A method and device for predicting tea garden yield based on leaf area index

Abstract

The present application provides a method and device for predicting tea garden yield based on leaf area index, which relates to the field of remote sensing detection technology, including: obtaining image data of the tea garden to be measured and performing atmospheric correction, spatial resolution resampling, and coordinate system conversion to obtain first data; calculating the leaf area index of the tea garden to be measured according to a preset formula and substituting the first data into the first data to obtain second data; performing regression fitting based on the second data and the single yield of one bud and one leaf to obtain a first equation; superimposing the temperature coefficient and shading management according to the first equation and calculating the yield of the tea garden to be measured according to the picking pattern to obtain the predicted yield of the tea garden. This technical solution is based on remote sensing images and the spectral characteristics of tea trees to invert their leaf area index, establish a regression relationship between the leaf area index and tea leaves for indirect yield estimation, does not rely on ground-based laser radar or manual measurement, reduces the consumption of manpower and material resources, and improves the efficiency and accuracy of prediction.

Description

Technical Field

[0001] The invention belongs to the technical field of remote sensing detection, and in particular relates to a method and device for predicting tea garden yield based on leaf area index. Background Art

[0002] Tea (Tea) is a perennial, evergreen, broad-leaved shrub widely cultivated in tropical and subtropical mountainous regions. As one of the world's three most popular beverages, tea is a major cash crop in many developing countries, including China, India, Kenya, and Sri Lanka. Tea yield is influenced by numerous factors. Crown area, bud density, and 100-bud weight are important factors influencing yield per plant, and interactions among these traits also have a significant impact on yield per plant. After rows of mature tea plantations are closed, bud density and bud weight are the primary factors influencing tea yield, assuming the picking area remains unchanged. In addition to these factors, tea yield is also significantly influenced by subsequent cultivation practices. However, frequent meteorological disasters such as cold damage and heat damage brought about by global warming have severely impacted tea production. Since the 1990s, with the restructuring of agricultural production and the shift toward more efficient agricultural production, tea farmers have gradually shifted away from traditional approaches to picking and production, focusing instead on improving the yield and quality of spring tea, which reduces costs and improves economic returns. As competition in the tea market becomes increasingly fierce, tea farmers are concerned about whether they can minimize losses caused by meteorological disasters, accurately grasp the appropriate tea picking period, and obtain tea products with high yield and quality.

[0003] Among the existing technical solutions for predicting tea tree yield, some only consider factors such as the plant morphology, physiological characteristics, leaf structure anatomy, and biochemical composition of a single plant. Most of them rely on ground-based radar for crop detection to achieve yield estimation, which is not conducive to large-scale tea tree yield estimation; some rely on ground-based lidar or manual measurement of plant morphology, supplemented by climate and light data, and use crop growth models to estimate yield, which consumes a lot of manpower and material resources; some have large deviations in tea yield due to different picking methods, so the regression target is mostly tea tree biomass rather than directly inverting yield; or yield inversion is performed for a specific tea variety, which has no universal applicability. Summary of the Invention

[0004] The present invention provides a tea garden yield prediction method and device based on leaf area index, aiming to solve the above-mentioned problems of relying on ground-based lidar for yield measurement, a small scope of application, a large amount of auxiliary data required, a complex model, high cost, a single inversion variety, and no universal applicability.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions, including:

[0006] Acquire image data of the tea garden to be measured and perform atmospheric correction, spatial resolution resampling, and coordinate system conversion to obtain first data;

[0007] Calculate the leaf area index of the tea garden to be tested according to a preset formula and input the first data to obtain second data;

[0008] Regression fitting is performed based on the second data and the single yield of one bud and one leaf to obtain a first equation. The temperature coefficient and shading management are superimposed on the first equation and the yield of the tea garden to be tested is calculated according to the picking mode to obtain the predicted yield of the tea garden. The one bud and one leaf is one of the tea picking modes.

[0009] Preferably, the leaf area index of the tea garden to be tested is calculated according to a preset formula and the first data is input to obtain the second data, including:

[0010] Substitute the first data into the normalized vegetation index calculation formula NDVI=(NIR-RED) / (NIR+RED) to calculate and obtain a first calculation result, wherein NDVI is the normalized vegetation index, NIR is the near infrared band, and RED is the red light band;

[0011] Substitute the first calculation result into the vegetation coverage calculation formula VFC=(NDVI-NDVImin) / (NDVImax-NDVImin) to obtain a second calculation result, where VFC is the vegetation coverage, NDVImin is the normalized vegetation index value of pure bare soil in the area, and NDVImax is the NDVI value of high vegetation coverage in the area;

[0012] The second calculation result is substituted into the leaf area index calculation formula LAI = -Cos(θ)ln(P(θ)) / (G(θ)Ω(θ)) to obtain the second data, where P(θ) is the canopy porosity, i.e., 1-VFC, θ is the orthophoto, G(θ) represents the average projected area of leaves per unit area on a plane perpendicular to the measurement direction, and Ω(θ) is the aggregation index.

[0013] Preferably, the method comprises performing regression fitting based on the second data and the single yield of one bud and one leaf to obtain a first equation, superimposing the temperature coefficient and shading management according to the first equation and calculating the yield of the tea garden to be tested according to the picking mode to obtain the predicted yield of the tea garden, including:

[0014] Fitting the temperature coefficient and the yield reduction coefficient of the tea garden to be tested yields the second equation Tindex=11.802*e^-0.545x, where Tindex is the temperature factor, e is the natural base, and x is the lowest daily average temperature between March and May. The first equation is Yield=0.0072*LAI^4.2368, where Yield is the per-acre yield of the tea garden under the one-bud-one-leaf picking mode.

[0015] According to the shading percentage and the yield increase coefficient of the tea garden to be tested, a third equation Shadowindex=-0.0074*x^2-0.1097*x+29.83 is obtained, where Shadowindex is the shading factor and x is the shading percentage.

[0016] Preferably, the method further comprises: performing regression fitting based on the second data and the single yield of one bud and one leaf to obtain a first equation; superimposing the temperature coefficient and shading management according to the first equation and calculating the yield of the tea garden to be tested according to the picking mode to obtain the predicted yield of the tea garden;

[0017] The yield of the tea garden to be tested is calculated according to the yield prediction formula Yield_mu = Yield*Tindex*Shadowindex*A*B to obtain the predicted yield of the tea garden, where Yield_mu is the yield per mu, A is the yield ratio coefficient of different picking modes to one bud and one leaf, and B is the number of picking times per year.

[0018] Preferably, the picking modes include single bud, one bud and one leaf, one bud and two leaves, and one bud and three leaves, and the ratio coefficients between the picking modes are single bud: one bud and one leaf: one bud and two leaves: one bud and three leaves = 1:3.63:13.07:30.692.

[0019] A tea garden yield prediction device based on leaf area index, comprising:

[0020] Image data preprocessing module: used to obtain the image data of the tea garden to be measured and perform atmospheric correction, spatial resolution resampling and coordinate system conversion to obtain the first data;

[0021] Leaf area index calculation module: used to calculate the leaf area index of the tea garden to be tested according to a preset formula and input the first data to obtain second data;

[0022] Yield prediction module: used to perform regression fitting based on the second data and the single yield of one bud and one leaf to obtain a first equation, and to calculate the yield of the tea garden to be tested according to the first equation by superimposing the temperature coefficient and shading management and according to the picking mode to obtain the predicted yield of the tea garden, where one bud and one leaf is one of the tea picking modes.

[0023] Preferably, the leaf area index calculation module includes:

[0024] The first index calculation module is used to input the first data into the normalized vegetation index calculation formula NDVI = (NIR-RED) / (NIR+RED) to calculate and obtain a first calculation result, wherein NDVI is the normalized vegetation index, NIR is the near infrared band, and RED is the red light band;

[0025] Index second calculation module: used to bring the first calculation result into the vegetation cover calculation formula VFC = (NDVI - NDVImin) / (NDVImax - NDVImin) to calculate and obtain a second calculation result, where VFC is the vegetation cover, NDVImin is the normalized vegetation index value of pure bare soil in the area, and NDVImax is the NDVI value of high vegetation cover in the area;

[0026] The third index calculation module is used to substitute the second calculation result into the leaf area index calculation formula LAI = -Cos(θ)ln(P(θ)) / (G(θ)Ω(θ)) to obtain the second data, where P(θ) is the canopy porosity, i.e. 1-VFC, θ is the orthophoto, G(θ) represents the average projected area of leaves per unit area on a plane perpendicular to the measurement direction, and Ω(θ) is the aggregation index.

[0027] Preferably, the yield prediction module includes:

[0028] The first yield influencing factor module is used to fit the temperature coefficient and the yield reduction coefficient of the tea garden to be tested, and obtain the second equation Tindex=11.802*e^-0.545x, where Tindex is the temperature factor, e is the natural base, and x is the lowest daily average temperature between March and May. The first equation is Yield=0.0072*LAI^4.2368, where Yield is the per-acre yield of the tea garden under the one-bud-one-leaf picking mode;

[0029] The second yield influencing factor module is used to fit the shading percentage and the yield increase coefficient of the tea garden to obtain the third equation Shadowindex=-0.0074*x^2-0.1097*x+29.83, where Shadowindex is the shading factor and x is the shading percentage;

[0030] Yield calculation module: used to calculate the yield of the tea garden to be tested according to the yield prediction formula Yield_mu = Yield*Tindex*Shadowindex*A*B to obtain the predicted yield of the tea garden, where Yield_mu is the yield per mu, A is the yield ratio coefficient of different picking modes and one bud and one leaf, and B is the number of picking times per year.

[0031] A tea garden yield prediction device based on leaf area index comprises a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement a tea garden yield prediction method based on leaf area index as described in any one of the above.

[0032] A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a computer, the method for predicting tea garden yield based on leaf area index as described above is implemented.

[0033] The present invention has the following beneficial effects:

[0034] (1) This technical solution is based on remote sensing images and the spectral characteristics of tea trees to invert their leaf area index. Since the yield of tea trees depends on the number of leaves, the yield is indirectly estimated by establishing a regression relationship between the leaf area index and tea leaves. Because this solution is a prediction result obtained by acquiring remote sensing images and further processing, this technical solution can estimate the yield of tea gardens on a large scale. It inverts the leaf area index by calculating it and establishes a regression equation based on the relationship with tea yield to estimate the yield. It does not rely on ground-based lidar or manual measurement, which reduces the consumption of manpower and material resources and improves the efficiency and accuracy of the prediction.

[0035] (2) This technical solution is based on the one-bud-one-leaf in the tea picking pattern for inversion, rather than tea tree biomass calculation or single tea variety inversion for yield prediction. It can be applied to tea yield prediction of different types and regions, with a wider scope of application and greater universality. In addition, when finally predicting tea yield, this technical solution divides different picking patterns into different proportional coefficients. The proportional coefficients are obtained from multiple experiments and are generally representative. Therefore, the yield prediction based on the proportional coefficients can improve the accuracy of yield prediction under different picking patterns.

[0036] (3) After calculating the per-acre yield prediction value under the one-bud-one-leaf picking mode, this technical solution superimposes the temperature coefficient and the shading coefficient, taking into account the external factors such as the yield reduction caused by some meteorological factors or the yield increase caused by shading management factors, and performs superimposed calculations to obtain the final yield prediction value. In this way, the accuracy of the final prediction value can be improved, external influencing factors are eliminated, and the calculation results have more practical reference value, and the calculated prediction value is more consistent with the actual yield. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 Flowchart of a tea garden yield prediction method based on leaf area index implemented in an embodiment of the present invention

[0038] Figure 2 Flowchart of a method for calculating leaf area index according to an embodiment of the present invention

[0039] Figure 3 A schematic diagram of a tea garden yield prediction device based on leaf area index according to an embodiment of the present invention

[0040] Figure 4 Schematic diagram of the structure of the leaf area index calculation module 20 in a tea garden yield prediction device based on leaf area index according to an embodiment of the present invention

[0041] Figure 5 Schematic diagram of the structure of the yield prediction module 30 in the tea garden yield prediction device based on leaf area index according to an embodiment of the present invention

[0042] Figure 6 Schematic diagram of an electronic device used in a tea garden yield prediction device based on leaf area index according to an embodiment of the present invention DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work shall fall within the scope of protection of the present invention.

[0044] The terms "first", "second", etc. in the claims and specification of this application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances. This is merely a way of distinguishing when describing objects with the same properties in the embodiments of this application. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, so that a process, method, system, product or apparatus that includes a series of units is not necessarily limited to those units, but may include other units not expressly listed or inherent to these processes, methods, products or apparatuses.

[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0046] Example 1

[0047] like Figure 1As shown, a tea garden yield prediction method based on leaf area index includes the following steps:

[0048] S11, obtaining image data of the tea garden to be measured and performing atmospheric correction, spatial resolution resampling and coordinate system conversion to obtain first data;

[0049] S12, calculating the leaf area index of the tea garden to be tested according to a preset formula and inputting the first data to obtain second data;

[0050] S13. Perform regression fitting based on the second data and the single yield of one bud and one leaf to obtain a first equation. Superimpose the temperature coefficient and shading management based on the first equation and calculate the yield of the tea garden to be tested according to the picking mode to obtain the predicted yield of the tea garden, where one bud and one leaf is one of the tea picking modes.

[0051] In this embodiment, first, remote sensing image data of the tea garden plot for tea yield prediction is obtained according to Sentinel-2, and atmospheric correction is performed on the image data using the toolkit Sen2Cor, spatial resolution is resampled using the software SNAP, and the coordinate system is converted to the WGS84 geographic coordinate system. After the above processing, the processed data is obtained, which is the "first data", and the normalized vegetation index and vegetation cover are calculated using some formulas, and the calculated normalized vegetation index and leaf area index are calculated according to the leaf area index calculation formula. Vegetation coverage was incorporated into the calculation to obtain the leaf area index (LEI). This calculation result became the "second data." A regression fit was then performed based on this LAI and the single yield under the one-bud-one-leaf picking model. The LAI values (LEI) for the camellia planting areas were calculated. LAI values were taken at every quintile (5th, 10th, 15th, ..., 95th, 100th percentiles). This was then combined with a series of one-bud-one-leaf yields per mu obtained from the survey and fitted. The yield per mu formula was obtained: Yield = 0.0072 * LAI^4.2368, which became the "first equation."

[0052] Then, considering that both temperature and shading factors will cause changes in tea yield, the correlation function formulas of the temperature coefficient and the shading coefficient are calculated, as follows: Late spring cold will seriously affect the yield of spring tea, so the extreme low temperature from March to May will put a pressure on tea yield. Therefore, this plan introduces the lowest daily average temperature during this period to calculate the low temperature yield reduction coefficient. The fitted formula is as follows: Tindex = 11.802*e^-0.545x, which is the "second equation", where x is the temperature from March to May. The lowest daily average temperature between tea gardens and trees is 2.718, where e refers to the natural base, an irrational number approximately equal to 2.718. Shading can significantly reduce the temperature of tea gardens, tree crowns, and soil, increase relative humidity, and improve soil moisture. Moderate shading can promote photosynthesis in tea trees and contribute to the accumulation of organic matter. A fitting relationship between shading percentage and yield increase coefficient is established here: Shadowindex = -0.0074*x^2 - 0.1097*x + 29.83. This formula is the "third equation," where x is the shading percentage.

[0053] After obtaining the relevant formulas for external factors, considering that there is a large gap in yield between different picking modes in actual tea picking, it is necessary to adjust the yield results under the one bud and one leaf picking mode inverted in this scheme. After many experiments, the proportional coefficients of yield under different picking modes are obtained. This proportional coefficient is generally representative, that is, "single bud: one bud and one leaf: one bud and two leaves: one bud and three leaves = 1:3.63:13.07:30.692". Then, according to the picking method in the actual scenario, the calculation formula is: Yield_mu = Yield*Tindex*Shadowindex*A* B, where Yield_mu is the yield per mu, A is the yield ratio coefficient of different picking modes to one bud and one leaf, and B is the number of pickings per year. An example is given below, such as: there is one bud and three leaves of tea, which is picked twice a year. The calculation method is as follows: Yield_mu = Yield * Tindex * Shadowindex * 2 * (3.63 / 30.692). Then, the predicted yield per mu (Yield) of one bud and one leaf, the calculated values of temperature factor (Tindex) and shading factor (Shadowindex) are substituted into the formula to obtain the predicted yield of tea under the one bud and three leaves picking mode.

[0054] The beneficial effects of this embodiment are:

[0055] (1) This technical solution is based on the one-bud-one-leaf in the tea picking pattern for inversion, rather than tea tree biomass calculation or single tea variety inversion for yield prediction. It can be applied to tea yield prediction of different types and regions, with a wider scope of application and greater universality. In addition, when finally predicting tea yield, this technical solution divides different picking patterns into different proportional coefficients. The proportional coefficients are obtained from multiple experiments and are generally representative. Therefore, the yield prediction based on the proportional coefficients can improve the accuracy of yield prediction under different picking patterns.

[0056] (2) After calculating the per-acre yield prediction value under the one-bud-one-leaf picking mode, this technical solution superimposes the temperature coefficient and the shading coefficient, taking into account the external factors such as the yield reduction caused by some meteorological factors or the yield increase caused by shading management factors, and performs superimposed calculations to obtain the final yield prediction value. In this way, the accuracy of the final prediction value can be improved, the external influencing factors are eliminated, the calculation results have more practical reference value, and the calculated prediction value is more consistent with the actual yield.

[0057] Example 2

[0058] like Figure 2 As shown, a method for calculating the leaf area index comprises the following steps:

[0059] S21. Substitute the first data into the normalized vegetation index calculation formula NDVI=(NIR-RED) / (NIR+RED) to calculate and obtain a first calculation result, where NDVI is the normalized vegetation index, NIR is the near infrared band, and RED is the red light band;

[0060] S22. Substitute the first calculation result into the vegetation coverage calculation formula VFC=(NDVI-NDVImin) / (NDVImax-NDVImin) to obtain a second calculation result, where VFC is the vegetation coverage, NDVImin is the normalized vegetation index value of pure bare soil in the area, and NDVImax is the NDVI value of high vegetation coverage in the area;

[0061] S23. Substitute the second calculation result into the leaf area index calculation formula LAI = -Cos(θ)ln(P(θ)) / (G(θ)Ω(θ)) to obtain the second data, where P(θ) is the canopy porosity, i.e. 1-VFC, θ is the orthophoto, G(θ) represents the average projected area of leaves per unit area on a plane perpendicular to the measurement direction, and Ω(θ) is the aggregation index.

[0062] In this embodiment, after the remote sensing image is processed to obtain the first data, a series of parameter calculations are performed to calculate the leaf area index in the one-bud-one-leaf picking mode, as follows:

[0063] First, NDVI and VFC calculations are performed. The calculation formula of the normalized vegetation index (NDVI) is: NDVI = (NIR-RED) / (NIR+RED) to obtain the normalized vegetation index calculation result, which is the "first calculation result", where NDVI is the normalized vegetation index, NIR is the near-infrared band, and RED is the red light band; then the vegetation coverage is calculated according to the vegetation coverage VFC calculation formula: VFC = (NDVI-NDVImin) / (NDVImax-NDVImin) to obtain the vegetation coverage calculation result, which is the "second calculation result", where NDVI is the normalized vegetation index value of the pixel, NDVImin is the normalized vegetation index value of pure bare soil in the area, and NDVImax is the NDVI value of high vegetation coverage in the area. Usually, 1000 bare soil pixels and vegetation pixels are extracted by manual interpretation, and their NDVIs are extracted respectively, and the average is used as NDVImin and NDVImax;

[0064] Then the leaf area index LAI is inverted. The finite length averaging method based on Beer's law has the following formula: P(θ)=e -G(θ)Ω(θ)LAI / cos(θ) After the formula transformation, we get: LAI = -Cos(θ)ln(P(θ)) / (G(θ)Ω(θ)). According to the formula, the parameters are substituted into the calculation to obtain the leaf area index calculation result, which is the "second data". In the formula, Pθ is the canopy porosity, that is, 1-VFC, θ is the observation zenith angle, for this image, it is an orthophoto, take 0°, Gθ represents the average projected area of leaves per unit area on the plane perpendicular to the measurement direction, generally taking a value of 0.5, Ωθ is the aggregation index, and the calculation formula is as follows: Ω(θ) = ln(mean(P(θ))) / mean(ln(P(θ))), where mean represents the average of the formula in the brackets.

[0065] The beneficial effects of this embodiment are as follows: this technical solution is based on remote sensing images and inverts the leaf area index of tea trees according to their spectral characteristics. Since the yield of tea trees depends on the number of leaves, the yield is indirectly estimated by establishing a regression relationship between the leaf area index and tea leaves. Because this solution obtains prediction results by acquiring remote sensing images and further processing them, this technical solution can estimate the yield of tea gardens on a large scale. It inverts by calculating the leaf area index and establishes a regression equation based on the relationship with tea yield to estimate the yield. It does not rely on ground-based lidar or manual measurement, thus reducing the consumption of manpower and material resources, while improving the efficiency and accuracy of the prediction.

[0066] Example 3

[0067] like Figure 3 As shown, a tea garden yield prediction device based on leaf area index includes:

[0068] Image data preprocessing module 10: used to obtain the image data of the tea garden to be measured and perform atmospheric correction, spatial resolution resampling and coordinate system conversion to obtain first data;

[0069] The leaf area index calculation module 20 is used to calculate the leaf area index of the tea garden to be tested according to a preset formula and the first data to obtain second data;

[0070] Yield prediction module 30: used to perform regression fitting based on the second data and the single yield of one bud and one leaf to obtain a first equation, and to calculate the yield of the tea garden to be tested according to the first equation by superimposing the temperature coefficient and shading management and according to the picking mode to obtain the predicted yield of the tea garden, where the one bud and one leaf is one of the tea picking modes.

[0071] One implementation of the above-mentioned device is that, in the image data preprocessing module 10, the image data of the tea garden to be tested is obtained and atmospheric correction, spatial resolution resampling and coordinate system conversion are performed to obtain first data; in the leaf area index calculation module 20, the leaf area index of the tea garden to be tested is calculated according to a preset formula and the first data is substituted into the first data to obtain second data; in the yield prediction module 30, regression fitting is performed based on the second data and the single yield of one bud and one leaf to obtain a first equation; according to the first equation, the temperature coefficient and shading management are superimposed and the yield of the tea garden to be tested is calculated according to the picking mode to obtain the predicted yield of the tea garden, where the one bud and one leaf is one of the tea picking modes.

[0072] Example 4

[0073] like Figure 4 As shown, a leaf area index calculation module 20 in a tea garden yield prediction device based on leaf area index includes:

[0074] Index first calculation module 21: used to bring the first data into the normalized vegetation index calculation formula NDVI = (NIR-RED) / (NIR+RED) to calculate and obtain a first calculation result, where NDVI is the normalized vegetation index, NIR is the near infrared band, and RED is the red light band;

[0075] Index second calculation module 22: used to substitute the first calculation result into the vegetation coverage calculation formula VFC=(NDVI-NDVImin) / (NDVImax-NDVImin) to obtain a second calculation result, where VFC is the vegetation coverage, NDVImin is the normalized vegetation index value of pure bare soil in the area, and NDVImax is the NDVI value of high vegetation coverage in the area;

[0076] The third index calculation module 23 is used to substitute the second calculation result into the leaf area index calculation formula LAI = -Cos(θ)ln(P(θ)) / (G(θ)Ω(θ)) to obtain the second data, wherein P(θ) is the canopy porosity, i.e., 1-VFC, θ is the orthophoto, G(θ) represents the average projected area of leaves per unit area on a plane perpendicular to the measurement direction, and Ω(θ) is the aggregation index.

[0077] One implementation of the above device is that, in the first index calculation module 21, the first data is brought into the normalized vegetation index calculation formula NDVI=(NIR-RED) / (NIR+RED) for calculation to obtain a first calculation result, wherein NDVI is the normalized vegetation index, NIR is the near infrared band, and RED is the red light band; in the second index calculation module 22, the first calculation result is brought into the vegetation coverage calculation formula VFC=(NDVI-NDVImin) / (NDVImax-NDVImin) for calculation to obtain a second calculation result, wherein VFC is vegetation coverage, NDVImin is the normalized vegetation index value of pure bare soil in the area, and NDVImax is the NDVI value of high vegetation coverage in the area. In the third index calculation module 23, the second calculation result is substituted into the leaf area index calculation formula LAI = -Cos(θ)ln(P(θ)) / (G(θ)Ω(θ)) for calculation to obtain the second data, where P(θ) is the canopy porosity, i.e. 1-VFC, θ is the orthophoto, G(θ) represents the average projected area of leaves per unit area on a plane perpendicular to the measurement direction, and Ω(θ) is the aggregation index.

[0078] Example 5

[0079] like Figure 5 As shown, a yield prediction module 30 in a tea garden yield prediction device based on leaf area index includes:

[0080] The first yield influencing factor module 31 is used to perform fitting based on the temperature coefficient and the yield reduction coefficient of the tea garden to obtain a second equation Tindex=11.802*e^-0.545x, where Tindex is the temperature factor, e is the natural base, and x is the lowest daily average temperature between March and May. The first equation is Yield=0.0072*LAI^4.2368, where Yield is the per-acre yield of the tea garden under the one-bud-one-leaf picking mode;

[0081] The second yield influencing factor module 32 is used to perform fitting based on the shading percentage and the yield increase coefficient of the tea garden to obtain the third equation Shadowindex=-0.0074*x^2-0.1097*x+29.83, where Shadowindex is the shading factor and x is the shading percentage;

[0082] Yield calculation module 33: used to calculate the yield of the tea garden to be tested according to the yield prediction formula Yield_mu = Yield*Tindex*Shadowindex*A*B to obtain the predicted yield of the tea garden, where Yield_mu is the yield per mu, A is the yield ratio coefficient of different picking modes and one bud and one leaf, and B is the number of picking times per year.

[0083] One embodiment of the above device is that in the first yield influencing factor module 31, fitting is performed based on the temperature coefficient and the yield reduction coefficient of the tea garden to be tested to obtain the second equation Tindex=11.802*e^-0.545x, where Tindex is the temperature factor, e is the natural base, and x is the lowest daily average temperature between March and May, and the first equation is Yield=0.0072*LAI^4.2368, where Yield is the per-acre yield of the tea garden under the one-bud and one-leaf picking mode, and in the second yield influencing factor module 32, according to the shading percentage and the yield increase coefficient of the tea garden to be tested, the yield reduction coefficient of the tea garden to be tested is obtained. The coefficients are fitted to obtain the third equation Shadowindex=-0.0074*x^2-0.1097*x+29.83, where Shadowindex is the shading factor and x is the shading percentage. In the yield calculation module 33, the yield of the tea garden to be tested is calculated according to the yield prediction formula Yield_mu=Yield*Tindex*Shadowindex*A*B to obtain the predicted yield of the tea garden, where Yield_mu is the yield per mu, A is the yield ratio coefficient of different picking modes to one bud and one leaf, and B is the number of picking times per year.

[0084] Example 6

[0085] like Figure 6As shown, an electronic device includes a memory 601 and a processor 602, wherein the memory 601 is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor 602 to implement any one of the above methods.

[0086] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the electronic device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0087] A computer-readable storage medium storing a computer program, wherein the computer program enables a computer to implement any one of the above methods when executed.

[0088] Exemplarily, a computer program may be divided into one or more modules / units, one or more modules / units being stored in the memory 601 and executed by the processor 602, and the input interface 605 and the output interface 606 completing the I / O interface transmission of data to complete the present invention. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in a computer device.

[0089] The computer device may be a desktop computer, laptop, PDA, cloud server, or other computing device. The computer device may include, but is not limited to, memory 601 and processor 602. Those skilled in the art will appreciate that this embodiment is merely an example of a computer device and does not limit the computer device. The computer device may include more or fewer components, or a combination of certain components, or different components. For example, the computer device may also include an input device 607, a network access device, a bus, and the like.

[0090] The processor 602 may be a central processing unit (CPU), other general-purpose processors 602, digital signal processors 602 (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor 602 may be a microprocessor 602 or any conventional processor 602.

[0091] The memory 601 can be an internal storage unit of the computer device, such as a hard disk or memory of the computer device. The memory 601 can also be an external storage device of the computer device, such as a plug-in hard disk equipped with the computer device, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Furthermore, the memory 601 can also include both an internal storage unit of the computer device and an external storage device. The memory 601 is used to store computer programs and other programs and data required by the computer device. The memory 601 can also be used to temporarily store data in the output device 608. The aforementioned storage media include various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM) 603, a random access memory (RAM) 604, a disk, or an optical disk.

[0092] The above description is only a specific embodiment of the present invention, but the technical features of the present invention are not limited thereto. Any changes or modifications made by any technician in this field within the scope of the present invention are included in the patent scope of the present invention.

Claims

1. A tea garden yield prediction method based on leaf area index, characterized in that: include: Acquire image data of the tea garden to be measured and perform atmospheric correction, spatial resolution resampling, and coordinate system conversion to obtain first data; Calculate the leaf area index of the tea garden to be tested according to a preset formula and input the first data to obtain second data; According to the temperature coefficient and the yield reduction coefficient of the tea garden to be tested, the second equation Tindex= , where Tindex is the temperature factor, e is the natural base, x is the lowest daily average temperature between March and May, and the first equation is Yield= , where Yield is the per-acre yield of tea garden under the one-bud-one-leaf picking mode, and LAI is the leaf area index; The third equation is obtained by fitting the shading percentage and the yield increase coefficient of the tea garden to be tested. ,in is the shading factor, x is the shading percentage; According to the production forecast formula = Calculate the yield of the tea garden to be tested to obtain the predicted yield of the tea garden, where Yield_mu is the yield per mu, A is the yield ratio coefficient of different picking modes and one bud and one leaf, and B is the number of picking times per year; The one bud and one leaf method is one of the tea picking modes.

2. A tea garden yield prediction method based on leaf area index according to claim 1, characterized in that: The step of calculating the leaf area index of the tea garden to be tested according to a preset formula and inputting the first data to obtain the second data includes: Substitute the first data into the normalized vegetation index calculation formula NDVI=(NIR-RED) / (NIR+RED) to calculate and obtain a first calculation result, wherein NDVI is the normalized vegetation index, NIR is the near infrared band, and RED is the red light band; The first calculation result is substituted into the vegetation coverage calculation formula VFC=(NDVI-NDVImin) / (NDVImax-NDVImin) to obtain a second calculation result, wherein VFC is the vegetation coverage, NDVImin is the normalized vegetation index value of pure bare soil in the tea garden area to be measured, and NDVImax is the NDVI value of high vegetation coverage in the tea garden area to be measured; the NDVImin and NDVImax are obtained by manually extracting the bare soil pixels and vegetation pixels in the tea garden area to be measured and calculating their NDVI mean values respectively; The second calculation result is substituted into the leaf area index calculation formula LAI=-Cos(θ)ln(P(θ)) / (G(θ)Ω(θ)) to obtain the second data, where P(θ) is the canopy porosity, i.e., 1-VFC, θ is the orthophoto, G(θ) represents the average projected area of leaves per unit area on a plane perpendicular to the measurement direction, and Ω(θ) is the aggregation index.

3. A tea garden yield prediction method based on leaf area index according to claim 1, characterized in that: The picking modes include single bud, one bud and one leaf, one bud and two leaves, and one bud and three leaves, and the ratio coefficients between the picking modes are single bud: one bud and one leaf: one bud and two leaves: one bud and three leaves=1:3.63:13.07:30.

692.

4. A tea garden yield prediction device based on leaf area index, used to implement the tea garden yield prediction method based on leaf area index as claimed in claim 1, characterized in that: include: Image data preprocessing module: used to obtain the image data of the tea garden to be measured and perform atmospheric correction, spatial resolution resampling and coordinate system conversion to obtain the first data; Leaf area index calculation module: used to calculate the leaf area index of the tea garden to be tested according to a preset formula and input the first data to obtain second data; A yield prediction module is configured to perform regression fitting based on the second data and the single yield of one bud and one leaf to obtain a first equation, and to calculate the yield of the tea garden to be tested according to the picking mode by superimposing the temperature coefficient and the shading management according to the first equation to obtain the predicted yield of the tea garden, where the one bud and one leaf is one of the tea picking modes; The output prediction module includes: The first yield influencing factor module is used to fit the temperature coefficient and the yield reduction coefficient of the tea garden to be tested, and obtain the second equation Tindex= , where Tindex is the temperature factor, e is the natural base, x is the lowest daily average temperature between March and May, and the first equation is Yield= , where Yield is the per-acre yield of tea garden under the one-bud-one-leaf picking mode; The second yield influencing factor module is used to fit the shading percentage and the yield increase coefficient of the tea garden to obtain the third equation Shadowindex= , where Shadowindex is the shading factor and x is the shading percentage; Yield calculation module: used to calculate the yield of the tea garden to be tested according to the yield prediction formula Yield_mu=Yield*Tindex*Shadowindex*A*B to obtain the predicted yield of the tea garden, where Yield_mu is the yield per mu, A is the yield ratio coefficient of different picking modes and one bud and one leaf, and B is the number of picking times per year.

5. The tea garden yield prediction device based on leaf area index according to claim 4, characterized in that: The leaf area index calculation module includes: The first index calculation module is used to input the first data into the normalized vegetation index calculation formula NDVI=(NIR-RED) / (NIR+RED) to calculate and obtain a first calculation result, wherein NDVI is the normalized vegetation index, NIR is the near infrared band, and RED is the red light band; Index second calculation module: used to bring the first calculation result into the vegetation coverage calculation formula VFC=(NDVI-NDVImin) / (NDVImax-NDVImin) to calculate and obtain the second calculation result, wherein VFC is the vegetation coverage, NDVImin is the normalized vegetation index value of pure bare soil in the tea garden area to be tested, and NDVImax is the NDVI value of high vegetation coverage in the tea garden area to be tested; the NDVImin and NDVImax are obtained by manually extracting the bare soil pixels and vegetation pixels in the tea garden area to be tested, and calculating their NDVI mean values respectively; Index third calculation module: used to substitute the second calculation result into the leaf area index calculation formula LAI=-Cos(θ)ln(P(θ)) / (G(θ)Ω(θ)) to calculate and obtain the second data, where P(θ) is the canopy porosity, i.e. 1-VFC, θ is the orthophoto, G(θ) represents the average projected area of leaves per unit area on a plane perpendicular to the measurement direction, and Ω(θ) is the aggregation index.

6. A tea garden yield prediction device based on leaf area index, characterized in that: The invention comprises a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement a tea garden yield prediction method based on leaf area index as described in any one of claims 1 to 3.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a computer, the method for predicting tea garden yield based on leaf area index according to any one of claims 1 to 3 is implemented.

Images