target area. This method can effectively identify the spatial distribution of mineral resources and potential mineral deposits, greatly improving the efficiency and accuracy of mineral exploration.

[0037] Compared with traditional mineral resource identification methods, this method has made significant improvements in many aspects. Traditional methods mostly rely on a single data source and mostly use static models for mineral identification, which are easily affected by data quality problems and the complexity of the geological environment, resulting in unstable identification results. In contrast, this method constructs an intelligent identification model based on deviation analysis and correction mechanism by integrating multi-source remote sensing data, geological data, and mineral reaction characteristic signals, which can dynamically adapt to different environmental conditions and significantly improve the accuracy and reliability of mineral resource exploration. Through dynamic correction and multi-coefficient integration, this method effectively reduces the misjudgment rate, improves the identification accuracy and precision rate of mineral target areas, and can quickly screen potential mining areas within a large range, reducing manual intervention and significantly improving the exploration efficiency.

[0038] Embodiment 2: Please refer to Figure 1 , step S1 completes data collection and preprocessing through the following steps; Step S1.1: Identify and extract the remote sensing data, geomorphic environment data collected by remote sensing, and mineral reaction data during the mineral identification process; Among them, the remote sensing data includes spectral reflectance index, terrain deformation rate, and lidar canopy height; The geomorphic environment data includes terrain complexity index, vegetation coverage, and rainfall erosivity index water; The mineral reaction data includes short-wave infrared absorption depth, thermal infrared emissivity anomaly index, and radar polarization scattering entropy; The spectral reflectance index, terrain deformation rate, lidar canopy height, terrain complexity index, vegetation coverage, rainfall erosivity index water, short-wave infrared absorption depth, thermal infrared emissivity anomaly index, and radar polarization scattering entropy constitute a multi-source data set; Step S1.2: Preprocess and dimensionless the multi-source data set, and reorganize the preprocessed multi-source data into a first data set, a second data set, and a third data set; The first dataset includes the spectral reflectance index A, the topographic deformation rate B, and the lidar canopy height C; The second dataset includes the topographic complexity index D, the vegetation coverage E, and the rainfall erosivity index water F; The third dataset includes the shortwave infrared absorption depth G, the thermal infrared emissivity anomaly index H, and the radar polarization scattering entropy I.

[0039] In this embodiment: Traditional methods usually rely on a single data source for mineral resource identification and are easily affected by local data biases or noises. In step S1, by integrating remote sensing data such as the spectral reflectance index, the topographic deformation rate, and the lidar canopy height, and combining geomorphic environment data and mineral reaction data, this method provides multi-dimensional and multi-source data support, effectively improving the accuracy and reliability of the identification process.

[0040] The processed data is reorganized into three independent datasets with specific functions - the first dataset, the second dataset, and the third dataset, making the data analysis more orderly and structured. This division of datasets not only facilitates subsequent calculations and analyses but also enables each dataset to focus on different mineral identification features, improving the pertinence and precision of the analysis. For example, the first dataset focuses on remote sensing signals and topographic changes, the second dataset focuses on geological and vegetation features, and the third dataset focuses on the reaction features of minerals. Through this categorization method, feature extraction and data processing can be carried out more efficiently.

[0041] Through the reasonable division and precise preprocessing of the multi-source datasets, this step provides a high-quality data foundation for subsequent remote sensing analysis, geological analysis, and mineral feature analysis. The processing and optimization of each dataset can ensure the accuracy and relevance of each data source in the subsequent analysis process, enhancing the robustness of the entire identification method.

[0042] Example 3: Please refer to Figure 1 , step S2 is completed by the following steps for the calculation and analysis of the first dataset; Step S2.1: Integrate and calculate the first dataset to generate the remote sensing deviation analysis coefficient YGF and the remote sensing correction coefficient YGJ; Step S2.2: Analyze the calculated remote sensing deviation analysis coefficient YGF to generate the first analysis result, specifically as follows: When , it represents that the current remote sensing data is normal and the remote sensing correction coefficient YGJ does not need to be used in the subsequent model analysis; When , it represents that the current remote sensing data has fluctuations and the remote sensing correction coefficient YGJ needs to be used in the subsequent model analysis.

[0043] In step S2.1, the remote sensing deviation analysis coefficient YGF and the remote sensing correction coefficient YGJ are calculated and obtained through the following formula;

[0044]

[0045] In the formula: A is the spectral reflectance index, B is the terrain deformation rate, C is the lidar canopy height, a1 and a2 are weight values, and the values of a1 and a2 are adjusted and set by the user, exp is the exponential function, max is the maximum value function, and ln is the natural logarithm function.

[0046] In this embodiment: Traditional methods usually use fixed thresholds or simple linear correction methods to handle the deviation of remote sensing data, which may lead to unstable model effects in complex geological environments. By introducing the remote sensing deviation analysis coefficient YGF and the remote sensing correction coefficient YGJ, this method can automatically determine whether correction is needed according to the quality fluctuations of the remote sensing data itself. Specifically, when YGF ≤ 0.3, it indicates that the data quality is good and the model does not need additional correction; when YGF > 0.3, it indicates that the data has fluctuations, and the model automatically enables the remote sensing correction coefficient YGJ for correction. This dynamic correction mechanism improves the intelligence and accuracy of data processing.

[0047] In step S2.1, the remote sensing deviation analysis coefficient YGF is calculated by combining polynomial calculation with the exponential function, considering multiple remote sensing parameters. This multi-dimensional and comprehensive calculation method can more comprehensively evaluate the quality of remote sensing data, especially can identify the deviations caused by different geological conditions and observation environments. Using the comprehensive calculation based on spectral, terrain and lidar data enables YGF to more accurately reflect the data deviation, thus providing a more accurate basis for the subsequent correction steps.

[0048] By combining the exponential function exp and the maximum value function max, the correction coefficient YGJ can be dynamically adjusted according to the most critical parameters of the remote sensing data, making the correction coefficient more sensitive to important parameters and able to make corresponding adjustments according to different data conditions. This method can more flexibly handle extreme fluctuations in the data compared with traditional linear correction schemes, further improving the adaptability and accuracy of the model.

[0049] When calculating YGF and YGJ, the weight values a1 and a2 are set by the user himself, which provides flexibility and personalized optimization options for practical applications. Users can customize the weight values according to the actual needs of different regions, mineral types and exploration targets, and adjust the sensitivity of the model. This flexible adjustment method enables this method to be widely applicable to different geological environments and mineral resource types, further enhancing the wide applicability of intelligent identification of mineral resources.

[0050] This method can effectively process the fluctuations or outliers that may appear in remote sensing data. Especially when dealing with data collected under complex geological conditions or adverse weather, the correction coefficient YGJ can eliminate the interference of unstable factors, making the final analysis results more robust and reliable. This intelligent correction of fluctuating data significantly improves the robustness and accuracy of the system, reducing misjudgments and missed judgments caused by data quality fluctuations.

[0051] Example 4: Please refer to Figure 1 , and step S3 completes the calculation and analysis of the second data set through the following steps; Step S3.1: Integrate and calculate the second data set to generate a geological deviation analysis coefficient DZF and a geological correction coefficient DZJ; Step S3.2: Analyze the calculated geological deviation analysis coefficient DZF to generate a second analysis result, specifically as follows: When , it means that the current geological data is normal and the geological correction coefficient DZJ does not need to be used in subsequent model analysis; When , it means that the current geological data has fluctuations and the geological correction coefficient DZJ needs to be used in subsequent model analysis.

[0052] In the middle of step S3.1, the geological deviation analysis coefficient DZF and the geological correction coefficient DZJ are calculated through the following formula;

[0053]

[0054] In the formula: D is the terrain complexity index, E is the vegetation coverage, F is the rainfall erosivity index water, b1, b2, and b3 are proportionality coefficients, and b1≠b2≠b3≠0, b1≠b2≠b3≠1, a3 and a4 are weight values, and the values of b1, b2, b3, a3, and a4 are adjusted and set by the user.

[0055] In this embodiment: Traditional mineral resource identification methods may rely only on a single geological data source and usually do not perform dynamic correction according to data fluctuations. This step dynamically evaluates the quality of geological data by calculating the geological deviation analysis coefficient DZF. If DZF≤0.7, it indicates that the geological data is relatively stable and the geological correction coefficient DZJ does not need to be used in the subsequent model; if DZF>0.7, it means that the geological data has fluctuations and the geological correction coefficient DZJ needs to be introduced for correction. This intelligent evaluation and correction mechanism can not only effectively improve the quality control of geological data, but also reduce the instability caused by data fluctuations and enhance the reliability of the identification results.

[0056] In step S3.1, the geological deviation analysis coefficient DZF is obtained through the comprehensive calculation of the terrain complexity index D, the vegetation coverage E, and the rainfall erosion force index F. This comprehensive calculation method of multi-dimensional geological data takes into account multiple factors such as terrain, vegetation, and rainfall, and can more comprehensively reflect the actual deviation of geological data. Especially in complex geological environments, it can more accurately evaluate the data quality. Through reasonable coefficient ratio settings, this method ensures the comprehensive analysis of each factor and is more adaptable to the characteristics of different geological environments.

[0057] The proportional coefficient and the weight coefficient in this step can both be adjusted and set by the user. This function of custom setting provides flexibility for the exploration of different regions or different types of mineral resources. Users can adjust these coefficients according to actual needs, thereby adjusting the sensitivity and correction strategy of geological deviation analysis. This characteristic makes this method have wide applicability and can meet the data analysis needs under various geological conditions.

[0058] When the DZF value exceeds 0.7, the geological correction coefficient DZJ will be enabled and adjusted according to the deviation of DZF. Through the quadratic correction formula, DZJ can make a more refined adjustment to the deviation of DZF, ensuring that the correction coefficient can more accurately reflect the fluctuation of the data. This polynomial correction method can provide stronger adaptability and correction accuracy than the traditional linear correction in the case of large data fluctuations, thus improving the reliability and accuracy of the entire model in complex geological environments.

[0059] This step can effectively identify potential mineral resources in complex geological environments through the comprehensive analysis of geological data. Especially when there are fluctuations in geological data, the correction coefficient DZJ can effectively eliminate the influence of these fluctuations on the identification of mineral resources. This correction mechanism with enhanced adaptability greatly improves the identification accuracy under complex geological conditions and avoids misidentification caused by changes in geological factors.

[0060] Example Five: Please refer to Figure 1 , step S4, which completes the calculation and analysis of the third data set through the following steps; Step S4.1: Integrate and calculate the third data set to generate the mineral reaction deviation analysis coefficient KWF and the mineral reaction correction coefficient KWJ; Step S4.2: Analyze the calculated mineral reaction deviation analysis coefficient KWF to generate the third analysis result, specifically as follows: When it means that the current mineral data is normal, and the mineral reaction correction coefficient KWJ does not need to be used in subsequent model analysis; When When it is, it means that there are fluctuations in the current mineral data, and the mineral reaction correction coefficient KWJ needs to be used in subsequent model analysis.

[0061] In step S4.1, the mineral reaction deviation analysis coefficient KWF and the mineral reaction correction coefficient KWJ are calculated and obtained through the following formula;

[0062]

[0063] In the formula: G is the short-wave infrared absorption depth, H is the thermal infrared emissivity anomaly index, I is the radar polarization scattering entropy, exp is the exponential function, max is the maximum value function, a5 is the weight value, K is the correction attenuation coefficient, and the values of a5 and K are adjusted and set by the user.

[0064] In this embodiment: The traditional method may not fully consider the fluctuations and anomalies in the mineral reaction data and often relies on static correction coefficients. By introducing the mineral reaction deviation analysis coefficient KWF and the mineral reaction correction coefficient KWJ, this method can dynamically evaluate the quality of mineral data and decide whether to enable correction according to the fluctuation situation. Specifically, when KWF ≤ 0.4, the mineral data is considered normal and no correction is required for subsequent analysis; when KWF > 0.4, it means that there are fluctuations in the mineral data, and the system automatically enables KWJ for correction. This intelligent evaluation and correction mechanism improves the adaptability to the fluctuations of mineral reaction data and ensures data quality control in the identification process.

[0065] In step S4.1, the calculation of the mineral reaction deviation analysis coefficient KWF involves the comprehensive analysis of the short-wave infrared absorption depth G, the thermal infrared emissivity anomaly index H, and the radar polarization scattering entropy I. This comprehensive calculation method of multi-dimensional mineral characteristics fully considers the reaction characteristics of different minerals, and improves the sensitivity of KWF to key mineral reaction characteristics through the maximum value function max and the exponential decay exp function, ensuring a more accurate deviation evaluation. This method effectively captures the changes and fluctuations existing in the mineral data and can better handle complex mineral reaction characteristics. Through the use of the exponential decay correction mechanism, the mineral reaction correction coefficient KWJ can be adjusted according to the fluctuation situation of the KWF value, so as to achieve effective correction in the case of large data fluctuations. This exponential decay method is more flexible and accurate than the traditional linear correction method, and can provide stronger adaptability especially for strongly fluctuating mineral data.

[0066] In this step, both the weight coefficient a5 and the correction attenuation coefficient K are adjusted by the user. This design of custom settings enables the mineral resource identification process to be optimized according to different regions and different mineral reaction characteristics. Users can adjust these coefficients according to actual needs to better adapt to various mineral types and geological environments, and improve the applicability and accuracy of the model.

[0067] During the mineral resource identification process, mineral reaction data may be affected by various factors, resulting in data fluctuations or anomalies. By introducing a dynamic correction mechanism, the system can automatically identify these fluctuations and take correction measures to ensure the stability and accuracy of the analysis results. Especially under complex geological conditions, the fluctuations of mineral data are often more obvious. This method can effectively improve the robustness and stability of the identification system and avoid unnecessary impacts of data fluctuations on the final results.

[0068] Example Six: Please refer to Figure 1 , step S5, which is completed by the following steps for the calculation and analysis of the third dataset; Step S4.1: Integrate and calculate the remote sensing deviation analysis coefficient YGF, the remote sensing correction coefficient YGJ, the geological deviation analysis coefficient DZF, the geological correction coefficient DZJ, the mineral reaction deviation analysis coefficient KWF, and the mineral reaction correction coefficient KWJ to generate multiple mineral marking guidance coefficients KWX; Step S4.2: Analyze the calculated results to generate the first analysis result, specifically as follows: When , it means that the current mineral data is abnormal and no guidance marking is performed; When , it means that the current mineral data is normal and guidance marking is performed; When , it means that the current mineral data is abnormal and no guidance marking is performed; When , it means that the current mineral data is normal and guidance marking is performed; When , it means that the current mineral data is abnormal and no guidance marking is performed; When , it means that the current mineral data is normal and guidance marking is performed; When , it means that the current mineral data is abnormal and no guidance marking is performed; When , it means that the current mineral data is normal and guidance marking is performed.

[0069] In step S5.1, multiple mineral marking guidance coefficients KWX are calculated through the following formula;

[0070]

[0071]

[0072]

[0073]

[0074] In the formula: YGJ is the remote sensing deviation analysis coefficient, YGJ is the remote sensing correction coefficient, DZF is the geological deviation analysis coefficient, DZJ is the geological correction coefficient, KWF is the mineral reaction deviation analysis coefficient, KWJ is the mineral reaction correction coefficient, exp is the exponential function, and K is the correction attenuation coefficient.

[0075] In this embodiment: This step generates multiple mineral marking guidance coefficients KWX through the integrated calculation of the remote sensing deviation analysis coefficient YGF, the remote sensing correction coefficient YGJ, the geological deviation analysis coefficient DZF, the geological correction coefficient DZJ, the mineral reaction deviation analysis coefficient KWF, and the mineral reaction correction coefficient KWJ. Through the weighted calculation of multiple parameters, this method can comprehensively consider the characteristics of remote sensing, geology, and mineral reactions, comprehensively evaluate the potential of mineral resources from multiple perspectives, and significantly improve the accuracy and stability of mineral identification.

[0076] In the calculation formula of the mineral marking guidance coefficient KWX, the exponential decay function and the maximum value function max are adopted, making the correction of different data more flexible and accurate. Especially through the introduction of the exponential correction exp, it can effectively reduce the adverse effects brought by the deviations in remote sensing, geological, and mineral reaction data, thus avoiding the situation of overcorrection or ignoring key factors. The maximum value function ensures that among multiple input conditions, the most significant factor can dominate the correction process, thus more accurately reflecting the characteristics of mineral data.

[0077] After generating the mineral marking guidance coefficient KWX, the system performs marking analysis according to the set threshold. When coefficients such as KWX1, KWX2, KWX3, and KWX4 are less than 0.4, it indicates that the current mineral data is abnormal and no guidance marking is performed; while when the coefficient is greater than or equal to 0.4, it indicates that the mineral data is normal and guidance marking is required. Through this dynamic threshold determination mechanism, it can effectively avoid incorrect marking or misleading, ensuring that the finally identified mineral target area has a high credibility.

[0078] When calculating the mineral marking guiding coefficient, multiple attenuation coefficients K and correction parameters are adopted, and these attenuation coefficients can be flexibly set by users according to actual needs. This provides strong flexibility and adaptability for the intelligent identification of different mineral types and geological environments. By adjusting the attenuation coefficients, the system can be optimized according to different regions or mineral resource characteristics, improving the accuracy of mineral identification.

[0079] This step provides more comprehensive data processing capabilities by comprehensively considering remote sensing data, geological environment data, and mineral reaction characteristics. Each mineral marking guiding coefficient is generated through weighted calculations of multiple data sources, thus comprehensively covering the multi-dimensional characteristics of mineral resources. This not only improves the accuracy of mineral identification but also enhances the system's identification ability in the face of complex geological conditions and diverse mineral characteristics.

[0080] Through the calculation and analysis of this step, the system can accurately identify potential areas of mineral resources in a short time. This optimization process helps exploration personnel quickly identify important target areas, improving the efficiency and accuracy of resource exploration and reducing the impact of human judgment errors.

[0081] The content not described in detail in this specification belongs to the prior art well-known to those skilled in the art.

[0082] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent recognition method for mineral resources based on multi-source remote sensing data, characterized in that: The specific steps are as follows: S1. Data collection: Collect multi-source data in the mineral identification process and perform preprocessing to generate the first dataset, the second dataset, and the third dataset. S2. Remote sensing analysis: Perform computational analysis on the first dataset to generate the remote sensing deviation analysis coefficient YGF, the remote sensing correction coefficient YGJ, and the first analysis result. S3. Geological analysis: Perform computational analysis on the second dataset to generate the geological deviation analysis coefficient DZF, the geological correction coefficient DZJ, and the second analysis result. S4. Mineral characteristic signal analysis: Perform computational analysis on the third dataset to generate the mineral reaction deviation analysis coefficient KWF, the mineral reaction correction coefficient KWJ, and the third analysis result. S5. Integrate and calculate the remote sensing deviation analysis coefficient YGF, the remote sensing correction coefficient YGJ, the geological deviation analysis coefficient DZF, the geological correction coefficient DZJ, the mineral reaction deviation analysis coefficient KWF, and the mineral reaction correction coefficient KWJ to generate multiple mineral marking guidance coefficients KWX. Analyze each of the multiple mineral marking guidance coefficients KWX to generate the fourth analysis result. According to the fourth analysis result, execute the mineral marking instruction for the target.

2. The intelligent identification method of mineral resources based on multi-source remote sensing data according to claim 1, wherein: Step S1 completes data collection and preprocessing through the following steps: Step S1.1: Identify and extract the remote sensing data, the geomorphic environment data collected by remote sensing, and the mineral reaction data in the mineral identification process. Among them, the remote sensing data includes the spectral reflectance index, the terrain deformation rate, and the lidar canopy height. The geomorphic environment data includes the terrain complexity index, the vegetation coverage, and the rainfall erosivity index water. The mineral reaction data includes the short-wave infrared absorption depth, the thermal infrared emissivity anomaly index, and the radar polarization scattering entropy. The spectral reflectance index, the terrain deformation rate, the lidar canopy height, the terrain complexity index, the vegetation coverage, the rainfall erosivity index water, the short-wave infrared absorption depth, the thermal infrared emissivity anomaly index, and the radar polarization scattering entropy constitute the multi-source dataset. Step S1.2: Perform preprocessing and dimensionless normalization on the multi-source dataset, and reorganize the preprocessed multi-source data into the first dataset, the second dataset, and the third dataset. The first dataset includes the spectral reflectance index A, the terrain deformation rate B, and the lidar canopy height C. The second dataset includes the terrain complexity index D, the vegetation coverage E, and the rainfall erosivity index water F. The third dataset includes the short-wave infrared absorption depth G, the thermal infrared emissivity anomaly index H, and the radar polarization scattering entropy I.

3. The intelligent identification method of mineral resources based on multi-source remote sensing data according to claim 2, wherein: The said step S2 completes the computational analysis of the first dataset through the following steps: Step S2.1: Integrate and calculate the first dataset to generate the remote sensing deviation analysis coefficient YGF and the remote sensing correction coefficient YGJ. Step S2.2: Analyze the calculated remote sensing deviation analysis coefficient YGF to generate the first analysis result, specifically as follows: When it indicates that the current remote sensing data is normal and there is no need to use the remote sensing correction coefficient YGJ in subsequent model analysis; When it indicates that there are fluctuations in the current remote sensing data, and the remote sensing correction coefficient YGJ needs to be used in the subsequent model analysis.

4. The intelligent mineral resource identification method based on multi-source remote sensing data according to claim 3, wherein: In the said step S2.1, the remote sensing deviation analysis coefficient YGF and the remote sensing correction coefficient YGJ are calculated through the following formula: ； ； Where: A is the spectral reflectance index, B is the terrain deformation rate, C is the lidar canopy height, a1 and a2 are weight values, and the values of a1 and a2 are adjusted and set by the user, exp is the exponential function, max is the maximum value function, and ln is the natural logarithm function.

5. The intelligent identification method of mineral resources based on multi-source remote sensing data according to claim 4, characterized in that: The above-mentioned step S3 completes the calculation and analysis of the second data set through the following steps; Step S3.1: Integrate and calculate the second data set to generate a geological deviation analysis coefficient DZF and a geological correction coefficient DZJ; Step S3.2: Analyze the calculated geological deviation analysis coefficient DZF to generate a second analysis result, specifically as follows: When it indicates that the current geological data is normal and there is no need to use the geological correction coefficient DZJ in subsequent model analysis; When it indicates that there are fluctuations in the current geological data, and the geological correction coefficient DZJ needs to be used in subsequent model analysis.

6. The intelligent identification method of mineral resources based on multi-source remote sensing data according to claim 5, characterized in that: In the middle of the above-mentioned step S3.1, the geological deviation analysis coefficient DZF and the geological correction coefficient DZJ are calculated through the following formula; ； ； Where: D is the terrain complexity index, E is the vegetation coverage, F is the rainfall erosivity index water, b1, b2, and b3 are proportionality coefficients, and b1≠b2≠b3≠0, b1≠b2≠b3≠1, a3 and a4 are weight values, and the values of b1, b2, b3, a3, and a4 are adjusted and set by the user.

7. The intelligent identification method of mineral resources based on multi-source remote sensing data according to claim 6, characterized in that: The above-mentioned step S4 completes the calculation and analysis of the third data set through the following steps; Step S4.1: Integrate and calculate the third data set to generate a mineral reaction deviation analysis coefficient KWF and a mineral reaction correction coefficient KWJ; Step S4.2: Analyze the calculated mineral reaction deviation analysis coefficient KWF to generate a third analysis result, specifically as follows: When it indicates that the current mineral data is normal, and there is no need to use the mineral reaction correction coefficient KWJ in subsequent model analysis; When it indicates that there are fluctuations in the current mineral data, and the mineral reaction correction coefficient KWJ needs to be used in subsequent model analysis.

8. The intelligent identification method of mineral resources based on multi-source remote sensing data according to claim 7, characterized in that: In the above-mentioned step S4.1, the mineral reaction deviation analysis coefficient KWF and the mineral reaction correction coefficient KWJ are calculated through the following formula; ； ； Where: G is the short-wave infrared absorption depth, H is the thermal infrared emissivity anomaly index, I is the radar polarization scattering entropy, exp is the exponential function, max is the maximum value function, a5 is the weight value, K is the correction attenuation coefficient, and the values of a5 and K are adjusted and set by the user.

9. The intelligent identification method of mineral resources based on multi-source remote sensing data according to claim 8, characterized in that: The above-mentioned step S5 completes the calculation and analysis of the third data set through the following steps; Step S4.1: Integrate and calculate the remote sensing deviation analysis coefficient YGF, the remote sensing correction coefficient YGJ, the geological deviation analysis coefficient DZF, the geological correction coefficient DZJ, the mineral reaction deviation analysis coefficient KWF, and the mineral reaction correction coefficient KWJ to generate multiple mineral marker guiding coefficients KWX; Step S4.2: Analyze the calculated results to generate a first analysis result, specifically as follows: When it indicates that the current mineral data is abnormal and no guidance mark is made; When it indicates that the current mineral data is normal and guiding marks are made; When it indicates that the current mineral data is abnormal and no guidance mark is made; When it indicates that the current mineral data is normal and a guiding mark is made; When it indicates that the current mineral data is abnormal and no guidance mark is made; When it indicates that the current mineral data is normal, and guiding marks are made; When it indicates that the current mineral data is abnormal and no guidance mark is made; When it indicates that the current mineral data is normal and a guiding mark is made.

10. The intelligent identification method of mineral resources based on multi-source remote sensing data according to claim 9, characterized in that: In step S5.1, multiple mineral marker guiding coefficients KWX are calculated through the following formula; ； ； ； ； ； Where: YGJ is the remote sensing deviation analysis coefficient, YGJ is the remote sensing correction coefficient, DZF is the geological deviation analysis coefficient, DZJ is the geological correction coefficient, KWF is the mineral reaction deviation analysis coefficient, KWJ is the mineral reaction correction coefficient, exp is the exponential function, and K is the correction attenuation coefficient.

Images