Maize variety waterlogging tolerance evaluation method and system based on data analysis

Abstract

The invention discloses a corn variety waterlogging tolerance evaluation method and system based on data analysis, and relates to the technical field of corn variety waterlogging tolerance evaluation.The corn variety waterlogging tolerance evaluation method comprises the following steps that according to existing monitoring requirements, an initial monitoring frequency is set for corn leaf information collection; after the initial monitoring frequency is set, regularly collecting corn leaf information according to the initial monitoring frequency; and along with the acquisition of the corn leaf data, comparing the currently acquired corn leaf data with the corn leaf data acquired last time. According to the method, the change trend of the corn leaves is accurately predicted through the pre-trained convolutional neural network, the monitoring frequency is automatically adjusted, the accuracy and the real-time performance of waterlogging tolerance evaluation are remarkably improved, the dynamic adjustment mechanism optimizes resource utilization, invalid high-frequency collection is avoided, the monitoring efficiency is improved, meanwhile, quick response is achieved in an emergent environment, and the method is suitable for popularization and application. The agricultural production stability is ensured, the anti-risk capability of corn is enhanced, and the stability of crop yield is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of waterlogging resistance evaluation of corn varieties, and in particular to a method and system for evaluating waterlogging resistance of corn varieties based on data analysis. Background Art

[0002] The corn variety waterlogging tolerance evaluation system is a comprehensive evaluation tool based on data analysis. It evaluates the waterlogging tolerance of different corn varieties by collecting and analyzing key indicator data during corn growth. The system collects crop physiological characteristics such as corn leaves, plant height, yield, disease resistance, as well as meteorological data and soil moisture data, and uses algorithms to generate a waterlogging tolerance index. The system can identify corn varieties with strong waterlogging tolerance in waterlogging-prone areas to guide farmers to select high-quality varieties suitable for planting in wet and waterlogged environments, thereby improving yield stability and agricultural risk resistance.

[0003] In the process of evaluating the waterlogging tolerance of corn varieties, it is important to collect information about corn leaves, because leaves are the main organ for photosynthesis in corn, and their health directly reflects the plant's ability to respond to environmental stress. In a waterlogged environment, leaves will wilt, turn yellow, and dry up at the edges. These changes are the result of plants suffering from excess water and insufficient oxygen. Therefore, by monitoring parameters such as leaf color, shape, size, and water content of leaf tissue, the physiological response of corn plants to waterlogging can be accurately evaluated, providing key data support for waterlogging tolerance evaluation. This information can help predict the growth performance of corn varieties under waterlogging conditions, thereby determining their waterlogging tolerance.

[0004] The prior art has the following deficiencies:

[0005] Existing technologies usually use a fixed monitoring frequency to collect information on corn leaves, and collect data regularly based on preset time intervals. This helps to simplify the monitoring process and ensure the stability and consistency of data collection. However, although this fixed frequency method can provide continuous monitoring data, in the face of different environmental conditions, especially sudden stress environments such as waterlogging, the physiological changes of corn leaves are often rapid, and fixed collection intervals may not be able to capture these key changes in real time, resulting in missing important reaction time points, thereby affecting the accuracy and timeliness of waterlogging resistance assessment.

[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 purpose of the present invention is to provide a method and system for evaluating the waterlogging resistance of corn varieties based on data analysis. The changing trend of corn leaves is accurately predicted and classified by a pre-trained convolutional neural network, which can effectively distinguish between rapid changes and conventional changes. When rapid changes are detected, the system automatically adjusts the monitoring frequency, greatly increases the acquisition frequency, ensures that key physiological change data are captured in a timely manner, and significantly improves the accuracy and real-time performance of waterlogging resistance assessment. At the same time, dynamically adjusting the acquisition frequency optimizes resource utilization, avoids invalid acquisition, and improves monitoring efficiency. It not only solves the problem that the fixed monitoring frequency cannot reflect the rapid changes of corn leaves in real time, but also ensures the efficient operation of the system under conventional and emergency conditions, improves the risk resistance and yield stability of corn, so as to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: a method for evaluating waterlogging resistance of corn varieties based on data analysis, comprising the following steps:

[0009] According to the existing monitoring needs, an initial monitoring frequency is set for corn leaf information collection;

[0010] After the initial monitoring frequency is set, the corn leaf information is collected regularly according to the initial monitoring frequency;

[0011] As the corn leaf data is collected, the currently collected corn leaf data is compared with the corn leaf data collected last time to form a comparison set to track the changes in the current corn leaves;

[0012] After establishing the comparison set, the two adjacent monitoring data in the comparison set are compared and analyzed, and the data after comparison and analysis are input into the pre-trained convolutional neural network to predict the current changes in corn leaves;

[0013] Based on the prediction results of convolutional neural networks, the current changes in corn leaves are divided into two categories: rapid changes and regular changes;

[0014] If the current changes in corn leaves are normal changes, continue to collect data according to the initial monitoring frequency;

[0015] If it is detected that the current changes in the corn leaves are rapid, the actual monitoring frequency will be automatically adjusted according to the changes in the corn leaves. Specifically, the collection frequency will be greatly increased to ensure that all key data in the changing process can be captured.

[0016] Preferably, after establishing a comparison set, the two adjacent monitoring data in the comparison set are compared and analyzed, and the changes in the degree of dryness of the corn leaf edges and the changes in the chlorophyll content in the corn leaves are extracted. After comparing and analyzing the changes in the degree of dryness of the corn leaf edges and the changes in the chlorophyll content in the corn leaves, a leaf edge dryness index and a chlorophyll degradation index are generated respectively. The leaf edge dryness index is used to measure the changes in the degree of dryness of the corn leaf edges, reflecting the damage of the leaves under environmental stress conditions. The chlorophyll degradation index is used to measure the changes in the chlorophyll content in the corn leaves, reflecting the decrease in photosynthesis efficiency and the deterioration of leaf health.

[0017] Preferably, after obtaining the leaf edge dryness index and chlorophyll degradation index generated by comparing and analyzing two adjacent monitoring data in the comparison set, the leaf edge dryness index and chlorophyll degradation index are input into a pre-trained convolutional neural network to generate a change trend evaluation coefficient, and the change trend evaluation coefficient is used to predict the current changes in corn leaves.

[0018] Preferably, the change trend assessment coefficient generated by predicting two adjacent monitoring data in the comparison set by the convolutional neural network is compared and analyzed with a preset reference threshold of the change trend assessment coefficient, and the change situation of the current corn leaves is divided. The specific division steps are as follows:

[0019] If the change trend assessment coefficient is greater than or equal to the change trend assessment coefficient reference threshold, the change of the current corn leaf is classified as a rapid change, and the rapid change indicates that the current corn leaf has undergone a drastic physiological change in a short period of time;

[0020] If the change trend assessment coefficient is less than the change trend assessment coefficient reference threshold, the current change of the corn leaves is classified as a normal change. The normal change indicates that the growth state of the current corn leaves is within the normal range, and the physiological characteristics gradually change with the growth cycle.

[0021] Preferably, the specific steps of comparing and analyzing two adjacent monitoring data in the comparison set, extracting the change in the degree of dryness of the corn leaf edges, and generating the leaf edge dryness index after comparing and analyzing the change in the degree of dryness of the corn leaf edges are as follows:

[0022] Based on the data from two adjacent monitorings, the corn leaf images were processed to extract the change information of the corn leaf edges. The leaf edge contours at each monitoring time point were generated through the image processing algorithm. Then, the change rate of the dry part of the corn leaf edge between two adjacent monitorings was calculated. The calculation expression is:

[0023] ,

[0024] Where ΔE t represents the edge drying change rate, Ct and C t-1 are the edge contour areas of corn leaves in the current and last monitoring, respectively, and A t is the overall area of ​​the corn leaf to avoid interference of the overall size of the corn leaf on the calculation results;

[0025] On the basis of extracting the dry area, the changes in the details of the corn leaf edge are further analyzed. The local curvature of the corn leaf edge and the refinement of the dry edge are taken as key parameters. The severity of the dryness of the corn leaf edge is described by point-by-point curvature changes, and the degree of change in the details of the dry edge is quantified. The specific quantitative expression is: In the formula, K t is the total curvature change of the dry edge, κ t (i) and κ t-1 (i) are the curvatures of the i-th edge point in the current and last monitoring, respectively, and n is the total number of edge points;

[0026] The final leaf edge drying index is generated by introducing the edge drying change rate and the total amount of curvature change of the drying edge to comprehensively quantify the degree of corn leaf edge drying. The expression for the leaf edge drying index is: t =α·ΔE t +β·(K t ) γ , where EDI t is the leaf edge drying index, α and β are the weight coefficients of the edge drying change rate and the total curvature change, respectively, and γ is the adjustment factor to enhance the sensitivity to curvature changes.

[0027] Preferably, the specific steps of comparing and analyzing two adjacent monitoring data in the comparison set, extracting the change of chlorophyll content in corn leaves, and generating the chlorophyll degradation index after comparing and analyzing the change of chlorophyll content in corn leaves are as follows:

[0028] Extract the chlorophyll content from the corn leaf data collected twice in succession, and assume that the chlorophyll content at the t1th collection is The chlorophyll content at the t2th collection was Calculate the chlorophyll change between two monitorings using the following formula: In the formula, ΔR represents the change in chlorophyll content between two monitoring periods;

[0029] The acceleration coefficient is introduced to reflect the acceleration of the chlorophyll content change rate, and the chlorophyll content change is amplified by a nonlinear formula. The specific amplification expression is:

[0030] ,

[0031] Where λ is the chlorophyll degradation acceleration coefficient, which measures the acceleration effect of chlorophyll loss, τ 12 is the time interval between two adjacent monitorings, and k is the adjustment index, which is used to amplify or reduce the acceleration degree of the change;

[0032] The chlorophyll degradation index is generated by combining the change in chlorophyll content with the chlorophyll degradation acceleration coefficient. The specific expression generated is:

[0033] ,

[0034] In the formula, δ chlor is the chlorophyll degradation index, and the final δ chlor Numerical values ​​are used to quantify the extent of chlorophyll degradation.

[0035] Preferably, the actual monitoring frequency is automatically adjusted according to the changes in the corn leaves, and the specific steps are as follows:

[0036] Calculate the deviation between the change trend assessment coefficient and the change trend assessment coefficient reference threshold to obtain the change trend deviation coefficient Δ δ , Δ δ =Chang trend -δ threshold Among them, Chang trend is the change trend evaluation coefficient generated based on the convolutional neural network, reflecting the degree of change of corn leaves, δ threshold It is a preset reference threshold value of the change trend assessment coefficient, which is used to distinguish between rapid changes and regular changes;

[0037] According to the variation trend deviation coefficient Δ δ , calculate the monitoring frequency adjustment factor, and use a nonlinear function to enhance the response to rapid changes. The calculation expression of the monitoring frequency adjustment factor is: Where, φ is the monitoring frequency adjustment factor, which is used to adjust the actual monitoring frequency, and w is the sensitivity coefficient, which controls the growth rate of the monitoring frequency adjustment factor;

[0038] Using the initial monitoring frequency and the monitoring frequency adjustment factor, the actual monitoring frequency after adjustment is calculated. The calculation expression is: actual =f initial ·φ, where f initial is the initial monitoring frequency, f actual The actual monitoring frequency after adjustment will be used for subsequent data collection;

[0039] In order to avoid excessive consumption of system resources due to excessive monitoring frequency, the upper limit of the actual monitoring frequency is set and the actual monitoring frequency is adjusted. The expression of the adjusted actual monitoring frequency is: actual =min(f actual , fmax ), where f max is the maximum allowable value of the actual monitoring frequency. The min(·) function takes the smaller of the two values ​​in the brackets to ensure that the actual monitoring frequency f actual Not exceeding the maximum permissible value f of the actual monitoring frequency max ;

[0040] According to the actual monitoring frequency f calculated actual , update the monitoring plan of the data acquisition system to perform high-frequency collection according to the new frequency to ensure that the key data in the change process of corn leaves is captured. At the same time, continue to monitor the change trend assessment coefficient. If the subsequent change trend assessment coefficient drops below the change trend assessment coefficient reference threshold, it will be restored to the initial monitoring frequency.

[0041] A corn variety waterlogging tolerance evaluation system based on data analysis, comprising an initial monitoring frequency setting module, a regular data collection module, a data comparison set generation module, a convolutional neural network prediction module, a change classification module, a conventional change monitoring module and a rapid change frequency adjustment module;

[0042] The initial monitoring frequency setting module sets an initial monitoring frequency for corn leaf information collection according to existing monitoring requirements;

[0043] A regular data collection module, after setting the initial monitoring frequency, regularly collects corn leaf information according to the initial monitoring frequency;

[0044] The data comparison set generation module compares the currently collected corn leaf data with the last collected corn leaf data as the corn leaf data is collected, forming a comparison set to track the changes of the current corn leaf;

[0045] The convolutional neural network prediction module, after establishing the comparison set, performs comparison and analysis on two adjacent monitoring data in the comparison set, inputs the compared and analyzed data into the pre-trained convolutional neural network, and predicts the current changes in corn leaves;

[0046] The change classification module, based on the prediction results of the convolutional neural network, divides the current changes of corn leaves into two categories: rapid changes and regular changes;

[0047] Conventional change monitoring module: if the current change of corn leaves is a regular change, it will continue to collect data according to the initial monitoring frequency;

[0048] The rapid change frequency adjustment module automatically adjusts the actual monitoring frequency according to the changes in the corn leaves if it detects that the current changes in the corn leaves are rapid. Specifically, it greatly increases the collection frequency to ensure that all key data in the change process can be captured.

[0049] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0050] The present invention uses a pre-trained convolutional neural network to accurately predict and classify the changing trends of corn leaves, and can effectively distinguish between rapid changes and regular changes. When rapid changes in corn leaves are detected, the system automatically adjusts the monitoring frequency, greatly increases the collection frequency, and ensures that all key physiological change data are captured in a timely manner, thereby significantly improving the accuracy and real-time performance of waterlogging resistance assessment. The mechanism of dynamically adjusting the collection frequency optimizes resource utilization, avoids ineffective high-frequency collection, and greatly improves monitoring efficiency. It not only solves the problem that traditional fixed monitoring frequencies cannot reflect the rapid changes of corn leaves in real time, but also ensures the efficient operation of the system under normal conditions, and can respond quickly in emergency environments, ensuring the stability of agricultural production, providing a more scientific and reliable decision-making basis for the waterlogging resistance assessment of corn varieties, significantly enhancing the risk resistance of corn, and helping to improve the stability of crop yields. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0052] Figure 1 The present invention is a method flow chart of a method for evaluating waterlogging resistance of corn varieties based on data analysis.

[0053] Figure 2 The present invention is a schematic diagram of a module of a corn variety waterlogging resistance evaluation system based on data analysis. DETAILED DESCRIPTION

[0054] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0055] The present invention provides Figure 1 A method for evaluating waterlogging resistance of corn varieties based on data analysis is shown, comprising the following steps:

[0056] According to the existing monitoring needs, an initial monitoring frequency is set for corn leaf information collection;

[0057] The initial monitoring frequency should take into account the changing patterns of corn leaves under normal growth conditions, and combine the different stages of corn growth and external environmental conditions (such as temperature, humidity, etc.) to develop a basic standard for the leaf collection interval. On this basis, the initial monitoring frequency can be optimized through long-term accumulated historical data to ensure that sufficient monitoring data can be provided under normal circumstances, thereby laying the foundation for subsequent dynamic adjustments. At the same time, the initial frequency setting must take into account the consumption of system resources, ensuring both the effective collection of information and avoiding unnecessary system pressure caused by excessively high frequencies.

[0058] After the initial monitoring frequency is set, the corn leaf information is collected regularly according to the initial monitoring frequency;

[0059] Sensors, image analysis equipment or drone monitoring systems are used to obtain leaf data, such as leaf color, shape, size, water content and other physiological characteristics. In order to ensure the accuracy and consistency of the data, the acquisition equipment needs to have high precision and be able to adapt to the complex environmental conditions in the field. During the data collection process, the impact of factors such as weather and light changes on data quality must also be considered. Therefore, the integration of multiple sensor devices can be introduced to improve the diversity and stability of data collection.

[0060] The collection equipment specifically includes spectral sensors, RGB and multispectral cameras, near-infrared sensors (for monitoring the moisture content of leaves), laser scanners (for measuring the shape and size of leaves), temperature and humidity sensors (for monitoring environmental conditions), and a combination of high-resolution cameras and sensors carried by drones. These devices can be used in combination to collect physiological characteristics such as color, shape, size and moisture content of corn leaves. At the same time, they have anti-interference capabilities in complex field environments, ensuring that they can still provide high-precision data under different lighting and weather conditions.

[0061] As the corn leaf data is collected, the currently collected corn leaf data is compared with the corn leaf data collected last time to form a comparison set to track the changes in the current corn leaves;

[0062] During the corn leaf data collection process, each new data collected will be compared and analyzed with the old data collected previously. By comparing the current corn leaf data (such as color, shape, size, water content, etc.) with the data collected last time, the system can identify changes in the leaves over a period of time. This comparison can help monitor the growth trend of corn leaves or the physiological response to environmental changes, determine whether the leaves have significant changes, and then decide whether it is necessary to adjust the monitoring frequency or take other management measures.

[0063] After establishing the comparison set, the two adjacent monitoring data in the comparison set are compared and analyzed, and the data after comparison and analysis are input into the pre-trained convolutional neural network to predict the current changes in corn leaves;

[0064] After establishing the comparison set, the two adjacent monitoring data in the comparison set are compared and analyzed to extract the changes in the degree of dryness of corn leaf edges and the changes in chlorophyll content in corn leaves. After comparing and analyzing the changes in the degree of dryness of corn leaf edges and the changes in chlorophyll content in corn leaves, a leaf edge dryness index and a chlorophyll degradation index are generated respectively. The leaf edge dryness index is used to measure the changes in the degree of dryness of corn leaf edges, reflecting the damage of leaves under environmental stress conditions. The chlorophyll degradation index is used to measure the changes in chlorophyll content in corn leaves, reflecting the decline in photosynthesis efficiency and the deterioration of leaf health.

[0065] After obtaining the leaf edge drying index and chlorophyll degradation index generated by comparing and analyzing two adjacent monitoring data in the comparison set, the leaf edge drying index and chlorophyll degradation index are input into the pre-trained convolutional neural network to generate a change trend evaluation coefficient, and the change trend evaluation coefficient is used to predict the current changes in corn leaves.

[0066] A pre-trained convolutional neural network refers to a neural network model that has been learned and optimized through a large amount of historical data. It is specifically used to analyze input images or time series data to help identify the changing trends of corn leaves. In this context, the input data of the convolutional neural network is the leaf edge dryness index and chlorophyll degradation index generated based on leaf monitoring information. Through the input of these indices, the convolutional neural network can automatically extract and identify the hidden features and patterns in the process of leaf changes. Unlike traditional analysis methods, convolutional neural networks can extract important local features from complex multidimensional data through adaptive learning, and gradually abstract through a hierarchical structure to discover nonlinear relationships. This makes it particularly suitable for dealing with the problem of evaluating physiological changes in corn leaves.

[0067] In the prediction of the changing trend of corn leaves, the convolutional neural network has learned to identify the typical characteristics of leaf changes under various environmental stress conditions through training on a large amount of historical data of corn leaves, and summarized the change patterns that can reflect the health of leaves. This pre-trained model not only has the ability to identify individual changes (such as chlorophyll decline and leaf edge drying), but also can comprehensively analyze the synergistic effects of multiple physiological changes through the correlation between data. Through layers of convolution and pooling operations, the model gradually simplifies and refines the input leaf edge drying index and chlorophyll degradation index, learns from them the changing trend of leaves under waterlogging or other environmental stresses, and finally generates a change trend evaluation coefficient. This change trend evaluation coefficient can be used to quantify the current health status of leaves, help predict whether the leaves will show a trend of accelerated deterioration or gradual recovery in the future, and thus provide agricultural managers with accurate decision-making basis.

[0068] If the change in the degree of dryness of the edges of the currently collected corn leaves suddenly accelerates, it indicates that the change trend of the corn leaves is changing rapidly under the waterlogged environment. This sudden intensification of dryness is usually the result of strong environmental stress on corn plants, such as long-term flooding or soil hypoxia, which leads to leaf water loss and increased cell damage. Therefore, the rapid deterioration of the degree of dryness at the edges can be regarded as a direct manifestation of the impact of waterlogging on corn leaves, indicating that the current physiological state of the leaves is deteriorating sharply and the plants may face greater growth pressure.

[0069] The specific steps of comparing and analyzing two adjacent monitoring data in the comparison set, extracting the changes in the dryness degree of the corn leaf edges, and generating the leaf edge dryness index after comparing and analyzing the changes in the dryness degree of the corn leaf edges are as follows:

[0070] Based on the data from two adjacent monitorings, the corn leaf images were processed to extract the change information of the corn leaf edges. The leaf edge contours at each monitoring time point were generated through the image processing algorithm. Then, the change rate of the dry part of the corn leaf edge between two adjacent monitorings was calculated. The calculation expression is:

[0071]

[0072] , where ΔE t represents the edge drying change rate, C t and C t-1 are the edge contour areas of corn leaves in the current and last monitoring, respectively, and A t is the overall area of ​​the corn leaf to avoid interference of the overall size of the corn leaf on the calculation results;

[0073] The image processing algorithms that can be used include Canny edge detection, Sobel operator, Laplacian edge detection, and Active Contour model (snake algorithm). Canny edge detection is a classic and efficient edge detection method that can accurately locate the edge of corn leaves and is suitable for high-noise environments. The Sobel operator extracts edge information by calculating the brightness gradient in the image, and is suitable for detecting smoother leaf edges. Laplacian edge detection obtains edge features that change dramatically in the image through the second-order derivative, and is particularly suitable for high-contrast areas. The Active Contour model is a contour-based segmentation method that can adaptively adjust the contour boundary as the leaf edge changes dynamically, and is used to more accurately capture the edges of leaves with complex shapes. Combining these algorithms can generate high-precision leaf edge contours to meet the needs of comparative analysis.

[0074] By calculating the change in edge contour area, the direct changes in the degree of dryness of the corn leaf edges are captured, with a focus on the changes in the dry edges relative to the overall area of ​​the corn leaf.

[0075] On the basis of extracting the dry area, the changes in the details of the corn leaf edge are further analyzed. The local curvature of the corn leaf edge and the refinement of the dry edge are taken as key parameters. The severity of the dryness of the corn leaf edge is described by point-by-point curvature changes, and the degree of change in the details of the dry edge is quantified. The specific quantitative expression is: In the formula, K t is the total curvature change of the dry edge, κ t (i) and κ t-1 (i) is the curvature of the i-th edge point in the current and last monitoring (corn leaf information monitoring), respectively, and n is the total number of edge points;

[0076] The change in curvature reflects the degree of drying of the leaf edge, especially when it dries quickly, the bending and damage of the edge will be more obvious. This step further quantifies the degree of drying of the edge by analyzing the geometric changes of the leaf edge.

[0077] The final leaf edge drying index is generated by introducing the edge drying change rate and the total amount of curvature change of the drying edge to comprehensively quantify the degree of corn leaf edge drying. The expression for the leaf edge drying index is: t =α·ΔE t +β·(K t ) γ , where EDI t is the leaf edge drying index, α and β are the weight coefficients of the edge drying change rate and the total curvature change, respectively, which are adjusted based on different experimental environments, and γ is the adjustment factor to enhance the sensitivity to curvature changes;

[0078] This step combines the edge drying change rate and the total curvature change of the dried edge. The leaf edge drying index is generated through a nonlinear combination of the two to reflect the degree of edge drying of corn leaves under environmental stress. The weight coefficients α, β and parameter γ can be adjusted according to the specific application scenario, so that the index can flexibly adapt to the changes of corn leaves in different growth environments.

[0079] It can be seen from the leaf edge dryness index that under waterlogging conditions, the larger the performance value of the leaf edge dryness index generated after comparing and analyzing the changes in the degree of dryness of the corn leaves, the greater the change in the current corn leaves compared to the last monitoring. This means that the degree of dryness of the corn leaves has intensified, and the leaf tissue may be seriously damaged due to continuous environmental stress. The leaf edge dryness index can intuitively reflect the health status of the leaves at different time points and the degree of waterlogging by quantifying the changes in the dry edges. Therefore, the larger the leaf edge dryness index, the faster the physiological state of the leaves deteriorates, and the range and degree of dryness of the edges increase significantly.

[0080] If the chlorophyll content in the currently collected corn leaf data decreases rapidly, it usually indicates that the change trend of corn leaves in a waterlogged environment is occurring rapidly. Chlorophyll is a key substance for plant photosynthesis. Waterlogging causes root hypoxia and blocked nutrient absorption, which directly affects the production and maintenance of chlorophyll, causing its content to drop rapidly. This rapid decrease usually reflects the physiological stress response of the plant in response to environmental pressure, indicating that the corn leaves are in a state of severe damage, and the overall health of the plant is rapidly deteriorating, which is a rapid change trend.

[0081] The specific steps of comparing and analyzing two adjacent monitoring data in the comparison set, extracting the changes in chlorophyll content in corn leaves, and generating the chlorophyll degradation index after comparing and analyzing the changes in chlorophyll content in corn leaves are as follows:

[0082] Extract the chlorophyll content from the corn leaf data collected twice in succession, and assume that the chlorophyll content at the t1th collection is The chlorophyll content at the t2th collection was Calculate the chlorophyll change between two monitorings using the following formula: In the formula, ΔR represents the change in chlorophyll content between two monitoring periods;

[0083] A greater change in chlorophyll content indicates a rapid loss of chlorophyll, which is usually related to the degree of environmental stress on the plant;

[0084] Chlorophyll content can be accurately measured using advanced spectral sensors or near-infrared (NIR) technology. Spectral sensors detect the chlorophyll content in leaves by analyzing the reflection or absorption characteristics of light at different wavelengths, especially in the red and near-infrared regions, because chlorophyll has significant absorption characteristics for these specific bands of light. Near-infrared technology indirectly estimates the concentration of chlorophyll by capturing the reflection of near-infrared light by water and other components in the leaves. Both technologies can monitor the health of plants in real time in a non-destructive manner and have high spatial and temporal resolution, allowing researchers to accurately capture the dynamic changes of chlorophyll under complex field conditions. These technologies are not only suitable for monitoring individual leaves, but can also be used to achieve large-scale crop health assessments in farmland through sensors carried by drones or satellites.

[0085] The acceleration coefficient is introduced to reflect the acceleration of the chlorophyll content change rate, and the chlorophyll content change is amplified by a nonlinear formula. The specific amplification expression is:

[0086] ,

[0087] Where λ is the chlorophyll degradation acceleration coefficient, which measures the acceleration effect of chlorophyll loss. A larger λ value means a rapid decrease in chlorophyll content, indicating that the plant is experiencing severe stress. 12 is the time interval between two adjacent monitorings, indicating the changes that occur in the blade within a certain period of time; κ is the adjustment index, which is used to amplify or reduce the acceleration of the change. It is usually adjusted according to experimental data, and the typical value is between 1.5 and 2.5;

[0088] The chlorophyll degradation index is generated by combining the change in chlorophyll content with the chlorophyll degradation acceleration coefficient. The specific expression generated is:

[0089] ,

[0090] In the formula, δ chlor is the chlorophyll degradation index, and the final δ chlor The numerical value is used to quantify the degree of chlorophyll degradation, δ chlor The larger the value, the more serious the chlorophyll loss is and the higher the degree of environmental stress on the plant.

[0091] From the chlorophyll degradation index, we can see that under waterlogging conditions, the larger the chlorophyll degradation index value generated by comparing and analyzing the changes in chlorophyll content in corn leaves, the greater the change in the current corn leaves compared to the last monitored corn leaves. The larger the chlorophyll degradation index, the faster the chlorophyll degradation rate, which usually means that the corn plants are experiencing severe physiological stress reactions, such as a large loss of chlorophyll and significant obstruction of photosynthesis. The increase in the chlorophyll degradation index can be used as an important indicator of the increasing degree of waterlogging damage to corn leaves, indicating that the health of the plant is rapidly deteriorating.

[0092] The convolutional neural network is not specifically limited here, and can realize the leaf edge dryness index EDI t and chlorophyll degradation index δ chlor Conduct comprehensive analysis to generate the change trend assessment coefficient Chang trend In order to realize the technical solution of the present invention, the present invention provides a specific implementation method to realize the technical solution of the present invention; the change trend evaluation coefficient Chang trend The generated calculation formula is: Chang trend =r1*EDI t +r2*δ chlor , where r1 and r2 are leaf edge dryness index EDI respectively. t and chlorophyll degradation index δ chlor The preset proportional coefficient, and r1 and r2 are both greater than 0.

[0093] It can be seen from the change trend assessment coefficient that under the waterlogged environment, the greater the performance value of the leaf edge dryness index generated after comparing and analyzing the changes in the degree of dryness of the corn leaf edges, the greater the performance value of the chlorophyll degradation index generated after comparing and analyzing the changes in the chlorophyll content in the corn leaves. That is, the greater the performance value of the change trend assessment coefficient generated by comparing the two adjacent monitoring data in the set through the convolutional neural network, the greater the change in the current corn leaves compared with the last monitored corn leaves, and vice versa, the smaller the change in the current corn leaves compared with the last monitored corn leaves.

[0094] Based on the prediction results of convolutional neural networks, the current changes in corn leaves are divided into two categories: rapid changes and regular changes;

[0095] The change trend assessment coefficient generated by predicting two adjacent monitoring data in the comparison set through the convolutional neural network is compared and analyzed with the preset reference threshold of the change trend assessment coefficient to divide the current change situation of the corn leaves. The specific division steps are as follows:

[0096] If the change trend assessment coefficient is greater than or equal to the change trend assessment coefficient reference threshold, the change of the current corn leaf is classified as rapid change. Rapid change indicates that the current corn leaf has undergone drastic physiological changes in a short period of time, which is usually caused by sudden stress conditions in the external environment. Rapid changes reflect that the corn plant is under greater physiological stress;

[0097] If the change trend assessment coefficient is less than the change trend assessment coefficient reference threshold, the current corn leaf change is classified as a normal change. A normal change indicates that the current corn leaf growth state is within the normal range, and the physiological characteristics gradually change with the growth cycle. Such changes are usually relatively stable, and there are no obvious signs of stress response within the expected growth stage. Normal changes indicate that the corn plant is in a good growth environment, can carry out normal photosynthesis and growth, and the overall health of the plant is stable.

[0098] If the current changes in corn leaves are normal changes, continue to collect data according to the initial monitoring frequency;

[0099] If it is detected that the current corn leaf changes are rapidly changing, the actual monitoring frequency is automatically adjusted according to the change of the corn leaf, specifically, the collection frequency is greatly increased to ensure that all key data in the change process can be captured;

[0100] Automatically adjust the actual monitoring frequency according to the changes in corn leaves. The specific steps are as follows:

[0101] Calculate the deviation between the change trend assessment coefficient and the change trend assessment coefficient reference threshold to obtain the change trend deviation coefficient Δ δ , Δ δ =Chang trend -δ threshold Among them, Chang trend is the change trend evaluation coefficient generated based on the convolutional neural network, reflecting the degree of change of corn leaves, δ threshold It is a preset reference threshold value of the change trend assessment coefficient, which is used to distinguish between rapid changes and regular changes;

[0102] According to the variation trend deviation coefficient Δ δ , calculate the monitoring frequency adjustment factor, and use a nonlinear function to enhance the response to rapid changes. The calculation expression of the monitoring frequency adjustment factor is: Where φ is the monitoring frequency adjustment factor, which is used to adjust the actual monitoring frequency; w is the sensitivity coefficient, which controls the growth rate of the monitoring frequency adjustment factor. Its typical value is a positive number. The larger the value, the higher the sensitivity to changes.

[0103] Using the initial monitoring frequency and the monitoring frequency adjustment factor, the actual monitoring frequency after adjustment is calculated. The calculation expression is:actual =f initial ·φ, where f initial is the initial monitoring frequency, i.e. the set basic acquisition frequency, f actual The actual monitoring frequency after adjustment will be used for subsequent data collection;

[0104] In order to avoid excessive consumption of system resources due to excessive monitoring frequency, the upper limit of the actual monitoring frequency is set and the actual monitoring frequency is adjusted. The expression of the adjusted actual monitoring frequency is: actual =min(f actual , f max ), where f max is the maximum allowable value of the actual monitoring frequency, which is preset according to system capabilities and resource constraints. The min(·) function takes the smaller of the two values ​​in the brackets to ensure that the actual monitoring frequency f actual Not exceeding the maximum permissible value f of the actual monitoring frequency max ;

[0105] According to the actual monitoring frequency f calculated actual , update the monitoring plan of the data acquisition system to perform high-frequency collection according to the new frequency to ensure that the key data in the change process of corn leaves is captured. At the same time, continue to monitor the change trend assessment coefficient. If the subsequent change trend assessment coefficient drops below the change trend assessment coefficient reference threshold, it will be restored to the initial monitoring frequency.

[0106] The present invention uses a pre-trained convolutional neural network to accurately predict and classify the changing trends of corn leaves, and can effectively distinguish between rapid changes and regular changes. When rapid changes in corn leaves are detected, the system automatically adjusts the monitoring frequency, greatly increases the collection frequency, and ensures that all key physiological change data are captured in a timely manner, thereby significantly improving the accuracy and real-time performance of waterlogging resistance assessment. The mechanism of dynamically adjusting the collection frequency optimizes resource utilization, avoids ineffective high-frequency collection, and greatly improves monitoring efficiency. It not only solves the problem that traditional fixed monitoring frequencies cannot reflect the rapid changes of corn leaves in real time, but also ensures the efficient operation of the system under normal conditions, and can respond quickly in emergency environments, ensuring the stability of agricultural production, providing a more scientific and reliable decision-making basis for the waterlogging resistance assessment of corn varieties, significantly enhancing the risk resistance of corn, and helping to improve the stability of crop yields.

[0107] The present invention provides Figure 2 A corn variety waterlogging tolerance evaluation system based on data analysis is shown, comprising an initial monitoring frequency setting module, a regular data collection module, a data comparison set generation module, a convolutional neural network prediction module, a change classification module, a conventional change monitoring module, and a rapid change frequency adjustment module;

[0108] The initial monitoring frequency setting module sets an initial monitoring frequency for corn leaf information collection according to existing monitoring requirements;

[0109] A regular data collection module, after setting the initial monitoring frequency, regularly collects corn leaf information according to the initial monitoring frequency;

[0110] The data comparison set generation module compares the currently collected corn leaf data with the last collected corn leaf data as the corn leaf data is collected, forming a comparison set to track the changes of the current corn leaf;

[0111] The convolutional neural network prediction module, after establishing the comparison set, performs comparison and analysis on two adjacent monitoring data in the comparison set, inputs the compared and analyzed data into the pre-trained convolutional neural network, and predicts the current changes in corn leaves;

[0112] The change classification module, based on the prediction results of the convolutional neural network, divides the current changes of corn leaves into two categories: rapid changes and regular changes;

[0113] Conventional change monitoring module: if the current change of corn leaves is a regular change, it will continue to collect data according to the initial monitoring frequency;

[0114] Rapid change frequency adjustment module, if it is detected that the current corn leaf changes are rapid changes, the actual monitoring frequency is automatically adjusted according to the changes in the corn leaves, specifically, the collection frequency is greatly increased to ensure that all key data in the change process can be captured;

[0115] A method for evaluating waterlogging resistance of corn varieties based on data analysis provided in an embodiment of the present invention is realized by the above-mentioned system for evaluating waterlogging resistance of corn varieties based on data analysis. The specific method and process of a system for evaluating waterlogging resistance of corn varieties based on data analysis are detailed in the embodiment of the above-mentioned method for evaluating waterlogging resistance of corn varieties based on data analysis, which will not be repeated here.

[0116] 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.

[0117] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present 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. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0118] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for evaluating waterlogging resistance of corn varieties based on data analysis, characterized in that: The following steps are involved: According to the existing monitoring needs, an initial monitoring frequency is set for corn leaf information collection; After the initial monitoring frequency is set, the corn leaf information is collected regularly according to the initial monitoring frequency; As the corn leaf data is collected, the currently collected corn leaf data is compared with the corn leaf data collected last time to form a comparison set to track the changes in the current corn leaves; After establishing the comparison set, the two adjacent monitoring data in the comparison set are compared and analyzed, and the data after comparison and analysis are input into the pre-trained convolutional neural network to predict the current changes in corn leaves; Based on the prediction results of convolutional neural networks, the current changes in corn leaves are divided into two categories: rapid changes and regular changes; If the current changes in corn leaves are normal changes, continue to collect data according to the initial monitoring frequency; If it is detected that the current changes in the corn leaves are rapid, the actual monitoring frequency will be automatically adjusted according to the changes in the corn leaves. Specifically, the collection frequency will be greatly increased to ensure that all key data in the changing process can be captured.

2. The method for evaluating waterlogging resistance of corn varieties based on data analysis according to claim 1, characterized in that: After establishing the comparison set, the two adjacent monitoring data in the comparison set are compared and analyzed to extract the changes in the degree of dryness of corn leaf edges and the changes in chlorophyll content in corn leaves. After comparing and analyzing the changes in the degree of dryness of corn leaf edges and the changes in chlorophyll content in corn leaves, a leaf edge dryness index and a chlorophyll degradation index are generated respectively. The leaf edge dryness index is used to measure the changes in the degree of dryness of corn leaf edges, reflecting the damage of leaves under environmental stress conditions. The chlorophyll degradation index is used to measure the changes in chlorophyll content in corn leaves, reflecting the decline in photosynthesis efficiency and the deterioration of leaf health.

3. A method for evaluating waterlogging resistance of corn varieties based on data analysis according to claim 2, characterized in that: After obtaining the leaf edge drying index and chlorophyll degradation index generated by comparing and analyzing two adjacent monitoring data in the comparison set, the leaf edge drying index and chlorophyll degradation index are input into the pre-trained convolutional neural network to generate a change trend evaluation coefficient, and the change trend evaluation coefficient is used to predict the current changes in corn leaves.

4. A method for evaluating waterlogging resistance of corn varieties based on data analysis according to claim 3, characterized in that: The change trend assessment coefficient generated by predicting two adjacent monitoring data in the comparison set through the convolutional neural network is compared and analyzed with the preset reference threshold of the change trend assessment coefficient to divide the current change situation of the corn leaves. The specific division steps are as follows: If the change trend assessment coefficient is greater than or equal to the change trend assessment coefficient reference threshold, the change of the current corn leaf is classified as a rapid change, and the rapid change indicates that the current corn leaf has undergone a drastic physiological change in a short period of time; If the change trend assessment coefficient is less than the change trend assessment coefficient reference threshold, the current change of the corn leaves is classified as a normal change. The normal change indicates that the growth state of the current corn leaves is within the normal range, and the physiological characteristics gradually change with the growth cycle.

5. The method for evaluating waterlogging resistance of corn varieties based on data analysis according to claim 2, characterized in that: The specific steps of comparing and analyzing two adjacent monitoring data in the comparison set, extracting the changes in the dryness degree of the corn leaf edges, and generating the leaf edge dryness index after comparing and analyzing the changes in the dryness degree of the corn leaf edges are as follows: Based on the data from two adjacent monitorings, the corn leaf images were processed to extract the change information of the corn leaf edges. The leaf edge contours at each monitoring time point were generated through the image processing algorithm. Then, the change rate of the dry part of the corn leaf edge between two adjacent monitorings was calculated. The calculation expression is: ， In the formula, ΔE t represents the edge drying change rate, C t and C t-1 are the edge contour areas of corn leaves in the current and last monitoring, respectively, and A t is the overall area of ​​the corn leaf to avoid interference of the overall size of the corn leaf on the calculation results; On the basis of extracting the dry area, the changes in the details of the corn leaf edge are further analyzed. The local curvature of the corn leaf edge and the refinement of the dry edge are taken as key parameters. The severity of the dryness of the corn leaf edge is described by point-by-point curvature changes, and the degree of change in the details of the dry edge is quantified. The specific quantitative expression is: In the formula, K t is the total curvature change of the dry edge, κ t (i) and κ t-1 (i) are the curvatures of the i-th edge point in the current and last monitoring, respectively, and n is the total number of edge points; The final leaf edge drying index is generated by introducing the edge drying change rate and the total amount of curvature change of the drying edge to comprehensively quantify the degree of corn leaf edge drying. The expression for the leaf edge drying index is: t =α·ΔE t +β·(K t ) γ , where EDI t is the leaf edge drying index, α and β are the weight coefficients of the edge drying change rate and the total curvature change, respectively, and γ is the adjustment factor to enhance the sensitivity to curvature changes.

6. The method for evaluating waterlogging resistance of corn varieties based on data analysis according to claim 2, characterized in that: The specific steps of comparing and analyzing two adjacent monitoring data in the comparison set, extracting the changes in chlorophyll content in corn leaves, and generating the chlorophyll degradation index after comparing and analyzing the changes in chlorophyll content in corn leaves are as follows: Extract the chlorophyll content from the corn leaf data collected twice in succession, and assume that the chlorophyll content at the t1th collection is The chlorophyll content at the t2th collection was Calculate the chlorophyll change between two monitorings using the following formula: In the formula, ΔR represents the change in chlorophyll content between two monitoring periods; The acceleration coefficient is introduced to reflect the acceleration of the chlorophyll content change rate, and the chlorophyll content change is amplified by a nonlinear formula. The specific amplification expression is: ， Where λ is the chlorophyll degradation acceleration coefficient, which measures the acceleration effect of chlorophyll loss, τ 12 is the time interval between two adjacent monitorings, and k is the adjustment index, which is used to amplify or reduce the acceleration degree of the change; The chlorophyll degradation index is generated by combining the change in chlorophyll content with the chlorophyll degradation acceleration coefficient. The specific expression generated is: ， In the formula, δ chlor is the chlorophyll degradation index, and the final δ chlor Numerical values ​​are used to quantify the extent of chlorophyll degradation.

7. The method for evaluating waterlogging resistance of corn varieties based on data analysis according to claim 4, characterized in that: Automatically adjust the actual monitoring frequency according to the changes in corn leaves. The specific steps are as follows: Calculate the deviation between the change trend assessment coefficient and the change trend assessment coefficient reference threshold to obtain the change trend deviation coefficient Δ δ , Δ δ =Chang trend -δ threshold Among them, Chang trend is the change trend evaluation coefficient generated based on the convolutional neural network, reflecting the degree of change of corn leaves, δ threshold It is a preset reference threshold value of the change trend assessment coefficient, which is used to distinguish between rapid changes and regular changes; According to the variation trend deviation coefficient Δ δ , calculate the monitoring frequency adjustment factor, and use a nonlinear function to enhance the response to rapid changes. The calculation expression of the monitoring frequency adjustment factor is: Where, φ is the monitoring frequency adjustment factor, which is used to adjust the actual monitoring frequency, and w is the sensitivity coefficient, which controls the growth rate of the monitoring frequency adjustment factor; Using the initial monitoring frequency and the monitoring frequency adjustment factor, the actual monitoring frequency after adjustment is calculated. The calculation expression is: actual =f initial ·φ, where f initial is the initial monitoring frequency, f actual The actual monitoring frequency after adjustment will be used for subsequent data collection; In order to avoid excessive consumption of system resources due to excessive monitoring frequency, the upper limit of the actual monitoring frequency is set and the actual monitoring frequency is adjusted. The expression of the adjusted actual monitoring frequency is: actual =min(f actual , f max ), where f max is the maximum allowable value of the actual monitoring frequency. The min(·) function takes the smaller of the two values ​​in the brackets to ensure that the actual monitoring frequency f actual Not exceeding the maximum permissible value f of the actual monitoring frequency max ; According to the actual monitoring frequency f calculated actual , update the monitoring plan of the data acquisition system to perform high-frequency collection according to the new frequency to ensure that the key data in the change process of corn leaves is captured. At the same time, continue to monitor the change trend assessment coefficient. If the subsequent change trend assessment coefficient drops below the change trend assessment coefficient reference threshold, it will be restored to the initial monitoring frequency.

8. A system for evaluating waterlogging resistance of corn varieties based on data analysis, used to implement the method for evaluating waterlogging resistance of corn varieties based on data analysis as described in any one of claims 1 to 7, characterized in that: It includes an initial monitoring frequency setting module, a regular data collection module, a data comparison set generation module, a convolutional neural network prediction module, a change classification module, a regular change monitoring module, and a rapid change frequency adjustment module; The initial monitoring frequency setting module sets an initial monitoring frequency for corn leaf information collection according to existing monitoring requirements; A regular data collection module, after setting the initial monitoring frequency, regularly collects corn leaf information according to the initial monitoring frequency; The data comparison set generation module compares the currently collected corn leaf data with the last collected corn leaf data as the corn leaf data is collected, forming a comparison set to track the changes of the current corn leaf; The convolutional neural network prediction module, after establishing the comparison set, performs comparison and analysis on two adjacent monitoring data in the comparison set, inputs the compared and analyzed data into the pre-trained convolutional neural network, and predicts the current changes in corn leaves; The change classification module, based on the prediction results of the convolutional neural network, divides the current changes of corn leaves into two categories: rapid changes and regular changes; Conventional change monitoring module: if the current change of corn leaves is a regular change, it will continue to collect data according to the initial monitoring frequency; The rapid change frequency adjustment module automatically adjusts the actual monitoring frequency according to the changes in the corn leaves if it detects that the current changes in the corn leaves are rapid. Specifically, it greatly increases the collection frequency to ensure that all key data in the change process can be captured.

Images