Visible light index and growth parameter coupled mature-period rice yield estimation method

Abstract

The invention discloses a mature-period rice yield estimation method coupling visible light indexes and growth parameters, and belongs to the technical field of smart agriculture, and the method comprises the steps: collecting test-area unmanned plane remote sensing data and ground crop data, and carrying out the data processing; estimating the biomass of the rice in the mature period based on the single characteristic variable; fusing the visible light index and the growth parameters to establish a mature-period rice biomass estimation model; and estimating the biomass of the mature rice in the test area. According to the mature-period rice yield estimation method coupling the visible light index and the growth parameter, the rice canopy visible light index and the rice growth parameter obtained by the unmanned aerial vehicle remote sensing technology are fused, and the rice biomass in the rice mature period can be effectively estimated in combination with a support vector machine regression method; a rapid and efficient method is provided for estimation of large-area rice biomass, and method reference can be provided for work such as growth monitoring and efficient yield estimation of rice in the mature period.

Description

Technical Field

[0001] The present invention relates to the field of smart agricultural technology, and in particular to a method for estimating rice yield at maturity by coupling a visible light index with growth parameters. Background Art

[0002] Accurately estimating rice biomass at maturity is of great significance for ensuring food security and achieving sustainable agricultural development. Traditional rice biomass measurement often requires destructive sampling, which is not only inefficient, but also difficult to meet the monitoring needs of large areas. In recent years, drone technology has been widely used in crop biomass estimation due to its high flexibility, high spatiotemporal resolution, and easy operation. The mainstream method is to analyze the relationship between spectral index and rice biomass in drone remote sensing images, and use linear regression, machine learning and other methods to construct a rice biomass estimation model, and achieve good estimation results. However, there are significant differences in the physiological characteristics and spectral response of rice at different growth stages. When rice is in the early growth stage, its canopy leaves are sparse and have a low overlap rate, which is more sensitive to the spectral index. At this time, the biomass is significantly correlated with the spectral index. In the late growth stage, the spectral index is saturated, which reduces the correlation with the biomass. Especially in the maturity stage, the yellowing and drying of leaves increase significantly, resulting in a significant deterioration in the estimation of rice biomass at maturity. The accuracy of estimating rice biomass at maturity using only the spectral information of the image is low.

[0003] In order to improve the estimation accuracy of crop growth parameters, by introducing texture features and structural features such as crop plant height on the basis of spectral information, it is found that the fusion of multiple features can reduce the impact of spectral index saturation, thereby improving the estimation accuracy of crop biomass. Therefore, through relevant research on crop growth monitoring, it is found that the multi-feature fusion method has achieved good prediction results in crop yield prediction or crop biomass estimation in the early stage of crop growth, but the improvement in the estimation effect of crop biomass in the later stage of crop growth is still small. Summary of the invention

[0004] The purpose of the present invention is to provide a method for estimating the yield of mature rice by coupling the visible light index with growth parameters. The method takes mature rice as the research object, and based on the definition of the aboveground biomass of the crop, the visible light index of the rice canopy image and the growth parameters such as rice plant height and water content are combined to construct a model for estimating the biomass of mature rice, wherein the visible light index mainly provides the spectral information of the growth state of rice, and the growth parameters mainly provide the direct information of the growth state of rice. Finally, the model is applied to the estimation of the biomass of mature rice in the experimental area, and the biomass distribution of the experimental area is analyzed to further verify the reliability of the model, so as to provide a new reference for the accurate estimation of the biomass of mature rice, and at the same time provide a more comprehensive scientific basis for rice growth monitoring and yield evaluation.

[0005] To achieve the above object, the present invention provides a method for estimating rice yield at maturity by coupling visible light index and growth parameters, comprising the following steps: S1. Collect UAV remote sensing data and ground crop data of the test area and process the data; S2, estimation of rice biomass at maturity based on a single characteristic variable; S3, integrating the visible light index and growth parameters to establish a rice biomass estimation model at maturity, including the following steps: S31, Test set determination coefficient of the rice biomass estimation model based on the visible light index in S2 R 2 _test , the visible light index was classified for index optimization, and the rice biomass estimation model at maturity was constructed using different categories of visible light index as input factors; S32, integrating rice plant height and rice plant water content to construct a rice biomass estimation model at maturity and compare the fitting results; S4. Estimate the rice biomass at maturity in the experimental area.

[0006] Preferably, in S1, the UAV remote sensing data includes visible light data and multispectral data; the ground crop data includes rice plant height, rice fresh weight and rice dry weight; the rice plant height is the distance from the bottom to the top of the canopy of rice in a natural growth state, the rice fresh weight is the weight of the rice after sampling and bagging, and the rice dry weight is the weight of the rice after drying to a constant weight; the data processing includes the following steps: S11. Use Pix4D Mapper software and Yusense Map software to stitch and correct the UAV remote sensing data, crop the UAV images according to the sampling area location, take the average reflectance of each sampling area as the spectral reflectance of the sampling point, and obtain the spectral reflectance data of different bands; S12, vegetation index construction; select visible light index as an indicator for constructing rice biomass model at maturity; S13. Calculate the rice biomass per square meter of land based on the dry weight of rice and rice planting density in the sampling area; S14. Calculate the water content of the rice plant by the ratio of the difference between the fresh weight of the rice and the dry weight of the rice to its fresh weight.

[0007] Preferably, in S2, the rice biomass at maturity is estimated based on a single characteristic variable as follows: S21. Pearson correlation analysis was used to evaluate the linear correlation between visible light index, rice plant height, rice plant water content and rice biomass. S22. Using visible light index, rice plant height, and rice plant water content as independent variables, a rice biomass estimation model was constructed using the support vector regression method. The training set determination coefficient R 2 _train and the test set determination coefficient R 2 _test Represent the accuracy of the training set and the accuracy of the test set respectively; S23. According to the accuracy of the training set and the accuracy of the test set, characteristic variables are selected from the visible light index, rice plant height and rice plant water content to fuse the visible light index and growth parameters to establish a rice biomass estimation model at maturity.

[0008] Preferably, in S32, the specific process is: the visible light index is sequentially integrated with the rice plant height, the rice plant water content, the rice plant height and the rice plant water content, and the three fitting effects are compared.

[0009] Preferably, in S4, estimating the biomass of rice at maturity in the experimental area comprises the following steps: S41, obtaining the height of rice plants at maturity; S42, obtaining the water content of rice at maturity; S43. Based on the plant height of mature rice obtained in S41 and the water content of mature rice obtained in S42, combined with the mature rice biomass estimation model constructed in S3, the biomass of mature rice in the experimental area is estimated to obtain the distribution of mature rice biomass in the experimental area.

[0010] Preferably, in S41, the specific process of obtaining the plant height of rice at maturity is: processing the UAV remote sensing data of the rice field when it is bare before rice planting and when the rice is mature, obtaining the digital surface model DSM of the corresponding period, which respectively represents the ground height of the rice field and the overall height of the mature rice; obtaining the plant height data of mature rice through the canopy height model CHM; and fitting and analyzing the plant height data obtained through the UAV remote sensing data with the measured plant height.

[0011] Preferably, in S42, the specific process of obtaining the moisture content of rice at maturity is: using a drone to obtain multispectral images and extracting a multispectral index related to the measured moisture content, combining the red light band reflectivity, the red edge band reflectivity and the near-infrared band reflectivity, and using a random forest regression method to construct a relationship model between the multispectral index and the moisture content, and estimate the moisture content of rice at maturity.

[0012] Therefore, the present invention adopts the above-mentioned method for estimating rice yield in the mature stage by coupling the visible light index and growth parameters, integrates the rice canopy visible light index and rice growth parameters obtained by unmanned aerial vehicle remote sensing technology, and combines the support vector machine regression method to effectively estimate the rice biomass in the rice mature stage, providing a fast and efficient method for estimating rice biomass in a large area, and providing a method reference for monitoring rice growth in the mature stage, efficient yield estimation, and the like.

[0013] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a technical roadmap of an embodiment of the method for estimating rice yield at maturity by coupling visible light index and growth parameters of the present invention; Figure 2 It is a correlation analysis between a single characteristic variable and biomass of an embodiment of the rice yield estimation method at maturity stage by coupling visible light index and growth parameters of the present invention; Figure 3 The biomass estimation accuracy based on a single characteristic variable in an embodiment of the rice yield estimation method at maturity period by coupling visible light index and growth parameters of the present invention; Figure 4 The following are the biomass estimation accuracy of the visible light index combined with plant height and water content in the embodiment of the rice yield estimation method for coupling the visible light index with growth parameters of the present invention: (a) using only the visible light index; (b) adding the rice plant height; (c) adding the rice plant water content; (d) adding the rice plant height and the rice plant water content; Figure 5 It is a distribution diagram of rice plant height at maturity in a test area of ​​an embodiment of the method for estimating rice yield at maturity by coupling visible light index and growth parameters of the present invention; Figure 6 It is a distribution diagram of the moisture content of rice at maturity in the test area of ​​an embodiment of the method for estimating rice yield at maturity by coupling visible light index and growth parameters of the present invention; Figure 7 The rice biomass distribution at maturity in the test area of ​​the embodiment of the rice yield estimation method at maturity by coupling the visible light index with the growth parameters of the present invention; Figure 8 It is the fitting analysis result of the estimated biomass and the measured yield in each area of ​​the test area of ​​the embodiment of the method for estimating rice yield at maturity by coupling visible light index and growth parameters of the present invention. DETAILED DESCRIPTION

[0015] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0016] Unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0017] Embodiment 1 The present invention provides a method for estimating rice yield at maturity by coupling visible light index and growth parameters. The technical route is as follows: Figure 1 As shown, the following steps are included: S1. Collect the UAV remote sensing data and ground crop data of the test area and process the data; the UAV remote sensing data includes visible light data and multispectral data; the ground crop data includes rice plant height, rice fresh weight and rice dry weight; in this embodiment, the specific settings for the UAV to collect ground data are: use the DJI Phantom 4 quad-rotor UAV to obtain the raw visible light data of the test area, the flight altitude is set to 100m, the flight speed is set to 7m / s, the heading overlap rate is 80%, the side overlap rate is 70%, and the flight angle is 0° and -45°. Use the DJI M300 RTK quad-rotor UAV equipped with the MS600 Pro six-channel multispectral sensor to obtain the raw multispectral data of the test area, the flight altitude is set to 80m, the heading overlap rate and the side overlap rate are set to 80% and 70% respectively, and the flight angle is 0°.

[0018] The height of rice plant refers to the distance from the bottom to the top of the canopy of rice under natural growth conditions (unit: cm); the fresh weight of rice is the weight of rice bagged and weighed immediately after sampling (unit: kg); the dry weight of rice is the weight of rice after drying to constant weight (unit: kg). In this example, the rice samples were packaged and then placed in an oven, withered at 105°C for 30 minutes, and then dried at 75°C for about 48 hours to constant weight, and finally weighed to obtain the dry weight of rice.

[0019] The data processing specifically includes the following steps: S11. Use Pix4D Mapper software and Yusense Map software to stitch and correct the UAV remote sensing data, crop the UAV images according to the sampling area location, take the average reflectance of each sampling area as the spectral reflectance of the sampling point, and obtain the spectral reflectance data of different bands.

[0020] S12, vegetation index construction, vegetation index is an important parameter to characterize crop growth information by combining spectra. According to the estimation requirements of rice biomass, this embodiment selects 11 visible light indices as indicators for constructing a rice maturity biomass model, and the visible light indices are specifically: Red light normalized value (r): R / (R+G+B); Green light normalized value (g): G / (R+G+B); Blue light normalized value (b): B / (R+G+B); Visible atmospheric impedance vegetation index (VARI): (GR) / (R+G+B); Normalized green-red difference index (GRVI): (GR) / (G+R); Modified Green-Red Vegetation Index (MGRVI): (G 2 -R 2 ) / (G 2 +R 2 ); Blue-green ratio index (BGI): B / G; Blue-Red Ratio Index (BRI): B / R; Green-Red Ratio Index (GRI): G / R; Supergreen vegetation index (ExG): 2 GRB; Red, Green and Blue Vegetation Index (RGBVI): (G 2 -R B) / (G 2 +R B); Among them, R, G, and B are the three basic color channels of red, green, and blue in the visible spectrum, and the wavelength ranges are: red light band R is 620-750 nm, green light band G is 500-560 nm, and blue light band B is 430-470 nm.

[0021] S13. Calculate the rice biomass per square meter of land (unit: kg / m 2 ).

[0022] S14. Calculate the water content of the rice plant by the ratio of the difference between the fresh weight of the rice and the dry weight of the rice to its fresh weight.

[0023] S2. Estimating the rice biomass at maturity based on a single characteristic variable, including the following steps: S21. Pearson correlation analysis was used to evaluate the linear correlation between visible light index, rice plant height (Height), rice plant moisture content (Moisture Content, MC) and rice biomass (Aboveground Biomass, AGB). The correlation analysis results in this embodiment are as follows: Figure 2 At maturity, the correlation between the rice canopy visible light index and rice biomass was generally low, among which g and RGBVI had higher correlations, with correlation coefficients of -0.36 and -0.34, respectively; the correlation between some indices and rice biomass was around 0.1, showing significant uncorrelation; the correlation coefficients between rice plant height and rice plant water content and rice biomass were 0.42 and -0.38, respectively, which were higher than the correlation between the visible light index and rice biomass.

[0024] S22. Using visible light index, rice plant height, and rice plant water content as independent variables, a rice biomass estimation model was constructed using the support vector regression method. The training set determination coefficient R 2 _train and the test set determination coefficient R 2 _test Represent the accuracy of the training set and the accuracy of the test set respectively. Support vector regression can well represent the nonlinear relationship between variables. Its core idea is to find an optimal hyperplane so that the deviation from the actual value is within an acceptable range. This method can effectively deal with high-dimensional data and has excellent generalization ability, but it requires experience and experiments to determine the appropriate hyperparameters and kernel functions.

[0025] According to the distribution of experimental data collected, the support vector regression method was used to estimate the rice biomass. To ensure comparability between different experiments, all experiments in this embodiment used the same data division and the same model parameters: penalty coefficient C = 6.5, radial basis kernel function (RBF) kernel function, tolerance deviation value epsilon = 0.5. The rice canopy visible light index, rice plant height and rice plant water content, and rice biomass data at maturity were used as experimental data sets. The experimental data sets were divided into training set and test set at a ratio of 8.5:1.5 to establish a model for estimating rice biomass at maturity. The results are shown in Figure 2. Figure 3 As shown: (1) The accuracy of the training set for rice biomass estimation using only a single visible light index is generally very low, and the coefficient of determination is R 2 _trainBetween 0 and 0.3, the fitting effect of the training data is poor. The model based on the green band standardized value g, the red, green and blue vegetation index RGBVI and the super green vegetation index ExG is constructed. R 2 _train Relatively high, at 0.25, 0.27 and 0.26 respectively.

[0026] (2) Model based on the visible atmospheric impedance vegetation index (VARI), the blue-green ratio index (BGI), and the blue-red ratio index (BRI) R 2 _test If the value is less than 0, it means that the three visible light indices have a very poor effect in estimating the rice biomass at maturity, and they will be eliminated in subsequent experiments. R 2 _test All are greater than 0, among which the model based on the red, green and blue vegetation index RGBVI performs best. R 2 _test and RMSE are 0.55 and 0.45 kg / m respectively. 2 .

[0027] (3) Among the growth parameters, the training set accuracy of using rice plant height to estimate biomass R 2 _train and test set accuracy of biomass estimation using rice plant water content R 2 _test Both were relatively high, with determination coefficients of 0.25 and 0.46, respectively.

[0028] S23. According to the accuracy of the training set and the accuracy of the test set, characteristic variables are selected from the visible light index, rice plant height and rice plant water content to fuse the visible light index and growth parameters to establish a rice biomass estimation model at maturity.

[0029] From the results of S22, it can be seen that using only a single characteristic variable such as visible light index or growth parameter may not be able to capture the changes in rice biomass at maturity, and the accuracy of the rice biomass estimation model at maturity constructed by this is generally low. Therefore, this embodiment selects 8 visible light indices and 2 growth parameters as input factors of the model, and integrates multiple characteristic variables for modeling and analysis.

[0030] S3, integrating the visible light index and growth parameters to establish a rice biomass estimation model at maturity, including the following steps: S31, Test set determination coefficient of the rice biomass estimation model based on the visible light index in S2 R 2 _test, the visible light index was classified for index optimization, and a rice biomass estimation model at maturity was constructed using different categories of visible light indices as input factors.

[0031] In this embodiment, the eight visible light indices selected in S23 are used as the test set determination coefficient of the rice biomass estimation model of a single visible light index. R 2 _test Based on the standard, the visible light index is divided into 5 categories for index optimization. The specific classification standards are shown in Table 1.

[0032] Table 1 Classification of visible light index ;

[0033] in, R 2 _test based on Figure 3 result.

[0034] S32. Integrate rice plant height and rice plant water content to construct a rice biomass estimation model at maturity and compare the fitting effects. The specific process is: the visible light index is integrated with rice plant height, rice plant water content, rice plant height and rice plant water content in turn, and the three fitting effects are compared.

[0035] In this embodiment, the accuracy of the rice biomass estimation model combining different types of visible light indices with growth parameters is as follows: Figure 4 As shown: (1) When only the visible light index is used as the model input factor to construct the rice biomass estimation model at maturity, Figure 4 As shown in (a), the determination coefficients of the test sets of Type 1 and Type 2 are less than 0, the determination coefficients of the test sets of Type 3 are less than 0.1, and the determination coefficients of the test sets of Type 4 and Type 5 are around 0.5, indicating that the optimization of the visible light index has a greater impact on the model accuracy.

[0036] (2) When rice plant height is added to the visible light index, Figure 4 As shown in (b) of , the coefficient of determination of the test set of the rice biomass estimation model has decreased, but it is still less than 0, and the root mean square error is still large. When only the water content of the rice plant is added, Figure 4 As shown in (c), the determination coefficient of the model test set has been significantly improved. The determination coefficient and root mean square error of the model with the highest accuracy are 0.58 and 0.44 kg / m 2 ; When adding rice plant height and rice plant water content, such as Figure 4As shown in (d) in the figure, the fitting effect of the constructed models on the training set is improved. Among them, the estimation accuracy of the rice biomass estimation model at maturity of visible light index category Type 4 is the highest, and the coefficient of determination and root mean square error of the test set are both optimal, which are 0.78 and 0.32 kg / m 2 .

[0037] (3) The optimization of the visible light index and the integration of growth parameters are the key links to improve the estimation accuracy of rice biomass at maturity. Therefore, when the green band standardized value g, the red, green and blue vegetation index RGBVI, the rice plant height and the water content of the rice plant are used as the input factors of the model, the estimation model of rice biomass at maturity achieves the optimal estimation effect, indicating that the integration of growth parameters can make up for the shortcomings of the visible light index and improve the fitting effect of the biomass estimation model on the data.

[0038] S4. Estimate the rice biomass at maturity in the experimental area. In order to explore the application of the above model in estimating rice biomass in a larger area, the spatial distribution of rice biomass at maturity in the experimental area was analyzed by obtaining the green light standardized value g and the red, green and blue vegetation index RGBVI, two rice canopy visible light indices at maturity, and two growth parameters, rice plant height and rice plant water content. The specific steps include: S41, obtain the plant height of rice at maturity; process the UAV remote sensing data of the rice field before rice planting when it is bare land and when the rice is mature, and obtain the digital surface model DSM of the corresponding period, which represents the ground height of the rice field and the overall height of the rice at maturity; obtain the plant height data of rice at maturity through the canopy height model CHM; fit the plant height data obtained through the UAV remote sensing data with the measured plant height for analysis. In this embodiment, the rice plant height extracted based on the canopy height model has a good fitting accuracy with the measured plant height, where R 2 is 0.75, RMSE 0.04m, Figure 5 This is the distribution map of rice plant height at maturity in the experimental area.

[0039] S42. Obtain the moisture content of rice plants at maturity. Use drones to obtain high-resolution multispectral images and extract multispectral indices with a high correlation with the measured moisture content. Combine the red light band reflectance, red edge band reflectance, and near-infrared band reflectance, and use the random forest regression method to construct a relationship model between the multispectral index and moisture content to estimate the moisture content of rice at maturity.

[0040] In this embodiment, a total of 6 multispectral indices, such as the difference vegetation index (DVI) with a high correlation with the measured moisture content, were extracted from the multispectral images of the test area (see Table 2), and the red light band reflectance, red edge band reflectance and near infrared band reflectance were combined to construct a relationship model between the multispectral index and the moisture content using the random forest regression method. The experimental results show that the estimation accuracy of the moisture content of mature rice using multispectral data and the random forest regression method is high, the model determination coefficient is 0.77, and the scatter distribution deviates less from the 1:1 line, and the fitting effect is good. The distribution of moisture content of mature rice in the test area is obtained. Figure 6 .

[0041] Table 2 Multispectral index ;

[0042] Among them, NIR represents the near infrared band with a central wavelength of 840nm, R' represents the reflectivity of the red light band with a central wavelength of 660nm, and RE represents the reflectivity of the red edge band with a central wavelength of 750nm.

[0043] S43. Based on the plant height of mature rice obtained in S41 and the water content of mature rice obtained in S42, combined with the biomass estimation model of mature rice constructed in S3, the biomass of mature rice in the experimental area is estimated to obtain the distribution of biomass of mature rice in the experimental area.

[0044] In this embodiment, the rice biomass distribution in the test area at maturity is finally obtained as follows: Figure 7-8 As shown: (1) The estimated values ​​of rice biomass at maturity in each region have the same magnitude relationship with the measured values. The estimated values ​​are generally higher, but the difference between them is small, with an absolute value of 0.15-0.39 kg / m 2 The model performed well overall. In terms of biomass distribution in the experimental areas, the overall levels of rice biomass in areas D and A were relatively the highest, while the overall levels of rice biomass in areas E, B, and C were relatively low. In terms of biomass distribution in each area, there were also differences in rice biomass within the same area.

[0045] (2) The estimated rice biomass of each area in the experimental area was fitted with the measured yield. The fitting coefficient of determination and root mean square error were 0.86, respectively. The fitting function was y = 0.04x − 0.59. The fitting results showed that there was an obvious linear correlation between yield and rice biomass. The regional yield was consistent with the rice biomass. That is, the higher the rice biomass value, the higher the yield.

[0046] This result indicates that the model is reliable in the application of rice biomass estimation at maturity stage over a larger area.

[0047] Therefore, the present invention adopts the above-mentioned method for estimating rice yield in the mature stage by coupling the visible light index and growth parameters, integrates the rice canopy visible light index and rice growth parameters obtained by unmanned aerial vehicle remote sensing technology, and combines the support vector machine regression method to effectively estimate the rice biomass in the rice mature stage, providing a fast and efficient method for estimating rice biomass in a large area, and providing a method reference for monitoring rice growth in the mature stage, efficient yield estimation, and the like.

[0048] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for estimating rice yield at maturity by coupling visible light index with growth parameters, characterized in that: The following steps are involved: S1. Collect UAV remote sensing data and ground crop data of the test area and process the data; S2, estimation of rice biomass at maturity based on a single characteristic variable; S3, integrating the visible light index and growth parameters to establish a rice biomass estimation model at maturity, including the following steps: S31, Test set determination coefficient of the rice biomass estimation model based on the visible light index in S2 R 2 _test , the visible light index was classified for index optimization, and the rice biomass estimation model at maturity was constructed using different categories of visible light index as input factors; S32, integrating rice plant height and rice plant water content to construct a rice biomass estimation model at maturity and compare the fitting results; S4. Estimate the rice biomass at maturity in the experimental area.

2. The method for estimating rice yield at maturity by coupling visible light index and growth parameters according to claim 1, characterized in that: In S1, the UAV remote sensing data includes visible light data and multispectral data; the ground crop data includes rice plant height, rice fresh weight and rice dry weight; The rice plant height is the distance from the bottom to the top of the canopy of rice under natural growth conditions; the rice fresh weight is the weight of the rice after sampling and bagging; the rice dry weight is the weight of the rice after drying to a constant weight; Data processing includes the following steps: S11. Use Pix4D Mapper software and Yusense Map software to stitch and correct the UAV remote sensing data, crop the UAV images according to the sampling area location, take the average reflectance of each sampling area as the spectral reflectance of the sampling point, and obtain the spectral reflectance data of different bands; S12, vegetation index construction; select visible light index as an indicator for constructing rice biomass model at maturity; S13. Calculate the rice biomass per square meter of land based on the dry weight of rice and rice planting density in the sampling area; S14. Calculate the water content of the rice plant by the ratio of the difference between the fresh weight of rice and the dry weight of rice to the fresh weight of rice.

3. The method for estimating rice yield at maturity by coupling visible light index and growth parameters according to claim 2, characterized in that: In S2, the rice biomass at maturity is estimated based on a single characteristic variable as follows: S21. Pearson correlation analysis was used to evaluate the linear correlation between visible light index, rice plant height, rice plant water content and rice biomass. S22. Using visible light index, rice plant height, and rice plant water content as independent variables, a rice biomass estimation model was constructed using the support vector regression method. The training set determination coefficient R 2 _train and the test set determination coefficient R 2 _test Represent the accuracy of the training set and the accuracy of the test set respectively; S23. According to the accuracy of the training set and the accuracy of the test set, characteristic variables are selected from the visible light index, rice plant height and rice plant water content to fuse the visible light index and growth parameters to establish a rice biomass estimation model at maturity.

4. The method for estimating rice yield at maturity by coupling visible light index and growth parameters according to claim 1, characterized in that: In S32, the specific process is: the visible light index is sequentially integrated with the rice plant height, the rice plant water content, the rice plant height and the rice plant water content, and the three fitting effects are compared.

5. The method for estimating rice yield at maturity by coupling visible light index and growth parameters according to claim 3, characterized in that: In S4, the estimation of rice biomass at maturity in the experimental area includes the following steps: S41, obtaining the height of rice plants at maturity; S42, obtaining the water content of rice at maturity; S43. Based on the plant height of mature rice obtained in S41 and the water content of mature rice obtained in S42, combined with the mature rice biomass estimation model constructed in S3, the biomass of mature rice in the experimental area is estimated to obtain the distribution of mature rice biomass in the experimental area.

6. The method for estimating rice yield at maturity by coupling visible light index and growth parameters according to claim 5, characterized in that: In S41, the specific process of obtaining the plant height of rice at maturity is as follows: the UAV remote sensing data of the rice field before rice planting when it is bare and when the rice is mature are processed to obtain the digital surface model DSM of the corresponding period, which represents the ground height of the rice field and the overall height of the rice at maturity, respectively; the plant height data of rice at maturity is obtained through the canopy height model CHM; the plant height data obtained through the UAV remote sensing data are fitted and analyzed with the measured plant height.

7. The method for estimating rice yield at maturity by coupling visible light index and growth parameters according to claim 5, characterized in that: In S42, the specific process of obtaining the moisture content of rice at maturity is as follows: using drones to obtain multispectral images and extract multispectral indices related to the measured moisture content, combining the red light band reflectivity, red edge band reflectivity and near-infrared band reflectivity, and using the random forest regression method to construct a relationship model between the multispectral index and moisture content, and estimate the moisture content of rice at maturity.

Images