Rare earth mineral extraction method and device and electronic equipment

Abstract

The invention provides a rare earth mineral extraction method and device and electronic equipment, and relates to the field of rare earth mineral extraction. The rare earth mineral extraction method comprises the following steps: calculating an absorption characteristic position of the reflectivity data in a rare earth mineral absorption wave band interval, the absorption characteristic position of the rare earth mineral comprises an absorption characteristic position of a wave band interval of 579-568nm, an absorption characteristic position of a wave band interval of 740-741nm, an absorption characteristic position of a wave band interval of 792-800nm and an absorption characteristic position of a wave band interval of 862-865nm. According to the rare earth mineral extraction method provided by the embodiment of the invention, the distribution condition of the rare earth minerals can be efficiently and precisely obtained in a large range.

Description

Technical Field

[0001] The present application relates to the field of rare earth mineral extraction, and in particular, to a rare earth mineral extraction method, device and electronic equipment. Background Art

[0002] As a key mineral resource in my country, rare earth elements have extremely high strategic significance. Rare earth minerals are widely used in high-tech industries, defense industries and new energy fields, and are known as "industrial vitamins". The exploration and mining of rare earth minerals are crucial to my country's economic development and national security.

[0003] Traditional remote sensing technology mainly relies on indirect prospecting methods when searching for rare earth minerals, inferring the existence of rare earth minerals by identifying the associated minerals or geological characteristics of rare earth minerals. In recent years, some scholars have used the absorption characteristics of a single band to identify rare earth minerals, ignoring other key bands. The extraction results are easily affected by the phenomenon of isochromatic heterogeneity, which reduces the recognition accuracy. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a rare earth mineral extraction method, device and electronic equipment. Through the method of characteristic absorption and weighted combination, four characteristic absorption peaks unique to rare earth minerals are comprehensively used. The rare earth mineral extraction method provided in the embodiments of the present application can achieve efficient, large-scale and high-precision acquisition of the distribution of rare earth minerals.

[0005] In a first aspect, the present application provides a method for extracting rare earth minerals, the method comprising:

[0006] Obtain reflectance data based on aerial hyperspectral data of the target area;

[0007] Calculating the matching degree between the standard spectrum of the rare earth mineral and the reflectivity data in the wavelength range of 500nm-950nm, and determining whether the matching degree meets the first preset condition;

[0008] Calculating the absorption characteristic position of the reflectivity data in the rare earth mineral absorption band interval, wherein the rare earth mineral absorption characteristic position includes the absorption characteristic position in the 568-597nm band interval, the absorption characteristic position in the 719-769nm band interval, the absorption characteristic position in the 783-826nm band interval, and the absorption characteristic position in the 862-876nm band interval;

[0009] Calculating the reflectivity ratio of each of the absorption characteristic positions to the shoulder position adjacent to the absorption characteristic position, and sequentially obtaining a first reflectivity ratio, a second reflectivity ratio, a third reflectivity ratio, and a fourth reflectivity ratio;

[0010] weighted sum of the first reflectivity ratio, the second reflectivity ratio, the third reflectivity ratio and the fourth reflectivity ratio based on the weighting coefficient to obtain a weighted sum value, and determine whether the weighted sum value meets a second preset condition;

[0011] The rare earth mineral distribution range of the target area is determined based on the intersection of the first rare earth mineral distribution information and the second rare earth mineral distribution information, wherein the first rare earth mineral distribution information is determined based on the weighted sum value that meets the second preset condition, and the second rare earth mineral distribution information is determined based on the reflectivity data within the wavelength range of 500nm-950nm.

[0012] In the above implementation process, the rare earth mineral extraction method provided by the embodiment of the present application can comprehensively consider the unique absorption characteristics of rare earth minerals in the four bands of 568-597nm, 719-769nm, 783-826nm, and 862-876nm in a weighted manner, avoiding misjudgment and recognition errors caused by single band identification, and can efficiently and accurately extract the distribution information of rare earth minerals from aerial hyperspectral data. Compared with the traditional method, the system mineral extraction method provided by the embodiment of the present application not only improves the accuracy and reliability of rare earth mineral detection, but also can quickly identify the distribution of rare earth minerals in a large range by combining the first rare earth mineral distribution information and the second rare earth mineral distribution information. In addition, when calculating the final reflectivity of the absorption characteristic position, the reflectivity ratio can be obtained by combining the reflectivity of the adjacent position of the absorption characteristic position, thereby improving the calculation accuracy of the final reflectivity of the absorption characteristic position.

[0013] Optionally, the numerical range of the absorption characteristic position in the 568-597nm band interval is 576-584nm, the numerical range of the absorption characteristic position in the 719-769nm band interval is 740-744nm, the numerical range of the absorption characteristic position in the 783-826nm band interval is 797-800nm, and the numerical range of the absorption characteristic position in the 862-876nm band interval is 866-869nm.

[0014] Optionally, in the embodiment of the present application, calculating the absorption characteristic position of the reflectivity data in the absorption band interval of the rare earth mineral includes:

[0015] Based on the reflectivity data, the minimum reflectivity value in the 568nm-597nm band, the minimum reflectivity value in the 719-769nm band, the minimum reflectivity value in the 783-826nm band, and the minimum reflectivity value in the 862-876nm band are calculated;

[0016] The spectral band position corresponding to the minimum reflectivity value in the 568nm-597nm band is determined as the absorption characteristic position in the 568nm-597nm band;

[0017] The spectral band position corresponding to the minimum reflectivity value in the 719-769nm band is determined as the absorption characteristic position in the 719-769nm band;

[0018] The spectral band position corresponding to the minimum reflectivity value in the 783-826nm band is determined as the absorption characteristic position in the 783-826nm band;

[0019] The spectral band position corresponding to the minimum reflectivity value in the 862-876nm band interval is determined as the absorption characteristic position in the 862-876nm band interval.

[0020] In the above implementation process, the absorption characteristic position of the 568-597nm band range, the absorption characteristic position of the 719-769nm band range, the absorption characteristic position of the 783-826nm band range and the absorption characteristic position of the 862-876nm band range can be determined in sequence according to the absorption characteristic position of the 568-597nm band range, the minimum reflectivity of the 719-769nm band range, the minimum reflectivity of the 783-826nm band range and the minimum reflectivity of the 862-876nm band range.

[0021] Optionally, in the embodiment of the present application, the reflectivity of the shoulder position adjacent to each of the absorption feature positions is determined based on the reflectivity data.

[0022] Optionally, in the embodiment of the present application, calculating the reflectivity ratio of each absorption characteristic position to an adjacent shoulder position of the absorption characteristic position includes:

[0023] Calculating the reflectivity of each absorption feature position;

[0024] Calculating the reflectivity of the adjacent shoulder position of each absorption feature position;

[0025] Based on the reflectivity of each of the absorption characteristic positions and the reflectivity of a shoulder position adjacent to the absorption characteristic position, a reflectivity ratio of each of the absorption characteristic positions to a shoulder position adjacent to the absorption characteristic position is calculated.

[0026] Optionally, in the embodiment of the present application, based on the reflectivity of each absorption characteristic position and the reflectivity of the shoulder position adjacent to the absorption characteristic position, the calculation formula corresponding to the reflectivity ratio of each absorption characteristic position to the shoulder position adjacent to the absorption characteristic position is:

[0027]

[0028] Wherein, Y represents the reflectivity ratio of the absorption characteristic position to the shoulder position adjacent to the absorption characteristic position, ρ m is the reflectivity of the shoulder position adjacent to the absorption characteristic position, ρ1 and ρ2 are the reflectivity of the shoulder position adjacent to the absorption characteristic position.

[0029] Optionally, in an embodiment of the present application, the step of acquiring reflectance data based on the aerial hyperspectral data of the target area includes:

[0030] The aerial hyperspectral data of the target area is preprocessed to obtain the reflectance data.

[0031] Optionally, in an embodiment of the present application, the reflectivity data within the wavelength range of 500nm-950nm is envelope-removed and normalized. In the above implementation process, after intercepting the absorption characteristic spectrum, the rare earth mineral extraction method provided in the embodiment of the present application performs envelope removal and spectrum normalization to make the absorption characteristics of the rare earth mineral more obvious, optimize the subsequent recognition and classification process based on multi-band absorption characteristics, and lay the foundation for high-precision rare earth mineral distribution detection.

[0032] In a second aspect, an embodiment of the present application provides a rare earth mineral extraction device, the device comprising:

[0033] An acquisition module, used to acquire reflectance data based on aerial hyperspectral data of a target area;

[0034] A second calculation module is used to calculate the matching degree between the standard spectrum of the rare earth mineral and the reflectivity data in the wavelength range of 500nm-950nm, and determine whether the matching degree meets the first preset condition;

[0035] A second calculation module is used to calculate the absorption characteristic position of the reflectivity data in the rare earth mineral absorption band interval, wherein the rare earth mineral absorption characteristic position includes the absorption characteristic position of the 568-597nm band interval, the absorption characteristic position of the 719-769nm band interval, the absorption characteristic position of the 783-826nm band interval and the absorption characteristic position of the 862-876nm band interval;

[0036] a third calculation module, used to calculate the reflectivity ratio of each of the absorption characteristic positions and the shoulder position adjacent to the absorption characteristic position, and obtain a first reflectivity ratio, a second reflectivity ratio, a third reflectivity ratio and a fourth reflectivity ratio in sequence;

[0037] a fourth calculation module, configured to weight the sum of the first reflectivity ratio, the second reflectivity ratio, the third reflectivity ratio and the fourth reflectivity ratio based on a weighting coefficient to obtain a weighted sum value, and determine whether the weighted sum value meets a second preset condition;

[0038] A determination module is used to determine the rare earth mineral distribution range of the target area based on the intersection of the first rare earth mineral distribution information and the second rare earth mineral distribution information, wherein the first rare earth mineral distribution information is determined based on a weighted sum value that meets the second preset condition, and the second rare earth mineral distribution information is determined based on the reflectivity data within the wavelength range of 500nm-950nm.

[0039] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores program instructions, and when the processor reads and runs the program instructions, it executes the steps in any of the above implementation methods.

[0040] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer program instructions, and when the computer program instructions are read and executed by a processor, the steps in any of the above-mentioned implementation methods are executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 is a flow chart of a rare earth mineral extraction method provided in an embodiment of the present application;

[0043] Figure 2 is a schematic diagram of quantifying a spectral absorption feature disclosed in an embodiment of the present application;

[0044] Figure 3 It is a structural schematic diagram of a rare earth mineral extraction device disclosed in an embodiment of the present application;

[0045] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings in the embodiments of the present application. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram may represent a module, a program segment or a part of a code, and a module, a program segment or a part of a code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of boxes in the block diagram and / or the flowchart, can be implemented by a dedicated hardware-based system that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. In addition, the functional modules in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0047] As a key mineral resource in my country, rare earth elements have extremely high strategic significance. Rare earth minerals are widely used in high-tech industries, defense industries and new energy fields, and are known as "industrial vitamins". The exploration and mining of rare earth minerals are crucial to my country's economic development and national security.

[0048] Traditional remote sensing technology mainly relies on indirect prospecting methods when searching for rare earth minerals, inferring the existence of rare earth minerals by identifying other minerals or geological features associated with rare earth minerals. In recent years, some scholars have used the absorption characteristics of the 740nm band in the Sentinel-2 satellite data to extract apatite from rare earth minerals, thereby indirectly locating rare earth minerals. However, this method often has certain limitations, because indirect prospecting cannot directly locate rare earth minerals, which can easily lead to identification errors.

[0049] On the other hand, rare earth minerals have unique spectral absorption characteristics in the visible light and short-wave infrared bands due to the electron transition effect. The spectral absorption characteristics of rare earth minerals usually appear in multiple bands. Relying only on the absorption characteristics of a single band to identify rare earth minerals ignores other key absorption characteristics, which can easily lead to incomplete identification results. In addition, different substances may show similar spectral characteristics in a certain band (i.e., the phenomenon of isochromatic heterogeneity). Relying on a single band can easily lead to misidentification and make it impossible to accurately locate the distribution of rare earth minerals.

[0050] Finally, drones are limited by their endurance and flight speed when acquiring hyperspectral data, and are unable to acquire hyperspectral data over large areas, making it difficult to meet the needs of large-scale, high-precision rare earth mineral detection.

[0051] Based on this, the present application proposes a rare earth mineral extraction method, device and electronic device. The rare earth mineral extraction method comprehensively considers four rare earth mineral characteristic absorption peaks through characteristic absorption and weighted combination method. The rare earth mineral extraction method provided in the embodiment of the present application can achieve efficient, large-scale and high-precision acquisition of the distribution of rare earth minerals.

[0052] Please see Figure 1 , Figure 1 Flow chart of the rare earth mineral extraction method provided in the embodiment of the present application; The present application provides a rare earth mineral extraction method, which can be Figure 4 The rare earth mineral extraction method comprises the following steps:

[0053] 101. Obtain reflectance data based on aerial hyperspectral data of the target area;

[0054] 102. Calculate the matching degree between the standard spectrum of the rare earth mineral and the reflectivity data in the wavelength range of 500nm-950nm, and determine whether the matching degree meets the first preset condition;

[0055] 103. Calculate the absorption characteristic position of the reflectivity data in the rare earth mineral absorption band interval, wherein the rare earth mineral absorption characteristic position includes the absorption characteristic position in the 568-597nm band interval, the absorption characteristic position in the 719-769nm band interval, the absorption characteristic position in the 783-826nm band interval, and the absorption characteristic position in the 862-876nm band interval;

[0056] 104. Calculate the reflectivity ratio between each absorption characteristic position and the shoulder position adjacent to the absorption characteristic position, and obtain a first reflectivity ratio, a second reflectivity ratio, a third reflectivity ratio, and a fourth reflectivity ratio in sequence;

[0057] 105. Perform weighted summation of the first reflectivity ratio, the second reflectivity ratio, the third reflectivity ratio, and the fourth reflectivity ratio based on the weighted coefficient to obtain a weighted summation value, and determine whether the weighted summation value satisfies a second preset condition;

[0058] 106. Determine the rare earth mineral distribution range of the target area based on the intersection of the first rare earth mineral distribution information and the second rare earth mineral distribution information, wherein the first rare earth mineral distribution information is determined based on a weighted sum value that meets the second preset condition, and the second rare earth mineral distribution information is determined based on reflectivity data within a wavelength range of 500nm-950nm.

[0059] In the above implementation process, the rare earth mineral extraction method provided by the embodiment of the present application can comprehensively consider the unique absorption characteristics of rare earth minerals in the four bands of 568-597nm, 719-769nm, 783-826nm, and 862-876nm in a weighted manner, avoiding misjudgment and recognition errors caused by single band identification, and can efficiently and accurately extract the distribution information of rare earth minerals from aerial hyperspectral data. Compared with the traditional method, the system mineral extraction method provided by the embodiment of the present application not only improves the accuracy and reliability of rare earth mineral detection, but also can quickly identify the distribution of rare earth minerals in a large range by combining the first rare earth mineral distribution information and the second rare earth mineral distribution information. In addition, when calculating the final reflectivity of the absorption characteristic position, the reflectivity ratio can be obtained by combining the reflectivity of the adjacent position of the absorption characteristic position, thereby improving the calculation accuracy of the final reflectivity of the absorption characteristic position.

[0060] As an example, assuming that the target area includes surface position A, surface position B, surface position C, and surface position D, accordingly, the acquired aerial hyperspectral data of the target area includes the aerial hyperspectral data of surface position A, surface position B, surface position C, and surface position D, and the initial reflectivity data includes the reflectivity data of surface position A, surface position B, surface position C, and surface position D. It should be noted that at this time, the reflectivity data of surface position A, surface position B, surface position C, and surface position D refers to the reflectivity data of surface position A, surface position B, surface position C, and surface position D within the full band range. Furthermore, the standard spectrum of rare earth minerals is matched with the initial reflectance data, specifically, the reflectance data of surface position A in the wavelength range of 500nm-950nm is matched with the standard spectrum of rare earth minerals, the reflectance data of surface position B in the wavelength range of 500nm-950nm is matched with the standard spectrum of rare earth minerals, the reflectance data of surface position C in the wavelength range of 500nm-950nm is matched with the standard spectrum of rare earth minerals, and the reflectance data of surface position D in the wavelength range of 500nm-950nm is matched with the standard spectrum of rare earth minerals, thereby obtaining the reflectance data corresponding to surface position A. The matching degree, the matching degree corresponding to the surface position B, the matching degree corresponding to the surface position C and the matching degree corresponding to the surface position D. At this time, if the matching degree corresponding to the surface position A does not meet the first preset condition, and the matching degree corresponding to the surface position B, the matching degree corresponding to the surface position C and the matching degree corresponding to the surface position D all meet the first preset condition, then the second rare earth mineral distribution information is determined, and the second rare earth mineral distribution information indicates that rare earth minerals may be distributed at the surface positions B, C and D, so as to first identify the surface positions that may have rare earth minerals in a large range based on the matching method of the standard spectrum of rare earth minerals.

[0061] However, the second rare earth mineral distribution information only marks the surface location where rare earth minerals may be distributed, and does not accurately determine whether the corresponding surface location is actually distributed with rare earth minerals. Based on this, through steps 104-106, the initial reflectivity data is searched for troughs, wherein, if a surface location is distributed with rare earth minerals, the reflectivity data of the surface location is reflected as a trough, and therefore, the trough position of the initial reflectivity data indicates that the surface location corresponding to the trough position may be distributed with rare earth minerals. It should be noted that, since the trough may also be caused by other factors, the trough position of the initial reflectivity data only indicates that the surface location corresponding to the trough position may be distributed with rare earth minerals, and it is not 100% certain. On the other hand, according to the characteristics of rare earth minerals, they only absorb light in a specific band, and thus only the troughs that appear in the specific band can indicate that the surface position corresponding to the trough position may be distributed with rare earth minerals. Therefore, looking for troughs in the initial reflectivity data is specifically: looking for troughs in a specific band in the initial reflectivity data, and the specific band refers to the 568-597nm band range, the 719-769nm band range, the 783-826nm band range and the 862-876nm band range. It should be noted that the troughs in the 568-597nm band range, the 719-769nm band range, the 783-826nm band range and the 862-876nm band range indicate that rare earth minerals may be distributed at the surface positions corresponding to the trough positions. Therefore, the troughs in the 568-597nm band range, the 719-769nm band range, the 783-826nm band range and the 862-876nm band range are also called the absorption characteristic positions of the 568-597nm band range, the absorption characteristic positions of the 719-769nm band range, the absorption characteristic positions of the 783-826nm band range and the absorption characteristic positions of the 862-876nm band range.

[0062] Furthermore, since the initial reflectivity data includes the full-band reflectivity data of the surface position B, the full-band reflectivity data of the surface position C, and the full-band reflectivity data of the surface position D, the absorption characteristic positions calculated based on the initial reflectivity data include the absorption characteristic positions of the surface position B in the 568-597nm band, the absorption characteristic positions in the 719-769nm band, the absorption characteristic positions in the 783-826nm band, and the absorption characteristic positions in the 862-876nm band, as well as, C the absorption characteristic position of the surface position in the 568-597nm band range, the absorption characteristic position in the 719-769nm band range, the absorption characteristic position in the 783-826nm band range and the absorption characteristic position in the 862-876nm band range, and D the absorption characteristic position of the surface position in the 568-597nm band range, the absorption characteristic position in the 719-769nm band range, the absorption characteristic position in the 783-826nm band range and the absorption characteristic position in the 862-876nm band range.

[0063] Furthermore, the accuracy of rare earth mineral identification can be improved based on multiple troughs. Specifically, for any of the surface positions B, C, and D, since the troughs may also be caused by other factors, it is not accurate to rely on the trough of a single specific fluctuation to determine whether the surface position has rare earth minerals. Taking surface position B as an example, if surface position B has substance S with the same spectrum as the rare earth mineral foreign body, the substance S may cause a trough in the 568-597nm band, but will not cause a trough in the 783-826nm band. In this case, the trough in the 568-597nm band can be avoided during identification. The trough mistakenly judges that rare earth minerals are distributed at the surface position B, that is, only when the trough appears at the same time in the 783-826nm band range and the 568-597nm band range can it be determined that rare earth minerals are distributed at the surface position B. Based on this, the embodiment of the present application comprehensively identifies whether rare earth minerals exist based on the absorption characteristic positions of the 568-597nm band range, the 719-769nm band range, the 783-826nm band range and the 862-876nm band range, which has higher accuracy than relying on the trough of a single specific fluctuation to determine whether rare earth minerals are distributed at the surface position.

[0064] Further, the numerical range of the absorption characteristic position of the 568-597nm band is 576-584nm, the numerical range of the absorption characteristic position of the 719-769nm band is 740-744nm, the numerical range of the absorption characteristic position of the 783-826nm band is 797-800nm, and the numerical range of the absorption characteristic position of the 862-876nm band is 866-869nm. That is, the absorption characteristic position of the 568-597nm band is always within the numerical range of 576-584nm, the absorption characteristic position of the 719-769nm band is within the numerical range of 740-744nm, the absorption characteristic position of the 783-826nm band is within the numerical range of 797-800nm, and the absorption characteristic position of the 862-876nm band is within the numerical range of 866-869nm. Among them, the numerical range of the above-mentioned absorption characteristic position covers the corresponding absorption characteristic position values ​​under various conditions. For example, under the condition that the spectral data is higher, the absorption characteristic position of the 568-597nm band is 579, and under the condition that the spectral data is lower, the absorption characteristic position of the 568-597nm band is 581.

[0065] Furthermore, the absorption feature position appears as a trough, but not all troughs are caused by rare earth minerals. For example, affected by the measurement factors, the reflectivity data of the surface position B has a slight trough in the 579-568nm fluctuation range. This trough cannot actually be used to identify whether rare earth minerals are distributed. Based on this, it is necessary to use the reflectivity ratio of the trough to determine whether the trough is caused by rare earth minerals.

[0066] In summary, the troughs of multiple specific band intervals in the reflectivity data of the surface location and the degree of each trough can be used to comprehensively judge whether rare earth minerals are distributed at the surface location. In step 102 of the embodiment of the present application, based on the matching degree, the reflectivity data within the wavelength range of 500nm-950nm can be intercepted when obtaining the reflectivity data, and then the second rare earth mineral distribution information can be determined based on the reflectivity data within the wavelength range of 500nm-950nm, so as to first screen out the surface positions in the target area whose data waveforms within the wavelength range of 500nm-950nm are close to the rare earth minerals. For example, when the reflectivity data within the wavelength range of 500nm-950nm includes the reflectivity data of the surface position B within the wavelength range of 500nm-950nm, the reflectivity data of the surface position C within the wavelength range of 500nm-950nm, and the reflectivity data of the surface position D within the wavelength range of 500nm-950nm, then the surface position B, the surface position C, and the surface position D can be first screened out from the target area, that is, the second rare earth mineral distribution information includes the surface position B, the surface position C, and the surface position D. On the other hand, based on steps 103, 104, and 105, the surface positions C and D of the four trough depressions that meet the second preset condition can be determined, that is, the first rare earth mineral distribution information includes the surface position C and the surface position D. Finally, the intersection of the first rare earth mineral distribution information and the second rare earth mineral distribution information is the surface position C and the surface position D, and the surface position C and the surface position D constitute the rare earth mineral distribution range of the target area.

[0067] In the above step 101, the target area includes multiple surface locations, such as surface location A and surface location B. Accordingly, the aerial hyperspectral data includes spectral data of surface materials at different surface locations in different bands, for example, spectral data of surface materials at location A in the 568-597nm band range, spectral data of surface materials at location A in the 719-769nm band range, spectral data of surface materials at location B in the 568-597nm band range, and spectral data of surface materials at location B in the 719-769nm band range.

[0068] In the above step 101, the aerial hyperspectral data of the target area can be acquired based on the CASI airborne hyperspectral imager, wherein the CASI airborne hyperspectral imager is mounted on a fixed-wing aircraft. Compared with the prior art of using drones to acquire aerial hyperspectral data, the battery life and flight speed of the drone limit the area it can cover. The use of drones to acquire hyperspectral data in complex terrain or large areas will be greatly restricted, and it is difficult to achieve extensive regional exploration. Due to the limitations of battery life and flight speed, the process of drones acquiring data is usually time-consuming and has a small coverage area. Therefore, the rare earth mineral extraction method provided in the embodiment of the present application uses a fixed-wing aircraft equipped with a CASI airborne hyperspectral imager. Compared with drones, fixed-wing aircraft have longer battery life and faster flight speed, can cover a wide area in a short time, and are suitable for a wide range of hyperspectral data acquisition.

[0069] In the above step 101, a specific implementation method of acquiring reflectance data based on the aerial hyperspectral data of the target area is:

[0070] The aerial hyperspectral data of the target area are preprocessed to obtain reflectance data.

[0071] Among them, data preprocessing of the aerial hyperspectral data of the target area may include processing steps such as radiation correction, geometric correction, and atmospheric correction.

[0072] In the above step 102, calculating the matching degree between the standard spectrum of rare earth minerals and the reflectance data in the wavelength range of 500nm-950nm means matching the standard spectrum of rare earth minerals with the reflectance data of all surface positions in the wavelength range of 500nm-950nm of the reflectance data, for example, matching the standard spectrum of rare earth minerals with the reflectance data of surface position A in the wavelength range of 500nm-950nm, and matching the standard spectrum of rare earth minerals with the reflectance data of surface position B in the wavelength range of 500nm-950nm, with the purpose of preliminarily screening out the surface positions where rare earth minerals may be distributed from the target area, wherein, if the matching degree satisfies the first preset condition, it means that rare earth minerals may be distributed at the surface position, and therefore it is necessary to extract the reflectance data of the surface position in the wavelength range of 500nm-950nm, and determine the second rare earth mineral distribution information.

[0073] In step 102, the matching degree satisfying the first preset condition may mean that the matching degree is greater than or equal to a first preset threshold, wherein the first preset threshold is the matching degree when the surface location does not contain rare earth minerals.

[0074] In step 102, the calculation of the matching degree between the standard spectrum of rare earth minerals and the reflectance data in the wavelength range of 500nm-950nm can be performed by ENVI software, wherein the ENVI software can calculate the matching degree between the standard spectrum of rare earth minerals and the reflectance data in the wavelength range of 500nm-950nm by a spectral angle matching method.

[0075] It should be noted that the standard spectra of rare earth minerals are obtained through laboratory or field measurements.

[0076] In the embodiment of the present application, the spectral angle matching method refers to using the spectral angle mapping method (SAM, SpectralAngleMapper) to calculate the angle between the target spectrum (aerial hyperspectral data) and the reference spectrum (rare earth mineral standard spectrum) vectors to measure the similarity between the two. The smaller the angle, the higher the matching degree; conversely, the larger the angle, the lower the matching degree.

[0077] In the above step 105, the first reflectivity ratio, the second reflectivity ratio, the third reflectivity ratio and the fourth reflectivity ratio are weighted and summed based on the weighting coefficients, and the calculation formula corresponding to the weighted sum value is obtained as follows:

[0078] Z=Y1×0.07+Y2×0.40+Y3×0.30+Y4×0.23;

[0079] Among them, Y1, Y2, Y3, and Y4 are the first reflectivity ratio, the second reflectivity ratio, the third reflectivity ratio, and the fourth reflectivity ratio, respectively; 0.07, 0.40, 0.30, and 0.23 are the weights of the first reflectivity ratio, the second reflectivity ratio, the third reflectivity ratio, and the fourth reflectivity ratio, respectively.

[0080] Optionally, in an embodiment of the present application, calculating the absorption characteristic position of the reflectivity data in the absorption band interval of the rare earth mineral includes the following steps:

[0081] Based on the reflectivity data, the minimum reflectivity value in the 568nm-597nm band, the minimum reflectivity value in the 719-769nm band, the minimum reflectivity value in the 783-826nm band, and the minimum reflectivity value in the 862-876nm band are calculated;

[0082] The spectral band position corresponding to the minimum reflectivity value in the 568nm-597nm band is determined as the absorption characteristic position in the 568nm-597nm band;

[0083] The spectral band position corresponding to the minimum reflectivity value in the 719-769nm band is determined as the absorption characteristic position in the 719-769nm band;

[0084] The spectral band position corresponding to the minimum reflectivity value in the 783-826nm band is determined as the absorption characteristic position in the 783-826nm band;

[0085] The spectral band position corresponding to the minimum reflectivity value in the 862-876nm band interval is determined as the absorption characteristic position in the 862-876nm band interval.

[0086] In the above implementation process, the absorption characteristic position of the 568-597nm band range, the absorption characteristic position of the 719-769nm band range, the absorption characteristic position of the 783-826nm band range and the absorption characteristic position of the 862-876nm band range can be determined in sequence according to the absorption characteristic position of the 568-597nm band range, the minimum reflectivity of the 719-769nm band range, the minimum reflectivity of the 783-826nm band range and the minimum reflectivity of the 862-876nm band range.

[0087] Optionally, in the embodiment of the present application, the reflectivity of the shoulder position adjacent to each absorption feature position is determined based on the reflectivity data.

[0088] Optionally, in the embodiment of the present application, calculating the reflectivity ratio of each absorption characteristic position to the shoulder position adjacent to the absorption characteristic position includes:

[0089] Calculate the reflectivity at each absorption feature location;

[0090] Calculate the reflectivity of the adjacent shoulder position of each absorption feature position;

[0091] Based on the reflectivity of each absorption feature position and the reflectivity of the shoulder position adjacent to the absorption feature position, a reflectivity ratio of each absorption feature position to the shoulder position adjacent to the absorption feature position is calculated.

[0092] In the embodiments of this application, please refer to Figure 2 , Figure 2 is a schematic diagram of quantifying a spectral absorption feature disclosed in an embodiment of the present application, such as Figure 2 As shown, based on the reflectivity of each absorption feature position and the reflectivity of the shoulder position adjacent to the absorption feature position, the calculation formula corresponding to the reflectivity ratio of each absorption feature position to the shoulder position adjacent to the absorption feature position is:

[0093]

[0094] Where Y represents the reflectivity ratio of the absorption feature position to the shoulder position adjacent to the absorption feature position, ρ mis the reflectivity of the shoulder positions (S1, S2) adjacent to the absorption characteristic position, and ρ1 and ρ2 are the reflectivity of the shoulder positions adjacent to the absorption characteristic position.

[0095] Optionally, in an embodiment of the present application, obtaining reflectance data based on aerial hyperspectral data of a target area includes:

[0096] The aerial hyperspectral data of the target area are preprocessed to obtain reflectance data.

[0097] Optionally, in an embodiment of the present application, obtaining reflectance data based on aerial hyperspectral data of a target area includes:

[0098] The aerial hyperspectral data of the target area are preprocessed to obtain reflectance data.

[0099] Optionally, in an embodiment of the present application, the reflectivity data within the wavelength range of 500nm-950nm is envelope-removed and normalized. In the above implementation process, after intercepting the absorption characteristic spectrum, the rare earth mineral extraction method provided in the embodiment of the present application performs envelope removal and spectrum normalization to make the absorption characteristics of the rare earth mineral more obvious, optimize the subsequent recognition and classification process based on multi-band absorption characteristics, and lay the foundation for high-precision rare earth mineral distribution detection.

[0100] Embodiment 2

[0101] See also Figure 3 , Figure 3 is a schematic diagram of the structure of a rare earth mineral extraction device disclosed in an embodiment of the present application, such as Figure 3 As shown, the device of the embodiment of the present application includes the following functional modules:

[0102] An acquisition module 201 is used to acquire reflectance data based on the aerial hyperspectral data of the target area;

[0103] The second calculation module 202 is used to calculate the matching degree between the standard spectrum of the rare earth mineral and the reflectivity data in the wavelength range of 500nm-950nm, and determine whether the matching degree meets the first preset condition;

[0104] The second calculation module 203 is used to calculate the absorption characteristic position of the reflectivity data in the rare earth mineral absorption band interval, wherein the rare earth mineral absorption characteristic position includes the absorption characteristic position of the 568-597nm band interval, the absorption characteristic position of the 719-769nm band interval, the absorption characteristic position of the 783-826nm band interval and the absorption characteristic position of the 862-876nm band interval;

[0105] A third calculation module 204 is used to calculate the reflectivity ratio between each absorption characteristic position and the shoulder position adjacent to the absorption characteristic position, and obtain a first reflectivity ratio, a second reflectivity ratio, a third reflectivity ratio and a fourth reflectivity ratio in sequence;

[0106] The fourth calculation module 205 is used to weight the sum of the first reflectivity ratio, the second reflectivity ratio, the third reflectivity ratio and the fourth reflectivity ratio based on the weighting coefficient to obtain a weighted sum value, and determine whether the weighted sum value meets the second preset condition;

[0107] Determination module 206 is used to determine the rare earth mineral distribution range of the target area based on the intersection of the first rare earth mineral distribution information and the second rare earth mineral distribution information, wherein the first rare earth mineral distribution information is determined based on the weighted sum value that meets the second preset condition, and the second rare earth mineral distribution information is determined based on the reflectivity data within the wavelength range of 500nm-950nm.

[0108] Embodiment 3

[0109] See also Figure 4 , Figure 4 The electronic device provided in the embodiment of the present application includes: a processor 301 and a memory 302, wherein the memory 302 stores machine-readable instructions executable by the processor 301, and when the machine-readable instructions are executed by the processor 301, the above method is executed.

[0110] Based on the same inventive concept, an embodiment of the present application also provides a computer-readable storage medium, in which computer program instructions are stored. When the computer program instructions are read and executed by a processor, the steps in any implementation method of the above-mentioned rare earth mineral extraction method are executed.

[0111] Computer-readable storage media can be random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), and other media that can store program codes.

[0112] In this article, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0113] The above are only embodiments of the present application and are not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for extracting rare earth minerals, characterized in that: The method comprises: Obtain reflectance data based on aerial hyperspectral data of the target area; Calculating the matching degree between the standard spectrum of rare earth minerals and the reflectivity data in the wavelength range of 500nm-950nm, and judging whether the matching degree meets the first preset condition; Calculating the absorption characteristic position of the reflectivity data in the rare earth mineral absorption band interval, wherein the rare earth mineral absorption characteristic position includes the absorption characteristic position in the 568-597nm band interval, the absorption characteristic position in the 719-769nm band interval, the absorption characteristic position in the 783-826nm band interval, and the absorption characteristic position in the 862-876nm band interval; Calculating the reflectivity ratio of each of the absorption characteristic positions to the shoulder position adjacent to the absorption characteristic position, and sequentially obtaining a first reflectivity ratio, a second reflectivity ratio, a third reflectivity ratio, and a fourth reflectivity ratio; weighted sum of the first reflectivity ratio, the second reflectivity ratio, the third reflectivity ratio and the fourth reflectivity ratio based on the weighting coefficient to obtain a weighted sum value, and determine whether the weighted sum value meets a second preset condition; The rare earth mineral distribution range of the target area is determined based on the intersection of the first rare earth mineral distribution information and the second rare earth mineral distribution information, wherein the first rare earth mineral distribution information is determined based on the weighted sum value that meets the second preset condition, and the second rare earth mineral distribution information is determined based on the reflectivity data within the wavelength range of 500nm-950nm.

2. The method according to claim 1, characterized in that The numerical range of the absorption characteristic position in the 568-597nm band range is 576-584nm, the numerical range of the absorption characteristic position in the 719-769nm band range is 740-744nm, the numerical range of the absorption characteristic position in the 783-826nm band range is 797-800nm, and the numerical range of the absorption characteristic position in the 862-876nm band range is 866-869nm.

3. The method according to claim 1, characterized in that The step of calculating the absorption characteristic position of the reflectivity data in the absorption band of the rare earth mineral comprises: Based on the reflectivity data, the minimum reflectivity value in the 568nm-597nm band, the minimum reflectivity value in the 719-769nm band, the minimum reflectivity value in the 783-826nm band, and the minimum reflectivity value in the 862-876nm band are calculated; The spectral band position corresponding to the minimum reflectivity value in the 568nm-597nm band is determined as the absorption characteristic position in the 568nm-597nm band; The spectral band position corresponding to the minimum reflectivity value in the 719-769nm band is determined as the absorption characteristic position in the 719-769nm band; The spectral band position corresponding to the minimum reflectivity value in the 783-826nm band is determined as the absorption characteristic position in the 783-826nm band; The spectral band position corresponding to the minimum reflectivity value in the 862-876nm band interval is determined as the absorption characteristic position in the 862-876nm band interval.

4. The method according to claim 1, characterized in that The method further comprises: The reflectivity of a shoulder position adjacent to each of the absorption feature positions is determined based on the reflectivity data.

5. The method according to claim 1, characterized in that The calculating of the reflectivity ratio between each absorption characteristic position and the shoulder position adjacent to the absorption characteristic position comprises: Calculating the reflectivity of each absorption feature position; Calculating the reflectivity of the adjacent shoulder position of each absorption feature position; Based on the reflectivity of each of the absorption characteristic positions and the reflectivity of a shoulder position adjacent to the absorption characteristic position, a reflectivity ratio of each of the absorption characteristic positions to a shoulder position adjacent to the absorption characteristic position is calculated.

6. The method according to claim 5, characterized in that The calculation formula corresponding to the reflectivity ratio of each absorption characteristic position to the shoulder position adjacent to the absorption characteristic position is calculated based on the reflectivity of each absorption characteristic position and the reflectivity of the shoulder position adjacent to the absorption characteristic position: Wherein, Y represents the reflectivity ratio of the absorption characteristic position to the shoulder position adjacent to the absorption characteristic position, ρ m is the reflectivity of the shoulder position adjacent to the absorption characteristic position, ρ1 and ρ2 are the reflectivity of the shoulder position adjacent to the absorption characteristic position.

7. The method according to claim 1, characterized in that The method of acquiring reflectance data based on the aerial hyperspectral data of the target area includes: The aerial hyperspectral data of the target area is preprocessed to obtain the reflectance data.

8. The method according to claim 1, characterized in that The method further comprises: The reflectivity data within the wavelength range of 500 nm-950 nm is subjected to envelope removal and normalization processing.

9. A rare earth mineral extraction device, characterized in that: The device comprises: An acquisition module, used to acquire reflectance data based on aerial hyperspectral data of a target area; A second calculation module is used to calculate the matching degree between the standard spectrum of the rare earth mineral and the reflectivity data in the wavelength range of 500nm-950nm, and determine whether the matching degree meets the first preset condition; A second calculation module is used to calculate the absorption characteristic position of the reflectivity data in the rare earth mineral absorption band interval, wherein the rare earth mineral absorption characteristic position includes the absorption characteristic position of the 568-597nm band interval, the absorption characteristic position of the 719-769nm band interval, the absorption characteristic position of the 783-826nm band interval and the absorption characteristic position of the 862-876nm band interval; a third calculation module, used to calculate the reflectivity ratio of each of the absorption characteristic positions and the shoulder position adjacent to the absorption characteristic position, and obtain a first reflectivity ratio, a second reflectivity ratio, a third reflectivity ratio and a fourth reflectivity ratio in sequence; a fourth calculation module, configured to weight the sum of the first reflectivity ratio, the second reflectivity ratio, the third reflectivity ratio and the fourth reflectivity ratio based on a weighting coefficient to obtain a weighted sum value, and determine whether the weighted sum value meets a second preset condition; A determination module is used to determine the rare earth mineral distribution range of the target area based on the intersection of the first rare earth mineral distribution information and the second rare earth mineral distribution information, wherein the first rare earth mineral distribution information is determined based on a weighted sum value that meets the second preset condition, and the second rare earth mineral distribution information is determined based on the reflectivity data within the wavelength range of 500nm-950nm.

10. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory stores program instructions, and when the processor runs the program instructions, the steps in the method according to any one of claims 1 to 8 are executed.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the steps in the method according to any one of claims 1 to 8 are executed.

Images