A crop photosynthetic parameter inversion method, device, medium and product

Abstract

The application discloses a crop photosynthetic parameter inversion method, device, medium and product, and relates to the field of phenomics technology.The method comprises the following steps: acquiring images of all characteristic wave bands of a crop to be predicted; determining reflectivity of a corresponding characteristic wave band based on the images of the characteristic wave bands; pre-processing the reflectivity of the corresponding characteristic wave band by using an optimal pre-processing strategy corresponding to the characteristic wave band, so as to obtain the reflectivity of the corresponding characteristic wave band after optimal pre-processing; inputting prediction values of prediction parameters corresponding to each photosynthetic parameter into a corresponding photosynthetic parameter inversion model in a preset order, so as to obtain the prediction values of the corresponding photosynthetic parameter; and the photosynthetic parameters comprise A1200, SPAD, chlorophyll a, chlorophyll b and leaf nitrogen content.The application can quickly, non-destructively and accurately determine multiple photosynthetic parameters of crops.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of phenomics, and in particular to a crop photosynthetic parameter inversion method, device, medium and product. BACKGROUND

[0002] The yield of crops is determined by light energy capture efficiency, economic coefficient and photosynthetic efficiency. At present, the light energy capture efficiency and the economic coefficient have reached the theoretical maximum, and cultivating high light efficiency crops has become a fundamental way to further greatly improve crop yield. Photosynthetic parameters are specific manifestations of crop photosynthetic efficiency, among which A1200, SPAD, chlorophyll a, chlorophyll b and leaf nitrogen content are important photosynthetic parameters. In the traditional photosynthetic parameter determination method, different photosynthetic parameters often need to be measured by different instruments, and the measurement process is time-consuming and complex to operate. In addition, photosynthetic physiological parameters such as chlorophyll content and nitrogen content are usually determined by a method that is harmful to crops. At present, phenomics research uses different sensors to measure the geometric and physiological shapes of crops, including using radar, high / multi-spectral cameras, infrared cameras, and light imaging sensors to observe crops. Among them, the hyperspectral imaging device can obtain many continuous and narrow-band spectral bands from visible light to infrared light spectrum. These band images contain rich information about the spectral and spatial distribution of different surface materials, and can realize non-destructive detection of invisible plant physiological processes. This feature makes it possible to non-destructively detect crop photosynthetic parameters.

[0003] Traditional spectral analysis work usually focuses on single targets for independent analysis, but multiple photosynthetic parameters of crops are usually interrelated and play a synergistic role. Single target analysis may lack a global perspective of the overall system, thereby affecting the understanding of complex systems. SUMMARY

[0004] The purpose of the present application is to provide a crop photosynthetic parameter inversion method, device, medium and product, which can quickly, non-destructively and accurately determine multiple photosynthetic parameters of crops.

[0005] To achieve the above purpose, the present application provides the following solutions:

[0006] In a first aspect, the present application provides a crop photosynthetic parameter inversion method, comprising:

[0007] obtaining images of all characteristic wavebands of a crop to be predicted;

[0008] determining reflectivity of a corresponding characteristic waveband based on the image of the characteristic waveband;

[0009] preprocessing the reflectivity of the corresponding characteristic waveband using the optimal preprocessing strategy corresponding to the characteristic waveband to obtain the optimal preprocessed reflectivity of the corresponding characteristic waveband;

[0010] inputting the predicted values of the prediction parameters corresponding to each photosynthetic parameter into the corresponding photosynthetic parameter inversion model in a preset order to obtain the predicted values of the corresponding photosynthetic parameter; the predicted values of the prediction parameters are first parameters or second parameters; the first parameters corresponding to the current photosynthetic parameter include the best pre-processed reflectance of all characteristic wavebands corresponding to the current photosynthetic parameter; the second parameters corresponding to the current photosynthetic parameter include the best pre-processed reflectance of all characteristic wavebands corresponding to the current photosynthetic parameter and the predicted values of inversion parameters; the inversion parameters include one or more photosynthetic parameters sequentially located before the current photosynthetic parameter, and the predicted values of the inversion parameters include the predicted values of the photosynthetic parameters output by the photosynthetic parameter inversion model corresponding to the inversion parameters; the photosynthetic parameter inversion model corresponding to the current photosynthetic parameter is determined by using the single-parameter prediction model corresponding to the current photosynthetic parameter, the best pre-processed reflectance of all characteristic wavebands and the true values of the inversion parameters; the photosynthetic parameters include AI2 000, SPAD, chlorophyll a, chlorophyll b and leaf nitrogen content.

[0011] Optionally, the determination process of the best pre-processing strategy corresponding to any current photosynthetic parameter includes:

[0012] obtaining the images of full wavebands of the training crops and the true values of the corresponding current photosynthetic parameters; the full wavebands include the characteristic wavebands corresponding to all photosynthetic parameters;

[0013] determining the reflectance of each waveband based on the images of the waveband;

[0014] constructing a plurality of initial pre-processing strategies based on a plurality of pre-processing methods; the pre-processing methods include baseline correction, scattering correction and scale scaling; the baseline correction includes Savitzky-Golay first-order differentiation, Savitzky-Golay second-order differentiation and continuous wavelet transform; the scattering correction includes multivariate scattering correction and standard normal transform; and the scale scaling includes mean centering and standardization;

[0015] respectively processing the reflectance of each waveband by using each initial pre-processing strategy to obtain the pre-processed reflectance of each waveband under the corresponding initial pre-processing strategy;

[0016] determining the predicted values of the current photosynthetic parameters of the training crops under each initial pre-processing strategy based on the pre-processed reflectance of all wavebands under each initial pre-processing strategy by using the partial least squares cross-validation method;

[0017] calculating the regression coefficients under each initial pre-processing strategy based on the true values of the current photosynthetic parameters of the training crops and the predicted values of the current photosynthetic parameters of the training crops under each initial pre-processing strategy;

[0018] determine the initial pretreatment strategy corresponding to the maximum regression coefficient as the optimal pretreatment strategy corresponding to the current photosynthetic parameter.

[0019] Optionally, the determination process of the single-parameter prediction model corresponding to any current photosynthetic parameter comprises:

[0020] The reflectivity of each band in the full wave band of the training crop is pretreated by using the optimal pretreatment strategy corresponding to the current photosynthetic parameter, to obtain the optimal pretreated reflectivity of each band in the full wave band.

[0021] The optimal pretreated reflectivity of all bands in the full wave band is input into the three first pre-trained models respectively, to obtain the predicted value of the current photosynthetic parameter output by the corresponding first pre-trained model; the three first pre-trained models are obtained by training the three initial models for the same number of times by using an initial model training set, wherein the initial model training set comprises the optimal pretreated reflectivity of all bands in the full wave band corresponding to the current photosynthetic parameter of the plurality of training crops and the corresponding true value of the current photosynthetic parameter, and the three initial models are least square regression, support vector regression and random forest respectively;

[0022] Based on the true value of the current photosynthetic parameter of the training crop and the predicted value of the current photosynthetic parameter output by each first pre-trained model, the regression coefficient of the corresponding first pre-trained model is calculated.

[0023] The first pre-trained model corresponding to the maximum regression coefficient is determined as the single-parameter prediction model corresponding to the current photosynthetic parameter.

[0024] Optionally, the determination process of the feature band corresponding to any current photosynthetic parameter comprises:

[0025] Each band in the full wave band is screened by using four band selection methods respectively, to obtain the initial screening band corresponding to the current photosynthetic parameter under the corresponding band selection method.

[0026] The reflectivity of each initial screening band under each band selection method is pretreated by using the optimal pretreatment strategy corresponding to the current photosynthetic parameter, to obtain the optimal pretreated reflectivity of the corresponding initial screening band.

[0027] The optimal pretreated reflectivity of all initial screening bands under each band selection method is input into the single-parameter prediction model corresponding to the current photosynthetic parameter respectively, to obtain the predicted value of the current photosynthetic parameter under the corresponding band selection method.

[0028] Based on the true value of the current photosynthetic parameter and the predicted value of the current photosynthetic parameter under each band selection method, the regression coefficient under the corresponding band selection method is calculated.

[0029] The initial screening band of the current photosynthetic parameter under the band selection method corresponding to the maximum regression coefficient is determined as the characteristic band corresponding to the current photosynthetic parameter.

[0030] Optionally, the determination process of the inversion parameter corresponding to any current photosynthetic parameter and the photosynthetic parameter inversion model comprises:

[0031] The photosynthetic parameters are numbered in the preset order to obtain the serial numbers of the photosynthetic parameters; the serial numbers of the photosynthetic parameters are 1, 2, 3, 4 and 5 in turn;

[0032] When the serial number of the current photosynthetic parameter is 1, the single-parameter prediction model of the current photosynthetic parameter is determined as the photosynthetic parameter inversion model of the current photosynthetic parameter;

[0033] When the serial number of the current photosynthetic parameter is not 1, the inversion parameter corresponding to the current photosynthetic parameter and the photosynthetic parameter inversion model are determined based on the single-parameter prediction model of the current photosynthetic parameter and the predicted values of the photosynthetic parameters with serial numbers smaller than that of the current photosynthetic parameter.

[0034] Optionally, the determination of the inversion parameter corresponding to the current photosynthetic parameter and the photosynthetic parameter inversion model based on the single-parameter prediction model of the current photosynthetic parameter and the predicted values of the photosynthetic parameters with serial numbers smaller than that of the current photosynthetic parameter comprises:

[0035] The best preprocessed reflectance of all the characteristic bands corresponding to the current photosynthetic parameter is input into the single-parameter prediction model corresponding to the current photosynthetic parameter to obtain a single predicted value of the current photosynthetic parameter;

[0036] The single regression coefficient of the current photosynthetic parameter is calculated based on the true value and the single predicted value of the current photosynthetic parameter;

[0037] The predicted values of the inversion parameters corresponding to the current photosynthetic parameter are obtained by arranging and combining the predicted values of the photosynthetic parameters with serial numbers smaller than that of the current photosynthetic parameter; one set of inversion parameters comprises one or more photosynthetic parameters;

[0038] Any set of inversion parameters corresponding to the current photosynthetic parameter is determined as the current inversion parameter, and the predicted value of the current inversion parameter and the best preprocessed reflectance of all the characteristic bands corresponding to the current photosynthetic parameter are determined as the predicted value of the current combined parameter;

[0039] The predicted value of the current combined parameter is input into the second pre-training model corresponding to the current combined parameter to obtain a joint predicted value of the current photosynthetic parameter under the current combined parameter; the second pre-training model corresponding to the current combined parameter is obtained by training the single-parameter prediction model corresponding to the current photosynthetic parameter using the true values of the current combined parameters of a plurality of training crops, and the training rounds of each second pre-training model are the same;

[0040] The joint regression coefficient of the current photosynthetic parameter under the current combination parameter is calculated based on the joint predicted value of the current photosynthetic parameter under the current combination parameter and the true value of the current photosynthetic parameter.

[0041] The optimal pre-processed reflectance of all characteristic wave bands corresponding to the combination parameter or the current photosynthetic parameter corresponding to the maximum value between the joint regression coefficient of the current photosynthetic parameter under all combination parameters and the individual regression coefficient of the current photosynthetic parameter is determined as a prediction parameter, and a second pre-training model corresponding to the prediction parameter is determined as a photosynthetic parameter inversion model corresponding to the current photosynthetic parameter.

[0042] Optionally, the reflectance of each characteristic wave band is determined based on the image of the corresponding characteristic wave band, and the reflectance of each characteristic wave band is determined based on the image of the corresponding characteristic wave band.

[0043] The reflectance of each characteristic wave band is determined based on the image of the corresponding characteristic wave band by using a reflectance calculation formula.

[0044]

[0045] wherein, F α is the reflectance of the wave band α; r α is the original average reflectance of the image of the wave band α; a is the reflectance of the dark current; b is the average reflectance of the white reference plate; and c is the true reflectance of the white reference plate.

[0046] In a second aspect, the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the crop photosynthetic parameter inversion method according to any one of the above aspects.

[0047] In a third aspect, the present application provides a computer readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the crop photosynthetic parameter inversion method according to any one of the above aspects.

[0048] In a fourth aspect, the present application provides a computer program product comprising a computer program, and the computer program is executed by a processor to implement the crop photosynthetic parameter inversion method according to any one of the above aspects.

[0049] According to the embodiments of the present application, the following technical effects are achieved:

[0050] The application discloses a crop photosynthetic parameter inversion method and device, a medium and a product. First, images of all characteristic wavebands of a crop to be predicted are acquired. Then, reflectivity of a corresponding characteristic waveband is determined based on the images of the characteristic wavebands. The reflectivity of the corresponding characteristic waveband is preprocessed by using an optimal preprocessing strategy corresponding to the characteristic waveband, so that the reflectivity of the corresponding characteristic waveband after optimal preprocessing is obtained. Finally, prediction values of prediction parameters corresponding to each photosynthetic parameter are sequentially input into a corresponding photosynthetic parameter inversion model in a preset order, so that the prediction values of the corresponding photosynthetic parameter are obtained. The prediction values of the prediction parameters are first parameters or second parameters. The first parameters corresponding to a current photosynthetic parameter include the reflectivity of all characteristic wavebands corresponding to the current photosynthetic parameter after optimal preprocessing. The second parameters corresponding to the current photosynthetic parameter include the reflectivity of all characteristic wavebands corresponding to the current photosynthetic parameter after optimal preprocessing and prediction values of inversion parameters. The inversion parameters include one or more photosynthetic parameters sequentially located before the current photosynthetic parameter, and the prediction values of the inversion parameters include prediction values of the photosynthetic parameters output by a photosynthetic parameter inversion model corresponding to the inversion parameters. The photosynthetic parameter inversion model corresponding to the current photosynthetic parameter is determined by using a single-parameter prediction model corresponding to the current photosynthetic parameter, the reflectivity of all characteristic wavebands after optimal preprocessing and true values of the inversion parameters. The photosynthetic parameters include A1200, SPAD, chlorophyll a, chlorophyll b and leaf nitrogen content. In the application, the photosynthetic parameter inversion model corresponding to the current photosynthetic parameter is determined by using the single-parameter prediction model corresponding to the current photosynthetic parameter, the reflectivity of all characteristic wavebands after optimal preprocessing and the true values of the inversion parameters, and the current photosynthetic parameter is predicted in combination with other photosynthetic parameters, so that multiple photosynthetic parameters of the crop can be quickly, non-destructively and accurately determined. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0052] Figure 1 A crop photosynthetic parameter inversion method flowchart is provided for an embodiment of the present application.

[0053] Figure 2 A best preprocessing strategy selection flowchart based on a multi-stage experimental design is provided.

[0054] Figure 3 A basic flowchart of a correlation stepwise regression chain model is provided.

[0055] Figure 4 A structural schematic diagram of a computer device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0057] The purpose of the present application is to provide a crop photosynthetic parameter inversion method, device, medium and product, aiming to quickly, non-destructively and accurately determine multiple photosynthetic parameters of crops.

[0058] In order to make the above-mentioned purposes, characteristics and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0059] In an exemplary embodiment, as shown in FIG. 1, the crop photosynthetic parameter inversion method in the present embodiment comprises: Figure 1

[0060] Step 1: Obtain images of all characteristic wave bands of the crop to be predicted.

[0061] Step 2: Determine the reflectivity of the corresponding characteristic wave band based on the image of each characteristic wave band.

[0062] As an optional implementation, step 2 comprises:

[0063] According to the reflectivity calculation formula, the reflectivity of the corresponding characteristic wave band is determined respectively according to the image of each characteristic wave band; the reflectivity calculation formula is:

[0064]

[0065] wherein, F α is the reflectivity of wave band a; r α is the original average reflectivity of the image of wave band a, i.e. the average reflectivity of all pixel points in the image of wave band a; a is the reflectivity of dark current, i.e. the reflectivity generated by the hyperspectral camera in the absence of light; b is the average reflectivity of the white reference plate, i.e. the value obtained by averaging the reflectivity of all pixel points in the image obtained by hyperspectral imaging of the white reference plate in the current imaging environment; c is the true reflectivity of the white reference plate.

[0066] Step 3: The reflectivity of the corresponding characteristic wave band is preprocessed by using the best preprocessing strategy corresponding to each characteristic wave band, to obtain the best preprocessed reflectivity of the corresponding characteristic wave band.

[0067] ​Step 4: input the prediction value of the prediction parameter corresponding to each photosynthetic parameter into the corresponding photosynthetic parameter inversion model in a preset order to obtain the prediction value of the corresponding photosynthetic parameter.

[0068] The prediction value of the prediction parameter is the first parameter or the second parameter; the first parameter corresponding to the current photosynthetic parameter includes the optimal pre-processed reflectivity of all characteristic wavebands corresponding to the current photosynthetic parameter; the second parameter corresponding to the current photosynthetic parameter includes the optimal pre-processed reflectivity of all characteristic wavebands corresponding to the current photosynthetic parameter and the prediction value of the inversion parameter; the inversion parameter includes one or more photosynthetic parameters sequentially located before the current photosynthetic parameter, and the prediction value of the inversion parameter includes the prediction value of the photosynthetic parameter output by the photosynthetic parameter inversion model corresponding to the inversion parameter; the photosynthetic parameter inversion model corresponding to the current photosynthetic parameter is determined by using the single-parameter prediction model corresponding to the current photosynthetic parameter, the optimal pre-processed reflectivity of all characteristic wavebands and the true value of the inversion parameter; the photosynthetic parameter includes A1200, SPAD, chlorophyll a, chlorophyll b and leaf nitrogen content.

[0069] As an optional implementation, the determination process of the optimal pre-processing strategy corresponding to any current photosynthetic parameter includes:

[0070] Step 11: obtaining the full-waveband image of the training crop and the true value of the corresponding current photosynthetic parameter; the full-waveband includes all characteristic wavebands corresponding to the photosynthetic parameter.

[0071] Specifically, the training crop is placed on a hyperspectral data acquisition system for overhead push-broom shooting. The hyperspectral data acquisition system is controlled by an electronic system, a plurality of halogen lamps are installed on the top to provide light supplement for the crop, a hyperspectral camera is installed on the top horizontal slide rail to horizontally push-broom shoot the leaves of the training crop, and the hyperspectral image of the crop is collected in real time, and the hyperspectral image includes the full-waveband image.

[0072] The ROI position of the hyperspectral image is manually identified by using ENVI software, and the hyperspectral image of the ROI region is used as the full-waveband image of the training crop.

[0073] Step 12: determining the reflectivity of each waveband in the full-waveband based on the image of the waveband.

[0074] Specifically, the reflectivity of each waveband in the full-waveband is determined based on the image of the waveband by using a reflectivity calculation formula.

[0075] Step 13: Based on multiple pretreatment methods, multiple initial pretreatment strategies are constructed; the pretreatment methods include baseline correction, scatter correction and scale scaling, the baseline correction includes Savitzky-Golay first-order differential, Savitzky-Golay second-order differential and continuous wavelet transform; the scatter correction includes multivariate scatter correction and standard normal transform; the scale scaling includes mean centering and standardization.

[0076] Step 14: The reflectivity of each waveband is processed respectively using each initial pretreatment strategy to obtain the pretreated reflectivity of each waveband under the corresponding initial pretreatment strategy.

[0077] Step 15: Based on the pretreated reflectivity of all wavebands under each initial pretreatment strategy, the prediction value of the current photosynthetic parameter of the training crop under the corresponding initial pretreatment strategy is determined using the partial least squares cross-validation method.

[0078] Step 16: Based on the true value of the current photosynthetic parameter of the training crop and the prediction value of the current photosynthetic parameter of the training crop under each initial pretreatment strategy, the regression coefficient under the corresponding initial pretreatment strategy is calculated.

[0079] Step 17: The initial pretreatment strategy corresponding to the maximum regression coefficient is determined as the best pretreatment strategy corresponding to the current photosynthetic parameter.

[0080] Specifically, as shown in the following table, the best pretreatment strategy is determined based on the principle of multi-stage experimental design, and the processing flow includes: Figure 2

[0081] S171: The specific process of multi-stage design includes three stages including execution sequence, inter-class action and specific method strategy, and the pretreatment methods used include three types of baseline correction, scatter correction and scale scaling, wherein the baseline correction includes Savitzky-Golay first-order differential, Savitzky-Golay second-order differential and continuous wavelet transform; the scatter correction includes multivariate scatter correction and standard normal transform; the scale scaling includes mean centering and standardization. The three types of pretreatment are applied in the order of baseline correction, scatter correction and scale scaling.

[0082] S172: For various pretreatment methods in S171, 36 initial pretreatment strategies are designed by permutation and combination, and the best pretreatment strategy is selected by partial least squares cross-validation.

[0083] S173: Determine whether each initial pretreatment strategy is the best performance (i.e. the regression coefficient is maximum), if yes, select the initial pretreatment strategy as the best pretreatment strategy, if not, eliminate the initial pretreatment strategy.

[0084] ​As an optional implementation, the determination process of the single-parameter prediction model corresponding to any current photosynthetic parameter comprises:

[0085] Step 21: The reflectivity of each band in the full wave band of the training crop is preprocessed by using the optimal preprocessing strategy corresponding to the current photosynthetic parameter, to obtain the optimal preprocessed reflectivity of each band in the full wave band.

[0086] Step 22: The optimal preprocessed reflectivity of all bands in the full wave band is respectively input into three first pre-trained models to obtain the predicted value of the current photosynthetic parameter output by the first pre-trained model; the three first pre-trained models are obtained by training the same number of initial models by using an initial model training set, and the initial model training set comprises the optimal preprocessed reflectivity of all bands in the full wave band corresponding to the current photosynthetic parameter of the plurality of training crops and the corresponding true value of the current photosynthetic parameter, and the three initial models are respectively: least square regression, support vector regression and random forest.

[0087] Step 23: Based on the true value of the current photosynthetic parameter of the training crop and the predicted value of the current photosynthetic parameter output by each first pre-trained model, the regression coefficient of the corresponding first pre-trained model is calculated.

[0088] Step 24: The first pre-trained model corresponding to the maximum regression coefficient is determined as the single-parameter prediction model corresponding to the current photosynthetic parameter.

[0089] As an optional implementation, the determination process of the feature band corresponding to any current photosynthetic parameter comprises:

[0090] Step 31: Each band in the full wave band is screened by using four band selection methods respectively to obtain the initial screening band corresponding to the current photosynthetic parameter under the corresponding band selection method.

[0091] Step 32: The reflectivity of each initial screening band under each band selection method is preprocessed by using the optimal preprocessing strategy corresponding to the current photosynthetic parameter to obtain the optimal preprocessed reflectivity of the corresponding initial screening band.

[0092] Step 33: The optimal preprocessed reflectivity of all initial screening bands under each band selection method is respectively input into the single-parameter prediction model corresponding to the current photosynthetic parameter to obtain the predicted value of the current photosynthetic parameter under the corresponding band selection method.

[0093] Step 34: Based on the true value of the current photosynthetic parameter and the predicted value of the current photosynthetic parameter under each band selection method, the regression coefficient under the corresponding band selection method is calculated.

[0094] Step 35: The initial screening band of the current photosynthetic parameter under the band selection method corresponding to the maximum regression coefficient is determined as the characteristic band corresponding to the current photosynthetic parameter.

[0095] As an optional implementation, as shown in Figure 3 the determination process of the inversion parameter and the photosynthetic parameter inversion model corresponding to any current photosynthetic parameter includes:

[0096] Step 41: Number the photosynthetic parameters in a preset order to obtain the serial numbers of the photosynthetic parameters; the serial numbers of the photosynthetic parameters are 1, 2, 3, 4, and 5 in turn.

[0097] Specifically, the determination process of the preset order includes:

[0098] (1) The correlation coefficients between two photosynthetic parameters are calculated respectively to obtain a 5x5 covariance matrix. The calculation formula of the correlation coefficient is:

[0099]

[0100] wherein, C XY is the correlation coefficient between the photosynthetic parameters X and Y; I is the number of crops when the correlation coefficient is determined; X i is the true value of the photosynthetic parameter X of crop i; is the average value of the photosynthetic parameter X; Y i is the true value of the photosynthetic parameter Y of crop i; Y is the average value of the photosynthetic parameter Y.

[0101] (2) The total correlation coefficient corresponding to each photosynthetic parameter is obtained by summing all the correlation coefficients corresponding to the photosynthetic parameter.

[0102] (3) The preset order is determined as the order of the total correlation coefficients from large to small.

[0103] Step 42: When the serial number of the current photosynthetic parameter is 1, the single-parameter prediction model of the current photosynthetic parameter is determined as the photosynthetic parameter inversion model of the current photosynthetic parameter.

[0104] Step 43: When the serial number of the current photosynthetic parameter is not 1, the inversion parameter and the photosynthetic parameter inversion model corresponding to the current photosynthetic parameter are determined based on the single-parameter prediction model of the current photosynthetic parameter and the predicted values of the photosynthetic parameters with serial numbers smaller than that of the current photosynthetic parameter.

[0105] As an optional implementation, the determination of the inversion parameter and the photosynthetic parameter inversion model corresponding to the current photosynthetic parameter based on the single-parameter prediction model of the current photosynthetic parameter and the predicted values of the photosynthetic parameters with serial numbers smaller than that of the current photosynthetic parameter in step 43 includes:

[0106] Step 431: input the best pre-processed reflectance of all characteristic bands corresponding to the current photosynthetic parameter into the single-parameter prediction model corresponding to the current photosynthetic parameter to obtain a single prediction value of the current photosynthetic parameter.

[0107] Step 432: based on the true value and the single prediction value of the current photosynthetic parameter, calculate a single regression coefficient of the current photosynthetic parameter.

[0108] Step 433: arrange and combine the prediction values of the photosynthetic parameters with serial numbers less than the current photosynthetic parameter to obtain prediction values of multiple groups of inversion parameters corresponding to the current photosynthetic parameter; one group of inversion parameters includes one or more photosynthetic parameters.

[0109] Step 434: determine any group of inversion parameters corresponding to the current photosynthetic parameter as the current inversion parameter, and determine the prediction value of the current inversion parameter and the best pre-processed reflectance of all characteristic bands corresponding to the current photosynthetic parameter as the prediction value of the current combined parameter.

[0110] Step 435: input the prediction value of the current combined parameter into the second pre-trained model corresponding to the current combined parameter to obtain a joint prediction value of the current photosynthetic parameter under the current combined parameter; the second pre-trained model corresponding to the current combined parameter is obtained by training the single-parameter prediction model corresponding to the current photosynthetic parameter using the true values of the current combined parameters of multiple training crops, and the training rounds of each second pre-trained model are the same.

[0111] Step 436: based on the joint prediction value of the current photosynthetic parameter under the current combined parameter and the true value of the current photosynthetic parameter, calculate a joint regression coefficient of the current photosynthetic parameter under the current combined parameter.

[0112] Step 437: determine the combined parameter or the best pre-processed reflectance of all characteristic bands corresponding to the current photosynthetic parameter corresponding to the maximum value of the joint regression coefficient of the current photosynthetic parameter under all combined parameters and the single regression coefficient of the current photosynthetic parameter as the prediction parameter, and determine the second pre-trained model corresponding to the prediction parameter as the photosynthetic parameter inversion model corresponding to the current photosynthetic parameter.

[0113] Specifically, when the current photosynthetic parameter is the photosynthetic parameter with serial number 3, the determination process of the inversion parameter and the photosynthetic parameter inversion model corresponding to the current photosynthetic parameter includes:

[0114] 1) input the best pre-processed reflectance of all characteristic bands corresponding to the photosynthetic parameter with serial number 3 into the single-parameter prediction model corresponding to the photosynthetic parameter with serial number 3 to obtain a single prediction value of the photosynthetic parameter with serial number 3.

[0115] 2) based on the true value and the single prediction value of the photosynthetic parameter with serial number 3, calculate a single regression coefficient R3 of the photosynthetic parameter with serial number 3.2 .

[0116] 3) The predicted values of the photosynthetic parameters with serial numbers 1 and 2 are arranged and combined to obtain the predicted values of 3 groups of inversion parameters corresponding to the current photosynthetic parameters. The 3 groups of inversion parameters are respectively denoted as A1, A2 and A3; the predicted value of the inversion parameter A1 includes the predicted value of the photosynthetic parameter with serial number 1, the predicted value of the inversion parameter A2 includes the predicted value of the photosynthetic parameter with serial number 2, and the predicted value of the inversion parameter A3 includes the predicted values of the photosynthetic parameters with serial numbers 1 and 2.

[0117] 4) The predicted value of the inversion parameter A1 and the best preprocessed reflectance of all characteristic wave bands corresponding to the photosynthetic parameter with serial number 3 are determined as the predicted value of the combined parameter B1, the predicted value of the inversion parameter A2 and the best preprocessed reflectance of all characteristic wave bands corresponding to the photosynthetic parameter with serial number 3 are determined as the predicted value of the combined parameter B2, and the predicted value of the inversion parameter A3 and the best preprocessed reflectance of all characteristic wave bands corresponding to the photosynthetic parameter with serial number 3 are determined as the predicted value of the combined parameter B3.

[0118] 5) The predicted value of the combined parameter B1 is input into the second pre-trained model corresponding to the combined parameter B1 to obtain the joint predicted value of the current photosynthetic parameter under the combined parameter B1; the predicted value of the combined parameter B2 is input into the second pre-trained model corresponding to the combined parameter B2 to obtain the joint predicted value of the current photosynthetic parameter under the combined parameter B2; and the predicted value of the combined parameter B3 is input into the second pre-trained model corresponding to the combined parameter B3 to obtain the joint predicted value of the current photosynthetic parameter under the combined parameter B3.

[0119] 6) Based on the predicted value of the photosynthetic parameter with serial number 3 and the joint predicted value of the current photosynthetic parameter under the combined parameter B1, the joint regression coefficient of the joint predicted value of the current photosynthetic parameter under the combined parameter B1 with respect to the photosynthetic parameter with serial number 3 is calculated Based on the predicted value of the photosynthetic parameter with serial number 3 and the joint predicted value of the current photosynthetic parameter under the combined parameter B2, the joint regression coefficient of the joint predicted value of the current photosynthetic parameter under the combined parameter B2 with respect to the photosynthetic parameter with serial number 3 is calculated Based on the predicted value of the photosynthetic parameter with serial number 3 and the joint predicted value of the current photosynthetic parameter under the combined parameter B3, the joint regression coefficient of the joint predicted value of the current photosynthetic parameter under the combined parameter B3 with respect to the photosynthetic parameter with serial number 3 is calculated

[0120] 7) The predicted value of the current photosynthetic parameter under the combined parameter B1 is calculated as follows and The optimal preprocessed reflectance of all characteristic bands corresponding to the combination parameter with the largest median or the photosynthetic parameter with the number 3 is determined as the prediction parameter corresponding to the photosynthetic parameter with the number 3. The second pre-trained model corresponding to the prediction parameter corresponding to the photosynthetic parameter with the number 3 is determined as the photosynthetic parameter inversion model corresponding to the photosynthetic parameter with the number 3.

[0121] Furthermore, to reduce the computational load, while keeping steps 1)-4) unchanged, steps 5)-7) can be replaced with steps S1-S3:

[0122] Step S1: Input the true value of combined parameter B1 into the second pre-trained model corresponding to combined parameter B1 to obtain the joint predicted value of the current photosynthetic parameter under combined parameter B1. Based on the true value of the photosynthetic parameter with index 3 and the joint predicted value of the current photosynthetic parameter under combined parameter B1, calculate the joint regression coefficient of the photosynthetic parameter with index 3 under combined parameter B1. Compare and The size. When If the value is large, proceed to step S2. When If the value is large, proceed to step S3.

[0123] Step S2: Input the true value of combined parameter B3 into the second pre-trained model corresponding to combined parameter B3 to obtain the joint predicted value of the current photosynthetic parameter under combined parameter B3; based on the true value of the photosynthetic parameter with index 3 and the joint predicted value of the current photosynthetic parameter under combined parameter B3, calculate the joint regression coefficient of the photosynthetic parameter with index 3 under combined parameter B3. Compare and The size. When When the value is large, the combined parameter B1 is determined as the prediction parameter corresponding to the photosynthetic parameter with index 3, and the second pre-trained model corresponding to the combined parameter B1 is determined as the photosynthetic parameter inversion model corresponding to the photosynthetic parameter with index 3. When When the value is large, the combined parameter B3 is determined as the prediction parameter corresponding to the photosynthetic parameter with the number 3, and the second pre-trained model corresponding to the combined parameter B3 is determined as the photosynthetic parameter inversion model corresponding to the photosynthetic parameter with the number 3.

[0124] Step S3: Input the true value of combined parameter B2 into the second pre-trained model corresponding to combined parameter B2 to obtain the joint predicted value of the current photosynthetic parameter under combined parameter B2; based on the true value of the photosynthetic parameter with index 3 and the joint predicted value of the current photosynthetic parameter under combined parameter B2, calculate the joint regression coefficient of the photosynthetic parameter with index 3 under combined parameter B2. comparing and . When is larger, the optimal pre-processed reflectance of all characteristic wavebands corresponding to the photosynthetic parameter with serial number 3 is determined as the prediction parameter corresponding to the photosynthetic parameter with serial number 3, and corresponding second pre-trained model is determined as the photosynthetic parameter inversion model corresponding to the photosynthetic parameter with serial number 3. When is larger, the combined parameter B2 is determined as the prediction parameter corresponding to the photosynthetic parameter with serial number 3, and the second pre-trained model corresponding to the combined parameter B2 is determined as the photosynthetic parameter inversion model corresponding to the photosynthetic parameter with serial number 3.

[0125] In an exemplary embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to implement the crop photosynthetic parameter inversion method.

[0126] In an exemplary embodiment, a computer readable storage medium is provided, having stored thereon a computer program, the computer program being executed by a processor to implement the crop photosynthetic parameter inversion method.

[0127] In an exemplary embodiment, a computer program product is provided, comprising a computer program, the computer program being executed by a processor to implement the crop photosynthetic parameter inversion method.

[0128] In an exemplary embodiment, a computer device is provided, which can be a server or a terminal, and its internal structure diagram can be as shown in Figure 4 . The computer device comprises a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a crop photosynthetic parameter inversion method.

[0129] Those skilled in the art can understand that Figure 4It should be noted that the structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0130] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0131] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments of each method. In the embodiments provided in the present application, any reference to memory, database or other medium can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetic variable memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc.

[0132] The database involved in each embodiment provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in each embodiment provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0133] Any combination of the technical features of the above embodiments can be made, and for the sake of brevity, not all possible combinations are described in the above description. However, it should be understood that the scope of the specification includes all possible combinations of the technical features.

[0134] The principles and implementation modes of the present application are described herein by using specific examples, and the above descriptions of the embodiments are only used to help understand the method and core idea of the present application. Meanwhile, according to the idea of the present application, the specific implementation modes and application ranges can be changed by those skilled in the art. In conclusion, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method for retrieving photosynthetic parameters of crops, characterized in that, The crop photosynthetic parameter inversion method comprises: acquiring images of all characteristic wavebands of a crop to be predicted; determining reflectivity of a corresponding characteristic waveband based on an image of the characteristic waveband; preprocessing the reflectivity of the corresponding characteristic waveband by using an optimal preprocessing strategy corresponding to the characteristic waveband to obtain optimal preprocessed reflectivity of the corresponding characteristic waveband; inputting prediction values of prediction parameters corresponding to each photosynthetic parameter in a preset order into a corresponding photosynthetic parameter inversion model to obtain a prediction value of the corresponding photosynthetic parameter; the prediction value of the prediction parameter is a first parameter or a second parameter; the first parameter corresponding to a current photosynthetic parameter comprises optimal preprocessed reflectivity of all characteristic wavebands corresponding to the current photosynthetic parameter; the second parameter corresponding to the current photosynthetic parameter comprises optimal preprocessed reflectivity of all characteristic wavebands corresponding to the current photosynthetic parameter and a prediction value of an inversion parameter; the inversion parameter comprises one or more photosynthetic parameters sequentially located before the current photosynthetic parameter, and the prediction value of the inversion parameter comprises a prediction value of a photosynthetic parameter output by a photosynthetic parameter inversion model corresponding to the inversion parameter; the photosynthetic parameter inversion model corresponding to the current photosynthetic parameter is determined by using a single-parameter prediction model corresponding to the current photosynthetic parameter, the optimal preprocessed reflectivity of all characteristic wavebands, and a true value of the inversion parameter; the photosynthetic parameter comprises A1200, SPAD, chlorophyll a, chlorophyll b, and leaf nitrogen content; a determination process of the optimal preprocessing strategy corresponding to any current photosynthetic parameter comprises: acquiring images of full wavebands of a training crop and a true value of a corresponding current photosynthetic parameter; the full wavebands comprise characteristic wavebands corresponding to all photosynthetic parameters; determining reflectivity of a corresponding waveband based on an image of each waveband in the full wavebands; constructing a plurality of initial preprocessing strategies based on a plurality of preprocessing methods; the preprocessing methods comprise baseline correction, scattering correction, and scale scaling; the baseline correction comprises Savitzky-Golay first-order differentiation, Savitzky-Golay second-order differentiation, and continuous wavelet transform; the scattering correction comprises multivariate scattering correction and standard normal transform; and the scale scaling comprises mean centering and standardization; respectively preprocessing reflectivity of each waveband by using each initial preprocessing strategy to obtain preprocessed reflectivity of each waveband under a corresponding initial preprocessing strategy; determining prediction values of the current photosynthetic parameter of the training crop under each initial preprocessing strategy based on the preprocessed reflectivity of all wavebands under each initial preprocessing strategy by using a partial least squares cross-validation method; calculating regression coefficients under a corresponding initial preprocessing strategy based on the true value of the current photosynthetic parameter of the training crop and the prediction values of the current photosynthetic parameter of the training crop under each initial preprocessing strategy; determining the initial preprocessing strategy corresponding to the maximum regression coefficient as the optimal preprocessing strategy corresponding to the current photosynthetic parameter; a determination process of a single-parameter prediction model corresponding to any current photosynthetic parameter comprises: The reflectivity of each band in the full band is preprocessed by using the optimal preprocessing strategy corresponding to the current photosynthetic parameter to obtain the optimal preprocessed reflectivity of each band in the full band; The optimal preprocessed reflectivity of all bands in the full band is input into three first pre-trained models to obtain the predicted value of the current photosynthetic parameter output by the first pre-trained model; the three first pre-trained models are obtained by training the three initial models for the same number of times by using an initial model training set, and the initial model training set includes the optimal preprocessed reflectivity of all bands in the full band corresponding to the current photosynthetic parameter of the plurality of training crops and the corresponding true value of the current photosynthetic parameter, and the three initial models are least square regression, support vector regression and random forest respectively; Based on the true value of the current photosynthetic parameter of the training crop and the predicted value of the current photosynthetic parameter output by each first pre-trained model, the regression coefficient of the corresponding first pre-trained model is calculated; The first pre-trained model corresponding to the maximum regression coefficient is determined as the single-parameter prediction model corresponding to the current photosynthetic parameter.

2. The crop photosynthetic parameter inversion method according to claim 1, characterized in that, The determination process of the characteristic band corresponding to any current photosynthetic parameter includes: Each band in the full band is screened by using four band selection methods to obtain the initial screening band corresponding to the current photosynthetic parameter under the corresponding band selection method; The reflectivity of each initial screening band under each band selection method is preprocessed by using the optimal preprocessing strategy corresponding to the current photosynthetic parameter to obtain the optimal preprocessed reflectivity of the corresponding initial screening band; The optimal preprocessed reflectivity of all initial screening bands under each band selection method is input into the single-parameter prediction model corresponding to the current photosynthetic parameter to obtain the predicted value of the current photosynthetic parameter under the corresponding band selection method; Based on the true value of the current photosynthetic parameter and the predicted value of the current photosynthetic parameter under each band selection method, the regression coefficient under the corresponding band selection method is calculated; The initial screening band of the current photosynthetic parameter under the band selection method corresponding to the maximum regression coefficient is determined as the characteristic band corresponding to the current photosynthetic parameter.

3. The crop photosynthetic parameter inversion method according to claim 2, characterized in that, The determination process of the inversion parameter and the photosynthetic parameter inversion model corresponding to any current photosynthetic parameter includes: The photosynthetic parameters are numbered according to the preset order to obtain the serial numbers of the photosynthetic parameters; the serial numbers of the photosynthetic parameters are 1, 2, 3, 4 and 5 in turn; When the serial number of the current photosynthetic parameter is 1, the single-parameter prediction model of the current photosynthetic parameter is determined as the photosynthetic parameter inversion model of the current photosynthetic parameter; When the serial number of the current photosynthetic parameter is not 1, the inversion parameter and the photosynthetic parameter inversion model corresponding to the current photosynthetic parameter are determined based on the predicted value of each photosynthetic parameter with a serial number smaller than that of the current photosynthetic parameter and the single-parameter prediction model of the current photosynthetic parameter.

4. The crop photosynthetic parameter inversion method according to claim 3, characterized in that, Based on the predicted value of each photosynthetic parameter with a serial number smaller than that of the current photosynthetic parameter and the single-parameter prediction model of the current photosynthetic parameter, the inversion parameter and the photosynthetic parameter inversion model corresponding to the current photosynthetic parameter are determined. input the optimal preprocessed reflectance of all characteristic bands corresponding to the current photosynthetic parameter into a single-parameter prediction model corresponding to the current photosynthetic parameter to obtain a single prediction value of the current photosynthetic parameter; based on the true value and the single prediction value of the current photosynthetic parameter, calculate a single regression coefficient of the current photosynthetic parameter; perform permutation and combination on the prediction values of the photosynthetic parameters with serial numbers less than the current photosynthetic parameter to obtain prediction values of multiple groups of inversion parameters corresponding to the current photosynthetic parameter; one group of inversion parameters includes one or more photosynthetic parameters; determine any one group of inversion parameters corresponding to the current photosynthetic parameter as the current inversion parameter, and determine the prediction value of the current inversion parameter and the optimal preprocessed reflectance of all characteristic bands corresponding to the current photosynthetic parameter as the prediction value of the current combination parameter; input the prediction value of the current combination parameter into a second pre-trained model corresponding to the current combination parameter to obtain a joint prediction value of the current photosynthetic parameter under the current combination parameter; the second pre-trained model corresponding to the current combination parameter is obtained by training the single-parameter prediction model corresponding to the current photosynthetic parameter using the true values of the current combination parameters of multiple training crops, and the training rounds of each second pre-trained model are the same; based on the joint prediction value of the current photosynthetic parameter under the current combination parameter and the true value of the current photosynthetic parameter, calculate a joint regression coefficient of the current photosynthetic parameter under the current combination parameter; determine the combination parameter or the optimal preprocessed reflectance of all characteristic bands corresponding to the current photosynthetic parameter corresponding to the maximum value between the joint regression coefficient of the current photosynthetic parameter under all combination parameters and the single regression coefficient of the current photosynthetic parameter as the prediction parameter, and determine the second pre-trained model corresponding to the prediction parameter as the photosynthetic parameter inversion model corresponding to the current photosynthetic parameter.

5. The crop photosynthetic parameter inversion method according to claim 1, characterized in that, determining reflectance of each characteristic band based on the image of the corresponding characteristic band, comprising: determining reflectance of each characteristic band based on the image of the corresponding characteristic band respectively by using a reflectance calculation formula; the reflectance calculation formula is: ； wherein is the reflectance of the waveband ; is the raw average reflectance of the image of the waveband ; is the reflectance of the dark current; is the average reflectance of the white reference panel; is the true reflectance of the white reference panel.

6. A computer apparatus comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the crop photosynthetic parameter inversion method of any one of claims 1-5.

7. A computer readable storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to implement the crop photosynthetic parameter inversion method of any one of claims 1-5.

8. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the crop photosynthetic parameter inversion method of any one of claims 1-5.

Images