A method and system for evaluating the lodging resistance of corn stalks during flowering period

Abstract

The present invention discloses a method and system for evaluating the lodging resistance of corn stalks during the flowering period, and the present invention relates to the technical field of evaluating the lodging resistance of corn stalks. The method comprises the following steps: collecting a number of corn flowering plants with known physiological characteristic parameters, performing infrared scanning on the surface of the stalks, obtaining infrared spectrum images, and establishing a sample data set with the physiological characteristic parameters; training a neural network model based on the sample data set, taking the infrared spectrum images as input and the physiological characteristic parameters as labels, and obtaining a prediction model for the physiological characteristic parameters of the plants; performing infrared scanning on the target plants, inputting the prediction model, and obtaining the predicted values ​​of the physiological characteristic parameters; calculating the stalk structure stability index in combination with the geometric structure parameters; calculating the environmental adaptability index according to the environmental parameters; generating the lodging resistance index by combining the two, and generating the lodging resistance evaluation result according to the lodging resistance index. The accuracy, comprehensiveness, precision and efficiency of the evaluation are significantly improved.

Description

Technical Field

[0001] The invention relates to the technical field of evaluating the lodging resistance of corn stalks, and in particular to a method and system for evaluating the lodging resistance of corn stalks during the flowering period. Background Art

[0002] Corn is one of the most important food crops in the world and is planted over a wide area. However, corn plants are easily affected by the natural environment during their growth, especially during the flowering period, when they are prone to lodging due to insufficient mechanical strength of the stalks or excessive environmental stress (such as strong winds). Corn lodging will not only seriously affect the normal growth and photosynthetic efficiency of crops, but will also lead to insufficient grain filling and difficulty in harvesting, resulting in a significant drop in yield and economic losses. Therefore, how to accurately evaluate the lodging resistance of corn stalks and take timely protective measures is an important technical problem in current agricultural production.

[0003] Traditional methods for evaluating the lodging resistance of corn stalks are mostly based on mechanical testing and physical measurements. For example, by measuring the physical properties of the stalks, such as puncture strength, elastic modulus, and wall thickness ratio. Although these methods can reflect the lodging resistance of corn plants to a certain extent, they have significant limitations: first, mechanical testing requires destructive measurements of the plants and is not suitable for large-scale, rapid evaluation; second, these methods rely more on external geometric structural parameters and ignore the physiological and chemical properties of the corn stalks (such as lignin content and cellulose content), which have an important influence on the strength and toughness of the stalks.

[0004] With the rapid development of hyperspectral imaging technology and artificial intelligence, non-destructive detection technology has gradually become an important tool in agricultural research and production. Infrared spectroscopy technology, in particular, can quickly obtain physiological and chemical information inside plants (such as lignin and cellulose content) by scanning the spectral characteristics of the surface of plant stems, showing great potential in evaluating the mechanical strength of plants. Therefore, in view of the limitations of traditional methods for evaluating plant lodging during the flowering period of corn, there is an urgent need for a method that effectively combines infrared spectroscopy technology and modern machine learning to achieve accurate evaluation of the lodging resistance of corn stems.

[0005] In the prior art, publication number CN105699600B discloses a method for evaluating the lodging resistance of corn stalks, which measures the puncture strength of the stem bark of the internodes below the ear position of the stalk and the inclination angle of the internodes above the ear position, and then combines the stem bark penetration hardness and flexibility to make an objective and comprehensive evaluation of the lodging resistance of the stalk. This method overcomes the shortcomings of the original single evaluation method for the lodging resistance of corn stalks based on the actual field operation of identification of lodging resistance of corn stalks. It not only considers the hardness factor of the stalks below the ear position, but also combines the toughness factor of the stalks above the ear position, which can accurately evaluate the lodging resistance of the stalks. However, the stem bark puncture strength in this method only reflects the hardness and puncture resistance of the cortex of the surface of the stalk, but cannot fully represent the mechanical strength of the stalk as a whole. The lodging resistance is also closely related to other structural characteristics of the stalk, such as the wall thickness, outer diameter and other geometric parameters of the stalk. At the same time, this method does not fully consider the impact of the environment and external factors. The risk of lodging is not only related to the characteristics of the plant itself, but also significantly affected by the external environment (such as wind, temperature, soil moisture and other environmental parameters), which may lead to the inadaptability of the evaluation of lodging resistance under different climatic conditions. Therefore, judging lodging resistance based solely on the characteristics of the plant itself reduces the accuracy and effectiveness of the evaluation results.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The object of the present invention is to provide a method and system for evaluating the lodging resistance of corn stalks during the flowering period, so as to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A method for evaluating the lodging resistance of corn stalks during the flowering period, comprising the following specific steps:

[0010] Collecting a number of corn plants at the flowering stage with known physiological characteristic parameters, performing infrared scanning on the surfaces of the stems of the collected corn plants at the flowering stage to obtain sample infrared spectrum images, and mapping each sample infrared spectrum image with the corresponding physiological characteristic parameters one by one to generate a sample data set, wherein the physiological characteristic parameters include lignin content and cellulose content;

[0011] A neural network prediction model is established based on the sample data set, the sample infrared spectrum image in the sample data set is used as the input of the neural network prediction model, and the corresponding physiological characteristic parameters in the sample data set are used as labels, the neural network prediction model is trained, and a plant physiological characteristic parameter prediction model is obtained;

[0012] Performing infrared scanning on the stem surface of the corn plant in the flowering period to be evaluated to obtain a target infrared spectrum image, inputting the target infrared spectrum image into the trained plant physiological characteristic parameter prediction model, and the model outputs the predicted value of the physiological characteristic parameter of the corn plant in the flowering period to be evaluated;

[0013] According to the predicted value of the physiological characteristic parameter, combined with the geometric structure parameters of the maize plant in the flowering period to be evaluated, the stalk structure stability index is calculated and generated, and the environmental parameters of the maize plant in the flowering period to be evaluated are collected, and based on the obtained environmental parameters, the environmental adaptability index is calculated and generated, the geometric structure parameters include the stalk elastic modulus, the average outer diameter of the stalk, the average thickness of the stem wall and the plant height, and the environmental parameters include the average environmental wind speed, soil moisture and average air temperature;

[0014] Based on the obtained environmental adaptability index and stalk structure stability index, a comprehensive lodging resistance index is calculated and generated, and the comprehensive lodging resistance index of the corn plants in the flowering period to be evaluated is compared with the lodging resistance judgment threshold. According to the comparison results, the corresponding lodging resistance evaluation results are generated.

[0015] Furthermore, the specific steps of performing infrared scanning on the surface of the stems of the corn plants collected at the flowering stage to obtain the sample infrared spectrum image include collecting initial spectrum data, visualizing the initial spectrum data, generating an infrared spectrum image, and preprocessing the infrared spectrum image to obtain the sample infrared spectrum image;

[0016] The steps of collecting initial spectral data include: cleaning the surface of the sample stem, removing dust, soil and other attachments, aiming the probe of the infrared spectrometer at the surface of the stem, pressing the start button, collecting infrared spectral data of the stem surface, and recording the sample number for easy one-to-one mapping with the physiological characteristic parameters;

[0017] Using spectrum analysis software to draw the processed spectrum data into an infrared spectrum image, preprocessing the infrared spectrum image, wherein the preprocessing includes signal denoising and enhancement processing, and finally obtaining a sample infrared spectrum image;

[0018] Several corn plants in the flowering period with known physiological characteristic parameters are collected in sequence, and each sample infrared spectrum image obtained is matched one by one with the corresponding physiological characteristic parameters according to the recorded sample number to generate a sample data set.

[0019] Furthermore, a neural network prediction model is established based on the long short-term memory network LSTM model, and the activation function and optimization algorithm are selected. The Tanh function is selected as the activation function, and Adam is selected as the optimization algorithm of the LSTM model; the formula of the Tanh function is:

[0020] ;

[0021] In the formula, Represents the Tanh function, independent variable Represents the weighted sum of the neuron's input, that is, the result of weighted summation of the input received by the neuron from the previous layer;

[0022] At the same time, the hyperparameters of the LSTM model are set, and the hyperparameters of the LSTM model include: the number of network layers, the number of iterations, the learning rate, the batch size, the number of training times, the batch processing number, and the number of hidden layer neurons;

[0023] The number of network layers is set to 3 layers, the number of iterations is set to 200, the learning rate is set to 0.001, the batch size is set to 32, the number of training times is set to 100, the batch size is set to 256, and the number of hidden layer neurons is 32;

[0024] The trained plant physiological characteristic parameter prediction model takes as input the infrared spectrum image of the stem surface of corn plants in the flowering period, and outputs the predicted values ​​of physiological characteristic parameters, including the predicted values ​​of lignin content and cellulose content.

[0025] Furthermore, according to the predicted value of the physiological characteristic parameter, combined with the geometric structure parameters of the maize plant to be evaluated at the flowering stage, the stalk structure stability index is calculated and generated, wherein the formula for calculating the stalk structure stability index is:

[0026] ;

[0027] In the formula, is the culm structure stability index, is the elastic modulus of the stem, is the average outer diameter of the stem, is the average thickness of the stem wall, is the plant height, It is a physiological influencing factor;

[0028] Physiological factors The calculation is based on the predicted value of the physiological characteristic parameter, and the specific formula is:

[0029] ;

[0030] In the formula, is the predicted value of lignin content, is the predicted value of cellulose content, and are the weight coefficients of the predicted values ​​of lignin content and cellulose content, respectively. and and Both are greater than 0.

[0031] Furthermore, based on the obtained environmental parameters, an environmental adaptability index is calculated and generated, wherein the environmental adaptability index is calculated according to the formula:

[0032] ;

[0033] In the formula, is the environmental adaptability index, is soil moisture, is the standard soil moisture, is the average air temperature, is the standard temperature value, The horizontal thrust generated by wind is It is calculated by the average wind speed of the environment and the windward area of ​​the plant. The specific calculation formula is:

[0034] ;

[0035] In the formula, is the wind pressure, is the windward area of ​​the plant, of which wind pressure The calculation is based on the formula:

[0036] ;

[0037] In the formula, is the air density, is the average ambient wind speed, is the angle between wind direction and horizontal plane.

[0038] Furthermore, based on the obtained environmental adaptability index and stalk structure stability index, a comprehensive lodging resistance index is calculated, wherein the formula for calculating the comprehensive lodging resistance index is:

[0039] ;

[0040] In the formula, is the comprehensive lodging resistance index, and are the weight coefficients of the culm structure stability index and the environmental adaptability index, respectively. and and Both are greater than 0.

[0041] Furthermore, the obtained comprehensive lodging resistance index of the corn plant in the flowering period to be evaluated is compared with the lodging resistance judgment threshold, and the corresponding lodging resistance evaluation result is generated according to the obtained comparison result, wherein the specific judgment logic is:

[0042] when When , it is judged as low lodging risk, indicating that the lodging risk of the maize plants to be evaluated during the flowering period is low and no protective measures are needed;

[0043] when When the lodging risk is judged to be medium, the lodging risk of the maize plants to be assessed during the flowering period is considered medium, and reinforcement and protection measures should be taken;

[0044] when When the lodging risk is high, it is judged as high, indicating that the lodging risk of the corn plants to be evaluated during the flowering period is high and cannot meet the normal growth requirements outdoors;

[0045] in is the lodging resistance judgment threshold, where Dynamic adjustment is made based on the height of the maize flowering plant to be evaluated and the average environmental rainfall. The specific formula is:

[0046] ;

[0047] In the formula, is the initial value of the anti-lodging force judgment threshold. is the average environmental rainfall.

[0048] The present invention also provides a system for evaluating the lodging resistance of corn stalks during flowering period, wherein the system for evaluating the lodging resistance of corn stalks during flowering period is used to execute the above-mentioned method for evaluating the lodging resistance of corn stalks during flowering period, and comprises:

[0049] The sample data processing module is used to collect a number of flowering corn plants with known physiological characteristic parameters, perform infrared scanning on the stem surfaces of the collected flowering corn plants, obtain sample infrared spectrum images, and map each sample infrared spectrum image with the corresponding physiological characteristic parameters one by one to generate a sample data set, wherein the physiological characteristic parameters include lignin content and cellulose content;

[0050] A neural network training module is used to establish a neural network prediction model based on a sample data set, use the sample infrared spectrum image in the sample data set as the input of the neural network prediction model, and use the corresponding physiological characteristic parameters in the sample data set as labels to train the neural network prediction model to obtain a plant physiological characteristic parameter prediction model;

[0051] A physiological parameter prediction module is used to perform infrared scanning on the stem surface of the corn plant in the flowering period to be evaluated, obtain a target infrared spectrum image, input the target infrared spectrum image into the trained plant physiological characteristic parameter prediction model, and the model outputs the predicted value of the physiological characteristic parameter of the corn plant in the flowering period to be evaluated;

[0052] A related index analysis module is used to calculate and generate a stalk structure stability index based on the predicted value of the physiological characteristic parameter in combination with the geometric structure parameters of the maize plant in the flowering period to be evaluated, and collect the environmental parameters of the maize plant in the flowering period to be evaluated, and calculate and generate an environmental adaptability index based on the obtained environmental parameters, wherein the geometric structure parameters include the stalk elastic modulus, the average outer diameter of the stalk, the average thickness of the stem wall and the plant height, and the environmental parameters include the average environmental wind speed, soil humidity and average air temperature;

[0053] The comprehensive lodging resistance evaluation module is used to calculate and generate a comprehensive lodging resistance index based on the obtained environmental adaptability index and stalk structure stability index, compare the obtained comprehensive lodging resistance index of the corn plants in the flowering period to be evaluated with the lodging resistance judgment threshold, and generate a corresponding lodging resistance evaluation result based on the comparison result.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] First, this solution solves the problem that traditional evaluation methods pay insufficient attention to the physiological and chemical characteristics of the stems. Lignin and cellulose are the key components that determine the mechanical strength and toughness of the stems. The surface of the stems is scanned by infrared spectroscopy technology, and the lignin and cellulose content is accurately predicted using a neural network prediction model, which effectively makes up for the lack of measurement of internal plant characteristics in traditional methods. Compared with traditional direct chemical detection methods, this method is fast, non-destructive and suitable for large-scale field detection, thereby significantly improving the evaluation efficiency. Secondly, by combining physiological and chemical characteristics with geometric structure parameters, a more comprehensive stalk structure stability index is constructed, which significantly improves the accuracy of the evaluation of plant lodging resistance. It makes up for the one-sidedness of traditional models and makes the evaluation results more scientific and reliable. In addition, the impact of environmental stress on the lodging resistance of corn is fully considered. By collecting environmental parameters such as wind speed, soil moisture and air temperature, the environmental adaptability index is calculated and generated, and combined with the stalk structure stability index to finally generate a comprehensive lodging resistance index. This significantly improves the accuracy, comprehensiveness, precision and efficiency of the evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0057] Figure 2 It is a schematic diagram of the overall system structure of the present invention. DETAILED DESCRIPTION

[0058] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0059] It should be noted that, 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.

[0060] Example:

[0061] See also Figure 1 , the present invention provides a technical solution:

[0062] A method for evaluating the lodging resistance of corn stalks during the flowering period, comprising the following specific steps:

[0063] Step 1: Collect several corn plants in the flowering period with known physiological characteristic parameters, perform infrared scanning on the stem surface of the collected corn plants in the flowering period, obtain sample infrared spectrum images, map each sample infrared spectrum image with the corresponding physiological characteristic parameters one by one, and generate a sample data set, wherein the physiological characteristic parameters include lignin content and cellulose content.

[0064] The specific steps of performing infrared scanning on the surface of the stem of the corn plant collected in the flowering period to obtain the sample infrared spectrum image include collecting initial spectrum data, visualizing the initial spectrum data, generating an infrared spectrum image, preprocessing the infrared spectrum image, and obtaining the sample infrared spectrum image;

[0065] The steps of collecting initial spectral data include: cleaning the surface of the sample stem, removing dust, soil and other attachments, aiming the probe of the infrared spectrometer at the surface of the stem, pressing the start button, collecting infrared spectral data of the stem surface, and recording the sample number for easy one-to-one mapping with the physiological characteristic parameters;

[0066] Using spectrum analysis software to draw the processed spectrum data into an infrared spectrum image, preprocessing the infrared spectrum image, wherein the preprocessing includes signal denoising and enhancement processing, and finally obtaining a sample infrared spectrum image;

[0067] Several corn plants in the flowering period with known physiological characteristic parameters are collected in sequence, and each sample infrared spectrum image obtained is matched one by one with the corresponding physiological characteristic parameters according to the recorded sample number to generate a sample data set.

[0068] Different chemical substances (such as lignin and cellulose) have specific infrared absorption characteristics. The chemical bonds in their molecular structures (such as CH, CO, OH, C=C, etc.) will absorb or vibrate infrared light of specific wavelengths. These absorption peaks of lignin and cellulose appear in a specific wavelength range. The main chemical component of lignin is an aromatic compound, and its characteristic absorption peaks are mainly concentrated in 1500cm⁻¹ to 1600cm⁻¹ (C=C aromatic ring stretching vibration) and 1200cm⁻¹ to 1270cm⁻¹ (COC vibration); cellulose is a polysaccharide, and its characteristic absorption peaks are mainly distributed in 1000cm⁻¹ to 1100cm⁻¹ (COC stretching vibration) and around 3300cm⁻¹ (OH group stretching vibration).

[0069] The method for performing noise reduction and enhancement processing on the collected infrared spectrum is: using a wavelet transform denoising method to perform denoising processing on the infrared spectrum image, and the specific steps of the wavelet transform denoising method include: decomposing the distortion-corrected image through wavelet transform to obtain wavelet coefficients of the image at different scales and directions; performing threshold processing on the wavelet coefficients to set the low-amplitude wavelet coefficients to zero and retain the high-amplitude wavelet coefficients; performing inverse transform on the wavelet coefficients after threshold processing, reconstructing the processed coefficients into an image, and completing the image denoising processing;

[0070] Bilateral filtering is used to enhance the details of infrared spectral images. The formula for the specific filtering transformation is:

[0071] ;

[0072] In the formula, is the coordinate vector in the image coordinate system, is the coordinate vector The gray value at Gray value The gray value after bilateral filtering transformation is are all Gaussian functions, where The formula is:

[0073] ;

[0074] ;

[0075] In the formula, is the coordinate vector in the image coordinate system, is the coordinate vector The gray value at and They are The standard deviation of .

[0076] Step 2: Establish a neural network prediction model based on the sample data set, use the sample infrared spectrum image in the sample data set as the input of the neural network prediction model, and use the corresponding physiological characteristic parameters in the sample data set as labels to train the neural network prediction model to obtain the plant physiological characteristic parameter prediction model.

[0077] A neural network prediction model is established based on the long short-term memory network LSTM model, and the activation function and optimization algorithm are selected. The Tanh function is selected as the activation function, and Adam is selected as the optimization algorithm of the LSTM model; the formula of the Tanh function is:

[0078] ;

[0079] In the formula, Represents the Tanh function, independent variable Represents the weighted sum of the neuron's input, that is, the result of weighted summation of the input received by the neuron from the previous layer;

[0080] At the same time, the hyperparameters of the LSTM model are set, and the hyperparameters of the LSTM model include: the number of network layers, the number of iterations, the learning rate, the batch size, the number of training times, the batch processing number, and the number of hidden layer neurons;

[0081] The number of network layers is set to 3 layers, the number of iterations is set to 200, the learning rate is set to 0.001, the batch size is set to 32, the number of training times is set to 100, the batch size is set to 256, and the number of hidden layer neurons is 32;

[0082] The trained plant physiological characteristic parameter prediction model takes as input the infrared spectrum image of the stem surface of corn plants in the flowering period, and outputs the predicted values ​​of physiological characteristic parameters, including the predicted values ​​of lignin content and cellulose content.

[0083] In practical applications, the lodging resistance of corn stalks may be affected by multiple factors such as lignin content and cellulose content. The relationship between these factors may be nonlinear and complex. LSTM can learn complex patterns and hidden characteristics from the input through its recursive structure and multi-layer network depth, thereby improving the prediction performance.

[0084] The physiological characteristic parameters of corn stalk lodging resistance (such as lignin and cellulose content) may change dynamically with the growth stage of the plant. LSTM can gradually process the time steps (time points) in the input sequence and effectively retain the sequence context information through memory units, thereby capturing the dynamic change trend of the time series during the prediction process.

[0085] LSTM can automatically learn the temporal relationship between features without the need for manual design of complex feature engineering. This is particularly significant when processing multidimensional data, reducing dependence on domain knowledge and improving development efficiency.

[0086] Step 3: Perform infrared scanning on the stem surface of the corn plant in the flowering period to be evaluated to obtain a target infrared spectrum image, and input the target infrared spectrum image into the trained plant physiological characteristic parameter prediction model, and the model outputs the predicted value of the physiological characteristic parameter of the corn plant in the flowering period to be evaluated.

[0087] The steps of performing infrared scanning on the stem surface of the corn plant in the flowering stage to be evaluated and obtaining the target infrared spectrum image are consistent with the above-mentioned method of obtaining the sample infrared spectrum image, which will not be described in detail here.

[0088] Step 4: Based on the predicted values ​​of the physiological characteristic parameters and the geometric structural parameters of the corn plants to be evaluated at the flowering stage, the stalk structure stability index is calculated and generated, and the environmental parameters of the corn plants to be evaluated at the flowering stage are collected. Based on the obtained environmental parameters, the environmental adaptability index is calculated and generated. The geometric structural parameters include the stalk elastic modulus, the average outer diameter of the stalk, the average thickness of the stem wall and the plant height. The environmental parameters include the average environmental wind speed, soil moisture and the average air temperature.

[0089] According to the predicted values ​​of physiological characteristic parameters, combined with the geometric structural parameters of the maize plant at the flowering stage to be evaluated, the stalk structure stability index is calculated and generated. The formula for calculating the stalk structure stability index is:

[0090] ;

[0091] In the formula, is the culm structure stability index, is the elastic modulus of the stem, is the average outer diameter of the stem, is the average thickness of the stem wall, is the plant height, Physiological influencing factors.

[0092] It should be noted that the culm structure stability index characterizes the structural stability by integrating the geometric parameters and physiological parameters of the corn plant. The larger the value, the more stable the stalk structure is and the stronger the lodging resistance is.

[0093] The elastic modulus of the stem The elastic modulus is a physical quantity that measures the material's ability to resist deformation. It reflects the rigidity and recovery ability of the stem under external force. The higher the elastic modulus, the harder it is to bend or break the stem, and the stronger its ability to resist lodging. Therefore, the elastic modulus of the stem is Stem structure stability index Directly proportional.

[0094] Average outer diameter of stem The outer diameter of the stem is the main determinant of its cross-sectional area and directly affects the stem's ability to resist bending. A larger outer diameter means a thicker stem and stronger resistance to lodging, so the average outer diameter of the stem is Stem structure stability index Proportional to the fourth power In the form of , the effect of the outer diameter is significantly amplified because the cross-sectional area and bending stiffness are extremely sensitive to changes in the outer diameter.

[0095] in The overall represents the moment of inertia of the circular cross section. Indicates the inner diameter of the stem wall (i.e. the diameter of the hollow area after removing the wall thickness). The more hollow the stem is (the thinner the wall), the lower the mechanical strength. Therefore, the inner diameter of the stem wall is closely related to the structural stability index of the stem. Inversely proportional.

[0096] Plant height It is an important factor affecting the risk of lodging. The higher the height, the higher the center of gravity. When external forces act, the longer the force arm of the stem is, and the greater the possibility of tilting or lodging. Therefore, the height of the plant Stem structure stability index Inversely proportional, the inverse relationship is represented by setting it as the denominator.

[0097] Physiological factors The calculation is based on the predicted value of the physiological characteristic parameter, and the specific formula is:

[0098] ;

[0099] In the formula, is the predicted value of lignin content, is the predicted value of cellulose content, and are the weight coefficients of the predicted values ​​of lignin content and cellulose content, respectively. and and Both are greater than 0.

[0100] It should be noted that physiological factors The larger the value, the stronger the plant's inherent characteristics are and the stronger its ability to resist lodging.

[0101] Lignin is an important component of plant cell walls, giving them rigidity and strength. Its main function is to increase the hardness and compression resistance of the stems. Cellulose is one of the main structural components of cell walls. Its main function is to give cell walls toughness and elasticity, enhancing their flexibility and resistance to fracture under mechanical stress. Therefore, the predicted value of cellulose content is and lignin content prediction Physiological factors is proportional to Represents the nonlinear contribution of lignin content. The higher the lignin content, the stronger the rigidity of the stem, and the marginal benefit of high lignin content on bending resistance is greater. Set to the denominator to represent the nonlinear effect of the predicted cellulose content on lodging resistance.

[0102] Lignin is a polymer with high hardness and rigidity. It is mainly deposited in the secondary layer of the cell wall, giving the cell wall greater mechanical strength. The higher the lignin content, the harder the stem is, and the bending and compression resistance are significantly enhanced. Therefore, lignin plays a major role in the plant's ability to resist external forces, so the design and and Both are greater than 0.

[0103] The methods for obtaining the stem elastic modulus, the average outer diameter of the stem, the average thickness of the stem wall and the plant height are as follows: using a universal material testing machine (such as a tensile testing machine or a bending testing machine) to measure the mechanical properties of the stem, calculating the elastic modulus based on the force-deformation data, or using literature data or typical values ​​(estimated values) of variety characteristics as a reference for the elastic modulus;

[0104] By randomly selecting a number of detection areas, measuring the outer diameter of the stems with a digital caliper or a vernier caliper, and taking the average value of the outer diameters of the stems in the detection areas as the average outer diameter of the stems;

[0105] The stem wall thickness was measured using a high-precision ultrasonic thickness gauge. Several test areas were also selected for measurement, and the average value of the stem wall thickness in the test areas was taken as the average stem wall thickness.

[0106] Plant height refers to the total height of a corn plant from the ground to the top. It is often used to assess the center of gravity and plant stability and can be measured directly.

[0107] Based on the obtained environmental parameters, the environmental adaptability index is calculated and generated, wherein the formula for calculating the environmental adaptability index is:

[0108] ;

[0109] In the formula, is the environmental adaptability index, is soil moisture, is the standard soil moisture, is the average air temperature, is the standard temperature value, The horizontal thrust generated by wind.

[0110] It should be noted that the environmental adaptability index The larger the value, the stronger the plant's adaptability to the environment and the stronger its ability to resist lodging.

[0111] The horizontal thrust generated by wind , plants can maintain a high adaptability under low wind force, but as the wind force increases, their adaptability will decrease rapidly, so the horizontal thrust generated by the wind Environmental adaptability index Inversely proportional, through the exponential function This means that the stronger the wind, the greater the mechanical pressure on the plant, and the probability of the stems falling or breaking increases significantly, thereby reducing their ability to survive and adapt.

[0112] The denominator combines the effects of soil moisture deviation and temperature deviation. Too high humidity reduces the root system's grip, and too high temperature may reduce the elastic modulus and hardness of the plant stems, increasing the probability of the stems falling or breaking. Therefore, soil moisture deviation and temperature deviation are both related to the environmental adaptability index. Inversely proportional, through the logarithmic function , which can compress the impact of small deviations and amplify the impact of large deviations. Slight humidity or temperature deviations have little effect on plant adaptability, but extreme deviations can bring significant adverse effects.

[0113] Among them, the soil standard humidity and standard temperature values ​​specifically refer to the optimal humidity and optimal temperature for corn growth during the flowering period. Generally take to Between, standard temperature values Generally take to between.

[0114] The horizontal thrust generated by wind It is calculated by the average wind speed of the environment and the windward area of ​​the plant. The specific calculation formula is:

[0115] ;

[0116] In the formula, is the wind pressure, is the windward area of ​​the plant, of which wind pressure The calculation is based on the formula:

[0117] ;

[0118] In the formula, is the air density, is the average ambient wind speed, is the angle between wind direction and horizontal plane.

[0119] Among them, the windward area of ​​the plant Calculated from the height and width of the plant.

[0120] Step 5: Based on the obtained environmental adaptability index and stalk structure stability index, a comprehensive lodging resistance index is calculated and generated, and the comprehensive lodging resistance index of the corn plants in the flowering period to be evaluated is compared with the lodging resistance judgment threshold, and the corresponding lodging resistance evaluation result is generated according to the comparison result.

[0121] Based on the obtained environmental adaptability index and culm structure stability index, the comprehensive lodging resistance index is calculated, and the formula for calculating the comprehensive lodging resistance index is:

[0122] ;

[0123] In the formula, is the comprehensive lodging resistance index, and are the weight coefficients of the culm structure stability index and the environmental adaptability index, respectively. and and Both are greater than 0.

[0124] The comprehensive lodging resistance index The higher the value, the stronger the plant's ability to resist lodging. It reflects the physical strength and geometric structure stability of the plant stem and is the core physical index of lodging resistance. The larger the value, the stronger the lodging resistance of the plant. It reflects the adaptability of plants to the external environment (such as wind, humidity, and temperature) and is an important external factor in lodging resistance. and stem structure stability index Comprehensive lodging resistance index is proportional to represents the application of a logarithmic function on a square basis, limiting Comprehensive lodging resistance index excessive influence.

[0125] when When it is small, taking the square root can magnify its effect (the effect of poorly adaptable environments on lodging resistance is more important); when When it is larger, the growth of the square root slows down, indicating that the environmental adaptability is close to saturation and the improvement of the ability to resist lodging is small.

[0126] Among them, the strong stem structure is the physical basis and core ability of plant resistance to lodging, so it has a greater weight. Although environmental adaptability is important, it is more of an external influencing factor. Its direct contribution to the resistance to lodging is small and its weight is relatively low, so it is set and and Both are greater than 0.

[0127] The obtained comprehensive lodging resistance index of the corn plant at the flowering stage to be evaluated is compared with the lodging resistance judgment threshold, and the corresponding lodging resistance evaluation result is generated according to the obtained comparison result, wherein the specific judgment logic is:

[0128] when When , it is judged as low lodging risk, indicating that the lodging risk of the maize plants to be evaluated during the flowering period is low and no protective measures are needed;

[0129] when When the lodging risk is judged to be medium, the lodging risk of the maize plants to be assessed during the flowering period is considered medium, and reinforcement and protection measures should be taken;

[0130] when When the lodging risk is high, it is judged as high, indicating that the lodging risk of the corn plants to be evaluated during the flowering period is high and cannot meet the normal growth requirements outdoors;

[0131] in is the lodging resistance judgment threshold, where Dynamic adjustment is made based on the height of the maize flowering plant to be evaluated and the average environmental rainfall. The specific formula is:

[0132] ;

[0133] In the formula, is the initial value of the anti-lodging force judgment threshold. is the average environmental rainfall.

[0134] Average environmental rainfall The larger the height, the greater the rainfall, which has a greater impact on plants growing in the outdoor environment. Therefore, when the rainfall is greater, the threshold should be increased to avoid missed judgments. At the same time, the higher the height, the higher the center of gravity, the longer the force arm of the stem when external forces act, and the greater the possibility of tilting or lodging. Therefore, the higher the height, the threshold should be adjusted accordingly. The environmental average rainfall is the monthly average rainfall, and relevant data can be obtained from the local meteorological department.

[0135] See also Figure 2 The present invention also provides a system for evaluating the lodging resistance of corn stalks during flowering period, wherein the system for evaluating the lodging resistance of corn stalks during flowering period is used to execute the above-mentioned method for evaluating the lodging resistance of corn stalks during flowering period, and comprises:

[0136] The sample data processing module is used to collect a number of flowering corn plants with known physiological characteristic parameters, perform infrared scanning on the stem surfaces of the collected flowering corn plants, obtain sample infrared spectrum images, and map each sample infrared spectrum image with the corresponding physiological characteristic parameters one by one to generate a sample data set, wherein the physiological characteristic parameters include lignin content and cellulose content;

[0137] A neural network training module is used to establish a neural network prediction model based on a sample data set, use the sample infrared spectrum image in the sample data set as the input of the neural network prediction model, and use the corresponding physiological characteristic parameters in the sample data set as labels to train the neural network prediction model to obtain a plant physiological characteristic parameter prediction model;

[0138] A physiological parameter prediction module is used to perform infrared scanning on the stem surface of the corn plant in the flowering period to be evaluated, obtain a target infrared spectrum image, input the target infrared spectrum image into the trained plant physiological characteristic parameter prediction model, and the model outputs the predicted value of the physiological characteristic parameter of the corn plant in the flowering period to be evaluated;

[0139] A related index analysis module is used to calculate and generate a stalk structure stability index based on the predicted value of the physiological characteristic parameter in combination with the geometric structure parameters of the maize plant in the flowering period to be evaluated, and collect the environmental parameters of the maize plant in the flowering period to be evaluated, and calculate and generate an environmental adaptability index based on the obtained environmental parameters, wherein the geometric structure parameters include the stalk elastic modulus, the average outer diameter of the stalk, the average thickness of the stem wall and the plant height, and the environmental parameters include the average environmental wind speed, soil humidity and average air temperature;

[0140] The comprehensive lodging resistance evaluation module is used to calculate and generate a comprehensive lodging resistance index based on the obtained environmental adaptability index and stalk structure stability index, compare the obtained comprehensive lodging resistance index of the corn plants in the flowering period to be evaluated with the lodging resistance judgment threshold, and generate a corresponding lodging resistance evaluation result based on the comparison result.

[0141] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0142] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0143] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0144] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for evaluating the lodging resistance of corn stalks during flowering period, characterized in that: The specific steps include: Collecting a number of corn plants at the flowering stage with known physiological characteristic parameters, performing infrared scanning on the surfaces of the stems of the collected corn plants at the flowering stage to obtain sample infrared spectrum images, and mapping each sample infrared spectrum image with the corresponding physiological characteristic parameters one by one to generate a sample data set, wherein the physiological characteristic parameters include lignin content and cellulose content; A neural network prediction model is established based on the sample data set, the sample infrared spectrum image in the sample data set is used as the input of the neural network prediction model, and the corresponding physiological characteristic parameters in the sample data set are used as labels, the neural network prediction model is trained, and a plant physiological characteristic parameter prediction model is obtained; Performing infrared scanning on the stem surface of the corn plant in the flowering period to be evaluated to obtain a target infrared spectrum image, inputting the target infrared spectrum image into the trained plant physiological characteristic parameter prediction model, and the model outputs the predicted value of the physiological characteristic parameter of the corn plant in the flowering period to be evaluated; According to the predicted value of the physiological characteristic parameter, combined with the geometric structure parameters of the maize plant in the flowering period to be evaluated, the stalk structure stability index is calculated and generated, and the environmental parameters of the maize plant in the flowering period to be evaluated are collected, and based on the obtained environmental parameters, the environmental adaptability index is calculated and generated, the geometric structure parameters include the stalk elastic modulus, the average outer diameter of the stalk, the average thickness of the stem wall and the plant height, and the environmental parameters include the average environmental wind speed, soil moisture and average air temperature; Based on the obtained environmental adaptability index and stalk structure stability index, a comprehensive lodging resistance index is calculated and generated, and the comprehensive lodging resistance index of the corn plants in the flowering period to be evaluated is compared with the lodging resistance judgment threshold. According to the comparison results, the corresponding lodging resistance evaluation results are generated.

2. The method for evaluating the lodging resistance of corn stalks during flowering period according to claim 1, characterized in that: The specific steps of performing infrared scanning on the surface of the stem of the corn plant collected in the flowering period to obtain the sample infrared spectrum image include collecting initial spectrum data, visualizing the initial spectrum data, generating an infrared spectrum image, preprocessing the infrared spectrum image, and obtaining the sample infrared spectrum image; The steps of collecting initial spectral data include: cleaning the surface of the sample stem, removing dust, soil and other attachments, aiming the probe of the infrared spectrometer at the surface of the stem, pressing the start button, collecting infrared spectral data of the stem surface, and recording the sample number for easy one-to-one mapping with the physiological characteristic parameters; Using spectrum analysis software to draw the processed spectrum data into an infrared spectrum image, preprocessing the infrared spectrum image, wherein the preprocessing includes signal denoising and enhancement processing, and finally obtaining a sample infrared spectrum image; Several corn plants in the flowering period with known physiological characteristic parameters are collected in sequence, and each sample infrared spectrum image obtained is matched one by one with the corresponding physiological characteristic parameters according to the recorded sample number to generate a sample data set.

3. A method for evaluating the lodging resistance of corn stalks during flowering period according to claim 2, characterized in that: A neural network prediction model is established based on the long short-term memory network LSTM model, and the activation function and optimization algorithm are selected. The Tanh function is selected as the activation function, and Adam is selected as the optimization algorithm of the LSTM model; the formula of the Tanh function is: ； In the formula, Represents the Tanh function, independent variable Represents the weighted sum of the neuron's input, that is, the result of weighted summation of the input received by the neuron from the previous layer; At the same time, the hyperparameters of the LSTM model are set, and the hyperparameters of the LSTM model include: the number of network layers, the number of iterations, the learning rate, the batch size, the number of training times, the batch processing number, and the number of hidden layer neurons; The number of network layers is set to 3 layers, the number of iterations is set to 200, the learning rate is set to 0.001, the batch size is set to 32, the number of training times is set to 100, the batch size is set to 256, and the number of hidden layer neurons is 32; The trained plant physiological characteristic parameter prediction model takes as input the infrared spectrum image of the stem surface of corn plants in the flowering period, and outputs the predicted values ​​of physiological characteristic parameters, including the predicted values ​​of lignin content and cellulose content.

4. The method for evaluating the lodging resistance of corn stalks during flowering period according to claim 3, characterized in that: According to the predicted values ​​of physiological characteristic parameters, combined with the geometric structural parameters of the maize plant at the flowering stage to be evaluated, the stalk structure stability index is calculated and generated. The formula for calculating the stalk structure stability index is: ； In the formula, is the culm structure stability index, is the elastic modulus of the stem, is the average outer diameter of the stem, is the average thickness of the stem wall, is the plant height, It is a physiological influencing factor; Physiological factors The calculation is based on the predicted value of the physiological characteristic parameter, and the specific formula is: ； In the formula, is the predicted value of lignin content, is the predicted value of cellulose content, and are the weight coefficients of the predicted values ​​of lignin content and cellulose content, respectively. and and Both are greater than 0.

5. The method for evaluating the lodging resistance of corn stalks during flowering period according to claim 4, characterized in that: Based on the obtained environmental parameters, the environmental adaptability index is calculated and generated, wherein the formula for calculating the environmental adaptability index is: ； In the formula, is the environmental adaptability index, is soil moisture, is the standard soil moisture, is the average air temperature, is the standard temperature value, The horizontal thrust generated by wind is It is calculated by the average wind speed of the environment and the windward area of ​​the plant. The specific calculation formula is: ； In the formula, is the wind pressure, is the windward area of ​​the plant, of which wind pressure The calculation is based on the formula: ； In the formula, is the air density, is the average ambient wind speed, is the angle between wind direction and horizontal plane.

6. A method for evaluating the lodging resistance of corn stalks during flowering period according to claim 5, characterized in that: Based on the obtained environmental adaptability index and culm structure stability index, the comprehensive lodging resistance index is calculated, and the formula for calculating the comprehensive lodging resistance index is: ； In the formula, is the comprehensive lodging resistance index, and are the weight coefficients of the culm structure stability index and the environmental adaptability index, respectively. and and Both are greater than 0.

7. A method for evaluating the lodging resistance of corn stalks during flowering period according to claim 6, characterized in that: The obtained comprehensive lodging resistance index of the corn plant at the flowering stage to be evaluated is compared with the lodging resistance judgment threshold, and the corresponding lodging resistance evaluation result is generated according to the obtained comparison result, wherein the specific judgment logic is: when When , it is judged as low lodging risk, indicating that the lodging risk of the maize plants to be evaluated during the flowering period is low and no protective measures are needed; when When the lodging risk is judged to be medium, the lodging risk of the maize plants to be assessed during the flowering period is considered medium, and reinforcement and protection measures should be taken; when When the lodging risk is high, it is judged as high, indicating that the lodging risk of the corn plants to be evaluated during the flowering period is high and cannot meet the normal growth requirements outdoors; in is the lodging resistance judgment threshold, where Dynamic adjustment is made based on the height of the maize flowering plant to be evaluated and the average environmental rainfall. The specific formula is: ； In the formula, is the initial value of the anti-lodging force judgment threshold. is the average environmental rainfall.

8. A system for evaluating the lodging resistance of corn stalks during flowering period, characterized in that: The system for evaluating the lodging resistance of corn stalks during flowering period is used to implement the method for evaluating the lodging resistance of corn stalks during flowering period according to any one of claims 1 to 7, comprising: The sample data processing module is used to collect a number of flowering corn plants with known physiological characteristic parameters, perform infrared scanning on the stem surfaces of the collected flowering corn plants, obtain sample infrared spectrum images, and map each sample infrared spectrum image with the corresponding physiological characteristic parameters one by one to generate a sample data set, wherein the physiological characteristic parameters include lignin content and cellulose content; A neural network training module is used to establish a neural network prediction model based on a sample data set, use the sample infrared spectrum image in the sample data set as the input of the neural network prediction model, and use the corresponding physiological characteristic parameters in the sample data set as labels to train the neural network prediction model to obtain a plant physiological characteristic parameter prediction model; A physiological parameter prediction module is used to perform infrared scanning on the stem surface of the corn plant in the flowering period to be evaluated, obtain a target infrared spectrum image, input the target infrared spectrum image into the trained plant physiological characteristic parameter prediction model, and the model outputs the predicted value of the physiological characteristic parameter of the corn plant in the flowering period to be evaluated; A related index analysis module is used to calculate and generate a stalk structure stability index based on the predicted value of the physiological characteristic parameter in combination with the geometric structure parameters of the maize plant in the flowering period to be evaluated, and collect the environmental parameters of the maize plant in the flowering period to be evaluated, and calculate and generate an environmental adaptability index based on the obtained environmental parameters, wherein the geometric structure parameters include the stalk elastic modulus, the average outer diameter of the stalk, the average thickness of the stem wall and the plant height, and the environmental parameters include the average environmental wind speed, soil humidity and average air temperature; The comprehensive lodging resistance evaluation module is used to calculate and generate a comprehensive lodging resistance index based on the obtained environmental adaptability index and stalk structure stability index, compare the obtained comprehensive lodging resistance index of the corn plants in the flowering period to be evaluated with the lodging resistance judgment threshold, and generate a corresponding lodging resistance evaluation result based on the comparison result.

Images