Soil iron content hyperspectral inversion method, system, equipment and medium

Abstract

The embodiment of the invention provides a hyperspectral inversion method, system and equipment for the iron content of soil and a medium, and belongs to the field of soil analysis. The method comprises the following steps: selecting a plurality of measuring points in a to-be-measured soil sample area to collect surface soil samples; performing spectral measurement on the surface soil sample to obtain spectral reflectivity, and performing data transformation on the spectral reflectivity; constructing a correlation curve of the spectral reflectance at different wavelength intervals after data conversion and the iron content of the soil, selecting the wavelength with the highest correlation coefficient as an initial inversion index, and constructing a hyperspectral inversion model of the iron content of the soil; and inverting the iron content of the to-be-detected soil sample area based on the soil iron content hyperspectral inversion model. The soil iron content hyperspectral inversion model suitable for different space-time ranges is established by performing simulation transformation on the soil hyperspectral reflectivity and analyzing a wave band sensitive to the soil iron content, so that space and time barriers of soil spectral data in soil iron content research are broken, and high data sharing is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of soil analysis, and particularly to a method, system, device and medium for inverting the hyperspectral soil iron content. Background Art

[0002] Soil, as one of the main objects of agricultural production, understanding its physical and chemical properties and conducting agricultural production management accordingly is an important prerequisite for ensuring stable, high-yield, high-quality and efficient agricultural production. Hyperspectral remote sensing uses electromagnetic waves in multiple bands to obtain relevant data from objects. Compared with multispectral remote sensing, the band division of hyperspectral remote sensing is narrower, and it can obtain more spectral information in narrow bands, generating a complete and continuous ground object spectral curve.

[0003] Iron is the most common substance in soil, and iron ions are widely dissolved in the soil solution under certain conditions. Among them, Fe 2+ , Fe 3+ contributes the most to the soil spectrum and has diagnostic spectral characteristics. The absorption characteristics are mainly manifested in the visible light range. However, due to the irregularity of the surface spatial distribution and the influence of factors such as soil moisture, vegetation, and human activities on the soil surface reflection spectrum, there are still certain problems in directly obtaining the spectral parameters corresponding to the soil physical and chemical properties from the spectral data of the current soil in the field; and there is no unified standard in the process of obtaining the soil spectral curve in the laboratory. As a result, due to different test conditions and soil sample treatment methods in the same experiment, the obtained spectral data vary greatly, which not only affects the error of the experiment, but also limits the sharing of spectral data between different studies and between different times in the same study. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide a method, system, device and medium for inverting the hyperspectral soil iron content, which simulate and transform the hyperspectral reflectance of the soil, analyze the bands sensitive to the soil iron content, and establish a hyperspectral inversion model for the soil iron content applicable to different space-time ranges, so as to break the spatial and time barriers of soil spectral data in the study of soil iron content and achieve high data sharing.

[0005] To achieve the above purpose, the embodiments of the present invention provide a method for inverting the hyperspectral soil iron content, including: Select multiple measuring points in the soil sample area to be measured to collect surface soil samples; Perform spectral measurement on the surface soil samples to obtain spectral reflectance, and perform data transformation on the spectral reflectance; Construct a correlation curve between the data-transformed spectral reflectance at different wavelength intervals and the soil iron content, and select the wavelength with the highest correlation coefficient as the initial inversion index to construct a hyperspectral inversion model for the soil iron content; Invert the iron content of the soil sample area to be measured based on the hyperspectral inversion model of the soil iron content.

[0006] Optionally, perform data transformation on the spectral reflectance using the first-order differential transformation method of logarithm.

[0007] Optionally, perform data transformation on the spectral reflectance according to the calculation formula:

[0008] In the formula, is the wavelength interval, is the spectral reflectance of the soil sample at wavelength 1, is the spectral reflectance of the soil sample at wavelength 2, 2 - 1|.

[0009] Optionally, select the wavelength with the highest correlation coefficient as the initial inversion index, and construct a hyperspectral inversion model of soil iron content, including: According to the initial inversion index, select single-band, double-band, and triple-band combined data, and construct sample data of the spectral reflectance corresponding to the single-band, double-band, and triple-band combined data and the soil iron content; Use the DPS data processing system to perform linear regression analysis on the single-band, double-band, and triple-band combined data in turn using the linear regression equation; Use the total root mean square error and the residual mean to jointly evaluate the accuracy of the linear regression analysis to obtain a linear regression model.

[0010] Optionally, the linear regression equation is as follows:

[0011] In the formula, x i represents the i th prediction band, Y represents the estimated soil iron content, b i is the i th regression coefficient sum, and b0 is the regression constant.

[0012] Optionally, evaluate the accuracy of the linear regression analysis according to the following formula:

[0013] In the formula, y and y i are the measured value and the predicted value respectively, n is the number of samples, and k is the number of selected bands.

[0014] Optionally, multiple measuring points are selected in the soil sample area to be measured to collect surface soil samples, including: Select a relatively flat and soil-exposed area within the area to be measured as the soil sample area to be measured. Among them, the soil sample area to be measured includes various land use types and soil types; Select multiple measuring points in each soil sample area, and collect a surface soil sample for each measuring point as the soil sample.

[0015] In a second aspect, an embodiment of the present invention further provides a hyperspectral inversion system for soil iron content, including: A collection unit for selecting multiple measuring points in the soil sample area to be measured to collect surface soil samples; A transformation unit for performing spectral measurement on the surface soil sample to obtain spectral reflectance, and performing data transformation on the spectral reflectance; A construction unit for constructing a correlation curve between the spectral reflectance after data transformation with different wavelength intervals and the soil iron content, and selecting the wavelength with the highest correlation coefficient as the initial inversion index to construct a hyperspectral inversion model for soil iron content; An inversion unit for inverting the iron content of the soil sample area to be measured based on the hyperspectral inversion model for soil iron content.

[0016] In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the above-mentioned hyperspectral inversion method for soil iron content are implemented.

[0017] In a fourth aspect, an embodiment of the present invention further provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned hyperspectral inversion method for soil iron content are implemented.

[0018] Through the above technical solutions, the hyperspectral reflectance of the soil is simulated and transformed, the bands sensitive to the soil iron content are analyzed, and a hyperspectral inversion model for soil iron content applicable to different spatio-temporal ranges is established to break the spatial and temporal barriers of soil spectral data in the study of soil iron content and achieve high data sharing.

[0019] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent specific implementation part. Description of the Drawings

[0020] The drawings are used to provide a further understanding of the embodiments of the present invention, and constitute a part of the specification. Together with the following specific implementation manners, they are used to explain the embodiments of the present invention, but do not constitute a limitation to the embodiments of the present invention. In the drawings: Figure 1It is a flowchart of a method for inverting the hyperspectral of soil iron content provided by an embodiment of the present invention; Figure 2 It is a process for constructing a hyperspectral inversion model of soil iron content provided by an embodiment of the present invention; Figure 3 It is a correlation coefficient curve with a wavelength interval of 5nm provided by an embodiment of the present invention; Figure 4 It is a correlation coefficient curve with a wavelength interval of 10nm provided by an embodiment of the present invention; Figure 5 It is a correlation coefficient curve with a wavelength interval of 15nm provided by an embodiment of the present invention; Figure 6 It is a correlation coefficient curve with a wavelength interval of 20nm provided by an embodiment of the present invention; Figure 7 It is a linear regression graph of the observed value and the fitted value of the No. 7 scheme provided by an embodiment of the present invention; Figure 8 It is a structural schematic diagram of a system for inverting the hyperspectral of soil iron content provided by an embodiment of the present invention; Figure 9 It is a hardware structural schematic diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0021] In the following detailed description, various embodiments of the present disclosure will be described more fully. The present disclosure may have various embodiments and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but the present disclosure should be understood to cover all adjustments, equivalents and / or alternative solutions falling within the spirit and scope of the various embodiments of the present disclosure.

[0022] In the following, the term "comprising" or "may comprise" that may be used in various embodiments of the present disclosure indicates the presence of the disclosed function or operation, and does not limit the addition of one or more functions or operations. In addition, as used in various embodiments of the present disclosure, the terms "comprising", "having" and their cognates are only intended to indicate a specific feature, number, step, operation or combination of the foregoing items, and should not be understood to first exclude the existence of one or more other features, numbers, steps, operations or combinations of the foregoing items or the possibility of adding one or more features, numbers, steps, operations or combinations of the foregoing items.

[0023] In various embodiments of the present disclosure, the expression "or" or "at least one of A or / and B" includes any combination or all combinations of the recited words. For example, the expression "A or B" or "at least one of A or / and B" may include A, may include B, or may include both A and B.

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0025] Refer to Figure 1 The figure shows a flow chart of a method for inverting the hyperspectral of soil iron content in a specific embodiment, including the following implementation steps: Step 100: Select multiple measurement points in the soil sample area to be measured and collect surface soil samples.

[0026] Specifically, select a relatively flat and soil-exposed area as the soil sample area to be measured within the range of the area to be measured. Among them, the soil sample area to be measured includes various land use types and soil types; select multiple measurement points in each soil sample area, and collect a surface soil sample for each measurement point as the soil sample.

[0027] Exemplarily, select a relatively flat and soil-exposed area as the sample area within the range of the area to be measured, and consider various land use types and soil types. Select 4-5 representative measurement points in each sample area, and collect a surface soil (about 20 cm) sample for each measurement point.

[0028] In a specific example, according to the sampling purpose, determine the range of the soil sample area to be measured, and consider the influence of factors such as terrain, landform, vegetation coverage, and soil type on the distribution of sampling points. In the soil sample area to be measured, the method of multi-point mixed sampling can be used to ensure the representativeness of the samples within the sample area. In the soil sample area to be measured, according to factors such as terrain, landform, and soil type, the sampling points are evenly distributed. For example, in a rectangular field, sampling points can be set at the four corners and the center point of each field according to the principle of the plum blossom method, and other sampling points can be set inside the field according to the checkerboard method or the snake method. If there are obvious terrain changes or soil type differences in the sample area, sampling points should be added in these areas to more accurately reflect the soil conditions within the sample area. For surface soil samples, the sampling depth is generally set to 0-15 cm or 0-20 cm. At each sampling point, dig a pit of appropriate size, remove the top sod and sundries. Then, vertically scrape the soil samples within the required depth range in the pit. For each sampling point, sufficient soil samples should be collected for subsequent analysis and testing. Generally, 1-2 kg of soil samples can be collected for each sampling point. While collecting soil samples, information such as the location, soil type, vegetation coverage, and terrain and landform of each sampling point should be recorded.

[0029] In some embodiments, for spectral testing, a series of treatments need to be performed on the sample, including: 1. Drying, removing the moisture in the soil sample to facilitate subsequent processing and analysis. Air drying can be used: place the soil sample in a cool, well-ventilated room without direct sunlight, spread it evenly on a soil drying rack, oilcloth, kraft paper, or plastic sheet, and let it dry naturally. Or oven drying: use a soil drying oven for heating and drying, with the temperature not exceeding 40°C. During the drying process, large soil clods need to be crushed to prevent hardening after drying. 2. Sorting, removing impurities such as plant residues, neoforms, and intrusions in the soil sample. 3. Grinding, grinding the soil sample to an appropriate particle size to meet the requirements of spectral testing. This includes manual grinding: gently roll the soil sample using tools such as a wooden roller, and then sieve it through a sieve. Grinding with a soil grinder: put the soil sample and grinding balls into an agate ball mill jar and grind it using a soil grinder. The particle size of the ground sample needs to be determined by sieving through a sieve. 4. Sieving, ensuring that the particle size of all soil samples meets the experimental requirements. Use a nylon sieve for sieving, and all the soil samples for each sieving need to pass through the sieve, and the coarse-grained parts that are difficult to grind fine cannot be discarded. 5. Sorting and bottling, sorting the ground and sieved soil samples and storing them in appropriate containers. Use the "quartering method" for sampling. Spread the ground and sieved soil sample in a circle, divide it into four equal parts, take two opposite parts and mix them, and then divide them equally until the requirements are met. Bottling: put the processed soil sample into a wide-mouth bottle with a ground stopper, a plastic bottle, or into a kraft paper bag. Attach a label inside and outside the container, indicating information such as the number, sampling location, soil name, soil depth, sieve hole, sampling date, and sampler. 6. Storage and management, ensuring that the soil sample is not contaminated and does not deteriorate during storage. Store the bottled soil sample in an environment that avoids direct sunlight, high temperature, and humidity. At the same time, pay attention to preventing the influence of acids, alkalis, and unclean gases on the soil sample. Generally, bottled soil samples can be stored for half a year to one year, and can only be discarded after all the analysis work is completed and the analysis data is verified to be correct. 7. Pretreatment for specific spectral testing (such as infrared spectroscopy). For infrared spectroscopy testing, the soil sample also needs to be processed more finely, such as finely grinding it using an agate grinder and passing it through a 0.053 mm splitting sieve. Then, dry it at a specific temperature until it reaches a constant weight state. Finally, accurately weigh an appropriate amount of soil sample using a ten-thousandth balance for subsequent testing.

[0030] Step 101: Perform spectral measurement on the topsoil soil sample to obtain spectral reflectance, and perform data transformation on the spectral reflectance.

[0031] Specifically, laboratory spectrum measurement: under the illumination of a 1000W halogen lamp that can provide parallel light, the ASDField Spec For the FR ground feature spectrometer, first, turn on the instrument in advance and preheat it for 20-30 minutes. Second, use a 1000W halogen lamp as the light source, with a 60-degree illumination angle and a 25-degree field of view. Place the soil sample that has passed a 100-mesh sieve in a sample dish with a black background material on the surface and extremely low spectral reflectivity, 15 cm from the spectrum probe, and calibrate it using a 40 cm × 40 cm white plate to obtain the absolute reflectivity. After the preparation is completed, measure the spectrum of each soil sample in turn, and obtain ten spectral curves for each soil sample to eliminate instability during the measurement process. In addition, calibrate it using a white plate every five soil samples. The scanning time for each spectral curve is set to 5 seconds, and the spectral measurement of each soil sample is repeated four times. After the measurement, use ViewSpecPro spectral processing software to view the spectrum of each sample and eliminate abnormal spectral curves. The average spectral reflectivity of each soil sample is calculated and used as the original spectral reflectivity value. The soil iron content of each sample is determined by atomic absorption spectrometry.

[0032] The spectral measurement process may be affected by factors such as instrument noise and environmental interference, resulting in fluctuations in the spectral data. Data transformations, such as smoothing filtering, can effectively remove noise, making spectral data smoother and improving data accuracy and reliability. Spectral data may contain outliers due to measurement errors or instrument failures. Data transformations, such as threshold setting or data interpolation, can identify and address these outliers to prevent them from interfering with subsequent analysis. Spectral data after data transformation has stronger feature expression capabilities and higher information density, which can expand the scope and depth of application of spectral technology in fields such as agricultural production, environmental monitoring, and geological exploration.

[0033] In some embodiments, a logarithmic first-order differential transformation is used to transform the spectral reflectance data. The first-order differential transformation equation is as follows:

[0034] Where, is the wavelength interval, For soil samples at wavelength Spectral reflectance at 1, For soil samples at wavelength Spectral reflectance at 2, 2- 1|.

[0035] In some embodiments, after obtaining a spectrogram by performing spectral measurement on the topsoil soil sample, the Savitzky-Golay convolution smoothing method is used to perform polynomial least squares fitting on the data within the moving window through a polynomial to smooth the spectrogram. Specifically, it is necessary to determine the moving window width and the polynomial degree. The measured spectral data is read into a computer, and usually, a spectrogram is plotted with the wavelength (or wave number) as the abscissa and the absorbance (or reflectance) as the ordinate. According to the characteristics of the spectral data and the analysis requirements, the area that needs to be smoothed is selected. After smoothing, it is necessary to check whether the smoothing effect meets the requirements. The smoothing effect can be evaluated by observing whether the smoothed spectrogram is smoother, whether the noise is reduced, and whether the useful information is retained. The smoothed spectral data can be saved in a new file or data format for subsequent analysis and processing. At the same time, further analysis and modeling can also be performed on the smoothed spectral data, such as principal component analysis, partial least squares regression, etc., to extract useful information and establish a prediction model.

[0036] Exemplarily, if the off-pavement signal period is T, the window length should satisfy n≥T / Δt (Δt is the sampling interval). Constraint conditions for the polynomial degree: It is necessary to satisfy n>k + 1 to ensure a unique solution for the normal equation. Selection principle: Signal complexity: For simple waveforms (such as sine waves), a low degree (k = 2) is used, and for complex signals (such as multi-peak waveforms), the degree needs to be increased. Overfitting risk: When k≥n / 2−1, overfitting is likely to occur, and usually k≤n / 2−1 is taken. Within the window, it is assumed that the data satisfies:

[0037] Among them, is the center point of the window, xi = x c +(i - n + 1 / 2)Δt , are the polynomial coefficients, is the noise.

[0038] Construct the design matrix X and the observation vector y:

[0039] Solve the coefficient vector a by the least squares method: a=(X T X) −1 X T y.

[0040] According to the following formula, calculate the smoothed value of the window center point x c :

[0041] Multiply the inverse matrix of X T X by XT Multiply with the first row to obtain the convolution coefficient vector c, such that: .

[0042] Step 102: Construct the correlation curve between the spectral reflectance with different wavelength intervals after data transformation and the iron content in the soil, and select the wavelength with the highest correlation coefficient as the initial inversion index to construct the hyperspectral inversion model for the iron content in the soil.

[0043] It should be noted that when constructing the correlation curve between the first-order differential transformation of the spectral reflectance with different wavelength intervals and the iron content in the soil, compare and analyze to select the wavelength interval curve with higher correlation, and take the wavelength with the highest correlation coefficient as the initial inversion index. Usually, select the three bands with the highest correlation for inversion.

[0044] By constructing the correlation curve, the correlation between the spectral reflectance at different wavelength intervals and the iron content in the soil can be intuitively displayed. Selecting the wavelength with the highest correlation coefficient as the initial inversion index means that the spectral information at this wavelength is the most sensitive to the change of the iron content in the soil, thus improving the prediction accuracy of the model. Selecting the most relevant bands for modeling among many bands helps to reduce the interference of other irrelevant or noisy bands and makes the model more robust.

[0045] Using the most relevant bands for modeling helps the model better learn the essential relationship between the iron content in the soil and the spectral reflectance, thereby enhancing the model's prediction ability for unknown data. Using hyperspectral technology for real-time monitoring of the iron content in the soil can timely detect changes in soil composition and provide timely and accurate decision-making support for agricultural production.

[0046] Specifically, refer to Figure 2 As shown, select the wavelength with the highest correlation coefficient as the initial inversion index, and the execution process of constructing the hyperspectral inversion model for the iron content in the soil is as follows: S200: According to the initial inversion index, select single-band, double-band, and triple-band combined data, and construct sample data of the spectral reflectance corresponding to the single-band, double-band, and triple-band combined data and the iron content in the soil.

[0047] Exemplarily, as shown in Table 1 below, establish the following scheme according to the selected inversion index, and successively select single-band, double-band, and triple-band to construct the inversion scheme.

[0048] Table 1 Inversion Scheme

[0049] Construct sample data of the spectral reflectance of three bands and the iron content in the soil, as shown in Table 2 below: Table 2 Sample Data

[0050] S201: Use the DPS data processing system to perform linear regression analysis on the single-band, dual-band, and triple-band combined data in turn using the linear regression equation.

[0051] Specifically, the linear regression equation is as follows:

[0052] In the formula, x i represents the i th predicted band, Y represents the estimated iron content in the soil, b i is the sum of the i th regression coefficients, and b0 is the regression constant.

[0053] S202: Use the root mean square of the total variance and the mean of the residuals to jointly evaluate the accuracy of the linear regression analysis to obtain a linear regression model.

[0054] Specifically, evaluate the accuracy of the linear regression analysis according to the following formula:

[0055] In the formula, y and y i are the measured value and the predicted value respectively, n is the number of samples, and k is the number of selected bands.

[0056] Step 103: Invert the iron content of the soil sample area to be measured based on the hyperspectral inversion model of the soil iron content.

[0057] Specifically, preprocess the spectral data of the soil sample area to be measured, including steps such as denoising and smoothing, to improve the data quality. Input the preprocessed spectral data into the trained hyperspectral inversion model. The model compares the input spectral data with the known substance database, thereby inferring the composition and content of the substance, that is, outputting the predicted iron content in the soil.

[0058] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0059] In a specific embodiment, the test area is Hengshan County, located in the northern part of Shaanxi Province (latitude 37°22′ - 38°14′, longitude 108°56′ - 110°02′). The main soil types are loessial soil, sandy loess, black loess soil, and aeolian sandy soil. In the experimental area of Hengshan County, 80 soil samples were collected according to the soil sample selection method. Laboratory spectral measurements were carried out on the collected soil samples.

[0060] Data transformation was carried out in Excel. A total of 4 transformations were carried out, taking 5, 10, 15, and 20 respectively. The correlation coefficients between the spectral reflectance after the first-order differential transformation of the logarithm and the total iron content in the soil are as Figures 3 - 6 shown.

[0061] After verification and comprehensive comparison, when = 15, the correlation is the best. Therefore, the wavelengths 1453nm, 1932nm, and 2180nm with the highest correlation coefficients are selected as the initial inversion indicators. An inversion scheme is established, and the DPS data processing system is used to perform linear regression analysis on the combinations of one to three factors in sequence. The statistical table of the regression constants and regression coefficients is shown in Table 3 below. According to the results calculated from 64 samples, a linear regression model is obtained, and then 16 samples are predicted. The analysis results are compared to obtain the best model.

[0062] Table 3 Statistical table of regression constants and regression coefficients

[0063] A scatter distribution diagram is established with the measured values of iron content in soil samples and the inversion values of the linear regression model. From the distribution of the modeling sample points, it can be seen that the linear regression model has achieved a high modeling accuracy, and the modeling sample points almost fall on the 1:1 line.

[0064] Through analysis and comparison, it can be obtained that the distributions between the measured values and the fitted values of soil iron content are generally the same, but the degrees of closeness between the measured values and the fitted values in different schemes are different. By comparing and combining with the residual statistical table, as shown in Table 4 below, it can be concluded that the overall fitting effect of the 7th scheme is the best, and its determination coefficient RR reaches 0.7818, as Figure 7 shown.

[0065] Table 4 Statistical table of the absolute values of standard residuals

[0066] Finally, the 7th scheme is selected for inversion modeling through comparison. Its regression equation is: Y = 43241.1635 - 8881438.784X1 - 17949144.42X2 + 7107937X3.

[0067] By processing the hyperspectral data of the soil using the logarithmic first derivative method, eliminating unreasonable data, and applying linear regression analysis, the relationship between the total iron content in the soil and the hyperspectrum was studied, and a corresponding inversion model was established, breaking the spatial and temporal barriers of soil spectral data in the study of soil iron content and achieving high data sharing. It provides a scientific basis for spaceborne hyperspectral data in the study of soil iron content, obtains soil information in a limited time, understands its physical and chemical properties, and conducts agricultural production management accordingly to ensure stable and high yields in agriculture.

[0068] As Figure 8 shown, the following is an embodiment of the inversion system for soil iron content hyperspectrum provided by the embodiments of the present disclosure, which belongs to the same inventive concept as the inversion method for soil iron content hyperspectrum in the above embodiments. For the details not described in detail in the embodiment of the inversion system for soil iron content hyperspectrum, reference may be made to the embodiment of the inversion method for soil iron content hyperspectrum.

[0069] A collection unit for collecting surface soil samples at multiple measurement points in a soil sample area to be measured; A transformation unit for performing spectral measurement on the surface soil samples to obtain spectral reflectance and performing data transformation on the spectral reflectance; A construction unit for constructing a correlation curve between the spectral reflectance after data transformation at different wavelength intervals and the soil iron content, and selecting the wavelength with the highest correlation coefficient as the initial inversion index to construct an inversion model for soil iron content hyperspectrum; An inversion unit for inverting the iron content of the soil sample area to be measured based on the inversion model for soil iron content hyperspectrum.

[0070] Figure 9 It is a schematic hardware structure diagram of an electronic device for implementing various embodiments of the present invention.

[0071] The inversion method for soil iron content hyperspectrum provided by the embodiments of the present application can be applied to an electronic device. Those skilled in the art can understand that the structure of the electronic device involved in the embodiments of the present invention does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements. In the embodiments of the present invention, the electronic device includes, but is not limited to, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the embodiments of the present application described herein and / or claimed.

[0072] An electronic device may include a processor, an external memory interface, an internal memory, a Universal Serial Bus (USB) interface, a charging management module, a power management module, a battery, a wireless communication module, an audio module, a speaker, a microphone, a sensor module, keys, a camera, a display screen, and a Subscriber Identity Module (SIM) card interface, etc.

[0073] It can be understood that the structure illustrated in the embodiments of this application does not constitute a specific limitation on the electronic device. In other embodiments of this application, the electronic device may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or have different component arrangements. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0074] The processor may include one or more processing units. For example, the processor may include a Central Processing Unit (CPU), etc., an Application Processor (AP), a modem processor, a Graphics Processing Unit (GPU), an Image Signal Processor (ISP), a controller, a memory, a video codec, a Digital Signal Processor (DSP), a baseband processor, and / or a Neural-Network Processing Unit (NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0075] Among them, the processor may be the nerve center and command center of the electronic device. The controller can generate operation control signals according to the instruction operation code and timing signals to complete the control of fetching and executing instructions.

[0076] A memory may also be provided in the processor for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can save the instructions or data that the processor has just used or recycled. If the processor needs to use the instruction or data again, it can directly call it from this memory. This avoids repeated accesses, reduces the waiting time of the processor, and thus improves the system efficiency.

[0077] The external memory interface can be used to connect an external memory card, such as a MicroSD card, to expand the storage capacity of the electronic device. The external memory card communicates with the processor through the external memory interface to achieve the data storage function. For example, files such as music and videos are saved in the external memory card.

[0078] The internal memory can be used to store computer-executable program code, which includes instructions. The processor executes various functional applications and data processing of the electronic device by running the instructions stored in the internal memory. The internal memory can include a program storage area and a data storage area. The internal memory can include a high-speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0079] The wireless communication function of the electronic device can be implemented by an antenna, a wireless communication module, a modulation and demodulation processor, a baseband processor, etc.

[0080] The wireless communication module can provide wireless communication solutions applied to the electronic device, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc.

[0081] The electronic device can implement audio functions, etc. through an audio module, a speaker, a receiver, a microphone, a headphone jack, an application processor, etc.

[0082] The electronic device can implement a shooting function through an ISP, a camera, a video codec, a GPU, a display screen, an application processor, etc.

[0083] The electronic device can implement a display function through a GPU, a display screen, an application processor, etc.

[0084] The GPU is a microprocessor for image processing, connecting the display screen and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor can include one or more GPUs, which execute program instructions to generate or change display information.

[0085] The display screen is used to display images, videos, etc. The display screen includes a display panel.

[0086] The above-mentioned electronic device implements the method for inverting the hyperspectral soil iron content of the present application's theme name by selecting multiple measuring points in the soil sample area to be measured to collect surface soil samples; performing spectral measurement on the surface soil samples to obtain spectral reflectance, and performing data transformation on the spectral reflectance; constructing a correlation curve between the spectral reflectance after data transformation at different wavelength intervals and the soil iron content, and selecting the wavelength with the highest correlation coefficient as the initial inversion index to construct a hyperspectral inversion model for soil iron content; inverting the iron content of the soil sample area to be measured based on the hyperspectral inversion model for soil iron content, achieving the processing of soil hyperspectral data using the logarithmic first derivative method, eliminating unreasonable data, studying the relationship between the total iron content in the soil and the hyperspectrum using linear regression analysis, and establishing a corresponding inversion model, breaking the spatial and temporal barriers in the study of soil spectral data for soil iron content, and realizing high data sharing. It provides a scientific basis for spaceborne hyperspectral data in the study of soil iron content, obtains soil information in a limited time, understands its physical and chemical properties, and conducts agricultural production management accordingly, ensuring the beneficial effects of stable and high agricultural yields.

[0087] In the storage medium provided by the present application, there is a program product capable of implementing the method for inverting the hyperspectral soil iron content.

[0088] The method for inverting the hyperspectral soil iron content includes: selecting multiple measuring points in the soil sample area to be measured to collect surface soil samples; performing spectral measurement on the surface soil samples to obtain spectral reflectance, and performing data transformation on the spectral reflectance; constructing a correlation curve between the spectral reflectance after data transformation at different wavelength intervals and the soil iron content, and selecting the wavelength with the highest correlation coefficient as the initial inversion index to construct a hyperspectral inversion model for soil iron content; inverting the iron content of the soil sample area to be measured based on the hyperspectral inversion model for soil iron content.

[0089] In some possible implementation manners, the theme name of the present disclosure, the method and system for inverting the hyperspectral soil iron content, can be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of this specification.

[0090] The storage medium of the present disclosure may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0091] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A hyperspectral inversion method for soil iron content, characterized in that Including: Select multiple measuring points in the soil sample area to be measured and collect surface soil samples; Perform spectral measurement on the surface soil samples to obtain spectral reflectance, and perform data transformation on the spectral reflectance; Construct a correlation curve between the spectral reflectance after data transformation with different wavelength intervals and the soil iron content, and select the wavelength with the highest correlation coefficient as the initial inversion index to construct a hyperspectral inversion model for soil iron content; Invert the iron content of the soil sample area to be measured based on the hyperspectral inversion model for soil iron content.

2. The hyperspectral inversion method for soil iron content according to claim 1, wherein Perform data transformation on the spectral reflectance by using the first-order differential transformation method of logarithm.

3. The inversion method of hyperspectral soil iron content according to claim 2, characterized in that Perform data transformation on the spectral reflectance according to the calculation formula: In the formula, is the wavelength interval, is the spectral reflectance of the soil sample at wavelength 1, is the spectral reflectance of the soil sample at wavelength 2, 2 - 1|.

4. The hyperspectral inversion method for soil iron content according to claim 1, wherein Select the wavelength with the highest correlation coefficient as the initial inversion index to construct a hyperspectral inversion model for soil iron content, including: According to the initial inversion index, select single-band, double-band, and triple-band combined data, and construct sample data of the spectral reflectance corresponding to the single-band, double-band, and triple-band combined data and the soil iron content; Use the DPS data processing system to perform linear regression analysis on the single-band, double-band, and triple-band combined data in turn by using the linear regression equation; Use the root mean square of the total variance and the mean value of the residuals to jointly evaluate the accuracy of the linear regression analysis to obtain a linear regression model.

5. The hyperspectral inversion method for soil iron content according to claim 4, wherein The linear regression equation is as follows: In the formula, x i represents the i th predicted band, Y represents the estimated iron content in the soil, b i is the sum of the i th regression coefficients, and b0 is the regression constant.

6. The inversion method of hyperspectral soil iron content according to claim 4, characterized in that, Evaluate the accuracy of the linear regression analysis according to the following formula: wherein, y and y i are the measured value and the predicted value respectively, n is the number of samples, and k is the number of selected bands.

7. The hyperspectral inversion method for soil iron content according to claim 1, wherein Select multiple measuring points in the soil sample area to be measured and collect surface soil samples, including: Select a relatively flat and soil-exposed area within the range of the area to be measured as the soil sample area to be measured, where the soil sample area to be measured includes various land use types and soil types; Select multiple measuring points in each soil sample area, and collect a surface soil sample for each measuring point as the soil sample.

8. A hyperspectral inversion system for soil iron content, characterized in that, Including: A collection unit for selecting multiple measuring points in the soil sample area to be measured and collecting surface soil samples; A transformation unit for performing spectral measurement on the surface soil samples to obtain spectral reflectance, and performing data transformation on the spectral reflectance; A construction unit for constructing a correlation curve between the spectral reflectance after data transformation with different wavelength intervals and the soil iron content, and selecting the wavelength with the highest correlation coefficient as the initial inversion index to construct a hyperspectral inversion model for soil iron content; An inversion unit for inverting the iron content of the soil sample area to be measured based on the hyperspectral inversion model for soil iron content.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method for inverting the hyperspectral soil iron content according to any one of claims 1 to 7.

10. A storage medium, on which a computer program is stored, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for inverting the hyperspectral soil iron content according to any one of claims 1 to 7.

Images