Soil total nitrogen rapid detection method based on remote sensing detection

Abstract

The invention relates to the technical field of remote sensing detection, in particular to a soil total nitrogen rapid detection method based on remote sensing detection, which comprises the following steps: extracting a correlation coefficient matrix of any two wave band spectrums under a plurality of sensitive indexes based on the total nitrogen content and soil hyperspectral data in an obtained soil sample; determining an optimal dual-band sensitive hyperspectral index according to the plurality of correlation coefficient matrixes; performing cross-regional verification on the plurality of optimal sensitive indexes, and selecting the optimal sensitive index with the optimal robustness as the soil total nitrogen content sensitive hyperspectral index; and performing broadband spectrum resampling on the hyperspectral data, calculating a total nitrogen content sensitive broadband index after resampling according to the optimal hyperspectral index correlation coefficient matrix, and completing soil total nitrogen content spatial and temporal distribution characteristic evaluation based on remote sensing data based on the index. The method provided by the invention has good reproducibility and popularization capability in cross-region and cross-time corresponding application.

Description

Technical Field

[0001] This invention belongs to the field of remote sensing detection technology, and in particular relates to a rapid detection method for total nitrogen in soil based on remote sensing detection. Background Technology

[0002] Existing soil total nitrogen (STN) models have a recognized limitation in their universality, making it extremely difficult to achieve cross-temporal and cross-regional replication. Although the development of satellite remote sensing technology and its combination with machine learning algorithms over the past 20 years has led to the development of numerous technical methods, key technical bottlenecks still exist in large-scale dynamic remote sensing monitoring of soil physicochemical properties. Soil itself is a complex system, and the transmission of electromagnetic waves within this system exhibits strong uncertainty, with complex "reciprocal effects" existing between different functional groups. For example, the characteristic bands of the STN spectrum can be weakened or shifted due to the involvement of iron oxides. This makes it very difficult to effectively predict (and invert) soil spectral characteristics using physical theoretical models. The modeling-validation strategy is currently a widely adopted technique for quantitative inversion of soil physicochemical properties, and multiple linear models such as partial least squares regression have been proven to effectively achieve quantitative analysis of total nitrogen content based on soil spectra. With the development of machine learning technology, algorithms such as artificial neural networks, random forests, and support vector machines have also been introduced to achieve quantitative estimation of STN content at local scales. However, the modeling-validation inversion process is highly dependent on ground sampling and the model has poor cross-regional universality, making it unsuitable for large-scale, high-time-sensitivity STN monitoring. Its main technical bottlenecks are as follows: (1) Traditional remote sensing quantitative estimation models for soil parameters based on statistical processes are highly sample-dependent and cannot be widely used across regions; (2) Statistical models such as partial least squares regression, as well as machine learning or deep learning models such as artificial neural networks, cannot provide explicit mathematical expressions for specific bands and are extremely difficult to be promoted and applied. Summary of the Invention

[0003] In view of this, the present invention aims to provide a rapid detection method for total nitrogen in soil based on remote sensing. It constructs a soil remote sensing index by combining data mining algorithms, and proposes a new type of soil total nitrogen sensitive broadband remote sensing index through cross-regional and cross-temporal verification. This provides a reliable and easily promoted technical method for monitoring farmland soil quality and agricultural ecological research, and fills the gap in cross-regional and cross-temporal monitoring technology for farmland SOC.

[0004] To achieve the above objectives, the technical solution created by this invention is implemented as follows: A rapid method for detecting total nitrogen in soil based on remote sensing includes: S1: Obtain the total nitrogen content and soil hyperspectral data from soil samples, and calculate multiple sensitivity indices between any two spectral bands; based on the relationship between total nitrogen content and soil hyperspectral data, extract the correlation coefficient matrix between each sensitivity index and total nitrogen content; S2: Based on the multiple correlation coefficient matrices obtained in step S1, determine the two optimal spectral bands for each sensitivity index, and the optimal sensitivity index corresponding to the two optimal spectral bands; S3: Cross-regional validation was conducted on multiple optimal sensitivity indices, and the optimal sensitivity index with the best robustness was selected as the soil total nitrogen content sensitive hyperspectral index; S4: Based on the spectral response function of the remote sensing data, the soil hyperspectral data in step S1 is resampled in a wide band. The correspondence of the resampled wide band in the correlation coefficient matrix in step S2 is calculated. Based on the soil total nitrogen content sensitive hyperspectral index in step S3, the soil total nitrogen content sensitive wide band remote sensing index is extracted. S5: Using the soil total nitrogen content sensitive broadband remote sensing index from step S4, predict the distribution of total nitrogen content in the remote sensing data of the area to be detected.

[0005] Furthermore, in step S1: using the Pearson correlation analysis algorithm, the correlation coefficient is calculated using the following formula: ; Where, r i,j X represents the correlation coefficient between the spectral bands of the i-th and j-th bands of the soil sample. i,j Let Y represent the sensitivity index between the spectral values ​​of the i-th band and the j-th band, and let Y represent the total nitrogen content. Arrange the obtained correlation coefficients in band order to form a correlation coefficient matrix.

[0006] Furthermore, the sensitivity indices are the difference index, the ratio index, and the normalization index.

[0007] Furthermore, in step S2: the two spectral bands corresponding to the largest correlation coefficient in the correlation coefficient matrix are selected as the two optimal spectral bands; each sensitivity index under the two optimal spectral bands is the corresponding optimal sensitivity index.

[0008] Furthermore, between steps S2 and S3, the following step is also included: verifying the optimal spectral band determined in step S2 using the ICO algorithm and / or SPA algorithm. This includes: calculating each sensitivity index for any two spectral bands in the soil hyperspectral data, constructing a spectral index set corresponding to each sensitivity index, with a size of N×N×n, where N represents the total number of bands in the soil hyperspectral data and n represents the number of soil samples; taking a sub-spectral index set of size N×n corresponding to any band in each spectral index set, and using the total nitrogen content of the corresponding sample for calculation using the ICO algorithm and / or SPA algorithm, so that the optimal sub-spectral index set is selected from the N sub-spectral index sets, and the band spectra corresponding to the optimal sub-spectral index set form the verification band spectrum set; if the optimal band spectrum determined in step S2 is in the band spectrum set, it indicates that the optimal band spectrum determined in step S2 is correct.

[0009] Furthermore, in step S4, the broadband spectral resampling of the soil hyperspectral data includes: setting a moving average window based on the full width at half maximum (FWHM) of the spectral response function of the remote sensing sensor, and resampling the spectral data within the effective spectral range of the soil hyperspectral data to obtain broadband spectral data.

[0010] Furthermore, step S4 also includes: expanding the resampled wideband spectral data based on the regression fitting transformation equation.

[0011] Furthermore, the broadband remote sensing index sensitive to total nitrogen content in soil is as follows: STNRSI=R SWIR / R GREEN ; STNRSI represents the broadband remote sensing index sensitive to total nitrogen content in soil, R SWIR R represents the spectral reflectance in the shortwave infrared band of the remote sensing data of the area to be detected. GREEN This represents the spectral reflectance of visible green light in the remote sensing data of the area to be detected.

[0012] Compared with the prior art, the present invention can achieve the following beneficial effects: The rapid soil total nitrogen detection method based on remote sensing described in this invention utilizes a remote sensing index with a clear physical meaning and a concise expression. By combining the spectral characteristics of soil total nitrogen content with multi-temporal remote sensing data, the spatiotemporal distribution characteristics of soil total nitrogen can be rapidly and quantitatively evaluated over a large area. This allows for the development of multi-year, cross-regional, and large-scale soil total nitrogen remote sensing indices, generating large-scale spatial distribution maps of soil total nitrogen with a resolution of 10 meters or higher, enabling precise tracking and dynamic analysis of the spatiotemporal variation trends of soil total nitrogen. Furthermore, the method provided by this invention has good cross-regional applicability and a simpler expression (ratio of shortwave infrared to near-infrared spectrum) compared to traditional models. It is also applicable to multiple types of satellite remote sensing data (with both shortwave and near-infrared channels), demonstrating strong scalability. Attached Figure Description

[0013] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments and descriptions of the invention are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 A schematic flowchart of the rapid detection method for total nitrogen in soil based on remote sensing, as described in the embodiments of the present invention; Figure 2 A flowchart illustrating the rapid detection method for total nitrogen in soil based on remote sensing, as described in the embodiments of the present invention; Figure 3 A schematic diagram illustrating the process of obtaining the correlation coefficient matrix in step S1 of the present invention embodiment; Figure 4 The correlation image under the ratio index described in the embodiments of the present invention; Figure 5 A schematic diagram illustrating the verification process of the optimal band spectrum described in the embodiments of the present invention. Detailed Implementation

[0014] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not constitute a limitation thereof.

[0015] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.

[0016] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on this invention. Furthermore, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0017] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0018] The invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0019] like Figure 1 and Figure 2 As shown in the embodiments of the present invention, the rapid soil total nitrogen detection method based on remote sensing includes: S1: Obtain the total nitrogen content and soil hyperspectral data from soil samples, and calculate multiple sensitivity indices between any two spectral bands; based on the relationship between total nitrogen content and soil hyperspectral data, extract the correlation coefficient matrix between each sensitivity index and total nitrogen content.

[0020] In this embodiment of the invention, the total nitrogen content and hyperspectral data of soil samples were acquired in a standardized laboratory environment. Specifically, the soil samples were sieved through a 0.075mm standard soil sieve, dried at 50°C for 24 hours, and then subjected to standardized spectral measurements. During the spectral measurements, ambient light interference needed to be minimized; therefore, the measurements were performed in a darkroom. An ASD portable hyperspectral analyzer was used with a high-density reflectance probe (2901±10°%K, 4.05W halogen lamp light source) to collect the spectral reflectance data of the soil samples (401nm-2400nm). The probe was fixed to... On the iron stand, soil samples were placed in clean petri dishes, with the probe as close to the soil sample surface as possible, but without direct contact to avoid contaminating the probe. The instrument and probe were preheated for at least 30 minutes before the spectral measurements began. The instrument was calibrated every 30 minutes using a standard diffuse reflectance reference white plate after the spectral measurements commenced. Each soil sample was measured five times, and the average value was used as the spectral data for that sample. Standardized spectral measurements were performed on a total of 1165 soil samples to construct a sensitive hyperspectral index for soil total nitrogen content. The total nitrogen content of all samples was measured using the Kjeldahl distillation volumetric method for analyzing the total nitrogen reflectance spectral characteristics.

[0021] This invention acquires hyperspectral data of soil samples under controlled laboratory conditions, strictly controlling the soil sample processing and preparation process, laboratory environmental conditions, and spectral measurement operation specifications to ensure the quality of spectral data acquisition and greatly reduce data errors introduced into further spectral analysis. It effectively solves the technical problem that current soil spectral analysis technology is difficult to achieve under standardized conditions for soil sample collection, preparation, and spectral testing during basic data acquisition, and the resulting spectral variation is a major factor restricting model sharing and cross-application. Furthermore, due to the influence of objective factors such as region and environment, soil spectral characteristics vary greatly. If only a small amount of data is used, it is impossible to fully characterize the correlation between soil spectral characteristics and total nitrogen content in the soil. Consequently, the constructed soil total nitrogen content sensitive hyperspectral index and soil total nitrogen content sensitive broadband remote sensing index lack reliability and generalization. Therefore, this invention constructs soil total nitrogen content sensitive hyperspectral index and soil total nitrogen content sensitive broadband remote sensing index based on a large amount of data from different regions under a controlled laboratory environment. This accurately finds the correlation between soil spectral characteristics and total nitrogen content in the soil, ensuring the generalization and reliability of the soil total nitrogen content sensitive hyperspectral index and soil total nitrogen content sensitive broadband remote sensing index.

[0022] In some embodiments, the process of obtaining the correlation coefficient matrix is ​​as follows: Figure 3 As shown, it includes: Using the Pearson correlation analysis algorithm, the correlation coefficient is calculated using the following formula: ; Where, r i,j X represents the correlation coefficient between the i-th and j-th bands of a soil sample. i,j Let Y represent the sensitivity index between the spectra of the i-th band and the j-th band, and let Y represent the total nitrogen content. Arrange the obtained correlation coefficients in band order to form a correlation coefficient matrix.

[0023] By traversing the full-band soil spectral data from 401 to 2400 nm, the sensitivity index of any two spectral bands is calculated. Then, based on correlation analysis, the correlation coefficient between any sensitivity index and total nitrogen content is calculated, and a three-dimensional correlation coefficient matrix is ​​constructed, thereby realizing the analysis and extraction of the total nitrogen sensitivity spectral index.

[0024] Specifically, in some embodiments, the sensitivity index is the difference index SSDI. i,j =R i -R j SSRI (Short-Term Ratio Index) i,j =R i / R j and normalized index SSNI i,j =(R i -R j ) / (R i +R j ), where R i and R j These represent the spectral reflectance of the i-th and j-th bands within the 401nm-2400nm wavelength range, respectively. In this embodiment of the invention, the 401nm-2400nm wavelength range is divided into 1nm band intervals, resulting in 2000 spectral bands. It is understandable that for the SSDI (Spectral Reflectance Difference Index)... i,j The corresponding correlation coefficient for: ; For the ratio index SSRI i,j The corresponding correlation coefficient for: ; For the normalized index SSNI i,j The corresponding correlation coefficient for: ; In this embodiment of the invention, based on the Pearson correlation coefficient, the correlation coefficients between the calculated sensitivity indices of any two bands and the total nitrogen content are filled into the corresponding positions of the correlation coefficient matrix. By traversing all bands (401nm-2400nm), a correlation coefficient matrix of size 2000×2000 for the entire band can be obtained.

[0025] like Figure 4 The high and low distribution of correlation coefficients shown characterizes the correlation coefficients between the total nitrogen content and any two-band index (difference, ratio, normalized difference) with a 1 nm interval in the spectral range from visible near-infrared to short-wave infrared. Figure 4 Figures (a) to (c) show the changes in the correlation between the difference index, ratio index, and normalization index and total nitrogen content, respectively. Figure 4 The colors, from blue to red, represent the transition from negative correlation to positive correlation. Figure 4 As can be seen, there is a response of the dual-band spectral combination index to STN with a correlation coefficient of over 0.75 in the short-wave infrared region.

[0026] S2: Based on the multiple correlation coefficient matrices obtained in step S1, determine the two optimal spectral bands for each sensitivity index, and the optimal sensitivity index corresponding to the two optimal spectral bands. In some embodiments, the two spectral bands corresponding to the largest correlation coefficient in the correlation coefficient matrix are selected as the two optimal spectral bands; each sensitivity index under the two optimal spectral bands is the corresponding optimal sensitivity index.

[0027] In this embodiment of the invention, step S2 specifically includes: for each sensitivity index among the difference index, ratio index, and normalized index, selecting the two spectral bands corresponding to the largest correlation coefficient in the correlation coefficient matrix as the two optimal spectral bands; each sensitivity index under the two optimal spectral bands is the corresponding optimal sensitivity index. Specifically, taking the ratio index as an example, selecting the largest correlation coefficient (e.g., the largest correlation coefficient in the correlation coefficient matrix corresponding to the ratio index) Figure 4 (b) The two bands corresponding to the point with the deepest red color (i.e., λ) i =2269, λ j =2230) represents two optimal spectral bands; based on the two optimal spectral bands λ i =2269 and λ j =2230 Calculate the optimal sensitivity index corresponding to the ratio index, that is: R-SSRI=R 2230 / R 2269 ; Where R-SSRI represents the optimal sensitivity index corresponding to the ratio index, R 2230 and R 2269 These represent the spectral reflectance at wavelengths of 2230 nm and 2269 nm, respectively. Using the above method, the optimal sensitivity indices R-SSDI and R-SSNI corresponding to the difference index and normalized index can be obtained as follows: R-SSDI=R 2232 -R 2270 ; R-SSNI=(R2230 -R 2269 ) / (R 2230 +R 2269 ).

[0028] In some embodiments, after step S2, the algorithm further includes: using the ICO (Interval Combination Optimization) algorithm and / or the SPA (Successive Projection Algorithm) algorithm to verify the optimal band spectrum determined in step S2. The SPA algorithm is a typical forward optimization algorithm based on the successive projection strategy. When extracting spectral feature bands, the successive projection algorithm starts from one band and iteratively selects the band data with the lowest correlation to the starting band spectral data to form a data subset. Then, stepwise multiple regression modeling and verification are performed based on this data subset. Since the data subset selected by the algorithm consists of band data with the lowest correlation, the SPA algorithm can effectively reduce collinearity between feature bands and is a major algorithm for constructing remote sensing indices. The ICO algorithm is a spectral feature band analysis method. This algorithm uses a soft contraction followed by local retrieval to achieve spectral interval combination optimization, and has the advantages of fewer parameters, soft contraction, and fast convergence. Similar to the SPA algorithm, the ICO algorithm is also based on multi-band spectral data combination, using a multi-band combination selection strategy that optimizes the model accuracy during multiple regression modeling and validation. Unlike the SPA algorithm, ICO employs spectral interval analysis, replacing the point-by-point analysis strategy used in algorithms like SPA. This significantly reduces the computational burden of soft contraction strategies during the optimization process and effectively mitigates the risk of overfitting, making it a primary algorithm for remote sensing index optimization. This invention further validates the optimal band spectrum determined in step S2 using two algorithms to ensure the accuracy of the optimal band spectrum.

[0029] The verification process for the optimal band spectrum is as follows: Figure 5 As shown, the specific steps include: calculating each sensitivity index for any two spectral bands in the soil hyperspectral data, constructing a spectral index set corresponding to each sensitivity index, with a size of N×N×n, where N represents the total number of bands in the soil hyperspectral data (N=2000 in this embodiment), and n represents the number of soil samples (n=10000 in this embodiment); within each spectral index set, taking a sub-spectral index set IDX of size N×n corresponding to any band, and using the total nitrogen content of the corresponding sample for calculation using the ICO algorithm and / or SPA algorithm, so that the optimal sub-spectral index set Opt is selected from the N sub-spectral index sets IDX. IDX Optimal subspectral index set Opt IDXThe corresponding band spectrum constitutes the verification band spectrum set; if the optimal band spectrum determined in step S2 is in the band spectrum set, it indicates that the optimal band spectrum determined in step S2 is correct.

[0030] S3: Cross-regional validation was conducted on multiple optimal sensitivity indices, and the optimal sensitivity index with the best robustness was selected as the soil total nitrogen content sensitive hyperspectral index.

[0031] In this embodiment of the invention, sample sets from regions A, B, and C, as well as the publicly available LUCAS2009 dataset from region D, are specifically used to perform cross-regional validation of the optimal sensitivity indices corresponding to the difference index, ratio index, and normalization index. The stability of the three optimal sensitivity indices in cross-regional application is tested, and the test results are shown in the table below. The results show that the optimal sensitivity index corresponding to the ratio index R-SSRI is R-SSRI = R. 2230 / R 2269 In the validation in four regions, it achieved a high correlation coefficient with total nitrogen content, and the expression is simpler than the normalized difference index. It has the best robustness in cross-regional validation and is the soil total nitrogen content sensitive hyperspectral index selected in the embodiments of this invention.

[0032] Table 1:

[0033] S4: Based on the spectral response function of the remote sensing data, the soil hyperspectral data from step S1 is resampled in a wideband. The correspondence between the resampled wideband data and the correlation coefficient matrix in step S2 is calculated. Based on the soil total nitrogen content sensitive hyperspectral index from step S3, the soil total nitrogen content sensitive wideband remote sensing index is extracted. This invention utilizes the spectral response function of the remote sensing sensor to perform wideband resampling of soil hyperspectral data, matching the sampling rate of soil hyperspectral data in the laboratory environment with that of the remote sensing data. This maps the hyperspectral data from the laboratory environment to the remote sensing data, thereby achieving the transfer from measured data in the laboratory environment to remote sensing data. The soil total nitrogen content sensitive wideband remote sensing index obtained in step S4 reflects the distribution of soil total nitrogen content when applied to the remote sensing data, thus enabling prediction of soil total nitrogen content distribution based on the remote sensing index.

[0034] In some embodiments, broadband spectral resampling of soil hyperspectral data includes: setting a moving average window based on the full width at half maximum (FWHM) of the spectral response function of the remote sensing sensor, and resampling the spectral data within the effective spectral range of the soil hyperspectral data to obtain broadband spectral data. Step S4 further includes: expanding the resampled broadband spectral data based on a regression-fitted transformation equation.

[0035] To verify the effectiveness of the method provided by this invention, this embodiment uses publicly available Landsat, Sentinel, and MODIS remote sensing data to predict the total nitrogen content distribution in a certain region. Step S4 specifically includes: using the full width at half maximum (FWHM) of the spectral response function of the remote sensing sensors corresponding to the Landsat, Sentinel, and MODIS data, respectively, setting a moving average window, and using spectral resampling technology. The moving average window is used to resample hyperspectral data within the effective spectral range of different remote sensing data, and then the hyperspectral data is converted to multispectral data based on a regression fitting transformation equation; based on the scale-transformed spectral data, the correlation coefficient matrix between the broadband spectral index and total nitrogen content is reconstructed; according to the soil total nitrogen content sensitive hyperspectral index in step S3, the soil total nitrogen content sensitive broadband remote sensing index is extracted. At this point, the following results are obtained: The sensitive broadband remote sensing index for total nitrogen content in soil from Landsat™ remote sensing data is: STNRSI Landsat TM / ETM+ =R B7 / R B2 ; STNRSI Landsat OLI =R B7 / R B3 ; Among them, STNRSI Landsat TM / ETM+ The Soil Total Nitrogen Ratio Soil Index (STNRSI) represents the soil total nitrogen content sensitive broadband remote sensing index based on Landsat TM or ETM+ sensor remote sensing data. B7 This represents the spectral reflectance of band 7 in Landsat™ / ETM+ remote sensing data, corresponding to the shortwave infrared band in the Landsat™ / ETM+ remote sensing data. R B2 This represents the spectral reflectance of band 2 in Landsat TM / ETM+ remote sensing data, corresponding to the visible green band in Landsat TM / ETM+ remote sensing data; STNRSI Landsat OLI R represents the sensitive broadband remote sensing index of total nitrogen content in soil from Landsat OLI sensor remote sensing data. B7 R represents the spectral reflectance of band 7 in Landsat OLI remote sensing data, corresponding to the shortwave infrared band in Landsat OLI remote sensing data. B3 This represents the spectral reflectance of band 3 in Landsat OLI remote sensing data, corresponding to the visible green band in Landsat remote sensing data. The Sentinel remote sensing data for soil total nitrogen content sensitive broadband remote sensing index is: STNRSISentinel =R B12 / R B3 ; Among them, STNRSI Sentinel R represents the sensitive broadband remote sensing index of total nitrogen content in soil from Sentinel-2 MSI remote sensing data. B12 R represents the spectral reflectance of band 12 in Sentinel-2 MSI remote sensing data, corresponding to the shortwave infrared band in the Sentinel-2 MSI remote sensing data. B3 This represents the spectral reflectance of the third band in the Sentinel-2 MSI remote sensing data, corresponding to the visible green band in the visible and near-infrared bands of the Sentinel-2 MSI remote sensing data. The sensitive broadband remote sensing index for total nitrogen content in soil from MODIS remote sensing data is: STNRSI MODIS =R B7 / R B4 ; Among them, STNRSI MODIS R represents the sensitive broadband remote sensing index of total nitrogen content in soil from MODIS remote sensing data. B7 This represents the spectral reflectance of band 7 in MODIS remote sensing data, corresponding to the 2105-2155 nm band in MODIS remote sensing data. R B4 This represents the spectral reflectance of band 4 in MODIS remote sensing data, corresponding to the 545-565nm band in MODIS remote sensing data. Based on the above three remote sensing data, the soil total nitrogen content sensitive broadband remote sensing index can be summarized as follows: STNRSI=R SWIR / R GREEN ; STNRSI represents the broadband remote sensing index sensitive to total nitrogen content in soil, R SWIR R represents the spectral reflectance in the shortwave infrared band of the remote sensing data of the area to be detected. GREEN This represents the spectral reflectance of the visible green band in the remote sensing data of the area to be detected.

[0036] S5: Using the soil total nitrogen content sensitive broadband remote sensing index from step S4, predict the distribution of total nitrogen content in the remote sensing data of the area to be detected.

[0037] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this invention disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this invention can be achieved, and this is not limited herein.

[0038] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A rapid detection method of total nitrogen in soil based on remote sensing detection, characterized in that, The method comprises the following steps: S1: Obtain the total nitrogen content in the soil sample and the soil hyperspectral data, and calculate a plurality of sensitive indexes between any two spectral bands; Based on the relationship between the total nitrogen content and the soil hyperspectral data, a correlation coefficient matrix of each sensitive index and the total nitrogen content is extracted; S2: According to the plurality of correlation coefficient matrices obtained in step S1, determine two optimal spectral bands under each sensitive index, and the optimal sensitive index corresponding to the two optimal spectral bands; S3: Cross-region verification is performed on a plurality of optimal sensitive indexes, and the optimal sensitive index with the best robustness is selected as the soil total nitrogen content sensitive hyperspectral index; S4: According to the spectral response function of remote sensing data, the soil hyperspectral data in step S1 is resampled in a wide band, the corresponding relationship of the resampled wide band in the correlation coefficient matrix in step S2 is calculated, and the soil total nitrogen content sensitive wide band remote sensing index is extracted according to the soil total nitrogen content sensitive hyperspectral index in step S3; S5: The soil total nitrogen content sensitive wide band remote sensing index in step S4 is used to predict the total nitrogen content distribution of the remote sensing data of the region to be detected.

2. The method for rapid detection of total nitrogen in soil based on remote sensing detection according to claim 1, characterized in that, In step S1: The correlation coefficient is calculated by using the Pearson correlation analysis algorithm through the following formula: ； wherein r i,j represents the correlation coefficient of the spectrum of the i-th wave band and the j-th wave band of the soil sample, X i,j represents the sensitive index between the i-th wave band and the j-th wave band spectrum, Y represents the total nitrogen content; The obtained correlation coefficient is arranged in the order of the band to form a correlation coefficient matrix. 3.The method according to claim 1, wherein, The sensitive index is a difference index, a ratio index and a normalized index. 4.The method according to claim 1, wherein, In step S2: The two spectral bands corresponding to the maximum correlation coefficient in the correlation coefficient matrix are selected as the two optimal spectral bands; and each sensitive index under the two optimal spectral bands is the corresponding optimal sensitive index.

5. The method for rapid detection of soil total nitrogen based on remote sensing detection according to claim 1, characterized in that, Between step S2 and step S3, it also includes: using the ICO algorithm and / or the SPA algorithm to verify the optimal spectral band determined in step S2, including: The calculation of each sensitive index is performed on any two spectral bands in the soil hyperspectral data, and a spectral index set corresponding to each sensitive index is constructed, and the size of the spectral index set is N×N×n, wherein N represents the total number of bands in the soil hyperspectral data, and n represents the number of soil samples; In each spectral index set, a sub-spectral index set with a size of N×n corresponding to any one band is taken, and the total nitrogen content of the corresponding sample is introduced to perform the ICO algorithm and / or the SPA algorithm calculation, so that the optimal sub-spectral index set is selected from the N sub-spectral index sets, and the band spectrum corresponding to the optimal sub-spectral index set constitutes a verification band spectrum set; If the optimal band spectrum determined in step S2 is in the band spectrum set, it indicates that the optimal band spectrum determined in step S2 is correct. 6.The method of claim 1, wherein, In step S4, the wide band spectral resampling of the soil hyperspectral data comprises: According to the full width at half maximum of the spectral response function of the remote sensing sensor, a moving average window is set, and the spectral data in the effective spectral interval of the soil hyperspectral data is resampled to obtain wide band spectral data. 7.The method according to claim 6, wherein, Step S4 further comprises: based on a regression fitting conversion equation, the resampled wide band spectral data is expanded. 8.The method according to claim 1, wherein, The soil total nitrogen content sensitive wide band remote sensing index is as follows: STNRSI = R SWIR / R GREEN ; Wherein, STNRSI represents the soil total nitrogen content sensitive wide band remote sensing index, R SWIR represents the spectral reflectance of the short-wave infrared band in the remote sensing data of the region to be detected, R GREEN represents the spectral reflectance of the visible green light in the remote sensing data of the region to be detected.

Images