Monitoring and management methods of corn stress resistance environment

Abstract

The present invention relates to the field of agricultural technology, and in particular to a method for monitoring and managing corn stress resistance environment, comprising the following steps: S1: real-time collection of environmental data of corn planting areas; S2: transmitting environmental data to a data center via a wireless network; S3: preprocessing the environmental data transmitted to the data center; S4: establishing an adversity stress assessment model based on the preprocessed environmental data; S5: assessing the stress resistance of corn under different environmental stresses; S6: predicting the type and intensity of adversity stress that will occur in the future and its impact on corn, forming a stress response prediction; S7: generating corn growth management decision suggestions. The present invention, through real-time environmental monitoring and accurate adversity stress assessment, combines the growth characteristics of corn and meteorological forecasts, dynamically adjusts irrigation, fertilization and pest control strategies, realizes accurate management of corn growth, improves stress resistance, optimizes resource utilization and increases yield.

Description

Technical Field

[0001] The invention relates to the field of agricultural technology, and in particular to a method for monitoring and managing corn stress resistance environment. Background Art

[0002] With the intensification of global climate change, agricultural production, especially corn planting, is facing increasingly severe environmental stress problems. Drought, high temperature, salinity and other adverse stress factors have become important factors restricting corn production. In recent years, due to the frequent occurrence of extreme climates caused by climate change, many corn-growing areas have encountered problems such as extreme drought, high temperature or soil salinization. These environmental factors directly affect the growth, development, yield and quality of corn. Traditional corn planting and management methods rely more on experience and lack accurate environmental monitoring and management strategies, resulting in uneven water and nutrient supply, untimely prevention and control of pests and diseases during corn planting, and other problems, which seriously affect the growth and health of corn.

[0003] In the existing technology, although there are some management methods based on environmental monitoring, most of the methods have the following problems: first, the environmental data collection technology and prediction technology are relatively backward, and real-time and accurate environmental monitoring cannot be achieved; second, most of the existing management methods are based on a single environmental factor or a relatively simple growth model, lacking a comprehensive analysis of multiple environmental stress factors, and unable to accurately assess the specific impact of different environmental stresses on corn; finally, many existing technologies rely too much on manual experience in the implementation of management measures, lack intelligent and automated decision support systems, and cannot provide efficient and accurate decision-making suggestions in practical applications. Therefore, there is an urgent need for a corn stress resistance environmental monitoring and management method to solve the above problems. Summary of the invention

[0004] Based on the above purpose, the present invention provides a method for monitoring and managing corn stress resistance environment.

[0005] The method for monitoring and managing corn stress resistance environment comprises the following steps:

[0006] S1: Collecting environmental data of the corn planting area in real time through a sensor network, wherein the environmental data includes temperature, humidity, light intensity, soil moisture content and soil salinity;

[0007] S2: Transmit environmental data to the data center via wireless network for storage and backup;

[0008] S3: Preprocess the environmental data transmitted to the data center, including data cleaning, denoising and standardization;

[0009] S4: Based on the pre-processed environmental data, an adversity stress assessment model is established to assess whether corn is subjected to environmental stresses such as drought, high temperature, and salinity;

[0010] S5: Based on the stress assessment results, evaluate the stress resistance of corn under different environmental stresses. The stress resistance assessment indicators include water use efficiency, photosynthesis efficiency and chlorophyll content;

[0011] S6: Based on the results of corn stress resistance assessment, combined with historical meteorological data and future meteorological forecast data, predict the type and intensity of adverse stress that will occur in the future and its impact on corn, and form a stress response prediction;

[0012] S7: Generate corn growth management decision recommendations based on the medium stress assessment results in S4, the medium corn stress resistance assessment results in S5, and the stress response prediction in S6.

[0013] Optionally, the S1 specifically includes:

[0014] S11: multiple temperature and humidity sensors are arranged in the corn planting area, and the air temperature and relative humidity are measured respectively by the temperature sensor and the humidity sensor, wherein the temperature sensor is an NTC thermistor sensor and the humidity sensor is a capacitive humidity sensor;

[0015] S12: deploying a light intensity sensor in the corn planting area, wherein the light intensity sensor is a photodiode sensor, and the current output of the photodiode responds to the ambient light intensity;

[0016] S13: deploying soil moisture sensors in the corn planting area, wherein the soil moisture sensors are resistive soil moisture sensors, which measure the change in soil resistance to estimate the moisture content in the soil, so as to collect soil moisture data in real time;

[0017] S14: Deploy soil salt sensors in the corn planting area. The soil salt sensors are conductivity sensors that measure changes in soil conductivity to estimate the salt content in the soil and record soil salt data in real time.

[0018] Optionally, the S2 specifically includes:

[0019] S21: Transmitting the environmental data collected in S1 through a wireless data transmission module, where the wireless data transmission module adopts low-power wide area network technology, specifically including LoRaWAN or NB-IoT;

[0020] S22: Packing the transmitted environmental data into a data packet through the wireless data transmission module, the data packet including the sensor ID, sensor type, acquisition timestamp, and data fields of the acquisition value, and sending the data packet to the data center through the wireless network;

[0021] S23: The data center receives the transmitted data packet, unpacks the data in the data packet, extracts the environmental data and performs verification to ensure the integrity and accuracy of the transmitted data;

[0022] S24: The data center stores the received environmental data in a database and regularly backs up the data to a remote cloud server;

[0023] S25: The data center also includes classifying and labeling the environmental data, and the classification and labeling include marking according to the dimensions of time, location, and data type.

[0024] Optionally, the S3 specifically includes:

[0025] S31: Cleaning the environmental data transmitted to the data center, wherein the data cleaning includes deleting abnormal values ​​and duplicate data, specifically by setting a data range threshold, identifying and removing abnormal data that exceeds the threshold range; at the same time, by checking the data collection timestamp, removing the collection records with duplicate time;

[0026] S32: performing denoising on the cleaned data, wherein the denoising includes smoothing the environmental data using a Kalman filter algorithm or a wavelet transform algorithm to reduce the influence of noise generated by environmental fluctuations during sensor acquisition;

[0027] S33: Standardizing the denoised data, wherein the standardization includes converting the data into dimensionless values ​​so that the dimensions of each environmental data are consistent. Specifically, a Z-score standardization method is used to subtract the mean of each environmental data and divide it by its standard deviation to obtain a standardized data value.

[0028] Optionally, the S4 specifically includes:

[0029] S41: Based on the environmental data preprocessed in S3, a stress assessment model is established using a support vector machine algorithm. Specifically, temperature, humidity, light intensity, soil water content and soil salinity in the environmental data are selected as input features, and the support vector machine model is trained through a historical annotated data set to obtain an stress assessment model for assessing whether corn is under drought, high temperature and saline-alkali environmental stress;

[0030] S42: Through regression analysis of historical environmental data and annotated data of corn growth records, the impact threshold of each type of environmental stress on corn growth is determined, and this impact threshold is used as the output label of the adversity stress assessment model for training the model to ensure that the assessment results are consistent with the actual environmental stress situation;

[0031] S43: Apply the trained stress assessment model to the preprocessed real-time environmental data, and determine whether the corn is in a state of drought, high temperature or salinity stress by classifying and evaluating the input environmental data.

[0032] Optionally, the S41 specifically includes:

[0033] S411: Selecting temperature, humidity, light intensity, soil water content and soil salinity in the environmental data as input feature vectors of the support vector machine algorithm;

[0034] S412: According to the historically labeled data set, the input feature vector is trained by a support vector machine algorithm to obtain an optimal hyperplane;

[0035] S413: By solving the optimization problem using the Lagrange multiplier method, the optimal solution of the support vector machine is obtained;

[0036] S414: Optimal hyperplane obtained based on the optimization problem and bias , establish an adversity stress assessment model; use the adversity stress assessment model to classify and evaluate each new sample input. The expression of the adversity stress assessment model is: ,in, is the feature vector of the sample to be evaluated, is the output value of the classification decision function; when When , it means that the sample is in a state of drought, high temperature or salinity stress; when , it means the sample is not in a state of duress.

[0037] Optionally, the S42 specifically includes:

[0038] S421: By performing regression analysis on historical environmental data and annotated data of corn growth records, a regression model was established to quantify the effect of each environmental stress type on corn growth;

[0039] S422: Determine the degree of influence of each environmental characteristic on corn growth through regression analysis. Specifically, identify the environmental factors that have the greatest influence on corn growth by calculating the statistical significance of each regression coefficient. For environmental characteristics that significantly influence corn growth, determine their influence thresholds. , that is, the critical value at which the environmental characteristics have a significant impact on corn growth;

[0040] S423: Determine the impact threshold As the output label of the adversity stress assessment model; each time the adversity stress assessment model is applied for evaluation, the impact threshold corresponding to each environmental stress type is used To calibrate the labels of the input samples, and compare the thresholds with the corresponding corn growth indicators; if a certain environmental characteristic value exceeds the corresponding impact threshold , then the environmental feature will be marked as the corresponding adversity oppression type;

[0041] S424: The above determined impact threshold is As a label, it is returned to the support vector machine algorithm used in step S41 for training to ensure that the output of the evaluation model is consistent with the actual environmental stress situation.

[0042] Optionally, the S5 specifically includes:

[0043] S51: The stress resistance of corn is evaluated by calculating the water use efficiency, and the calculation formula is: ,in, is water use efficiency, GPP is the gross primary productivity of corn, which indicates the amount of carbon absorbed by corn through photosynthesis per unit time; is the evapotranspiration, which indicates the amount of water required by corn per unit time; the higher the water use efficiency, the better the corn can use water under drought stress conditions;

[0044] S52: The stress resistance of corn is evaluated by calculating the photosynthesis efficiency. The calculation formula is: ,in, is the photosynthesis efficiency, is the gross primary productivity, Photosynthetically active radiation is the amount of light radiation available for photosynthesis of plants. The higher the photosynthetic efficiency, the more efficient the corn can use light energy under adverse conditions.

[0045] S53: The stress resistance of corn is evaluated by calculating the chlorophyll content. The calculation formula is: ,in, is the chlorophyll content, is the total amount of chlorophyll in leaves, is the area of ​​the leaves; the higher the chlorophyll content, the stronger the photosynthesis potential of the corn.

[0046] Optionally, the S6 specifically includes:

[0047] S61: Through multiple regression analysis, a relationship model between meteorological data and adverse stress types is established, and the expression is: ,in, represents the predicted intensity of adverse stress, is the intercept of the regression model, For the The regression coefficients of the meteorological factors are For the The sample Meteorological characteristics, is the total number of meteorological features, is the error term;

[0048] S62: Establish a stress response function to calculate and predict the intensity and impact of future stress based on historical meteorological data, future meteorological forecast data and corn stress resistance assessment results; the stress response function is used to quantify the impact of different types of stress on corn growth, and make a comprehensive prediction based on the corn stress resistance assessment results; the expression of the stress response function is: ,in, For the The stress response value of a sample indicates the predicted impact of the corresponding sample under future adverse stress conditions; is the intercept of the regression model; For the The regression coefficients of the meteorological factors are For the The sample meteorological characteristics; For the The stress resistance evaluation value of corn samples; For the The influencing factors of historical environmental data of samples on corn growth; and is the regression coefficient of stress resistance assessment value and historical environmental data factor; is the error term.

[0049] Optionally, the S7 specifically includes:

[0050] S71: Based on the stress assessment results in S4, analyze the types and intensities of drought, high temperature, and salinity stresses to which corn is subjected, and determine the changes in its demand for water, light, and soil nutrients in combination with the current growth stage of corn;

[0051] S72: According to the corn stress resistance evaluation results in S5, determine the stress resistance level of corn, and combine the growth characteristics of corn under different stress resistance levels to generate irrigation, fertilization and pest and disease control strategies under different stress resistance levels;

[0052] S73: Combined with the stress response prediction in S6, analyze the future trend of environmental stress changes and predict the fluctuations of moisture, light and temperature under future meteorological conditions;

[0053] S74: Based on the evaluation and prediction results in S71 to S73, a comprehensive corn growth management decision recommendation is generated, wherein the decision recommendation includes irrigation amount, fertilizer amount and fertilizer type, and specific pest and disease control measures.

[0054] Beneficial effects of the present invention:

[0055] The present invention collects environmental data of corn-growing areas in real time, uses advanced algorithms and models to accurately evaluate the types and intensities of adverse stresses such as drought, high temperature, and salinity to which corn is subjected, and, combined with the growth characteristics of corn, can dynamically adjust irrigation, fertilization, and pest and disease control strategies to ensure that corn obtains the most suitable growth environment under different environmental conditions, thereby reducing resource waste and improving crop growth efficiency and yield.

[0056] The present invention, by combining environmental monitoring, stress resistance assessment and weather forecasting, can predict possible adverse stress in the future in advance and take corresponding management measures before the stress occurs, thereby greatly reducing the negative impact of environmental stress on corn growth. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 Schematic diagram of a method for monitoring and managing corn stress resistance environment according to an embodiment of the present invention;

[0059] Figure 2 Schematic diagram of a method for establishing an adversity stress assessment model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0061] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0062] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0063] like Figure 1-Figure 2 As shown, the method for monitoring and managing corn stress resistance environment includes the following steps:

[0064] S1: Collect environmental data of the corn planting area in real time through the sensor network. The environmental data include temperature, humidity, light intensity, soil moisture content and soil salinity;

[0065] S2: Transmit environmental data to the data center via wireless network for storage and backup, ensure the real-time and security of data, and provide data support for subsequent processing;

[0066] S3: Preprocess the environmental data transmitted to the data center, including data cleaning, denoising and standardization, to ensure data quality and improve data accuracy and consistency;

[0067] S4: Based on the pre-processed environmental data, an adversity stress assessment model is established to assess whether corn is subjected to environmental stresses such as drought, high temperature, and salinity;

[0068] S5: Based on the stress assessment results, evaluate the stress resistance of corn under different environmental stresses. The stress resistance assessment indicators include water use efficiency, photosynthesis efficiency and chlorophyll content;

[0069] S6: Based on the results of corn stress resistance assessment, combined with historical meteorological data and future meteorological forecast data, predict the type and intensity of adverse stress that will occur in the future and its impact on corn, and form a stress response prediction;

[0070] S7: Generate corn growth management decision recommendations based on the medium stress assessment results in S4, the medium corn stress resistance assessment results in S5, and the stress response prediction in S6.

[0071] S1 specifically includes:

[0072] S11: multiple temperature and humidity sensors are arranged in the corn planting area, and the air temperature and relative humidity are measured respectively by the temperature sensor and the humidity sensor. The temperature sensor is an NTC thermistor sensor, and the humidity sensor is a capacitive humidity sensor.

[0073] S12: A light intensity sensor is arranged in the corn planting area. The light intensity sensor is a photodiode sensor. The current output of the photodiode responds to the ambient light intensity. The sensor can measure the light intensity per unit area and record the data in real time.

[0074] S13: deploying soil moisture sensors in the corn planting area. The soil moisture sensors are resistive soil moisture sensors that measure soil resistance changes to estimate the moisture content in the soil, so as to collect soil moisture data in real time.

[0075] S14: Soil salt sensors are deployed in corn planting areas. Soil salt sensors are conductivity sensors that measure changes in soil conductivity to estimate the salt content in the soil and record soil salt data in real time.

[0076] S2 specifically includes:

[0077] S21: The environmental data collected in S1 is transmitted through a wireless data transmission module. The wireless data transmission module adopts low power wide area network (LPWAN) technology, including LoRaWAN or NB-IoT, to ensure stable data transmission in a wide range of corn planting areas;

[0078] S22: Packing the transmitted environmental data into a data packet through the wireless data transmission module, the data packet including the sensor ID, sensor type, acquisition timestamp, and data fields of the acquisition value, and sending the data packet to the data center through the wireless network;

[0079] S23: The data center receives the transmitted data packet, unpacks the data in the data packet, extracts the environmental data and performs verification to ensure the integrity and accuracy of the transmitted data;

[0080] S24: The data center stores the received environmental data in a database and regularly backs up the data to a remote cloud server to prevent data loss or damage;

[0081] S25: The data center also includes the classification and labeling of environmental data. The classification and labeling include marking by time, location, and data type to provide support for subsequent data analysis and processing. Through the above technical solutions, the environmental data of the corn-growing area can be efficiently and stably transmitted to the data center via the wireless network for storage and backup. The use of low-power wide-area network technology (such as LoRaWAN or NB-IoT) ensures the stability of data transmission and long-distance coverage capabilities, ensuring real-time transmission of data over a large area.

[0082] S3 specifically includes:

[0083] S31: Clean the environmental data transmitted to the data center. Data cleaning includes deleting abnormal values ​​and duplicate data. Specifically, by setting a data range threshold, abnormal data that exceeds the threshold range is identified and removed. At the same time, by checking the data collection timestamp, the collection records with duplicate time are removed.

[0084] S32: performing denoising on the cleaned data, wherein the denoising includes smoothing the environmental data using a Kalman filter algorithm or a wavelet transform algorithm, thereby reducing the influence of noise caused by environmental fluctuations during sensor acquisition and ensuring the accuracy and reliability of the data;

[0085] S33: Standardize the denoised data. Standardization includes converting the data into dimensionless values ​​to make the dimensions of each environmental data consistent for subsequent unified analysis. Specifically, the Z-score standardization method is used to subtract the mean of each environmental data and divide it by its standard deviation to obtain the standardized data value. Through the above technical solution, the environmental data transmitted to the data center can be effectively preprocessed to ensure the accuracy and availability of the data. Data cleaning avoids the impact of erroneous data caused by collection problems on the analysis results by eliminating missing, abnormal and duplicate data. De-noising eliminates noise in the data through Kalman filtering or wavelet transform methods, further improving data quality. Standardization unifies data of different dimensions into dimensionless values, making various environmental data comparable, facilitating subsequent unified analysis, and providing more reliable data support for decision-making.

[0086] S4 specifically includes:

[0087] S41: Based on the environmental data preprocessed in S3, a support vector machine (SVM) algorithm is used to establish an adversity stress assessment model. Specifically, temperature, humidity, light intensity, soil water content and soil salinity in the environmental data are selected as input features, and the support vector machine model is trained through the historical annotation data set to obtain an adversity stress assessment model for assessing whether corn is under drought, high temperature and saline-alkali environmental stress;

[0088] S42: Through regression analysis of historical environmental data and annotated data of corn growth records, determine the impact threshold of each type of environmental stress (such as drought, high temperature, salinity) on corn growth, and use this impact threshold as the output label of the adversity stress assessment model for training the model to ensure that the assessment results are consistent with the actual environmental stress situation;

[0089] S43: Apply the trained stress assessment model to the real-time environmental data after preprocessing, and judge whether the corn is in a state of drought, high temperature or salinity stress by classifying and evaluating the input environmental data; through the above technical scheme, the support vector machine algorithm can be efficiently used to establish an stress assessment model, and accurately evaluate the type and intensity of stress encountered by corn; the support vector machine algorithm can perform nonlinear classification through the input environmental data characteristics, so as to accurately identify whether corn is affected by drought, high temperature, salinity and other stress types. The regression analysis in the model training process effectively ensures the accuracy of the evaluation results and provides data support for decision-making in agricultural production.

[0090] The adversity stress assessment model established in S41 specifically includes:

[0091] S411: Select temperature, humidity, light intensity, soil moisture content and soil salinity in the environmental data as input feature vectors of the support vector machine algorithm, and set the input features as: ,in Indicates The sample eigenvalues, is the total number of input features, , is the sample size; here, For the The temperature value of each sample, is the humidity value, is the light intensity value, is the soil moisture content, is the soil salinity value;

[0092] S412: Based on the historically labeled data set, the input feature vector is trained by a support vector machine algorithm to obtain an optimal hyperplane; the support vector machine achieves the maximum separation of the hyperplane by solving the following optimization problem:

[0093] ,in, is the normal vector of the hyperplane, is the bias term, For sample Category labels (such as drought, high temperature, salinity), For the The input feature vector of samples;

[0094] S413: By using the Lagrange multiplier method to solve the optimization problem, the optimal solution of the support vector machine is obtained; the Lagrange dual problem can be expressed as: ,in, is a Lagrange multiplier that satisfies the constraints is the penalty parameter;

[0095] S414: Optimal hyperplane obtained based on the optimization problem and bias , establish an adversity stress assessment model; use the adversity stress assessment model to input each new sample Carry out classification evaluation, the expression of adversity forced evaluation model is: ,in, is the feature vector of the sample to be evaluated, is the output value of the classification decision function; when When , it means that the sample is in a state of drought, high temperature or salinity stress; when When , it indicates that the sample is not in a stress state; through the above technical solution, using the support vector machine algorithm, it is possible to obtain an efficient and accurate stress assessment model by training historical environmental data and labeled data. This model can accurately assess whether corn is in a state of stress such as drought, high temperature or salinity based on the input environmental characteristic data, thereby providing a scientific basis for management decisions on corn resistance to stress.

[0096] S42 specifically includes:

[0097] S421: By performing regression analysis on historical environmental data and annotated data of corn growth records, a regression model is established to quantify the effect of each type of environmental stress on corn growth; specifically, assuming that there is a certain linear or nonlinear relationship between environmental data and corn growth indicators, the form of the regression model is: ,in, It is Corn growth indicators of samples (such as chlorophyll content, photosynthesis efficiency, etc.), is the intercept of the regression model, It is The regression coefficient of each environmental characteristic is It is The sample Environmental characteristic values ​​(such as temperature, humidity, soil moisture content, etc.), is the error term, is the total number of environmental features;

[0098] S422: Determine the degree of influence of each environmental characteristic on corn growth through regression analysis, specifically by calculating each regression coefficient The statistical significance of the environmental factors that have the greatest impact on corn growth was identified; for the environmental characteristics that significantly affect corn growth, their impact thresholds were determined. , that is, the critical value at which the environmental characteristics have a significant impact on corn growth; threshold Determined by the following formula: ,in, For the The impact threshold of an environmental feature indicates that when the environmental feature When this threshold is reached or exceeded, corn growth will be significantly affected;

[0099] S423: Determine the impact threshold As the output label of the stress assessment model; each time the stress assessment model is applied for evaluation, the impact threshold corresponding to each environmental stress type (such as drought, high temperature, salinity) is used To calibrate the label of the input sample , and compare the threshold with the corresponding corn growth index; if a certain environmental characteristic value Exceeds the corresponding impact threshold When , the environmental feature will be marked as the corresponding adversity stress type;

[0100] S424: The above determined impact threshold is As a label, it is returned to the support vector machine algorithm used in step S41 for training to ensure that the output of the evaluation model is consistent with the actual environmental stress situation, thereby improving the prediction accuracy of the model; through the above technical solution, the impact of different environmental factors on corn growth can be accurately quantified, and the impact threshold of each type of environmental stress can be determined based on the regression analysis results; in this way, a more accurate label can be provided for the support vector machine model to ensure that the model can accurately determine whether corn is experiencing environmental stress in practical applications; at the same time, through regression analysis, the contribution of various environmental characteristics to corn growth can be effectively evaluated, providing a scientific basis for subsequent decision-making.

[0101] S5 specifically includes:

[0102] S51: The stress resistance of corn is evaluated by calculating the water use efficiency (WUE). Water use efficiency is an indicator to measure the water use efficiency of corn under different environmental stress conditions. The calculation formula is: ,in, is water use efficiency, GPP is the gross primary productivity of corn, which indicates the amount of carbon absorbed by corn through photosynthesis per unit time; is the evapotranspiration, which indicates the amount of water required by corn per unit time; the higher the water use efficiency, the better the corn can use water under drought stress conditions and the stronger its stress resistance;

[0103] S52: The stress resistance of corn is evaluated by calculating the photosynthetic efficiency (PE). The photosynthetic efficiency reflects the ability of corn to use light energy for biosynthesis under stress. The calculation formula is: ,in, is the photosynthesis efficiency, is the total primary productivity (same as S51), Photosynthetically active radiation is the amount of light radiation available for photosynthesis of plants. The higher the photosynthetic efficiency, the more efficient the corn is in utilizing light energy under adverse conditions, thus enhancing its ability to adapt to environmental stress.

[0104] S53: The stress resistance of corn is evaluated by calculating the chlorophyll content (Chl). The chlorophyll content directly affects the photosynthesis capacity of corn. The calculation formula is: ,in, is the chlorophyll content, is the total amount of chlorophyll in leaves, is the area of ​​the leaves; the higher the chlorophyll content, the stronger the photosynthesis potential of the corn. The chlorophyll content can be measured by a spectrometer or a chlorophyll fluorescence meter. Through the above technical solution, the stress resistance of corn under different environmental stresses can be comprehensively and accurately evaluated, and a scientific basis can be provided for subsequent agricultural management decisions.

[0105] S6 specifically includes:

[0106] S61: Through multiple regression analysis, a relationship model between meteorological data and adverse stress types is established, and the expression is: ,in, Indicates the predicted intensity of adverse stress (such as drought intensity, salinity intensity, etc.), is the intercept of the regression model, For the The regression coefficients of the meteorological factors are For the The sample meteorological characteristics (such as temperature, precipitation, etc.), is the total number of meteorological features, is the error term, and the stress intensity under each meteorological condition is obtained through regression analysis method;

[0107] S62: Establish a stress response function to calculate and predict the intensity and impact of future stress based on historical meteorological data, future meteorological forecast data and corn stress resistance assessment results; the stress response function is used to quantify the impact of different types of stress (such as drought, high temperature, salinity) on corn growth, and make a comprehensive prediction based on the corn stress resistance assessment results; the expression of the stress response function is: ,in, For the The stress response value of a sample indicates the predicted impact of the corresponding sample under future adverse stress conditions; is the intercept of the regression model; For the The regression coefficients of the meteorological factors are For the The sample Meteorological characteristic values ​​(such as temperature, humidity, precipitation, etc.); For the The stress resistance assessment value of corn samples (such as water use efficiency, photosynthesis efficiency, etc.); For the The influencing factors of historical environmental data of samples on corn growth; and is the regression coefficient of stress resistance assessment value and historical environmental data factor; is the error term; through the stress response function, the impact of adverse stress type and intensity on corn can be quantified more accurately. Combined with the results of corn stress resistance assessment, accurate prediction of future adverse stress can be achieved. This prediction provides a scientific basis for the management of corn planting and can help growers take corresponding agricultural management measures under different climatic conditions to improve corn yield and quality.

[0108] S7 specifically includes:

[0109] S71: Based on the stress assessment results in S4, analyze the types and intensities of drought, high temperature, and salinity stresses to which corn is subjected, and determine the changes in its demand for water, light, and soil nutrients in combination with the current growth stage of corn; specifically, quantitatively analyze the specific effects of different stress types (such as drought, salinity, and heat stress) on corn growth, and determine the changing trends in its demand for environmental factors (such as water, light, and soil nutrients);

[0110] S72: According to the corn stress resistance assessment results in S5, determine the stress resistance level of corn, and combine the growth characteristics of corn under different stress resistance levels to generate irrigation, fertilization and pest and disease control strategies under different stress resistance levels; specifically, based on the corn stress resistance assessment (such as water use efficiency, photosynthesis efficiency, chlorophyll content, etc.), customize personalized management plans for corn with different stress resistance levels, adjust irrigation amount, fertilization type and pest and disease control measures to optimize the growth environment of corn;

[0111] S73: Combined with the stress response prediction in S6, analyze the trend of future environmental stress changes, predict the fluctuations in moisture, light and temperature under future meteorological conditions, and then adjust the irrigation and fertilization strategies; based on the predicted meteorological data (such as precipitation and temperature in the next few days), dynamically adjust the moisture and nutrient supply of corn, and make irrigation and fertilization adjustment decisions in advance;

[0112] S74: Based on the evaluation and prediction results in S71 to S73, comprehensively generate corn growth management decision recommendations, including irrigation amount, fertilizer amount and type, and specific pest and disease control measures to ensure that the decision recommendations can achieve accurate management in the actual planting process;

[0113] Irrigation volume is used to determine the irrigation frequency and amount according to the changes in water demand to ensure the water supply required for corn growth under drought or high temperature stress;

[0114] Fertilizer amount and type are used to determine the amount and type of fertilizer (such as nitrogen fertilizer, phosphorus fertilizer, etc.) according to the soil nutritional status and corn's stress resistance level, so as to improve the soil's nutrient supply and support the healthy growth of corn;

[0115] Pest and disease control measures are used to propose pest and disease control strategies according to the changing trends of environmental stress and the growth stage of corn, such as adjusting the spraying time and using different control methods.

[0116] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0117] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for monitoring and managing corn stress resistance environment, characterized in that: The following steps are involved: S1: Collecting environmental data of the corn planting area in real time through a sensor network, wherein the environmental data includes temperature, humidity, light intensity, soil moisture content and soil salinity; S2: Transmit environmental data to the data center via wireless network for storage and backup; S3: Preprocess the environmental data transmitted to the data center, including data cleaning, denoising and standardization; S4: Based on the pre-processed environmental data, an adversity stress assessment model is established to assess whether corn is subjected to environmental stresses such as drought, high temperature, and salinity; S5: Based on the stress assessment results, evaluate the stress resistance of corn under different environmental stresses. The stress resistance assessment indicators include water use efficiency, photosynthesis efficiency and chlorophyll content; S6: Based on the results of corn stress resistance assessment, combined with historical meteorological data and future meteorological forecast data, predict the type and intensity of adverse stress that will occur in the future and its impact on corn, and form a stress response prediction; The S6 specifically includes: S61: Through multiple regression analysis, a relationship model between meteorological data and adverse stress types is established, and the expression is: ,in, represents the predicted intensity of adverse stress, is the intercept of the regression model, For the The regression coefficients of the meteorological factors are For the The sample Meteorological characteristics, is the total number of meteorological features, is the error term; S62: Establish a stress response function to calculate and predict the intensity and impact of future stress based on historical meteorological data, future meteorological forecast data and corn stress resistance assessment results; the stress response function is used to quantify the impact of different types of stress on corn growth, and make a comprehensive prediction based on the corn stress resistance assessment results; the expression of the stress response function is: ,in, For the The stress response value of a sample indicates the predicted impact of the corresponding sample under future adverse stress conditions; is the intercept of the regression model; For the The regression coefficients of the meteorological factors are For the The sample meteorological characteristics; For the The stress resistance evaluation value of corn samples; For the The influencing factors of historical environmental data of samples on corn growth; and is the regression coefficient of stress resistance assessment value and historical environmental data factor; is the error term; S7: Generate corn growth management decision recommendations based on the medium stress assessment results in S4, the medium corn stress resistance assessment results in S5, and the stress response prediction in S6.

2. The method for monitoring and managing corn stress resistance environment according to claim 1, characterized in that: The S1 specifically includes: S11: multiple temperature and humidity sensors are arranged in the corn planting area, and the air temperature and relative humidity are measured respectively by the temperature sensor and the humidity sensor, wherein the temperature sensor is an NTC thermistor sensor and the humidity sensor is a capacitive humidity sensor; S12: deploying a light intensity sensor in the corn planting area, wherein the light intensity sensor is a photodiode sensor, and the current output of the photodiode responds to the ambient light intensity; S13: deploying soil moisture sensors in the corn planting area, wherein the soil moisture sensors are resistive soil moisture sensors, which measure the change in soil resistance to estimate the moisture content in the soil, so as to collect soil moisture data in real time; S14: Deploy soil salt sensors in the corn planting area. The soil salt sensors are conductivity sensors that measure changes in soil conductivity to estimate the salt content in the soil and record soil salt data in real time.

3. The method for monitoring and managing corn stress resistance environment according to claim 1, characterized in that: The S2 specifically includes: S21: Transmitting the environmental data collected in S1 through a wireless data transmission module, where the wireless data transmission module adopts low-power wide area network technology, specifically including LoRaWAN or NB-IoT; S22: Packing the transmitted environmental data into a data packet through the wireless data transmission module, the data packet including the sensor ID, sensor type, acquisition timestamp, and data fields of the acquisition value, and sending the data packet to the data center through the wireless network; S23: The data center receives the transmitted data packet, unpacks the data in the data packet, extracts the environmental data and performs verification to ensure the integrity and accuracy of the transmitted data; S24: The data center stores the received environmental data in a database and regularly backs up the data to a remote cloud server; S25: The data center also includes classifying and labeling the environmental data, and the classification and labeling include marking according to the dimensions of time, location, and data type.

4. The method for monitoring and managing corn stress resistance environment according to claim 1, characterized in that: The S3 specifically includes: S31: Cleaning the environmental data transmitted to the data center, wherein the data cleaning includes deleting abnormal values ​​and duplicate data, specifically by setting a data range threshold, identifying and removing abnormal data that exceeds the threshold range; at the same time, by checking the data collection timestamp, removing the collection records with duplicate time; S32: performing denoising on the cleaned data, wherein the denoising includes smoothing the environmental data using a Kalman filter algorithm or a wavelet transform algorithm to reduce the influence of noise generated by environmental fluctuations during sensor acquisition; S33: Standardizing the denoised data, wherein the standardization includes converting the data into dimensionless values ​​so that the dimensions of each environmental data are consistent. Specifically, a Z-score standardization method is used to subtract the mean of each environmental data and divide it by its standard deviation to obtain a standardized data value.

5. The method for monitoring and managing corn stress resistance environment according to claim 1, characterized in that: The S4 specifically includes: S41: Based on the environmental data preprocessed in S3, a stress assessment model is established using a support vector machine algorithm. Specifically, temperature, humidity, light intensity, soil water content and soil salinity in the environmental data are selected as input features, and the support vector machine model is trained through a historical annotated data set to obtain an stress assessment model for assessing whether corn is under drought, high temperature and saline-alkali environmental stress; S42: Through regression analysis of historical environmental data and annotated data of corn growth records, the impact threshold of each type of environmental stress on corn growth is determined, and this impact threshold is used as the output label of the adversity stress assessment model for training the model to ensure that the assessment results are consistent with the actual environmental stress situation; S43: Apply the trained stress assessment model to the preprocessed real-time environmental data, and determine whether the corn is in a state of drought, high temperature or salinity stress by classifying and evaluating the input environmental data.

6. The method for monitoring and managing corn stress resistance environment according to claim 5, characterized in that: The S41 specifically includes: S411: Selecting temperature, humidity, light intensity, soil water content and soil salinity in the environmental data as input feature vectors of the support vector machine algorithm; S412: According to the historically labeled data set, the input feature vector is trained by a support vector machine algorithm to obtain an optimal hyperplane; S413: By solving the optimization problem using the Lagrange multiplier method, the optimal solution of the support vector machine is obtained; S414: Optimal hyperplane obtained based on the optimization problem and bias , establish an adversity stress assessment model; use the adversity stress assessment model to classify and evaluate each new sample input. The expression of the adversity stress assessment model is: ,in, is the feature vector of the sample to be evaluated, is the output value of the classification decision function; when When , it means that the sample is under drought, high temperature or salinity stress; when , it means the sample is not in a state of duress.

7. The method for monitoring and managing corn stress resistance environment according to claim 6, characterized in that: The S42 specifically includes: S421: By performing regression analysis on historical environmental data and annotated data of corn growth records, a regression model was established to quantify the effect of each environmental stress type on corn growth; S422: Determine the degree of influence of each environmental characteristic on corn growth through regression analysis. Specifically, identify the environmental factors that have the greatest influence on corn growth by calculating the statistical significance of each regression coefficient. For environmental characteristics that significantly influence corn growth, determine their influence thresholds. , that is, the critical value at which the environmental characteristics have a significant impact on corn growth; S423: Determine the impact threshold As the output label of the adversity stress assessment model; each time the adversity stress assessment model is applied for evaluation, the impact threshold corresponding to each environmental stress type is used To calibrate the labels of the input samples, and compare the thresholds with the corresponding corn growth indicators; if a certain environmental characteristic value exceeds the corresponding impact threshold , then the environmental feature will be marked as the corresponding adversity oppression type; S424: The above determined impact threshold is As a label, it is returned to the support vector machine algorithm used in step S41 for training to ensure that the output of the evaluation model is consistent with the actual environmental stress situation.

8. The method for monitoring and managing corn stress resistance environment according to claim 1, characterized in that: The S5 specifically includes: S51: The stress resistance of corn is evaluated by calculating the water use efficiency, and the calculation formula is: ,in, is water use efficiency, GPP is the gross primary productivity of corn, which indicates the amount of carbon absorbed by corn through photosynthesis per unit time; is the evapotranspiration, which indicates the amount of water required by corn per unit time; the higher the water use efficiency, the better the corn can use water under drought stress conditions; S52: The stress resistance of corn is evaluated by calculating the photosynthesis efficiency. The calculation formula is: ,in, is the photosynthesis efficiency, is the total primary productivity, Photosynthetically active radiation is the amount of light radiation available for photosynthesis of plants. The higher the photosynthetic efficiency, the more efficient the corn can use light energy under adverse conditions. S53: The stress resistance of corn is evaluated by calculating the chlorophyll content. The calculation formula is: ,in, is the chlorophyll content, is the total amount of chlorophyll in leaves, is the area of ​​the leaves; the higher the chlorophyll content, the stronger the photosynthesis potential of the corn.

9. The method for monitoring and managing corn stress resistance environment according to claim 1, characterized in that: The S7 specifically includes: S71: Based on the stress assessment results in S4, analyze the types and intensities of drought, high temperature, and salinity stresses to which corn is subjected, and determine the changes in its demand for water, light, and soil nutrients in combination with the current growth stage of corn; S72: According to the corn stress resistance evaluation results in S5, determine the stress resistance level of corn, and combine the growth characteristics of corn under different stress resistance levels to generate irrigation, fertilization and pest and disease control strategies under different stress resistance levels; S73: Combined with the stress response prediction in S6, analyze the future trend of environmental stress changes and predict the fluctuations of moisture, light and temperature under future meteorological conditions; S74: Based on the evaluation and prediction results in S71 to S73, a comprehensive corn growth management decision recommendation is generated, wherein the decision recommendation includes irrigation amount, fertilizer amount and fertilizer type, and specific pest and disease control measures.

Images