Intelligent pesticide application monitoring method and system based on crop protection

Abstract

The invention discloses an intelligent pesticide application monitoring method and system based on crop protection, and relates to the technical field of pesticide application monitoring, and the method comprises the steps of transpiration detection, soil state detection, pesticide quality detection and pesticide use control. The transpiration state is judged in combination with a pesticide standard transpiration concentration change slope interval of an artificial climate chamber experiment and current data, then the pesticide loss state is judged through soil state detection according to a pesticide standard soil concentration change slope interval preset in the experiment, and then the pesticide quality is detected. Through crop growth picture feature similarity calculation, the pesticide use state is determined, finally through pesticide use control, differential regulation and control are carried out according to three states, the pesticide utilization rate is increased, pollution is reduced, and the crop growth quality is improved.

Description

Technical Field

[0001] This invention relates to the field of pesticide application monitoring technology, specifically to an intelligent monitoring method and system for pesticide application based on crop protection. Background Art

[0002] As an industry that connects most industrial chains, the quality of agriculture's development directly affects upstream and downstream sectors such as agricultural product processing, logistics, and sales. In addition, modern agriculture also bears the responsibility of ecological protection, and needs to reduce the environmental impact of pesticides while ensuring yield. Therefore, there is a need for an intelligent monitoring method and system for pesticide application based on crop protection.

[0003] In current agricultural production, pesticide application is still mainly based on human experience and judgment, lacking a scientific and systematic monitoring and control mechanism. On the one hand, pesticide application decisions are not fully linked to dynamic environmental factors. Environmental factors such as temperature, humidity, light intensity, and wind speed directly affect crop transpiration, causing fluctuations in the retention and volatilization rate of pesticides on the leaf surface. For example, pesticides evaporate too quickly under high temperature and strong wind conditions, which can easily lead to loss of efficacy. Pesticide penetration and retention in the soil can cause excessive pesticide loss to deep soil or water bodies, resulting in pollution.

[0004] Traditional methods are insufficient for accurately assessing the effectiveness of pesticide application. Judging the rationality of pesticide application relies solely on manual observation of crop growth, which fails to quantify the dynamic changes of pesticides in the environment. This often leads to problems such as over-application causing crop damage and environmental pollution, or insufficient application failing to effectively control pests and diseases. This not only wastes pesticide resources and exacerbates agricultural non-point source pollution, but also restricts the improvement of crop yield and quality, making it difficult to meet the needs of modern agriculture for green, efficient, and precise production. Summary of the Invention

[0005] To address the aforementioned technical shortcomings, the present invention aims to provide an intelligent monitoring method and system for pesticide application based on crop protection.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides an intelligent monitoring method for pesticide application based on crop protection, comprising the following steps: Step 1, transpiration detection: Collect historical transpiration environment data, analyze the historical transpiration environment data to establish a standard crop transpiration environment model, and then conduct experiments on the transpiration state of various pesticides to obtain the transpiration rate change curves of various pesticides. Further collect current transpiration environment data and air quality data, analyze the current transpiration environment data and air quality data, and then determine the current transpiration state of various pesticides.

[0007] Step 2: Soil condition detection: Collect current soil environmental data, analyze the current soil environmental data, and determine the current pesticide loss status of various pesticides.

[0008] Step 3: Pesticide quality testing: Collect data on the current crop growth status, analyze the data to determine the current usage status of various pesticides.

[0009] Step 4: Pesticide use control: Based on the current transpiration, pesticide runoff, and usage status of various pesticides, set up the current pesticide use control plan.

[0010] Preferably, the analysis of the current evapotranspiration environment data and air quality data is carried out as follows: The current evapotranspiration environment data includes, but is not limited to, the temperature, humidity, light intensity, wind speed, and precipitation at each application time for the target crop; the air quality data includes the evapotranspiration rate at each application time for the current pesticide and the concentration of each pesticide at each application time for the current pesticides; the current evapotranspiration environment data is input into a standard crop evapotranspiration environment model to obtain the standard evapotranspiration rate at each application time for the current environment; the standard evapotranspiration rate at each application time for the current environment is divided by the corresponding evapotranspiration rate to obtain the evapotranspiration correction rate at each application time for the current environment; and the concentration of each pesticide at each application time for the current pesticides is multiplied by the corresponding environmental evapotranspiration correction rate to obtain the converted pesticide concentration at each application time for the current pesticides.

[0011] Plot the change curves to obtain the slope of the drug concentration change at various post-application times for different types of pesticides.

[0012] Preferably, the determination of the transpiration state of various pesticides is carried out as follows: if the slope of the pesticide concentration change falls within the standard transpiration concentration change slope range, it indicates that the transpiration state is normal, and the transpiration characteristic value is recorded as 0; if the slope of the pesticide concentration change is less than the minimum value of the standard transpiration concentration change slope range, it indicates that the transpiration state is too low, and the transpiration characteristic value is recorded as -1; if the slope of the pesticide concentration change is greater than the maximum value of the standard transpiration concentration change slope range, it indicates that the transpiration state is excessive, and the transpiration characteristic value is recorded as 1. In this way, the transpiration state and transpiration characteristic value of various pesticides at different application times are obtained.

[0013] The weighting factors for each application duration of various pesticides are obtained from the database. The characteristic values ​​of each application duration of various pesticides are multiplied by the corresponding weighting factors and summed to obtain the transpiration characteristic values ​​of various pesticides. The standard transpiration characteristic value range is obtained from the database to obtain the transpiration status of various pesticides.

[0014] On the other hand, the present invention provides an intelligent monitoring system for pesticide application based on crop protection, comprising the following modules: a transpiration detection module, used to collect historical transpiration environmental data, analyze the historical transpiration environmental data to establish a standard crop transpiration environmental model, and then conduct experiments on the transpiration state of various pesticides to obtain the transpiration rate change curves of various pesticides; further, it collects current transpiration environmental data and air quality data, analyzes the current transpiration environmental data and air quality data, and then determines the current transpiration state of various pesticides.

[0015] The soil condition detection module is used to collect current soil environmental data, analyze the current soil environmental data, and determine the current pesticide loss status of various pesticides.

[0016] The pesticide quality testing module is used to collect data on the current crop growth status, analyze the data, and obtain the current usage status of various pesticides.

[0017] The pesticide use control module is used to set the current pesticide use control scheme based on the current transpiration status, pesticide loss status, and usage status of various pesticides.

[0018] The beneficial effects of this invention are as follows: 1. This invention first collects historical environmental data through transpiration detection, and combines it with artificial climate chamber experiments to obtain the slope range of pesticide standard transpiration concentration changes. It then judges the transpiration state based on the current data. Secondly, it judges the pesticide loss state through soil condition detection, based on the preset pesticide standard soil concentration change slope range. Then, it judges the pesticide use state through pesticide quality detection and by calculating the similarity of crop growth image features. Finally, it judges the pesticide use state through pesticide use control, and differentiates the regulation according to the three states. This invention improves pesticide utilization, reduces pollution, and improves crop growth quality.

[0019] 2. This invention reduces the waste of pesticides and solvents caused by traditional indiscriminate application by precisely controlling the application rate and solvent ratio, thereby reducing agricultural production costs. For example, when there is excessive transpiration, the solvent is increased instead of additional pesticides, and when there is insufficient leaching, the application rate is reduced instead of the total amount, thus improving the efficiency of pesticide resource utilization. In terms of ecological protection, the application height is adjusted by monitoring the pesticide leaching status to reduce the penetration of pesticides into deep soil and water bodies, thereby reducing the risk of agricultural non-point source pollution. At the same time, it avoids the harm of excessive pesticides to beneficial organisms in the field and maintains the balance of the farmland ecosystem.

[0020] 3. On the one hand, this invention judges the pesticide application status based on the similarity of crop growth image features, avoiding residue accumulation due to excessive application; on the other hand, it ensures that pesticides work according to the expected path through transpiration and soil monitoring, reducing the adsorption of excess pesticides in crop fruits and roots, and ultimately controlling the amount of pesticide residues in agricultural products from the source. While ensuring crop yield through normal pesticide application, it enhances the market competitiveness of agricultural products. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of the implementation steps of the method of the present invention.

[0023] Figure 2 This is a schematic diagram of the system structure connection of the present invention. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0025] according to Figure 1 As shown, this invention provides an intelligent monitoring method for pesticide application based on crop protection, comprising the following steps: Step 1, transpiration detection: Collect historical transpiration environmental data, analyze the historical transpiration environmental data to establish a standard crop transpiration environmental model, and then conduct experiments on the transpiration state of various pesticides to obtain the transpiration rate change curves of various pesticides. Further collect current transpiration environmental data and air quality data, analyze the current transpiration environmental data and air quality data, and then determine the current transpiration state of various pesticides.

[0026] In one specific embodiment, the historical evapotranspiration environmental data is collected in the following specific process: the historical evapotranspiration environmental data includes, but is not limited to, the temperature, humidity, light intensity, wind speed and precipitation of each historical pesticide application of the target crop. Temperature is collected by a temperature sensor, humidity is collected by a humidity sensor, light intensity is collected by a photosynthetically active radiation sensor, wind speed is collected by a small ultrasonic anemometer, and precipitation is collected by a tipping bucket rain gauge.

[0027] In one specific embodiment, the analysis of historical transpiration environment data is carried out as follows: the transpiration rate of the target crop after each historical pesticide application for a preset time is obtained from the database, and the mapping relationship between the historical transpiration environment data and the transpiration rate of the target crop is established through multiple linear regression of machine learning algorithm, so as to obtain a standard crop transpiration environment model: inputting transpiration environment data of various scenarios and outputting standard transpiration rate.

[0028] It should be noted that the transpiration rate of the target crop after each historical pesticide application at a preset time can be collected using a small transpiration rate measuring instrument.

[0029] Machine learning algorithms are existing technologies and can be found on the internet, so I will not go into detail here.

[0030] In one specific embodiment, the experiment on the transpiration state of various pesticides is conducted as follows: Select the target crop, simulate the field environment in an artificial climate chamber, set up a blank control group without pesticides and experimental groups of various pesticides, and conduct the experiment.

[0031] It should be noted that the artificial climate chamber allows staff to control transpiration environmental data such as temperature, humidity, light intensity, wind speed, and precipitation.

[0032] The experimental group applied the target pesticide according to the standard dosage preset by the staff, and collected the pesticide concentration at various time points after application to obtain the pesticide concentration of each type of pesticide in the experimental group at various time points after application.

[0033] It should be noted that the standard dosage for each pesticide is preset by staff, obtained through experience or by searching on the Internet.

[0034] The staff applied water at a pre-set standard dose to the blank control group and collected the transpiration rate at a pre-set time after watering to obtain the standard transpiration rate of the blank control group. The transpiration environment data of the artificial climate chamber was then input into the standard crop transpiration environment model to obtain the standard transpiration rate of the artificial climate chamber.

[0035] It should be noted that the standard dosage of water is set by the staff and is generally the same mass of water as the standard dosage of pesticide.

[0036] The evapotranspiration data in the artificial climate chamber are preset by the staff, including evapotranspiration data such as temperature, humidity, light intensity, wind speed, and precipitation.

[0037] Divide the standard transpiration rate of the artificial climate chamber by the standard transpiration rate of the blank control group to obtain the transpiration correction rate of the experimental group. Multiply the drug concentration of each pesticide at each time after application in the experimental group by the transpiration correction rate to obtain the ideal drug concentration of each pesticide at each time after application in the experimental group.

[0038] In one specific embodiment, the process of obtaining the transpiration rate change curves of various pesticides is as follows: plot the ideal pesticide concentration change curves of various pesticides in the experimental group with the time after each application as the horizontal axis and the ideal pesticide concentration as the vertical axis, thereby obtaining the slope of the pesticide concentration change of various pesticides in the experimental group at each time after application. Staff conducted experiments on the transpiration state of various pesticides according to a preset number of times, and then plotted the concentration change curves of each experiment. This yielded the slope of the pesticide concentration change at each application time for each pesticide in each experiment, and thus obtained the standard transpiration concentration change slope range for each pesticide at each application time.

[0039] It should be noted that the minimum slope of the pesticide concentration change at each application time in each experiment for various pesticides is recorded as the lower limit of the standard transpiration concentration change slope interval, and the maximum slope of the pesticide concentration change at each application time in each experiment for various pesticides is recorded as the upper limit of the standard transpiration concentration change slope interval. In this way, the standard transpiration concentration change slope interval for each application time for various pesticides can be obtained.

[0040] In one specific embodiment, the collection of current evapotranspiration environment data and air quality data is carried out in the following specific process: the current evapotranspiration environment data includes, but is not limited to, the temperature, humidity, light intensity, wind speed and precipitation of the target crop at each time after application. Temperature is collected by a temperature sensor, humidity is collected by a humidity sensor, light intensity is collected by a photosynthetically active radiation sensor, wind speed is collected by a small ultrasonic anemometer, and precipitation is collected by a tipping bucket rain gauge.

[0041] Air quality data includes the transpiration rate of pesticides at various times after application and the concentration of various pesticides at various times after application. The transpiration rate of pesticides at various times after application is collected using a small transpiration rate meter, and the concentration of various pesticides at various times after application is collected using a gas chromatography-mass spectrometry system.

[0042] In one specific embodiment, the analysis of the current evapotranspiration environment data and air quality data is carried out as follows: the current evapotranspiration environment data is input into a standard crop evapotranspiration environment model to obtain the standard evapotranspiration rate for each application time in the current environment; the standard evapotranspiration rate for each application time in the current environment is divided by the corresponding evapotranspiration rate to obtain the evapotranspiration correction rate for each application time in the current environment; the pesticide concentration for each application time of various pesticides is multiplied by the corresponding environmental evapotranspiration correction rate to obtain the converted pesticide concentration for each application time of various pesticides.

[0043] Plot the change curves to obtain the slope of the drug concentration change at various post-application times for different types of pesticides.

[0044] It should be noted that by plotting the duration of application on the horizontal axis and the converted pesticide concentration on the vertical axis, the curves showing the changes in the converted pesticide concentrations of various pesticides can be drawn, thereby obtaining the slope of the pesticide concentration changes at various application durations for various pesticides.

[0045] In one specific embodiment, the determination of the transpiration state of various pesticides is carried out as follows: if the slope of the pesticide concentration change falls within the standard transpiration concentration change slope range, it indicates that the transpiration state is normal, and the transpiration characteristic value is recorded as 0; if the slope of the pesticide concentration change is less than the minimum value of the standard transpiration concentration change slope range, it indicates that the transpiration state is too low, and the transpiration characteristic value is recorded as -1; if the slope of the pesticide concentration change is greater than the maximum value of the standard transpiration concentration change slope range, it indicates that the transpiration state is excessive, and the transpiration characteristic value is recorded as 1. In this way, the transpiration state and transpiration characteristic value of various pesticides at different application times are obtained.

[0046] The weighting factors for each application duration of various pesticides are obtained from the database. The characteristic values ​​of each application duration of various pesticides are multiplied by the corresponding weighting factors and summed to obtain the transpiration characteristic values ​​of various pesticides. The standard transpiration characteristic value range is obtained from the database to obtain the transpiration status of various pesticides.

[0047] It should be noted that the weighting factors for the duration of application of various pesticides are set by the staff, and the longer the duration of application, the greater the weighting factor.

[0048] The standard transpiration characteristic value range is set by the staff. For example, the standard transpiration characteristic value range is set to -0.5 to 0.5. When the transpiration characteristic value of a certain type of pesticide is less than the lower limit of the standard transpiration characteristic value range, the current transpiration status of that type of pesticide is too low. When the transpiration characteristic value of a certain type of pesticide is greater than the upper limit of the standard transpiration characteristic value range, the current transpiration status of that type of pesticide is excessive. When the transpiration characteristic value of a certain type of pesticide is within the standard transpiration characteristic value range, the current transpiration status of that type of pesticide is normal. This is an example and not the only limitation.

[0049] Step 2: Soil condition detection: Collect current soil environmental data, analyze the current soil environmental data, and determine the current pesticide loss status of various pesticides.

[0050] In one specific embodiment, the collection of current soil environmental data is carried out as follows: the current soil environmental data includes the concentration of various pesticides in the soil at various times after application. The current soil is sampled, pesticide extracts are prepared, and the concentrations of various pesticides are detected by a spectral sensor and recorded as the standard soil concentrations of various pesticides.

[0051] In one specific embodiment, the analysis of the current soil environmental data is carried out as follows: the standard soil concentration change slope range of various pesticides after each application time is obtained through experiments, and the pesticide loss status of various pesticides is determined according to the current transpiration status of various pesticides.

[0052] In one specific embodiment, the process of obtaining the standard soil concentration change slope range of various pesticides at different application times through experiments is as follows: Select the target crop, simulate the field environment in an artificial climate chamber, set up experimental groups of various pesticides, apply the target pesticides to the experimental groups according to the standard dosage preset by the staff, and collect the concentration of various pesticides in the soil at the corresponding time points at different application times to obtain the soil pesticide concentration of various pesticides at different application times in the experimental groups.

[0053] Plot the soil pesticide concentration change curves for each pesticide in the experimental group with the time after application as the horizontal axis and the soil pesticide concentration as the vertical axis, thereby obtaining the slope of the soil pesticide concentration change for each pesticide in the experimental group at each time after application.

[0054] Staff conducted soil experiments on various pesticides according to a predetermined number of times, and then plotted the soil pesticide concentration change curves for each experiment. This yielded the slope of soil pesticide concentration change for each pesticide at each application time after each experiment. The minimum slope of soil pesticide concentration change for each pesticide at each application time after each experiment was recorded as the lower limit of the standard soil concentration change slope interval, and the maximum slope of soil pesticide concentration change for each pesticide at each application time after each experiment was recorded as the upper limit of the standard soil concentration change slope interval. This yielded the standard soil concentration change slope interval for each pesticide at each application time after each experiment.

[0055] In one specific embodiment, the determination of the current pesticide loss status of various pesticides is carried out as follows: plotting the soil pesticide concentration change curves of various pesticides in the soil with the time after each application as the horizontal axis and the soil pesticide concentration as the vertical axis, thereby obtaining the slope of the soil pesticide concentration change of various pesticides in the soil at each time after application.

[0056] If the slope of soil pesticide concentration change falls within the standard soil concentration change slope range, it indicates that the pesticide loss is normal, and the pesticide loss characteristic value is recorded as 0. If the slope of soil pesticide concentration change is less than the minimum value of the standard soil concentration change slope range, it indicates that the pesticide loss is too low, and the pesticide loss characteristic value is recorded as -1. If the slope of soil pesticide concentration change is greater than the maximum value of the standard soil concentration change slope range, it indicates that the pesticide loss is excessive, and the pesticide loss characteristic value is recorded as 1. This allows us to obtain the pesticide loss status and pesticide loss characteristic value for each type of pesticide at different application times.

[0057] The weighting factors for each application duration of various pesticides are obtained from the database. The pesticide loss characteristic values ​​for each application duration of various pesticides are multiplied by the corresponding weighting factors and then summed to obtain the pesticide loss characteristic values ​​for various pesticides. The standard pesticide loss characteristic value range is obtained from the database to obtain the pesticide loss status of various pesticides.

[0058] It should be noted that the standard pesticide loss characteristic value range is set by the staff. For example, the standard pesticide loss characteristic value range is set to -0.3 to 0.3. When the pesticide loss characteristic value of a certain type of pesticide is less than the lower limit of the standard pesticide loss characteristic value range, the current pesticide loss status of that type of pesticide is too low. When the pesticide loss characteristic value of a certain type of pesticide is greater than the upper limit of the standard pesticide loss characteristic value range, the current pesticide loss status of that type of pesticide is excessive. When the pesticide loss characteristic value of a certain type of pesticide is within the standard transpiration characteristic value range, the current pesticide loss effect status of that type of pesticide is normal. This is an example and not the only limitation.

[0059] Step 3: Pesticide quality testing: Collect data on the current crop growth status, analyze the data to determine the current usage status of various pesticides.

[0060] In one specific embodiment, the process of collecting crop growth status data is as follows: the crop growth status data is crop image feature data, crop images are collected through a camera, and crop image feature data is obtained from the crop images through machine vision.

[0061] In one specific embodiment, the analysis of the current crop growth status data is carried out as follows: Excessive crop growth image feature data, normal crop growth image feature data, and low crop growth image feature data of various pesticides are obtained from the database. The crop growth status data is the crop image feature data. Similarity calculation is performed to obtain the excessive, normal, and low similarity of various pesticides on the current crop. The state corresponding to the highest similarity is recorded as the current pesticide usage status of the crop.

[0062] It should be noted that the characteristic data of crop growth images with excessive pesticide use can be obtained from the images of crop growth with excessive pesticide use. These images can be found on the Internet and entered into the database by staff. Similarly, the characteristic data of normal crop growth images and crop growth images with excessive pesticide use can be obtained in this way.

[0063] Step 4: Pesticide use control: Based on the current transpiration, pesticide runoff, and usage status of various pesticides, set up the current pesticide use control plan.

[0064] In one specific embodiment, the setting of the current pesticide use control scheme is specifically controlled as follows: if the current use status of a certain type of pesticide is excessive, the preset usage amount of that type of pesticide is reduced; if the current use status of a certain type of pesticide is insufficient, the preset usage amount of that type of pesticide is increased.

[0065] It should be noted that the preset usage amount is set by the staff.

[0066] If the current transpiration state of a certain type of pesticide is excessive, increase the preset unit amount of pesticide solvent for that type of pesticide; if the current transpiration state of a certain type of pesticide is insufficient, decrease the preset unit amount of pesticide solvent for that type of pesticide.

[0067] It should be noted that the preset unit amount of pesticide solvent is set by the staff.

[0068] If the current pesticide loss status of a certain type of pesticide is excessive, increase the pesticide application height of the preset unit amount of that type of pesticide; if the current pesticide loss status of a certain type of pesticide is insufficient, decrease the pesticide application height of the preset unit amount of that type of pesticide.

[0069] It should be noted that the preset application height for each unit of pesticide is set by the staff.

[0070] according to Figure 2 As shown, the present invention provides an intelligent monitoring system for pesticide application based on crop protection, comprising the following modules: transpiration detection module, soil condition detection module, pesticide quality detection module, pesticide use control module, and database.

[0071] The soil condition detection module is connected to the transpiration detection module and the pesticide quality detection module, respectively. The pesticide use control module is connected to the pesticide quality detection module. The transpiration detection module, soil condition detection module, pesticide quality detection module, and pesticide use control module are all connected to the database.

[0072] The transpiration detection module is used to collect historical transpiration environmental data, analyze the historical transpiration environmental data to establish a standard crop transpiration environment model, and then conduct experiments on the transpiration state of various pesticides to obtain the transpiration rate change curves of various pesticides. Furthermore, it collects current transpiration environmental data and air quality data, analyzes the current transpiration environmental data and air quality data, and then determines the current transpiration state of various pesticides.

[0073] The soil condition detection module is used to collect current soil environmental data, analyze the current soil environmental data, and determine the current pesticide loss status of various pesticides.

[0074] The pesticide quality testing module is used to collect data on the current crop growth status, analyze the data, and obtain the current usage status of various pesticides.

[0075] The pesticide use control module is used to set the current pesticide use control scheme based on the current transpiration status, pesticide loss status, and usage status of various pesticides.

[0076] The database stores standard transpiration characteristic value ranges, transpiration rates of target crops after each historical pesticide application for a preset time, weighting factors for each application time of various pesticides, standard transpiration characteristic value ranges, standard pesticide loss characteristic value ranges, crop growth image characteristic data for excessive pesticides, normal crop growth image characteristic data for various pesticides, and crop growth image characteristic data for excessive pesticides.

[0077] The above description is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they should all fall within the protection scope of the present invention.

Claims

1. A smart monitoring method for pesticide application based on crop protection, characterized in that, The steps include: Step 1: Transpiration detection: Collect historical transpiration environmental data, analyze the historical transpiration environmental data to establish a standard crop transpiration environment model, and then conduct experiments on the transpiration state of various pesticides to obtain the transpiration rate change curves of various pesticides. Further collect current transpiration environmental data and air quality data, analyze the current transpiration environmental data and air quality data, and then determine the current transpiration state of various pesticides. Step 2: Soil condition detection: Collect current soil environmental data, analyze the current soil environmental data, and determine the current pesticide loss status of various pesticides; Step 3: Pesticide quality testing: Collect data on the current crop growth status, analyze the data to determine the current usage status of various pesticides; Step 4: Pesticide use control: Based on the current transpiration, pesticide runoff, and usage status of various pesticides, set up the current pesticide use control plan.

2. The intelligent monitoring method for pesticide application based on crop protection according to claim 1, characterized in that, The analysis of historical evapotranspiration environmental data is carried out in the following specific process: Historical transpiration environment data includes, but is not limited to, temperature, humidity, light intensity, wind speed, and precipitation for each historical pesticide application of the target crop. The transpiration rate of the target crop after each historical pesticide application for a preset time is obtained from the database. Through multiple linear regression using machine learning algorithms, a mapping relationship between the historical transpiration environment data and the transpiration rate of the target crop is established, thereby obtaining a standard crop transpiration environment model: inputting transpiration environment data for various scenarios and outputting the standard transpiration rate.

3. The intelligent monitoring method for pesticide application based on crop protection according to claim 2, characterized in that, The experiment on the transpiration state of various pesticides was conducted, and the specific experimental procedure is as follows: Select target crops, simulate field environment in artificial climate chamber, set up a blank control group without pesticides and experimental groups with various pesticides, and conduct experiments; The experimental group applied the target pesticide according to the standard dosage preset by the staff, and collected the pesticide concentration at each time point after application to obtain the pesticide concentration of each type of pesticide in the experimental group at each time point after application. The staff applied water at a pre-set standard dose to the blank control group and collected the transpiration rate at a pre-set time after watering to obtain the standard transpiration rate of the blank control group. The transpiration environment data of the artificial climate chamber was then input into the standard crop transpiration environment model to obtain the standard transpiration rate of the artificial climate chamber. Divide the standard transpiration rate of the artificial climate chamber by the standard transpiration rate of the blank control group to obtain the transpiration correction rate of the experimental group. Multiply the drug concentration of each pesticide at each time after application in the experimental group by the transpiration correction rate to obtain the ideal drug concentration of each pesticide at each time after application in the experimental group.

4. The intelligent monitoring method for pesticide application based on crop protection according to claim 3, characterized in that, The specific process for obtaining the transpiration rate change curves of various pesticides is as follows: Plot the ideal drug concentration change curves of various pesticides in the experimental group with the time after each application as the horizontal axis and the ideal drug concentration as the vertical axis, so as to obtain the slope of the drug concentration change of various pesticides in the experimental group at each time after application. Staff conducted experiments on the transpiration state of various pesticides according to a preset number of times, and then plotted the concentration change curves of each experiment. This yielded the slope of the pesticide concentration change at each application time for each pesticide in each experiment, and thus obtained the standard transpiration concentration change slope range for each pesticide at each application time.

5. The intelligent monitoring method for pesticide application based on crop protection according to claim 4, characterized in that, The analysis of current evapotranspiration and air quality data is as follows: The current transpiration environment data includes, but is not limited to, the temperature, humidity, light intensity, wind speed, and precipitation at each application time for the target crop. The air quality data includes the transpiration rate at each application time for the current pesticide and the concentration of each pesticide at each application time for the current pesticides. The current transpiration environment data is input into the standard crop transpiration environment model to obtain the standard transpiration rate at each application time for the current environment. The standard transpiration rate at each application time for the current environment is divided by the corresponding transpiration rate to obtain the transpiration correction rate at each application time for the current environment. The concentration of each pesticide at each application time for the current pesticides is multiplied by the corresponding environmental transpiration correction rate to obtain the converted pesticide concentration at each application time for the current pesticides. Plot the change curves to obtain the slope of the drug concentration change at various post-application times for different types of pesticides.

6. The intelligent monitoring method for pesticide application based on crop protection according to claim 5, characterized in that, The specific process for determining the current transpiration status of various pesticides is as follows: If the slope of the drug concentration change falls within the standard transpiration concentration change slope range, it indicates that the transpiration state is normal, and the transpiration characteristic value is recorded as 0. If the slope of the drug concentration change is less than the minimum value of the standard transpiration concentration change slope range, it indicates that the transpiration state is too low, and the transpiration characteristic value is recorded as -1. If the slope of the drug concentration change is greater than the maximum value of the standard transpiration concentration change slope range, it indicates that the transpiration state is excessive, and the transpiration characteristic value is recorded as 1. In this way, the transpiration state and transpiration characteristic value of various pesticides at different application times can be obtained. The weighting factors for each application duration of various pesticides are obtained from the database. The characteristic values ​​of each application duration of various pesticides are multiplied by the corresponding weighting factors and summed to obtain the transpiration characteristic values ​​of various pesticides. The standard transpiration characteristic value range is obtained from the database to obtain the transpiration status of various pesticides.

7. The intelligent monitoring method for pesticide application based on crop protection according to claim 6, characterized in that, The analysis of the current soil environmental data is as follows: The standard soil concentration change slope range of various pesticides at different application times was obtained through experiments. The current soil environmental data includes the concentration of various pesticides at different application times in the current soil. Based on the method for judging the transpiration state of various pesticides, the pesticide loss state of various pesticides at the current time was determined.

8. The intelligent monitoring method for pesticide application based on crop protection according to claim 7, characterized in that, The analysis of current crop growth status data is performed as follows: The database retrieves image feature data of crops with excessive, normal, and low pesticide levels, as well as crop growth status data. Similarity calculations are performed to obtain the current similarity scores for excessive, normal, and low pesticide levels for various crops. The status corresponding to the highest similarity score is recorded as the current pesticide application status for various crops.

9. The intelligent monitoring method for pesticide application based on crop protection according to claim 8, characterized in that, The specific control process for setting the current pesticide use control scheme is as follows: If the current application status of a certain type of pesticide is excessive, reduce the preset application amount of that type of pesticide; if the current application status of a certain type of pesticide is insufficient, increase the preset application amount of that type of pesticide. If the current transpiration state of a certain type of pesticide is excessive, increase the preset unit amount of pesticide solvent for that type of pesticide; if the current transpiration state of a certain type of pesticide is insufficient, decrease the preset unit amount of pesticide solvent for that type of pesticide. If the current pesticide loss status of a certain type of pesticide is excessive, increase the pesticide application height of the preset unit amount of that type of pesticide; if the current pesticide loss status of a certain type of pesticide is insufficient, decrease the pesticide application height of the preset unit amount of that type of pesticide.

10. An intelligent monitoring system applying the intelligent monitoring method for pesticide application based on crop protection as described in any one of claims 1-9, characterized in that, Includes the following modules: The transpiration detection module is used to collect historical transpiration environmental data, analyze the historical transpiration environmental data to establish a standard crop transpiration environment model, and then conduct experiments on the transpiration state of various pesticides to obtain the transpiration rate change curves of various pesticides. It further collects current transpiration environmental data and air quality data, analyzes the current transpiration environmental data and air quality data, and then determines the current transpiration state of various pesticides. The soil condition detection module is used to collect current soil environmental data, analyze the current soil environmental data, and determine the current pesticide loss status of various pesticides. The pesticide quality testing module is used to collect data on the current crop growth status, analyze the data, and obtain the current usage status of various pesticides. The pesticide use control module is used to set the current pesticide use control scheme based on the current transpiration status, pesticide loss status, and usage status of various pesticides.

Images