Mineral prediction method and device based on geological big data

Abstract

The application discloses a mineral prediction method and device based on geological big data, and relates to the technical field of mineral prediction, and comprises the following steps: obtaining relevant element content data of an area where a to-be-predicted region is located, collecting relevant element content in soil of the to-be-predicted region, and obtaining soil element content data; dividing the to-be-predicted region, calculating the discrete variation coefficient of the relevant element based on the soil element content data, and marking a suspicious mineral region; dividing the suspicious mineral region, continuously collecting soil temperature of the suspicious mineral region, and obtaining soil temperature change data; and performing mineral prediction screening on the suspicious mineral data, and obtaining a predicted mineral region; the application is used to solve the problem that the existing mineral prediction technology cannot accurately obtain the discrete degree of element content in geology in a region where water system distribution is uneven when the element content in geology is used for mineral prediction, and cannot accurately predict the mineral in the region.

Description

Technical Field

[0001] This invention relates to the field of mineral prediction technology, specifically to a method and apparatus for mineral prediction based on geological big data. Background Technology

[0002] Mineral resource prediction technology refers to a series of technical methods that utilize theories and methods from multiple disciplines such as geology, geophysics, geochemistry, and remote sensing geology, as well as various advanced technical means, to investigate, study, and analyze areas where mineral resources may exist, thereby predicting the distribution, reserves, grade, and other characteristics of mineral resources.

[0003] Existing mineral prediction technologies often utilize stream sediments to measure elemental content and calculate the coefficient of variation (COP) for analysis. While stream sediment measurements are convenient for collecting large quantities of samples in densely populated river areas, accurately reflecting elemental distribution, uneven stream distribution in some regions results in insufficient sample sizes to comprehensively represent regional geological elemental characteristics, leading to biases in mineral prediction. The COP, as a crucial indicator of elemental dispersion, helps identify uneven elemental distribution and provides a basis for mineral prediction. However, the presence of a few extremely large or small extreme values ​​in the data can also be problematic. When this happens, the coefficient of variation changes significantly, distorting the true dispersion of element content and leading to biases in mineral prediction. For example, patent application CN114898109A discloses a deep learning-based method and system for predicting porphyry mineral deposits. This method measures element content through stream sediments, which is not suitable for areas with uneven stream distribution. Furthermore, the accuracy of prediction range when using element content in geology for mineral prediction is not high. Therefore, existing mineral prediction technologies cannot accurately obtain the dispersion of element content in geology in areas with uneven stream distribution, thus failing to accurately predict mineral deposits within the region. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in the prior art. It obtains relevant element content data for the region to be predicted and collects relevant element content data from the soil in the region to be predicted, thus obtaining soil element content data. The region to be predicted is then divided into areas, and the discrete variation coefficients of relevant elements are calculated based on the soil element content data, marking suspected mineral deposit areas. Suspected mineral deposit areas are further divided, and soil temperature in these areas is continuously collected to obtain soil temperature change data. Based on the soil temperature change data, the suspected mineral deposit data is screened for mineral prediction to obtain predicted mineral deposit areas. This addresses the problem that existing mineral prediction technologies, when using geological element content for mineral prediction, cannot accurately obtain the dispersion of geological element content in areas with uneven water distribution, thus failing to accurately predict mineral deposits within the region.

[0005] To achieve the above objectives, firstly, this application provides a mineral prediction method based on geological big data, comprising the following steps:

[0006] Obtain relevant element content data for the region to be predicted, and collect relevant element content data in the soil of the region to be predicted to obtain soil element content data;

[0007] The area to be predicted is divided into regions, the discrete variation coefficients of relevant elements are calculated based on soil element content data, and suspected mineral areas are marked.

[0008] The suspected mineral deposit areas were divided, and the soil temperature in the suspected mineral deposit areas was continuously collected to obtain soil temperature change data;

[0009] Based on soil temperature change data, suspected mineral data are screened for mineral prediction to obtain predicted mineral areas.

[0010] Furthermore, obtaining relevant element content data for the region to be predicted and collecting relevant element content data from the soil in the region to be predicted, resulting in soil element content data, includes the following sub-steps:

[0011] The type of mineral to be predicted is denoted as the predicted mineral. The constituent elements related to the predicted mineral are obtained and denoted as the relevant elements. The average content of the relevant elements in the soil of the area to be predicted is obtained and denoted as the relevant element content data.

[0012] The location of the predicted mineral deposit in the area to be predicted is recorded as the reference mineral location. A1 sampling points are selected from the reference mineral location. For each sampling point, soil is collected at a first interval distance within a first depth distance, and the content of relevant elements in the collected soil is obtained and recorded as the first relevant element content, and marked according to the collection depth. The first depth distance is SL1, and the first interval distance is GL1.

[0013] Furthermore, obtaining relevant element content data for the region to be predicted and collecting relevant element content data from the soil in the region to be predicted, to obtain soil element content data, also includes the following sub-steps:

[0014] For the content of the first relevant element at any sampling depth of any sampling point, calculate the absolute difference between the content of the first relevant element and the content of the relevant element according to the element type, and sum them up, which is recorded as the individual content difference at the sampling depth of the corresponding sampling point.

[0015] Repeatedly obtain the individual content difference of all sampling points at all sampling depths. For any sampling point at the same sampling depth, calculate the average content difference and record it as the average content difference of the corresponding sampling depth. Obtain the average content difference of all sampling depths and find the largest average content difference. Mark the sampling depth corresponding to the largest average content difference as the excellent sampling depth.

[0016] A2 sampling points are uniformly selected from the area to be predicted, and denoted as sampling point A1. For each sampling point A1, the content of relevant elements in the soil at the optimal sampling depth at the location of sampling point A1 is collected, and the soil element content data is recorded according to the classification of sampling point A1.

[0017] Furthermore, the area to be predicted is divided into regions, and the discrete variation coefficients of relevant elements are calculated based on soil element content data. Suspicious mineral areas are marked, including the following sub-steps:

[0018] Set the main grid size to b1*b1, use the main grid to divide the region to be predicted into grids, and ensure that any two adjacent main grids have k1% overlap.

[0019] For any principal grid, denoted as the first grid, the soil element content data corresponding to all sampling points within the first grid are denoted as the first grid element data. The first grid element data corresponding to any related element are arranged in ascending order and denoted as the first related element sequence. The 25th percentile, 75th percentile, and median of the first related element sequence are obtained and denoted as E1, E2, and E0 respectively. The content of the corresponding related element in the related element content data is obtained and denoted as Ba.

[0020] The discrete variation coefficients of the relevant elements are calculated using the discrete variation formula, which is as follows: Wherein, RND represents the discrete variation coefficient of the corresponding related element; the discrete variation coefficients of all related elements in the first grid are repeatedly obtained and recorded as the discrete variation data of the first grid.

[0021] Furthermore, the process of dividing the area to be predicted into regions, calculating the discrete variation coefficients of relevant elements based on soil element content data, and marking suspected mineral areas also includes the following sub-steps:

[0022] Repeatedly acquire discrete variation data for all major grids. For any correlation element, the discrete variation coefficients corresponding to all major grids are sorted in ascending order and denoted as the first coefficient sequence. Obtain the 25th percentile and 75th percentile of the first coefficient sequence and denote them as P1 and P2 respectively. Calculate P0 = P2 + q1 * (P2 - P1) and mark P0 as the variation threshold of the corresponding correlation element, where q1 is the set scaling factor. Repeatedly acquire the variation thresholds of all correlation elements.

[0023] For the first grid, if the discrete variation coefficients of all relevant elements in the discrete variation data of the first grid are greater than or equal to the corresponding variation threshold, then the first grid is marked as a suspicious mineral area; otherwise, it is marked as a normal grid area. The marking is repeated for all main grids.

[0024] Furthermore, the suspected mineral deposit areas are divided into zones, and soil temperature data in these areas is continuously collected to obtain soil temperature change data, including the following sub-steps:

[0025] Set the secondary grid and reference grid size to b2*b2, use the secondary grid to divide the suspected mineral area into grids, and ensure that any two adjacent secondary grids have k2% area overlap.

[0026] For any minor grid, denoted as the second grid, the soil temperature at the optimal sampling depth of all sampling points within the second grid is collected, and the average value is calculated and denoted as the average soil temperature of the second grid.

[0027] The average soil temperature of the second grid is collected at the first time interval within the first time period, and the collection time is recorded and marked as the soil temperature change data of the second grid; the soil temperature change data of all secondary grids are collected repeatedly, where the first time period is RA and the first time interval is GA.

[0028] Furthermore, the process of dividing the suspected mineral deposit areas and continuously collecting soil temperature data in these areas to obtain soil temperature change data includes the following sub-steps:

[0029] The reference mineral location is divided into grids using a reference grid; any reference grid is denoted as the third grid; A3 sampling points are selected from the third grid, and the soil temperature at the optimal sampling depth of all sampling points in the third grid is collected, and the average value is calculated and denoted as the average soil temperature of the third grid.

[0030] The average soil temperature of the third grid was collected at the first time interval within the first time period, and the collection time was recorded and marked as the reference temperature change data of the third grid; the reference temperature change data of all reference grids were collected repeatedly.

[0031] Furthermore, the process of screening suspected mineral resources based on soil temperature change data to obtain predicted mineral resource areas also includes the following sub-steps:

[0032] For any reference temperature change data of a reference grid or any soil temperature change data of a secondary grid, denoted as the first temperature change data; for any two adjacent average soil temperatures in the first temperature change data, the corresponding average temperature change rate is calculated using the rate of change formula, and sorted in the corresponding order, denoted as the temperature change rate sequence; the rate of change formula is as follows: Where BT(i) represents the corresponding average temperature change rate, T(i+1) and T(i) represent the (i+1)th and ithth average soil temperatures, respectively, and VTi represents the time interval between the collection times of T(i+1) and T(i).

[0033] Furthermore, the process of screening suspected mineral resources based on soil temperature change data to obtain predicted mineral resource areas also includes the following sub-steps:

[0034] Repeatedly obtain all corresponding temperature change rate sequences, and label the temperature change rate sequences corresponding to the reference temperature change data and soil temperature change data as the reference change rate sequence and the soil change rate sequence, respectively;

[0035] Obtain the maximum and minimum values ​​of the average temperature change rate at the same index position in all reference change rate sequences, and denote them as BTm and BTx respectively. Mark [BTx, BTm] as the temperature change interval at the corresponding index position; repeat to obtain the temperature change intervals corresponding to all index positions.

[0036] Furthermore, the process of screening suspected mineral resources based on soil temperature change data to obtain predicted mineral resource areas also includes the following sub-steps:

[0037] For any soil change rate sequence, denoted as the first change rate sequence, the total number of average temperature change rates in the first change rate sequence is denoted as U0;

[0038] Determine whether the average temperature change rate at the index position in the first rate of change sequence belongs to the corresponding temperature change interval, and count the total number of average temperature change rates belonging to the corresponding temperature change interval, denoted as H;

[0039] If H ≥ C1*U0, then the secondary grid corresponding to the first rate of change sequence is marked as a strongly predicted mineral area; if C1*U0 > H ≥ C2*U0, then the secondary grid corresponding to the first rate of change sequence is marked as a moderately predicted mineral area; if C2*U0 > H ≥ C3*U0, then the secondary grid corresponding to the first rate of change sequence is marked as a weakly predicted mineral area; if C4*U0 > H, then the secondary grid corresponding to the first rate of change sequence is marked as a normal grid area; repeat the marking of the secondary grids to obtain the corresponding predicted mineral areas.

[0040] The beneficial effects of this invention are as follows: This invention obtains relevant element content data of the region to be predicted and collects relevant element content data in the soil of the region to be predicted to obtain soil element content data; it divides the region to be predicted into areas, calculates the discrete variation coefficient of relevant elements based on the soil element content data, and marks suspicious mineral areas; it divides the suspicious mineral areas and continuously collects soil temperature data in the suspicious mineral areas to obtain soil temperature change data; it performs mineral prediction screening on the suspicious mineral data based on the soil temperature change data to obtain predicted mineral areas; it can accurately obtain the dispersion of element content in geology in areas with uneven water distribution, and accurately predict minerals in the region;

[0041] This invention determines the optimal sampling depth by calculating the absolute difference between the relevant element content and the relevant element content data. Its advantages include the ability to find the depth with the greatest variation in element content, which better reflects the differences from the surrounding environment, resulting in more representative and effective data that helps to more accurately identify potential mineral deposit areas. Furthermore, it identifies suspicious mineral deposit areas by calculating the coefficient of variation, which is less affected by outliers compared to traditional coefficients of variation. This allows for more precise identification of data anomalies in local areas, aiding in the discovery of potential mineral deposit areas. Finally, it further determines mineral deposit areas by collecting temperature change data, helping to more accurately delineate these areas and more comprehensively cover suspected deposits, thus improving the accuracy of mineral deposit area determination. Attached Figure Description

[0042] Figure 1 This is a flowchart illustrating the steps of the method of the present invention;

[0043] Figure 2 This is a schematic diagram of the main grid division of the present invention;

[0044] Figure 3 This is a flowchart of the mineral prediction and screening steps of the present invention;

[0045] Figure 4 This is a schematic diagram of the device of the present invention. Detailed Implementation

[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] Example 1, please refer to Figure 1 As shown, this application provides a mineral prediction method based on geological big data, including the following steps:

[0048] Step S1: Obtain relevant element content data for the region to be predicted, and collect relevant element content data from the soil in the region to be predicted to obtain soil element content data; Step S1 includes the following sub-steps:

[0049] Step S101: The type of mineral to be predicted is denoted as the predicted mineral; the constituent elements related to the predicted mineral are obtained and denoted as the relevant elements; the average content of the relevant elements in the soil of the area to be predicted is obtained and denoted as the relevant element content data; for example, the relevant elements of gold ore include Au (gold), As (arsenic), Sb (antimony), Hg (mercury), Ag (silver), S (sulfur), and Te (tellurium), etc.

[0050] Step S102: Record the location of the predicted mineral in the area to be predicted as the reference mineral location, and select A1 sampling points from the reference mineral location; if there is a predicted mineral that has been discovered in the area to be predicted, select from the predicted mineral in the area to be predicted, otherwise select from the predicted mineral in the area to be predicted; A1 can be set according to the specific application scenario. In this embodiment, A1 is 20.

[0051] Step S103: For each sampling point, soil is collected at a first interval distance within a first depth distance, and the content of relevant elements in the collected soil is obtained and recorded as the first relevant element content, and marked according to the collection depth; wherein, the first depth distance is SL1, and the first interval distance is GL1; SL1 and GL1 can be set according to specific application scenarios. In this embodiment, SL1 is 200cm and GL1 is 10cm.

[0052] Step S104: For the content of the first related element at any sampling depth of any sampling point, calculate the absolute difference between the content of the first related element and the content of the related element according to the element type, and sum them up, and record them as the individual content difference at the sampling depth of the corresponding sampling point; that is, calculate the absolute value of the difference between the collected data and the local average data, and sum them up.

[0053] Step S105: Repeatedly obtain the individual content difference of all sampling points at all sampling depths. For any sampling point at the same sampling depth, calculate the average content difference and record it as the average content difference of the corresponding sampling depth. Obtain the average content difference of all sampling depths and obtain the largest average content difference. Mark the sampling depth corresponding to the largest average content difference as the excellent sampling depth.

[0054] Step S106: Select A2 sampling points evenly from the area to be predicted, and record them as sampling points 1. For each sampling point 1, collect the content of relevant elements in the soil at the optimal sampling depth at the location of sampling point 1, and classify them according to sampling point 1, and record them as soil element content data; A2 can be set according to the area to be predicted.

[0055] In practice, by calculating the absolute difference between the content of relevant elements in soil at different sampling depths and the average content of relevant elements in soil in the same region, the depth with the greatest variation in element content can be found. Soil samples collected at this depth can better reflect the differences in element content with the surrounding environment, and the data obtained is more representative and effective for mineral prediction, helping to more accurately identify potential mineral areas. Moreover, soil at different depths is subject to different external interference factors. Determining the optimal sampling depth can avoid some depths with more interference factors and select depths that are more significantly affected by specific geological conditions for sampling, thereby reducing the interference of irrelevant factors on element content and improving the accuracy of mineral prediction.

[0056] Step S2 involves dividing the area to be predicted into regions, calculating the discrete variation coefficients of relevant elements based on soil element content data, and marking suspected mineral deposit areas. Step S2 includes the following sub-steps:

[0057] For step S201, please refer to... Figure 2 As shown, the main grid size is set to b1*b1. The area to be predicted is divided into grids using the main grid, ensuring that any two adjacent main grids have a k1% overlap. b1 and k1 can be set according to the specific application scenario, with k1% typically ranging from 25% to 50%. Ensuring a k1% overlap between two adjacent main grids avoids the hidden mineral area being evenly divided between two grids. If a mineral area is evenly divided, the relevant element data characteristics within each grid may be unclear, making it difficult to accurately determine whether the area is a mineral area. Avoiding even division allows a complete mineral area to fall within a single grid as much as possible, making the relevant element data within the grid more representative and accurately reflecting the characteristics of the mineral area, thereby improving the accuracy of identification.

[0058] Step S202: For any main grid, denoted as the first grid, the soil element content data corresponding to all sampling points within the first grid are denoted as the first grid element data;

[0059] Step S203: Arrange the first grid element data corresponding to any related element in ascending order, denoted as the first related element sequence. Obtain the 25th percentile, 75th percentile, and median of the first related element sequence, denoted as E1, E2, and E0 respectively. Obtain the content of the corresponding related element in the related element content data, denoted as Ba. The 25th percentile and 75th percentile refer to the values ​​at the 25th and 75th percentiles after sorting a set of data from smallest to largest.

[0060] Step S204: Calculate the discrete variation coefficient of the corresponding relevant elements according to the discrete variation formula, which is as follows: Wherein, RND represents the discrete variation coefficient of the corresponding related element; the discrete variation coefficients of all related elements in the first grid are repeatedly obtained and recorded as the discrete variation data of the first grid.

[0061] Step S205: Repeatedly acquire discrete variation data of all main grids. For any related element, the discrete variation coefficients corresponding to all main grids are sorted in ascending order and denoted as the first coefficient sequence. The 25th percentile and 75th percentile of the first coefficient sequence are acquired and denoted as P1 and P2 respectively. Calculate P0 = P2 + q1 * (P2 - P1). Mark P0 as the variation threshold of the corresponding related element, where q1 is the set proportional coefficient. Repeatedly acquire the variation thresholds of all related elements. In this embodiment, q1 = 1.5.

[0062] Step S206: For the first grid, if the discrete variation coefficients of all relevant elements in the discrete variation data of the first grid are greater than or equal to the corresponding variation threshold, then the first grid is marked as a suspected mineral area; otherwise, it is marked as a normal grid area. This marking process is repeated for all main grids. A small discrete variation coefficient indicates that the content of relevant elements in the soil varies little between different sampling points and is relatively uniformly distributed. This may mean that the geological conditions in this area are relatively stable, with no obvious local enrichment. A large discrete variation coefficient indicates that the content of relevant elements in the soil varies greatly between different sampling points and is unevenly distributed; elements are enriched in local areas; there may be special geological phenomena or potential mineral enrichment areas.

[0063] In practical implementation, compared to the traditional coefficient of variation which only considers the mean and standard deviation, the discrete coefficient of variation can more comprehensively reflect the distribution characteristics of the data. Especially for non-normally distributed data, it can more accurately capture the discreteness and variability of the data, thus more effectively identifying suspicious areas where mineral deposits may exist. The traditional coefficient of variation is more sensitive to outliers. An extreme outlier may significantly affect the mean and standard deviation, and thus affect the size of the coefficient of variation, leading to incorrect judgments on the degree of data dispersion. The discrete coefficient of variation, on the other hand, is calculated based on quantiles and is less affected by outliers, thus having better robustness.

[0064] Step S3 involves dividing the suspected mineral deposit area into sections and continuously collecting soil temperature data from these areas to obtain soil temperature change data. Step S3 includes the following sub-steps:

[0065] Step S301: Set the size of the secondary grid and the reference grid to b2*b2. Use the secondary grid to divide the suspected mineral area into grids and ensure that any two adjacent secondary grids have a k2% overlap. b2 can be set according to the actual application scenario, but it can be less than b1. k2 is generally taken as 25%-50%.

[0066] Step S302: For any secondary grid, denoted as the second grid, collect the soil temperature at the optimal sampling depth of all sampling points within the second grid, and calculate the average value, which is recorded as the average soil temperature of the second grid; that is, use the average value of the data collected at the same time from all sampling points in the second grid to obtain the average soil temperature.

[0067] Step S303: Collect the average soil temperature of the second grid at a first time interval within the first time period, record the collection time, and mark it as the soil temperature change data of the second grid; repeat the acquisition of soil temperature change data of all secondary grids, wherein the first time period is RA and the first time interval is GA. In this embodiment, the first time period RA is 9 months and the first time interval GA is 12 hours.

[0068] Step S304: Divide the reference mineral location into grids using a reference grid; denote any reference grid as the third grid; select A3 sampling points from the third grid, collect the soil temperature at the optimal sampling depth of all sampling points in the third grid, and calculate the average value, which is recorded as the average soil temperature of the third grid.

[0069] Step S305: Collect the average soil temperature of the third grid at a first time interval within the first time period, record the collection time, and mark it as the reference temperature change data of the third grid; repeat the acquisition of reference temperature change data of all reference grids.

[0070] In practice, underground ore bodies, due to their geological structure, rock type, thermal conductivity, impact on groundwater, and possible geothermal anomalies, will cause the underground temperature in ore-bearing areas to exhibit different variation characteristics compared to non-ore-bearing areas. For example, in certain seasons, the temperature change rate in ore-bearing areas is faster, the timing of temperature extremes differs, or the temperature fluctuation range is larger. By conducting long-term, synchronous temperature monitoring of known ore-bearing and non-ore-bearing areas, some temperature changes caused by common factors such as macro-climate and topography can be eliminated, thus highlighting the temperature differences caused by the presence of ore bodies. These temperature differences can serve as indicators for finding the same mineral deposits.

[0071] Step S4 involves screening suspicious mineral data based on soil temperature change data to obtain predicted mineral areas. Step S4 includes the following sub-steps:

[0072] Step S401: For any reference temperature change data of a reference grid or any soil temperature change data of a secondary grid, denoted as the first temperature change data; for any two adjacent average soil temperatures in the first temperature change data, the corresponding average temperature change rate is calculated using the change rate formula, and sorted in the corresponding order, denoted as the temperature change rate sequence; the change rate formula is as follows: Where BT(i) represents the corresponding average temperature change rate, T(i+1) and T(i) represent the (i+1)th and ithth average soil temperatures, respectively, and VTi represents the time interval between the collection of T(i+1) and T(i). Under normal circumstances, VTi is equal to the first time interval. If VTi is slightly larger or smaller than the first time interval due to other external factors, the actual time interval shall prevail.

[0073] Step S402: Repeatedly acquire all corresponding temperature change rate sequences, and mark the temperature change rate sequences corresponding to the reference temperature change data and soil temperature change data as the reference change rate sequence and the soil change rate sequence, respectively, in order.

[0074] For step S403, please refer to... Figure 3 As shown, the maximum and minimum values ​​of the average temperature change rate at the same index position in all reference change rate sequences are obtained and denoted as BTm and BTx respectively. The range [BTx, BTm] is marked as the temperature change range at the corresponding index position. The temperature change range corresponding to all index positions is obtained repeatedly. For example, to obtain the temperature change range corresponding to the first index position, the first data in all reference change rate sequences is obtained, and the maximum and minimum values ​​are obtained to form [BTx, BTm], which is marked as the temperature change range at the first index position.

[0075] Step S404: For any soil change rate sequence, denoted as the first change rate sequence, the total number of average temperature change rates in the first change rate sequence is denoted as U0;

[0076] Step S405: Determine whether the average temperature change rate at the indexed position in the first rate of change sequence belongs to the corresponding temperature change interval, and count the total number of average temperature change rates belonging to the corresponding temperature change interval, denoted as H; for example, if there are 545 average temperature change rates in the first rate of change sequence, of which 487 average temperature change rates belong to the corresponding temperature change interval, then U0 = 545, H = 487.

[0077] Step S406: If H ≥ C1*U0, then the secondary grid corresponding to the first rate of change sequence is marked as a strongly predicted mineral area; if C1*U0 > H ≥ C2*U0, then the secondary grid corresponding to the first rate of change sequence is marked as a moderately predicted mineral area; in this embodiment, C1 = 0.90, C2 = 0.78; a strongly predicted mineral area represents that the area is very likely to have corresponding minerals; a moderately predicted mineral area represents that the area is somewhat likely to have corresponding minerals.

[0078] Step S407: If C2*U0>H≥C3*U0, then the secondary grid corresponding to the first rate of change sequence is marked as a weakly predicted mineral area; if C3*U0>H, then the secondary grid corresponding to the first rate of change sequence is marked as a normal grid area; the secondary grid is marked repeatedly to obtain the corresponding predicted mineral area; in this embodiment, C3=0.6; a weakly predicted mineral area means that the possibility of the corresponding mineral exists in the area is small, and a normal grid area means that the corresponding mineral is basically impossible to exist in the area;

[0079] In practice, temperature change data provides additional information for mineral prediction beyond conventional information such as soil element content. It allows for a more comprehensive understanding of the geological conditions of the area to be predicted, improving the accuracy and reliability of the prediction. Relying solely on soil element content may have limitations, while temperature changes can reveal potential mineral clues from another perspective. The two complement each other, helping to more accurately delineate mineral areas. Furthermore, obtaining soil temperature change data is relatively easy and less costly than some traditional mineral exploration methods, thus enabling more comprehensive coverage of the area to be predicted, improving the accuracy of mineral area determination, and reducing the overall cost of mineral prediction.

[0080] Example 2, please refer to Figure 4 As shown, Figure 4This paper presents a schematic diagram of a mineral prediction device based on geological big data. The device includes a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other via the communication bus. The memory stores computer-readable instructions, which the processor can call. When the processor executes these instructions, it performs steps similar to those in a geological big data-based mineral prediction method to achieve the following functions: acquiring relevant element content data for the region to be predicted and collecting relevant element content data from the soil in the region to be predicted; dividing the region to be predicted into sub-regions, calculating the coefficient of variation of relevant elements based on the soil element content data, and marking suspicious mineral areas; dividing the suspicious mineral areas and continuously collecting soil temperature data from these sub-regions to obtain soil temperature change data; and filtering the suspicious mineral data based on the soil temperature change data to obtain predicted mineral areas.

[0081] Furthermore, when the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0082] Example 3: This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it performs the steps of the above-mentioned mineral prediction method based on geological big data to achieve the following functions: acquiring relevant element content data of the area to be predicted, and collecting relevant element content data in the soil of the area to be predicted to obtain soil element content data; dividing the area to be predicted into regions, calculating the discrete variation coefficient of relevant elements based on the soil element content data, and marking suspicious mineral areas; dividing the suspicious mineral areas, and continuously collecting soil temperature data of the suspicious mineral areas to obtain soil temperature change data; and performing mineral prediction screening on the suspicious mineral data based on the soil temperature change data to obtain predicted mineral areas.

[0083] Based on the above description of the embodiments, the embodiments of the present invention can be provided as methods, systems, or computer program products. Based on this understanding, the technical solutions described above, or the parts that contribute to the prior art, can be embodied in the form of software products. These computer software products can be stored in computer-readable storage media, such as ROM / RAM, magnetic disks, optical disks, etc., and include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or certain parts of the embodiments.

[0084] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces. The indirect coupling or communication connection between systems, modules, and units may be electrical, mechanical, or other forms.

[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A mineral prediction method based on geological big data, characterized in that, Includes the following steps: Obtain relevant element content data for the region to be predicted, and collect relevant element content data in the soil of the region to be predicted to obtain soil element content data. The area to be predicted is divided into regions, the discrete variation coefficients of relevant elements are calculated based on soil element content data, and suspected mineral areas are marked. The suspected mineral deposit areas were divided, and the soil temperature in the suspected mineral deposit areas was continuously collected to obtain soil temperature change data; Based on soil temperature change data, suspected mineral data are screened for mineral prediction to obtain predicted mineral areas; Obtaining relevant element content data for the region to be predicted, and collecting relevant element content data from the soil in the region to be predicted, to obtain soil element content data includes the following sub-steps: The type of mineral to be predicted is denoted as the predicted mineral. The constituent elements related to the predicted mineral are obtained and denoted as the relevant elements. The average content of the relevant elements in the soil of the area to be predicted is obtained and denoted as the relevant element content data. The location of the predicted mineral deposit in the area to be predicted is recorded as the reference mineral location. A1 sampling points are selected from the reference mineral location. For each sampling point, soil is collected at a first interval distance within a first depth distance, and the content of relevant elements in the collected soil is obtained and recorded as the first relevant element content, and marked according to the collection depth. Wherein, the first depth distance is SL1, and the first interval distance is GL1. For the content of the first relevant element at any sampling depth of any sampling point, calculate the absolute difference between the content of the first relevant element and the content of the relevant element according to the element type, and sum them up, which is recorded as the individual content difference at the sampling depth of the corresponding sampling point. Repeatedly obtain the individual content difference of all sampling points at all sampling depths. For any sampling point at the same sampling depth, calculate the average content difference and record it as the average content difference of the corresponding sampling depth. Obtain the average content difference of all sampling depths and find the largest average content difference. Mark the sampling depth corresponding to the largest average content difference as the excellent sampling depth. A2 sampling points are uniformly selected from the area to be predicted, and denoted as sampling point A1. For each sampling point A1, the content of relevant elements in the soil at the optimal sampling depth at the location of sampling point A1 is collected, and the soil element content data is recorded according to the sampling point A1. The process of dividing the area to be predicted into regions, calculating the coefficient of variation of relevant elements based on soil element content data, and marking suspected mineral areas includes the following sub-steps: Set the main grid size to b1*b1, use the main grid to divide the region to be predicted into grids, and ensure that any two adjacent main grids have k1% overlap. For any principal grid, denoted as the first grid, the soil element content data corresponding to all sampling points within the first grid are denoted as the first grid element data. The first grid element data corresponding to any related element are arranged in ascending order and denoted as the first related element sequence. The 25th percentile, 75th percentile, and median of the first related element sequence are obtained and denoted as E1, E2, and E0 respectively. The content of the corresponding related element in the related element content data is obtained and denoted as Ba. The discrete variation coefficients of the relevant elements are calculated using the discrete variation formula, which is as follows: Wherein, RND represents the discrete variation coefficient of the corresponding related element; the discrete variation coefficients of all related elements in the first grid are repeatedly obtained and recorded as the discrete variation data of the first grid. The process of delineating suspected mineral deposit areas and continuously collecting soil temperature data in these areas to obtain soil temperature change data includes the following sub-steps: Set the secondary grid and reference grid size to b2*b2, use the secondary grid to divide the suspected mineral area into grids, and ensure that any two adjacent secondary grids have k2% area overlap. For any minor grid, denoted as the second grid, the soil temperature at the optimal sampling depth of all sampling points within the second grid is collected, and the average value is calculated and denoted as the average soil temperature of the second grid. The average soil temperature of the second grid is collected at the first time interval within the first time period, and the collection time is recorded and marked as the soil temperature change data of the second grid; the soil temperature change data of all secondary grids are collected repeatedly, where the first time period is RA and the first time interval is GA. The reference mineral location is divided into grids using a reference grid; any reference grid is denoted as the third grid; A3 sampling points are selected from the third grid, and the soil temperature at the optimal sampling depth of all sampling points in the third grid is collected, and the average value is calculated and denoted as the average soil temperature of the third grid. The average soil temperature of the third grid was collected at the first time interval within the first time period, and the collection time was recorded and marked as the reference temperature change data of the third grid; the reference temperature change data of all reference grids were collected repeatedly. The process of screening and predicting potential mineral deposits based on soil temperature variation data to obtain predicted mineral deposit areas includes the following sub-steps: For any reference temperature variation data of a reference grid or any secondary grid, denoted as the first temperature variation data; for any two adjacent average soil temperatures in the first temperature variation data, the corresponding average temperature variation rate is calculated using the variation rate formula, and sorted in the corresponding order, denoted as the temperature variation rate sequence; the variation rate formula is as follows: , where BT(i) represents the corresponding average temperature change rate, T(i+1) and T(i) represent the (i+1)th and ith average soil temperatures, respectively, and VTi represents the time interval between the collection of T(i+1) and T(i); Repeatedly obtain all corresponding temperature change rate sequences, and label the temperature change rate sequences corresponding to the reference temperature change data and soil temperature change data as the reference change rate sequence and the soil change rate sequence, respectively; Obtain the maximum and minimum values ​​of the average temperature change rate at the same index position in all reference change rate sequences, and denote them as BTm and BTx respectively. Mark [BTx, BTm] as the temperature change interval at the corresponding index position; repeat the process to obtain the temperature change intervals corresponding to all index positions. For any soil change rate sequence, denoted as the first change rate sequence, the total number of average temperature change rates in the first change rate sequence is denoted as U0; Determine whether the average temperature change rate at the index position in the first rate of change sequence belongs to the corresponding temperature change interval, and count the total number of average temperature change rates belonging to the corresponding temperature change interval, denoted as H; If H ≥ C1*U0, then the secondary grid corresponding to the first rate of change sequence is marked as a strongly predicted mineral area; if C1*U0 > H ≥ C2*U0, then the secondary grid corresponding to the first rate of change sequence is marked as a moderately predicted mineral area; if C2*U0 > H ≥ C3*U0, then the secondary grid corresponding to the first rate of change sequence is marked as a weakly predicted mineral area; if C3*U0 > H, then the secondary grid corresponding to the first rate of change sequence is marked as a normal grid area; repeat the marking of the secondary grids to obtain the corresponding predicted mineral areas.

2. The mineral prediction method based on geological big data according to claim 1, characterized in that, The process of dividing the area to be predicted into regions, calculating the coefficients of variation of relevant elements based on soil element content data, and marking suspected mineral areas also includes the following sub-steps: Repeatedly acquire discrete variation data for all major grids. For any correlation element, the discrete variation coefficients corresponding to all major grids are sorted in ascending order and denoted as the first coefficient sequence. Obtain the 25th percentile and 75th percentile of the first coefficient sequence and denote them as P1 and P2 respectively. Calculate P0 = P2 + q1 * (P2 - P1) and mark P0 as the variation threshold of the corresponding correlation element, where q1 is the set scaling factor. Repeatedly acquire the variation thresholds of all correlation elements. For the first grid, if the discrete variation coefficients of all relevant elements in the discrete variation data of the first grid are greater than or equal to the corresponding variation threshold, then the first grid is marked as a suspected mineral area; otherwise, it is marked as a normal grid area. The marking is repeated for all main grids.

Images