Maize northern leaf blight early warning method and system based on data analysis

Abstract

The invention discloses a northern corn leaf blight early warning method and system based on data analysis, and relates to the technical field of agricultural disease early warning, and the main scheme is as follows: a data acquisition module acquires meteorological data, planting density data, pathogenic bacteria transmission data and physiological status data of corn growth in real time; the method comprises the following steps that: a data analysis module analyzes various data to obtain a meteorological influence coefficient # imgabs0 #, a planting density influence coefficient # imgabs1 #, a pathogenic bacterium propagation rate # imgabs2 # and a physiological state influence coefficient # imgabs3 #, an early warning issuing module calculates a northern leaf blight influence index # imgabs4 # according to the coefficients, whether risk early warning is triggered or not is judged and a protection instruction is generated, and a user interaction module receives early warning data and sends the early warning data to a control module. Early warning information and a data labeling graph are displayed, an early warning analysis report is generated, related personnel are notified through mails, short messages or systems, comprehensive, accurate and timely corn northern leaf blight early warning is achieved, and powerful guarantee is provided for agricultural production.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural disease early warning, and specifically to a method and system for early warning of northern corn leaf blight based on data analysis. Background Art

[0002] Meteorological conditions are one of the key factors for the occurrence of northern corn leaf blight. A high-temperature and high-humidity environment is conducive to the reproduction and spread of pathogenic bacteria, increasing the likelihood of disease occurrence. At the same time, temperature changes also affect the activity and pathogenicity of pathogenic bacteria, thereby affecting the degree of disease occurrence; planting density is also an important factor affecting the occurrence of northern corn leaf blight. Excessive planting density will lead to poor ventilation and light transmission between corn plants, increased humidity, providing a favorable environment for the growth of pathogenic bacteria. In addition, dense plants will also increase the transmission speed and range of pathogenic bacteria, causing the disease to spread rapidly in a short time; the transmission speed and mode of pathogenic bacteria are also important factors determining the occurrence risk of northern corn leaf blight. Under suitable meteorological conditions, the spores of pathogenic bacteria can be dispersed by the wind over a long distance, causing large-scale occurrence of the disease; the physiological state of corn plants also has an important impact on the occurrence of the disease. Healthy corn plants have strong disease resistance and can resist the invasion and spread of pathogenic bacteria, while plants with poor growth, nutrient deficiency or suffering from other stress conditions are more vulnerable to the invasion of pathogenic bacteria.

[0003] In current agricultural production, the existing technology for monitoring northern corn leaf blight is usually relatively traditional and single. Some simple meteorological monitoring devices are used to pay attention to the impact of weather conditions on northern corn leaf blight. For example, meteorological factors such as temperature and humidity are monitored, but these factors are often considered in isolation. Since the occurrence of northern corn leaf blight is the result of the combined action of multiple factors, this single monitoring is difficult to accurately predict the occurrence risk of northern corn leaf blight; in addition, there is a lack of prediction of the spread of pathogenic bacteria, and it is impossible to give early warning of the possible harm caused by pathogenic bacteria to corn fields. At the same time, the monitoring of the physiological state of corn plants may not be comprehensive and in-depth enough to timely discover potential problems in corn plants' resistance to northern corn leaf blight. Summary of the Invention

[0004] (I) Technical Problems to be Solved Aiming at the deficiencies of the existing technology, the present invention provides a method and system for early warning of northern corn leaf blight based on data analysis. Through the meteorological influence coefficient , planting density influence coefficient , pathogenic bacteria transmission rate , and physiological state influence coefficient , and by comprehensively calculating these coefficients, the northern corn leaf blight influence index , which solves the problem of inaccurate prediction of disease risks, generates protection instructions based on the evaluation results, and guides farmers to take targeted prevention and control measures, which can better prevent and control diseases. It displays early warning information and data annotation charts in real time through the user interaction interface, so that farmers can intuitively understand the trend of disease occurrence and prevention and control effects. The system also supports sending early warning analysis reports to relevant personnel via email, SMS or system notifications, solving the problem of inconvenient information display and transmission.

[0005] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: a method and system for early warning of corn leaf blight based on data analysis, comprising: Data collection module, used to collect meteorological data, planting density data, pathogen transmission data and physiological status data of corn growth in real time; The data analysis module analyzes meteorological data, planting density data, pathogen transmission data, and corn plant physiological status data to obtain the meteorological impact coefficient , Planting density influence coefficient , pathogen transmission rate And the physiological state influence coefficient ; Warning release module, based on the meteorological impact coefficient , Planting density influence coefficient , pathogen transmission rate And the physiological state influence coefficient , calculate the big spot disease impact index ; Set the threshold set for the impact of big spot disease , according to the big spot disease impact index and the threshold set for the impact of the disease Determine whether to trigger a risk warning for corn leaf blight and generate matching protection instructions; Data display module, used to receive the impact index of the giant spot disease from the early warning release module and the threshold set for the impact of the disease , display warning information and data annotation graphs in real time, and generate warning analysis reports, which are sent to relevant personnel via email, SMS or system notification.

[0006] In the preferred embodiment of the corn leaf blight early warning system based on data analysis: meteorological data includes rainfall ,temperature , humidity X and light intensity ; Planting density data include corn field area , Number of corn plants and soil fertility data; The pathogen transmission data includes the number of diseased plants in the discovery period , the number of diseased plants in the diffusion period and the historical meteorological influence coefficient ; The physiological state data includes the real-time chlorophyll content of the plants , the real-time water content H of the plants and the real-time temperature content T of the plants.

[0007] In the above-mentioned preferred scheme of the maize northern leaf blight warning system based on data analysis: The specific steps for calculating the meteorological influence coefficient are as follows: According to the meteorological data in the future time period, calculate the meteorological influence coefficient , and the specific formula is as follows:

[0008] where is the influence factor of rainfall , and the value range is 0.1 ≤ ≤ 0.3, is the influence factor of temperature , and the value range is 0.2 ≤ ≤ 0.4, is the influence factor of humidity X, and the value range is 0.3 ≤ ≤ 0.5, is the influence factor of light intensity , and the value range is 0.1 < ≤ 0.3 and , represents the error term of the meteorological data on the meteorological influence coefficient .

[0009] In the above-mentioned preferred scheme of the maize northern leaf blight warning system based on data analysis: The specific steps for calculating the planting density influence coefficient are as follows: Set the standard value of planting density according to the historical planting data; According to the maize field area , the number of maize plants , the standard value of planting density and the meteorological influence coefficient , calculate the planting density influence coefficient , and the specific formula is as follows:

[0010] where represents the adjustment factor of soil fertility and climate conditions, and the value range is positive real numbers; represents the soil fertility index, with a value range of >0.

[0011] In the above preferred solution of the large leaf spot warning system for corn based on data analysis: calculating the soil fertility index The specific steps are as follows: The soil fertility data includes organic matter content , nitrogen content , phosphorus content , potassium content and soil value ; Set the optimal value of organic matter content , the optimal value of soil pH , the minimum threshold of nitrogen content , the minimum threshold of phosphorus content , the minimum threshold of potassium content , and the change range of soil pH ; Calculate the soil fertility index , the optimal value of soil pH , the minimum threshold of nitrogen content , the minimum threshold of phosphorus content , the minimum threshold of potassium content and the change range of soil pH , ,

[0012] Among them, represents the change range of soil pH, with a value of 0 < < 1, represents the weight coefficient of organic matter content , with a value range of >0, represents the weight coefficient of nitrogen content , with a value range of >0, represents the weight coefficient of phosphorus content , with a value range of >0, represents the weight coefficient of potassium content , with a value range of >0, represents the error term of soil fertility data for the soil fertility index .

[0013] In the above preferred embodiment of the corn northern leaf blight early warning system based on data analysis: calculate the pathogen transmission rate The specific steps are as follows: Set the basic transmission rate according to historical planting data ;; According to the pathogen transmission data and the basic transmission rate calculate the pathogen transmission rate The specific formula is as follows:

[0014] Wherein, represents the number of infected plants during the time period from time point to time point in the process of the spread of diseased plants, represents the serial number of the collection time point, and the values are 1, 2, 3... , represents the total number of collection time points, represents the influence index of the time efficiency factor, and the value range is a positive integer, represents the weight coefficient of meteorological factors, and the value range is 0 < ≤1.

[0015] In the above preferred embodiment of the corn northern leaf blight early warning system based on data analysis: calculate the physiological state influence coefficient The specific steps are as follows: Obtain the normal growth data of corn according to historical growth data The normal growth data of corn includes the minimum chlorophyll content and the maximum chlorophyll content , the minimum water content and the maximum water content as well as the optimal growth temperature ; According to the normal growth data of corn and the physiological state data, calculate the physiological state influence coefficient of corn The specific formula is as follows:

[0016] Wherein, represents the adjustment parameter of the chlorophyll content , and the value range >0; is the adjustment parameter of the water content H, and the value range is <0; is the adjustment parameter of the real-time temperature content T, and the value range is the real number 0 < ≤5; represents the chlorophyll content weight coefficient, with a value range of 0.1 < ≤0.3, is the weight coefficient of the moisture content H, with a value range of 0.3 ≤ ≤0.6, is the weight coefficient of the real-time temperature content T, with a value range of 0.2 ≤ ≤0.5, and + + = 1.

[0017] In the above preferred solution of the northern corn leaf blight early warning system based on data analysis: calculating the northern corn leaf blight impact index The specific steps are as follows: According to the meteorological impact coefficient , the planting density impact coefficient , the pathogen transmission rate and the corn physiological state impact coefficient , calculate the northern corn leaf blight impact index , and the specific formula is as follows:

[0018] Among them, is the weight coefficient of the meteorological impact coefficient , with a value range of 0 < ≤0.2, is the weight coefficient of the planting density impact coefficient , with a value range of 0.1 ≤ ≤0.3, is the weight coefficient of the pathogen transmission rate , with a value range of 0.2 ≤ ≤0.4, is the weight coefficient of the corn physiological state impact coefficient , with a value range of 0.1 < ≤0.4, and ; Set the northern corn leaf blight impact threshold set , the northern corn leaf blight impact threshold set F includes the primary threshold , the secondary threshold and the tertiary threshold , among which, < < ; When the northern corn leaf blight impact index ≤ , do not trigger the northern corn leaf blight risk warning; When <Large leaf spot impact index ≤ When, trigger the first-level risk warning of large leaf spot in corn and generate primary protection instructions; When <Large leaf spot impact index ≤ When, trigger the second-level risk warning of large leaf spot in corn and generate intermediate protection instructions; When <Large leaf spot impact index When, trigger the third-level risk warning of large leaf spot in corn and generate advanced protection instructions.

[0019] In the preferred solution of the above-mentioned corn large leaf spot warning system based on data analysis: The data annotation map includes: According to the statistical meteorological impact coefficient within multiple unit time periods The generated meteorological impact coefficient line graph, the statistical planting density impact coefficient within multiple unit time periods The generated planting density impact bar graph, the statistical pathogen transmission rate within multiple unit time periods The generated pathogen transmission rate impact radar graph, the statistical physiological state impact coefficient within multiple unit time periods The generated physiological state scatter plot and the large leaf spot impact index trend graph; The present invention also discloses a method for warning large leaf spot in corn based on data analysis, which is used to implement the corn large leaf spot warning system based on data analysis, including the following steps: Step 1: Real-time collect meteorological data, planting density data, pathogen transmission data and physiological state data of corn growth; Step 2: Analyze the meteorological data, planting density data, pathogen transmission data and physiological state data of corn plants respectively to obtain the meteorological impact coefficient , planting density impact coefficient , pathogen transmission rate And physiological state impact coefficient ; Step 3: According to the meteorological impact coefficient , planting density impact coefficient , pathogen transmission rate And physiological state impact coefficient , calculate the large leaf spot impact index ; Set the large leaf spot impact threshold set , according to the large leaf spot impact index And the large leaf spot impact threshold set Judge whether to trigger the risk warning of large leaf spot in corn and generate matching protection instructions; Step 4: Display the warning information and data annotation map in real time, generate a warning analysis report, and send it to relevant personnel via email, text message, or system notification.

[0020] (III) Beneficial Effects The present invention provides a warning method and system for northern corn leaf blight based on data analysis, having the following beneficial effects: (1) The data acquisition module collects meteorological data, planting density data, pathogen transmission data, and physiological state data of corn growth in real time, ensuring comprehensive and in-depth monitoring of the key factors affecting the occurrence of northern corn leaf blight, avoiding the limitations of a single data source, providing a rich data basis for subsequent analysis and warning, being able to capture potential risk factors at the early stage of disease occurrence, timely discovering potential problems of corn plants in resisting northern corn leaf blight, and improving the comprehensiveness of warning; (2) The data analysis module obtains the meteorological influence coefficient , planting density influence coefficient , pathogen transmission rate , and physiological state influence coefficient by analyzing different types of data, converting complex influencing factors into specific quantitative indicators, making the assessment of disease risk more accurate, helping users quickly understand the specific influence degree of each factor on the occurrence of northern corn leaf blight, and thus being able to take preventive and control measures targeted; (3) The warning release module calculates the northern corn leaf blight influence index according to multiple influence coefficients, can more accurately judge the risk of disease occurrence, trigger a warning in time, avoid misjudgment and missed judgment of traditional monitoring methods, generate a protection instruction, and help take effective prevention and control measures before or at the initial stage of disease occurrence, reducing the impact of the disease on corn yield; (4) The data display module displays the warning information and data annotation map in real time, enabling users to intuitively understand the degree and change trend of disease risk, quickly master key information without complex data analysis, generate a warning analysis report, and send it to relevant personnel via email, text message, or system notification, ensuring timely transmission of information, facilitating the joint participation of multiple relevant parties in the prevention and control of the disease, and improving the response efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic flow chart of the warning method for northern corn leaf blight based on data analysis of the present invention; DETAILED DESCRIPTION OF THE INVENTION

[0022] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0023] Please refer to Figure 1 , the present invention provides a warning system for northern corn leaf blight based on data analysis, including: A data acquisition module for real-time acquisition of meteorological data, planting density data, pathogen transmission data, and physiological state data of corn growth; Specifically, the data acquisition module is responsible for real-time acquisition of key data in multiple aspects related to the occurrence of northern corn leaf blight; the meteorological data includes rainfall , temperature , humidity X, and light intensity ; the planting density data mainly includes the area of the corn field , the number of corn plants , and soil fertility data; the pathogen transmission data mainly includes the time of discovery of diseased plants , the diffusion time period of diseased plants , and the historical meteorological influence coefficient ; the physiological state data mainly includes the chlorophyll content of plants , the water content H of plants, and the temperature content T of plants; these conditions have important influences on the reproduction and transmission of pathogens and the growth state of corn plants.

[0024] It should be noted that by collecting these four types of data, a comprehensive information basis is provided for the system, which can analyze the occurrence risk of northern corn leaf blight from multiple angles and avoid the limitations of a single data source; real-time acquisition ensures the timeliness of the data, can timely reflect the changes in the corn growth environment and plant state, and provides the latest data support for accurate warning.

[0025] A data analysis module for analyzing meteorological data, planting density data, pathogen transmission data, and physiological state data of corn plants respectively to obtain a meteorological influence coefficient , a planting density influence coefficient , a pathogen transmission rate , and a physiological state influence coefficient .

[0026] Specifically, the collected meteorological data is analyzed to calculate the meteorological influence coefficient ; the planting density data is analyzed to calculate the planting density influence coefficient ; Analyze the pathogen transmission data, calculate the transmission rate of the pathogen. The faster the transmission rate, the higher the risk of disease spread. Analyze the physiological state data to obtain the physiological state influence coefficient. , determine the impact of the plant's health status on the occurrence of northern leaf blight of maize. The physiological state influence coefficient of healthy plants is relatively low, while that of plants with poor growth or under stress is relatively high.

[0027] Early warning release module, according to the meteorological influence coefficient , planting density influence coefficient , pathogen transmission rate and physiological state influence coefficient , calculate the northern leaf blight influence index ; Set the northern leaf blight influence threshold set , according to the northern leaf blight influence index and the northern leaf blight influence threshold set to judge whether to trigger the risk early warning of northern leaf blight of maize and generate a matching protection instruction.

[0028] Specifically, the northern leaf blight influence index comprehensively reflects the possibility and severity of the occurrence of northern leaf blight of maize. Compare the calculated northern leaf blight influence index with the preset threshold set to judge whether to trigger the risk early warning of northern leaf blight of maize. If the index exceeds the threshold, it indicates a higher risk of disease occurrence and an early warning needs to be issued in a timely manner; when the early warning is triggered, generate a protection instruction matching the early warning level according to the current situation. The protection instruction can include suggestions on taking control measures.

[0029] By calculating the influence index by integrating multiple factors, it is possible to more accurately judge the risk of northern leaf blight of maize, issue an early warning in a timely manner, gain time for farmers to take preventive measures, and the generated protection instructions provide farmers with specific action plans, which helps to improve the control effect and reduce disease losses.

[0030] Data display module, used to receive the northern leaf blight influence index and the northern leaf blight influence threshold set from the early warning release module, and display the early warning information and data annotation map in real time, and generate an early warning analysis report, which is sent to relevant personnel by email, text message or system notification.

[0031] Specifically, the early warning information can reflect the current early warning level, and the data annotation map can visually display the change trend of each influence coefficient.

[0032] Specifically, the early warning analysis report elaborates on the risk status of northern corn leaf blight, the analysis of influencing factors, and the recommended control measures, enabling relevant personnel to intuitively understand the risk status of northern corn leaf blight and grasp key information without complex data analysis; Furthermore, the early warning analysis report is sent to relevant personnel via email, text message, or system notification to ensure timely information dissemination, facilitate joint response measures by all parties, and improve the coordination and efficiency in dealing with the disease.

[0033] In the preferred solution of the above-mentioned northern corn leaf blight early warning system based on data analysis: calculating the meteorological influence coefficient The specific steps are as follows: Obtain meteorological data for a future time period based on weather forecasts, analyze the meteorological data, and calculate the meteorological influence coefficient , and the specific formula is as follows:

[0034] Among them, is the influence factor of rainfall , with a value range of 0.1 ≤ ≤ 0.3, is the influence factor of temperature , with a value range of 0.2 ≤ ≤ 0.4, is the influence factor of humidity X, with a value range of 0.3 ≤ ≤ 0.5, is the influence factor of light intensity , with a value range of 0.1 < ≤ 0.3 and ,, represents the error term of the meteorological data on the meteorological influence coefficient ; It should be noted that for different meteorological factors, such as rainfall , temperature , humidity X, and light intensity , the influence on the occurrence of the disease is quantified and summed up. Each factor is weighted by a weight coefficient, and these coefficients reflect the relative importance of each factor to the disease risk, and the meteorological influence coefficient is calculated based on specific meteorological data; The meteorological influence coefficient is calculated through the above formula., mainly used for predicting the impact of diseases by comprehensively considering multiple meteorological factors such as future rainfall, temperature, humidity, and light intensity per unit time, which can more comprehensively evaluate the combined impact of these factors on the occurrence risk of northern corn leaf blight. This comprehensive evaluation is more accurate and comprehensive than considering single factors; by assigning a weight coefficient to each meteorological factor, it is possible to more clearly understand which factors have a greater impact on the occurrence of diseases, and thus take targeted measures for prevention and control; the calculated meteorological impact coefficient can be an important part of the early warning system, providing timely and accurate meteorological risk information for farmers, agricultural managers, and decision-makers. This helps to take preventive measures in advance according to the changes in meteorological conditions, reduce the occurrence and losses of diseases, and improve agricultural production efficiency.

[0035] In the preferred solution of the above-mentioned northern corn leaf blight early warning system based on data analysis: analyze the planting density data and calculate the planting density impact coefficient The specific steps are as follows: Set the planting density standard value according to the average value of the planting density data of high-yield fields in historical planting data .

[0036] Real-time monitor the area of the corn field in the planting density data through unmanned aerial vehicle technology and the number of corn plants ; According to the planting density data, the planting density standard value , the meteorological impact coefficient and the soil fertility index , calculate the planting density impact coefficient , and the specific formula is as follows:

[0037] Among them, the yield conditions under different soil fertilities and different climate conditions are statistically analyzed based on historical planting data, and the calculation model is trained through multiple groups of data. Input the current soil fertility data and climate data, and then obtain the adjustment factor , and the value range is positive real numbers; represents the soil fertility index, and the value range is >0; It should be noted that on the basis of the simple planting density ratio, this formula introduces the non-linear adjustment of soil fertility and climate conditions. Through the adjustment factor , the sensitivity of the soil fertility and climate conditions to the planting density impact coefficient can be controlled. When the soil fertility is high and the climate conditions are favorable, the values of the soil fertility index and the meteorological impact coefficient are close to 1, making the planting density impact coefficient There is an increase compared to the simple ratio, indicating that a good growth environment may allow for higher planting densities without increasing the disease risk. Conversely, when soil fertility is low or climatic conditions are unfavorable, the soil fertility index and the meteorological impact coefficient decrease, resulting in decreasing, suggesting that it may be necessary to reduce the planting density to reduce the disease risk; not only considering the actual planting density in the corn field, but also incorporating the soil fertility index and the influence of climatic conditions, this comprehensive consideration makes the calculation of the planting density impact coefficient more comprehensive and accurate, and can more truly reflect the impact of planting density on the occurrence risk of northern leaf blight of corn; the adjustment factor in the formula can be adjusted according to different soil and climatic conditions, and this flexibility enables the formula to be applicable to the corn planting environments in different regions, improving its universality and practicality; by quantifying factors such as planting density, soil fertility, and climatic conditions, and calculating through a mathematical formula, the planting density impact coefficient provides a specific value to evaluate the impact of planting density on the occurrence risk of northern leaf blight of corn. This quantitative evaluation helps farmers and agricultural technicians more intuitively understand the relationship between planting density and disease risk, and thus make more accurate decisions.

[0038] In the above preferred scheme of the early warning system for northern leaf blight of corn based on data analysis: The specific steps for calculating the soil fertility index are as follows: Obtain soil fertility data through a soil fertility monitor or regular soil sampling and testing. The soil fertility data includes organic matter content , nitrogen content , phosphorus content , potassium content and the soil value .

[0039] Set the optimal value of organic matter content , the optimal value of soil pH , the minimum threshold of nitrogen content , the minimum threshold of phosphorus content and the minimum threshold of potassium content according to historical planting data.

[0040] Obtain the change range of soil pH based on the organic matter content data of high-yield fields.

[0041] According to the soil fertility data, the optimal value of organic content , the optimal value of soil pH , the minimum threshold of nitrogen content 、Minimum threshold of phosphorus content 、Minimum threshold of potassium content and the change range of soil pH value Calculate the soil fertility index ,

[0042] Among them, represents the change range of soil pH value, and the value is 0 < < 1, represents the weight coefficient of organic matter content with a value range of > 0, represents the weight coefficient of nitrogen content with a value range of > 0, represents the weight coefficient of phosphorus content with a value range of > 0, represents the weight coefficient of potassium content with a value range of > 0, represents the error term of soil fertility data for the soil fertility index .

[0043] It should be noted that by comprehensively considering the organic matter content in the soil , nitrogen content , phosphorus content , potassium content and soil value , the fertility status of the soil is evaluated. Each nutrient content and pH value are standardized to near their optimal or minimum values, and weighted summation is performed in exponential form to obtain a comprehensive soil fertility index .

[0044] This comprehensive evaluation method can reflect the actual fertility level of the soil better than a single index, providing a scientific basis for optimizing the growth environment of corn. Each nutrient content and pH value in the formula are standardized to near their optimal or minimum values. This treatment eliminates the differences in dimension and order of magnitude between different nutrient contents and pH values, enabling them to be compared and weighted summed on the same scale, thus improving the accuracy and comparability of the evaluation results. By performing weighted summation in exponential form, different weight coefficients can be assigned according to the contribution degree of different nutrient contents and pH values to soil fertility, which can more reasonably reflect the importance of each factor in soil fertility evaluation and make the evaluation results more in line with the actual situation.

[0045] In the preferred embodiment of the above-mentioned corn northern leaf blight early warning system based on data analysis: calculating the pathogen transmission rate The specific steps are as follows: Set the basic transmission rate according to the average value of the historical northern leaf blight transmission rate .

[0046] According to the pathogen transmission data and the basic transmission rate , calculate the pathogen transmission rate , and the specific formula is as follows:

[0047] Wherein, represents the number of infected plants during the time period from time point to time point during the spread of diseased plants, represents the serial number of the collection time point, and the values are 1, 2, 3... , represents the total number of collection time points, represents the influence index of the time efficiency factor, and the value range is a positive integer, represents the weight coefficient of meteorological factors, and the value range is 0 < ≤1.

[0048] It should be noted that the operating principle of the present invention is: the basic transmission rate is a constant set according to historical data, representing the natural transmission speed of the pathogen without the interference of other external factors; reflects the time efficiency of the pathogen transmission, that is, the diffusion speed of the pathogen within a given time period; the influence index of the time efficiency factor is a positive integer, used to adjust the influence degree of the time efficiency factor on the transmission rate; considers the influence of multiple meteorological factors on the pathogen transmission rate. Each meteorological factor has a corresponding weight coefficient, and the value range of the weight coefficient is between 0 and 1, indicating the relative importance of the meteorological factor to the transmission rate. By weighted summing all meteorological factors, the comprehensive influence of meteorological factors on the transmission rate is obtained.

[0049] By comprehensively considering the time efficiency and meteorological factors, this formula can more accurately predict the pathogen transmission rate, provide timely disease early warning information for farmers, help them take effective prevention and control measures. Precise disease early warning helps to optimize the use of pesticides and other prevention and control resources, reduce unnecessary waste, and reduce agricultural production costs.

[0050] In the preferred embodiment of the above-mentioned early warning system for northern corn leaf blight based on data analysis: Calculate the physiological state influence coefficient The specific steps are as follows: Obtain the normal growth data of corn based on historical growth data The normal growth data of corn includes: taking the minimum value of the chlorophyll content of corn in high-yield fields with an average of many years , the maximum value of the chlorophyll content , the minimum value of the moisture content , the maximum value of the moisture content and the optimal growth temperature .

[0051] According to the normal growth data of corn and the physiological state data, calculate the physiological state influence coefficient of corn , and the specific formula is as follows:

[0052] Wherein, represents the adjustment parameter of the chlorophyll content , and the value range >0; is the adjustment parameter of the moisture content H, and the value range is <0; is the adjustment parameter of the real-time temperature content T, and the value range is real number 0< ≤5; represents the weight coefficient of the chlorophyll content , and the value is 0.1< ≤0.3, is the weight coefficient of the moisture content H, and the value range is 0.3≤ ≤0.6, is the weight coefficient of the real-time temperature content T, and the value is 0.2≤ ≤0.5, and + + =1.

[0053] It should be noted that for the chlorophyll content, calculate the relative deviation degree between the current content and the minimum value, and take the adjustment parameter as the exponent and multiply it by the weight coefficient ; for the moisture content, also calculate the relative deviation degree between the current content and the minimum value, and take the adjustment parameter as the exponent and multiply it by the corresponding weight coefficient ; for the temperature, calculate the reciprocal of the absolute deviation between the current temperature and the optimal temperature, and take the adjustment parameter As an exponent and multiply by the weight coefficient 3. Here, the reciprocal of the absolute deviation is used to reflect the positive or negative impact of temperature on the physiological state, that is, the closer to the optimal temperature, the greater the impact coefficient. Add the evaluation results of the three aspects to obtain the physiological state impact coefficient , this coefficient synthesizes the real-time chlorophyll content , the real-time water content H of the plant, and the real-time temperature content T of the plant on the physiological state of maize, and is used to evaluate the current disease resistance ability of maize

[0054] Through real-time monitoring and calculation, the current physiological state of maize can be accurately evaluated, providing an accurate basis for disease early warning. When the physiological state impact coefficient is low, it indicates that maize may be in a state vulnerable to disease invasion. At this time, early intervention measures can be taken, such as strengthening nutrient management, adjusting irrigation volume, etc., to improve the resistance of maize. According to the evaluation result of the physiological state impact coefficient , prevention and control resources can be more reasonably allocated to avoid unnecessary waste. Through timely intervention and optimized management, the disease resistance ability and growth quality of maize can be improved, thereby increasing yield and economic benefits

[0055] In the preferred scheme of the above-mentioned Setosphaeria turcica early warning system for maize based on data analysis: The specific steps for calculating the Setosphaeria turcica impact index are as follows According to the meteorological impact coefficient , the planting density impact coefficient , the pathogen transmission rate , and the physiological state impact coefficient of maize , calculate the Setosphaeria turcica impact index . The specific formula is as follows

[0056] Among them is the weight coefficient of the meteorological impact coefficient , and its value range is 0 < ≤0.2 is the weight coefficient of the planting density impact coefficient , and its value range is 0.1 ≤ ≤0.3 is the weight coefficient of the pathogen transmission rate , and its value range is 0.2 ≤ ≤0.4 is the physiological state impact coefficient of maize , and its value range is 0.1 < ≤0.4, and ; Set the set of northern leaf blight impact thresholds , the set of northern leaf blight impact thresholds F includes the first-level threshold , the second-level threshold and the third-level threshold , where < < ; When the northern leaf blight impact index ≤ , no northern leaf blight risk warning for maize is triggered; When < northern leaf blight impact index ≤ , a first-level northern leaf blight risk warning for maize is triggered, and a primary protection instruction is generated; When < northern leaf blight impact index ≤ , a second-level northern leaf blight risk warning for maize is triggered, and an intermediate protection instruction is generated; When < northern leaf blight impact index , a third-level northern leaf blight risk warning for maize is triggered, and an advanced protection instruction is generated; By conducting a large number of field experiments and data analysis, the set of northern leaf blight impact thresholds is set, and the risk of northern leaf blight in maize is divided into different levels, each level corresponding to different protection measures and warning levels. This threshold can reflect the potential loss of maize yield under different disease levels; It should be noted that by calculating the northern leaf blight impact index , multiple key factors affecting the occurrence and development of northern leaf blight in maize are comprehensively considered, including meteorological conditions, planting density, pathogen transmission rate, and the physiological state of maize. Each factor is weighted by its corresponding weight coefficient to ensure that the contribution of different factors to the final impact index is reasonably reflected. These weight coefficients are set according to the relative importance of each factor in promoting or inhibiting the development of northern leaf blight, and their value ranges are determined through experiments or expert experience; Not triggering a northern leaf blight risk warning for maize indicates that under the current environmental conditions, the risk of northern leaf blight in maize is extremely low, and no special protection measures are required. Without special instructions, routine agricultural management can be maintained; A first-level northern leaf blight risk warning for maize indicates that the risk of northern leaf blight in maize begins to rise but is still within a controllable range, and it is necessary to pay attention to and execute the primary protection instruction; the primary protection instruction includes strengthening field inspections, optimizing irrigation and fertilization strategies, and moderately reducing the planting density to reduce the risk of disease occurrence.

[0057] The secondary risk warning for northern corn leaf blight indicates a significant increase in the occurrence risk of northern corn leaf blight, and intermediate protection instructions need to be implemented; the intermediate protection instructions include using biological or chemical control methods, increasing field ventilation, timely removing diseased plants and plant residues, etc., to control the spread of the disease.

[0058] The tertiary risk warning for northern corn leaf blight indicates an extremely high occurrence risk of northern corn leaf blight, which may have caused relatively serious diseases, and immediate implementation of advanced protection instructions is required; the advanced protection instructions include comprehensively spraying highly effective fungicides, urgently adjusting the planting structure, strengthening disease monitoring and reporting, to minimize the impact of the disease on corn yield.

[0059] In the preferred solution of the above-mentioned early warning system for northern corn leaf blight based on data analysis: The steps of the data display module are as follows: The line graph of the meteorological influence coefficient uses the meteorological influence coefficient as the vertical axis, and shows the impact of meteorological conditions on the occurrence risk of northern corn leaf blight through a line graph, helping users quickly identify which time periods have relatively favorable or unfavorable meteorological conditions for the occurrence of northern corn leaf blight, so as to take corresponding management measures.

[0060] The bar graph of the influence of planting density is classified by different planting density intervals, and shows the corresponding planting density influence coefficients for each density interval to intuitively show the influence of planting density on the occurrence risk of northern corn leaf blight and provide a basis for adjusting the planting density.

[0061] The radar chart of the influence of the pathogen transmission rate shows the changes in the pathogen transmission rate, and the data for each unit time corresponds to an axis on the radar chart.

[0062] The scatter plot of the physiological state uses a certain or certain physiological indicators of corn as the horizontal axis and the influence coefficient of corn physiological state as the vertical axis, and shows the changes in the resistance of corn to northern corn leaf blight under different physiological states through scatter points, helping users understand the current physiological state of corn, evaluate its disease resistance ability, and thus take appropriate protection measures.

[0063] The trend chart of the northern corn leaf blight influence index uses time as the horizontal axis and the northern corn leaf blight influence index as the vertical axis, and shows the change trend of the northern corn leaf blight influence index over time through a line graph, directly reflecting the dynamic change of the occurrence risk of northern corn leaf blight, and providing an important basis for formulating warning levels and protection instructions.

[0064] On the above-mentioned various types of data annotation diagrams, the system will automatically mark the corresponding coefficient or exponent values to ensure the accuracy and readability of the information. By integrating all the warning information and data annotation diagrams, the system generates a detailed warning analysis report. Finally, the system sends the warning analysis report to users in a timely manner via email, text message, or internal system notification, ensuring that they can obtain the latest warning information in a timely manner and take corresponding management measures accordingly.

[0065] On the other hand, the present invention also discloses a method for warning of northern corn leaf blight based on data analysis. A warning system for northern corn leaf blight that realizes data analysis includes the following steps: Step 1: Real-time collect meteorological data, planting density data, pathogen transmission data, and physiological state data of corn growth; Step 2: Analyze the meteorological data, planting density data, pathogen transmission data, and physiological state data of corn plants respectively to obtain a meteorological influence coefficient , a planting density influence coefficient , a pathogen transmission rate , and a physiological state influence coefficient ; Step 3: According to the meteorological influence coefficient , the planting density influence coefficient , the pathogen transmission rate , and the physiological state influence coefficient , calculate the northern corn leaf blight influence index ; Set a set of northern corn leaf blight influence thresholds , and judge whether to trigger a risk warning for northern corn leaf blight and generate a matching protection instruction according to the northern corn leaf blight influence index and the set of northern corn leaf blight influence thresholds ; Step 4: Real-time display the warning information and data annotation diagrams, and generate a warning analysis report, which is sent to relevant personnel via email, text message, or system notification.

[0066] The above-mentioned embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above-mentioned embodiments can be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution.

[0067] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0068] As described above, the foregoing is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application.

Claims

1. The corn leaf blight early warning system based on data analysis is characterized by: include: Data collection module, used to collect meteorological data, planting density data, pathogen transmission data and physiological status data of corn growth in real time; The data analysis module analyzes meteorological data, planting density data, pathogen transmission data, and physiological status data to obtain the meteorological impact coefficient , Planting density influence coefficient , pathogen transmission rate And the physiological state influence coefficient ; Warning release module, based on the meteorological impact coefficient , Planting density influence coefficient , pathogen transmission rate And the physiological state influence coefficient , calculate the big spot disease impact index ; Set the threshold set for the impact of big spot disease , according to the big spot disease impact index and the threshold set for the impact of the disease Determine whether to trigger a risk warning for corn leaf blight and generate matching protection instructions; Data display module, used to receive the impact index of the giant spot disease from the early warning release module and the threshold set for the impact of the disease , display warning information and data annotation graphs in real time, and generate warning analysis reports, which are sent to relevant personnel via email, SMS or system notification.

2. The corn leaf blight early warning system based on data analysis according to claim 1, characterized in that: Weather data including rainfall ,temperature , humidity X and light intensity ; Planting density data include corn field area , Number of corn plants and soil fertility data; Pathogen transmission data including the number of diseased strains during the discovery period , Number of diseased plants during the spreading period And the historical meteorological influence coefficient ; Physiological status data including real-time chlorophyll content of plants , real-time plant moisture content H and real-time plant temperature content T.

3. The corn leaf blight early warning system based on data analysis according to claim 2 is characterized in that: Calculate the meteorological influence coefficient The specific steps are: Calculate the meteorological impact coefficient based on the meteorological data of the future time period , the specific formula is as follows: ； in, For rainfall The impact factor is 0.1≤ ≤0.3, For temperature The impact factor is 0.2≤ ≤0.4, is the influence factor of humidity X, and its value is 0.3≤ ≤0.5, Light intensity The impact factor is 0.1< ≤0.3 and , Represents the meteorological data's influence on the meteorological The error term of .

4. The corn leaf blight early warning system based on data analysis according to claim 3 is characterized by: Calculate the influence coefficient of planting density The specific steps are: Set standard planting density values ​​based on historical planting data ; According to the area of ​​corn field , Number of corn plants , Planting density standard value And the meteorological influence coefficient , calculate the planting density influence coefficient The specific formula is as follows: ； in, The adjustment factor representing soil fertility and climate conditions, with a range of positive real numbers; Represents the soil fertility index, with a value range of >

0.

5. The corn leaf blight early warning system based on data analysis according to claim 4 is characterized in that: Calculate soil fertility index The specific steps are: Soil fertility data including organic matter content , nitrogen content , phosphorus content Potassium content and soil value ; Set the optimal value of organic matter content based on historical planting data Optimal pH value , minimum nitrogen content threshold , minimum threshold of phosphorus content , minimum threshold of potassium content and the range of soil pH ; According to soil fertility data, optimal organic content Optimal pH value , minimum nitrogen content threshold , minimum threshold of phosphorus content , minimum threshold of potassium content and the range of soil pH Calculate soil fertility index , ;in, Represents the range of soil pH, with a value of 0< <1, Represents organic matter content The weight coefficient ranges from >0, Represents nitrogen content The weight coefficient ranges from >0, Represents phosphorus content The weight coefficient ranges from >0, Represents potassium content The weight coefficient ranges from >0, Represents soil fertility data to soil fertility index The error term of .

6. The corn leaf blight early warning system based on data analysis according to claim 5 is characterized in that: Calculating pathogen transmission rate The specific steps are: Set base propagation rate based on historical planting data ; Based on pathogen transmission data and basic transmission rate , calculate the pathogen transmission rate , the specific formula is as follows: ； in, Indicates the time point in the process of disease spread To time point The number of infected plants in a given period of time, Indicates the sequence number of the collection time point, the value is 1, 2, 3... , Represents the total number of acquisition time points, Represents the influence index of the time efficiency factor, and its value range is a positive integer. Represents the weight coefficient of meteorological factors, with a value range of 0< ≤1.

7. The corn leaf blight early warning system based on data analysis according to claim 6 is characterized in that: Calculate the influence coefficient of physiological state The specific steps are: Obtain normal growth data of corn based on historical growth data , normal growth data of corn Including minimum chlorophyll content and maximum chlorophyll content , minimum moisture content and maximum moisture content The optimal growth temperature ; According to the normal growth data of corn and physiological status data, calculate the influence coefficient of corn physiological status , the specific formula is as follows: ； in, Represents chlorophyll content The adjustment parameters, the value range >0; is the adjustment parameter of moisture content H, and its value range is <0; is the adjustment parameter of the real-time temperature content T, and its value range is real number 0< ≤5; Represents chlorophyll content The weight coefficient is 0.1< ≤0.3, is the weight coefficient of moisture content H, and its value range is 0.3≤ ≤0.6, is the weight coefficient of the temperature real-time content T, and its value is 0.2≤ ≤0.5, and + + =1.

8. The corn leaf blight early warning system based on data analysis according to claim 7 is characterized in that: Calculation of the Big Spot Impact Index The specific steps are: According to the meteorological influence coefficient , Planting density influence coefficient , pathogen transmission rate And the influence coefficient of corn physiological state , calculate the big spot disease impact index , the specific formula is as follows: ； in, is the meteorological influence coefficient The weight coefficient ranges from 0< ≤0.2, is the planting density influence coefficient The weight coefficient ranges from 0.1 to ≤0.3, The pathogen transmission rate The weight coefficient is in the range of 0.2≤ ≤0.4, is the influence coefficient of corn physiological state The weight coefficient ranges from 0.1< ≤0.4, and ; Set the threshold set for the impact of the disease , the threshold set F for the impact of the disease includes the first-level threshold , Secondary threshold and the third threshold ,in, < < ; When the big spot disease impact index ≤ When the risk warning of corn leaf blight is triggered, when <Big spot disease impact index ≤ When the first-level corn leaf blight risk alarm is triggered, the primary protection instruction is generated; when <Big spot disease impact index ≤ When the second-level corn leaf blight risk warning is triggered, an intermediate protection instruction is generated; when <Big spot disease impact index When the third-level corn leaf blight risk warning is triggered, an advanced protection instruction is generated.

9. The corn leaf blight early warning system based on data analysis according to claim 8, characterized in that: Data annotation graphs include: Based on statistics of meteorological influence coefficients in multiple unit time periods Generate a line graph of meteorological influence coefficients and count the influence coefficients of planting density in multiple unit time periods The generated planting density affects the histogram and statistics of the pathogen transmission rate in multiple unit time periods Generate a radar chart of the pathogen transmission rate and calculate the influence coefficient of physiological status in multiple unit time periods Generated scatter plot of physiological status and trend graph of the big spot disease impact index.

10. The early warning method for corn leaf blight based on data analysis is characterized by: The method for implementing the corn leaf blight early warning system according to any one of claims 1 to 9 comprises the following steps: Step 1: Real-time collection of meteorological data, planting density data, pathogen transmission data, and physiological status data of corn growth; Step 2: Analyze the meteorological data, planting density data, pathogen transmission data, and corn plant physiological status data to obtain the meteorological impact coefficient , Planting density influence coefficient , pathogen transmission rate And the physiological state influence coefficient ; Step 3: According to the meteorological influence coefficient , Planting density influence coefficient , pathogen transmission rate And the physiological state influence coefficient , calculate the big spot disease impact index ; Set the threshold set for the impact of big spot disease , according to the big spot disease impact index and the threshold set for the impact of the disease Determine whether to trigger a risk warning for corn leaf blight and generate matching protection instructions; Step 4: Display warning information and data annotation graphs in real time, generate a warning analysis report, and send it to relevant personnel via email, SMS or system notification.

Images