Meteorological data fused potato late blight unmanned aerial vehicle spraying method and system

Abstract

The invention provides a potato late blight unmanned aerial vehicle spraying method and system fused with meteorological data. The method comprises the steps of obtaining meteorological characteristic data of an area where a target potato field is located, processing the meteorological characteristic data to obtain a late blight risk grade coefficient, judging whether unmanned aerial vehicle spraying operation needs to be executed or not, obtaining characteristic data of the target potato field if the unmanned aerial vehicle spraying operation needs to be executed, and processing the characteristic data in combination with the meteorological characteristic data, obtaining optimal spraying parameters of the unmanned aerial vehicle, executing unmanned aerial vehicle spraying operation on the target potato field, obtaining spraying state data after the spraying operation of the unmanned aerial vehicle is completed, and processing to obtain a spraying conformity coefficient; and obtaining prevention and control effect index data after a preset time period after completion, performing processing to obtain a prevention and control effect coefficient, judging the reliability of unmanned aerial vehicle spraying operation according to the spraying conformity coefficient and the prevention and control effect coefficient, and taking corresponding optimization measures, thereby realizing the potato late blight unmanned aerial vehicle spraying technology fused with meteorological data.

Description

Technical Field

[0001] This application relates to the technical field of drone spraying, and more specifically, to a method and system for spraying potato late blight by drones that integrates meteorological data. Background Art

[0002] Potato late blight is a fungal disease that seriously endangers potato production. It has a rapid onset and a wide spread range. Once it breaks out, it will cause huge economic losses to potato growers. Traditional prevention and control of potato late blight mainly rely on manual experience judgment and manual spraying control. This method has many drawbacks, such as inaccurate prevention and control timing, uneven spraying, low efficiency, etc., and cannot meet the prevention and control needs of large-scale potato planting.

[0003] With the application of drone technology in the agricultural field, drone spraying has gradually become a new means of preventing and controlling potato late blight. However, existing drone spraying prevention and control methods often ignore the impact of meteorological factors on the occurrence and development of potato late blight, as well as the effect evaluation after the spraying operation is completed, resulting in insufficient pertinence and effectiveness of the spraying operation and being difficult to achieve the ideal prevention and control effect.

[0004] In view of the above problems, there is an urgent need for an effective technical solution at present. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for spraying potato late blight by drones that integrates meteorological data. It can judge whether it is necessary to perform drone spraying operations according to the late blight risk level coefficient. If it is necessary to perform drone spraying operations, obtain the characteristic data of the target potato field, combine and process the meteorological characteristic data to obtain the optimal spraying parameters of the drone, obtain the spraying state data after the drone spraying operation is completed, and process to obtain the spraying compliance coefficient; obtain the prevention and control effect index data after a preset time period after completion, and process to obtain the prevention and control effectiveness coefficient. Judge the reliability of the drone spraying operation according to the spraying compliance coefficient and the prevention and control effectiveness coefficient, and take corresponding optimization measures to realize the technology of spraying potato late blight by drones that integrates meteorological data.

[0006] This application also provides a method for spraying potato late blight by drones that integrates meteorological data, including the following steps:

[0007] Obtain the meteorological characteristic data of the area where the target potato field is located, and process to obtain the late blight risk level coefficient;

[0008] Judge whether it is necessary to perform drone spraying operations according to the late blight risk level coefficient;

[0009] If it is necessary to perform drone spraying operations, obtain the characteristic data of the target potato field, and process it in combination with the meteorological characteristic data to obtain the optimal spraying parameters of the drone;

[0010] Perform drone spraying operations on the target potato field;

[0011] Obtain the spraying status data after the drone spraying operation is completed, and process it to obtain the spraying compliance coefficient; obtain the prevention and control effect index data after a preset time period after completion, and process it to obtain the prevention and control effectiveness coefficient;

[0012] Judge the reliability of the drone spraying operation according to the spraying compliance coefficient and the prevention and control effectiveness coefficient, and take corresponding optimization measures.

[0013] Optionally, in the method for spraying potatoes with late blight by drones integrating meteorological data of the present application, the obtaining of the meteorological characteristic data of the area where the target potato field is located, and processing to obtain the late blight risk level coefficient includes:

[0014] Obtain the meteorological characteristic data of the area where the target potato field is located, including temperature, humidity, wind speed, wind direction, and precipitation;

[0015] Process the temperature, humidity, wind speed, wind direction, and precipitation through a preset late blight prediction model to obtain the late blight risk level coefficient.

[0016] Optionally, in the method for spraying potatoes with late blight by drones integrating meteorological data of the present application, the judging whether it is necessary to perform drone spraying operations according to the late blight risk level coefficient includes:

[0017] Compare the late blight risk level coefficient with a preset late blight risk level threshold to obtain a threshold comparison result;

[0018] Judge whether it is necessary to perform drone spraying operations according to the threshold comparison result;

[0019] If the late blight risk level coefficient is greater than the preset late blight risk level threshold, it is necessary to perform drone spraying operations.

[0020] Optionally, in the method for spraying potatoes with late blight by drones integrating meteorological data of the present application, the if it is necessary to perform drone spraying operations, obtaining the characteristic data of the target potato field, and processing it in combination with the meteorological characteristic data to obtain the optimal spraying parameters of the drone includes:

[0021] If it is necessary to perform drone spraying operations, obtain the characteristic data of the target potato field, including the field area, field shape, field terrain, potato growth stage, and the degree of pest and disease occurrence;

[0022] Based on the area, shape, terrain of the field, the growth stage of the potato, and the degree of occurrence of diseases and pests, and combined with the temperature, humidity, wind speed, and wind direction, it is processed through a preset spray parameter setting model to obtain the optimal spray parameters of the drone;

[0023] The spray parameters include spray height, spray width, spray volume, and flight speed.

[0024] Optionally, in the method for spraying potato late blight by drone integrating meteorological data described in this application, the obtaining of the spray status data after the drone spray operation is completed, and processing to obtain a spray compliance coefficient; obtaining the control effect index data after a preset time period after completion, and processing to obtain a control effectiveness coefficient, includes:

[0025] Obtaining the spray status data after the drone spray operation is completed, including spray coverage rate and spray uniformity;

[0026] Performing weighted processing according to the spray coverage rate and spray uniformity to obtain a spray compliance coefficient;

[0027] Obtaining the control effect index data after a preset time period after completion, including the incidence of diseases and pests and potato growth indicators;

[0028] Obtaining the potato growth indicators before spraying, and performing comparative processing in combination with the potato growth indicators to obtain a growth difference index;

[0029] Performing weighted processing according to the incidence of diseases and pests and the growth difference index to obtain a control effectiveness coefficient.

[0030] Optionally, in the method for spraying potato late blight by drone integrating meteorological data described in this application, the judging of the reliability of the drone spray operation according to the spray compliance coefficient and the control effectiveness coefficient, and taking corresponding optimization measures, includes:

[0031] Obtaining a preset spray reliability threshold set, including a spray compliance threshold and a control effectiveness threshold;

[0032] Performing threshold comparison on the spray compliance coefficient and the control effectiveness coefficient with the two thresholds corresponding to the preset spray reliability threshold set;

[0033] If the results of the two threshold comparisons are both greater than the corresponding thresholds of the preset spray reliability threshold set, the reliability of the drone spray operation meets the requirements;

[0034] If the comparison results of the two thresholds are not both greater than the corresponding thresholds in the preset spray reliability threshold set, the reliability of the UAV spraying operation does not meet the requirements, and corresponding optimization measures need to be taken.

[0035] In a second aspect, the present application provides a UAV spraying system for potato late blight that integrates meteorological data. The system includes: a memory and a processor. The memory includes a program for the method of UAV spraying for potato late blight that integrates meteorological data. When the program for the method of UAV spraying for potato late blight that integrates meteorological data is executed by the processor, the following steps are implemented:

[0036] Obtain the meteorological characteristic data of the area where the target potato field is located, and process it to obtain the late blight risk level coefficient;

[0037] Judge whether it is necessary to perform UAV spraying operation according to the late blight risk level coefficient;

[0038] If it is necessary to perform UAV spraying operation, obtain the characteristic data of the target potato field, and process it in combination with the meteorological characteristic data to obtain the optimal spray parameters of the UAV;

[0039] Perform UAV spraying operation on the target potato field;

[0040] Obtain the spray state data after the UAV spraying operation is completed, and process it to obtain the spray compliance coefficient; obtain the control effect index data after a preset time period after completion, and process it to obtain the control effectiveness coefficient;

[0041] Judge the reliability of the UAV spraying operation according to the spray compliance coefficient and the control effectiveness coefficient, and take corresponding optimization measures.

[0042] Optionally, in the UAV spraying system for potato late blight that integrates meteorological data according to the present application, the obtaining the meteorological characteristic data of the area where the target potato field is located, and processing it to obtain the late blight risk level coefficient includes:

[0043] Obtain the meteorological characteristic data of the area where the target potato field is located, including temperature, humidity, wind speed, wind direction, and precipitation;

[0044] Process the temperature, humidity, wind speed, wind direction, and precipitation through a preset late blight prediction model to obtain the late blight risk level coefficient.

[0045] Optionally, in the UAV spraying system for potato late blight that integrates meteorological data according to the present application, the judging whether it is necessary to perform UAV spraying operation according to the late blight risk level coefficient includes:

[0046] Compare the late blight risk level coefficient with the preset late blight risk level threshold to obtain a threshold comparison result;

[0047] Judge whether it is necessary to perform drone spraying operation according to the threshold comparison result;

[0048] If the late blight risk level coefficient is greater than the preset late blight risk level threshold, it is necessary to perform drone spraying operation.

[0049] Optionally, in the potato late blight drone spraying system integrating meteorological data according to the present application, if it is necessary to perform drone spraying operation, obtain the characteristic data of the target potato field, and process it in combination with the meteorological characteristic data to obtain the optimal spraying parameters of the drone, including:

[0050] If it is necessary to perform drone spraying operation, obtain the characteristic data of the target potato field, including the field area, field shape, field terrain, potato growth stage, and the degree of occurrence of pests and diseases;

[0051] According to the field area, field shape, field terrain, potato growth stage, and the degree of occurrence of pests and diseases, process through a preset spraying parameter setting model in combination with the temperature, humidity, wind speed, and wind direction to obtain the optimal spraying parameters of the drone;

[0052] The spraying parameters include spraying height, spraying width, spraying volume, and flight speed.

[0053] As can be seen from the above, the potato late blight drone spraying method and system integrating meteorological data provided by the present application obtain the meteorological characteristic data of the area where the target potato field is located, and process to obtain the late blight risk level coefficient. Judge whether it is necessary to perform drone spraying operation according to the late blight risk level coefficient. If it is necessary to perform drone spraying operation, obtain the characteristic data of the target potato field, process it in combination with the meteorological characteristic data to obtain the optimal spraying parameters of the drone, perform drone spraying operation on the target potato field, obtain the spraying state data after the drone spraying operation is completed, and process to obtain the spraying compliance coefficient; obtain the control effect index data after a preset time period after completion, process to obtain the control effectiveness coefficient, and judge the reliability of the drone spraying operation according to the spraying compliance coefficient and the control effectiveness coefficient, and take corresponding optimization measures, so as to realize the technology of potato late blight drone spraying integrating meteorological data.

[0054] Other features and advantages of the present application will be described in the subsequent specification, and, in part, will become apparent from the specification, or can be understood by implementing the embodiments of the present application. The objectives and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written specification and the drawings. Description of the Drawings

[0055] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0056] Figure 1 It is a flowchart of the method for spraying potatoes with late blight by an unmanned aerial vehicle that integrates meteorological data provided by the embodiments of the present application;

[0057] Figure 2 It is a flowchart of obtaining the late blight risk level coefficient of the method for spraying potatoes with late blight by an unmanned aerial vehicle that integrates meteorological data provided by the embodiments of the present application;

[0058] Figure 3 It is a flowchart of obtaining the optimal spraying parameters of the unmanned aerial vehicle for the method for spraying potatoes with late blight that integrates meteorological data provided by the embodiments of the present application;

[0059] Figure 4 It is a flowchart of obtaining the spraying compliance coefficient and the control effectiveness coefficient of the method for spraying potatoes with late blight by an unmanned aerial vehicle that integrates meteorological data provided by the embodiments of the present application. Detailed implementation manners

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Usually, the components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the detailed description of the embodiments of the present application provided in the following drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0061] It should be noted that similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first" and "second" are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0062] Please refer to Figure 1 , Figure 1It is a flowchart of a method for spraying potato late blight by an unmanned aerial vehicle (UAV) that integrates meteorological data in some embodiments of the present application. The method for spraying potato late blight by integrating meteorological data is used in a terminal device, such as a computer, a mobile phone terminal, etc. The method for spraying potato late blight by integrating meteorological data includes the following steps:

[0063] S11. Obtain meteorological characteristic data of the area where the target potato field is located, and process it to obtain a late blight risk level coefficient;

[0064] S12. Judge whether it is necessary to perform UAV spraying operation according to the late blight risk level coefficient;

[0065] S13. If it is necessary to perform UAV spraying operation, obtain characteristic data of the target potato field, combine and process the meteorological characteristic data to obtain the optimal spraying parameters of the UAV;

[0066] S14. Perform UAV spraying operation on the target potato field;

[0067] S15. Obtain spraying state data after the UAV spraying operation is completed, and process it to obtain a spraying compliance coefficient; obtain control effect index data after a preset time period after completion, and process it to obtain a control effectiveness coefficient;

[0068] S16. Judge the reliability of the UAV spraying operation according to the spraying compliance coefficient and the control effectiveness coefficient, and take corresponding optimization measures.

[0069] It should be noted that through a professional meteorological monitoring network, including weather stations, satellite remote sensing equipment, and meteorological radars distributed around the target potato fields, meteorological characteristic data of the area where the target potato fields are located are comprehensively obtained. These data cover multiple dimensions such as temperature, humidity, wind speed, wind direction, and precipitation. After obtaining the data, professional data processing algorithms are used, combined with the disease incidence pattern model of potato late blight, to deeply analyze and process the meteorological characteristic data, thereby obtaining the late blight risk level coefficient. Then, according to the calculated late blight risk level coefficient, it is compared with a pre-set risk threshold to determine whether to perform drone spraying operations. If the late blight risk level coefficient exceeds the set high-risk threshold, it indicates that the potato fields face a relatively high risk of late blight, and at this time, drone spraying operations need to be carried out; conversely, if it does not exceed the threshold, there is no need to perform drone spraying operations temporarily. When it is determined that drone spraying operations need to be carried out, through a high-precision geographic information system (GIS) and on-site survey equipment, characteristic data of the target potato fields are obtained, including information such as the field area, field shape, field terrain, potato growth stage, and the degree of pest and disease occurrence. Then, these field characteristic data are combined with the previously obtained meteorological characteristic data and processed using a special drone spraying parameter calculation model. This model comprehensively considers factors such as the impact of wind speed on spray diffusion, the restriction of field terrain on flight paths, and the demand for chemical dosage in the potato growth stage, thereby obtaining the optimal spraying parameters for the drone, such as spraying height, spray width, spraying volume, and flight speed. After obtaining the optimal spraying parameters, the drone is controlled to perform spraying operations on the target potato fields according to the set parameters. After the drone spraying operations are completed, through various sensors installed on the drone, such as spray pressure sensors, flow sensors, and high-definition cameras, spray status data are obtained. These data are processed and analyzed, and a specific calculation method is used to obtain the spray compliance coefficient, which reflects the degree of compliance between the actual spraying operation parameters and the optimal spraying parameters. At the same time, within a preset time period (such as 7 days, 14 days, etc.) after the spraying operations are completed, through on-site investigations, sample detections, etc., control effect index data are obtained. These control effect index data are processed and analyzed, and a specific calculation method is used to obtain the control effectiveness coefficient, which reflects the actual control effect of the spraying operations on potato late blight. Finally, based on the calculated spray compliance coefficient and control effectiveness coefficient, the reliability of the drone spraying operations is comprehensively judged. If both the spray compliance coefficient and the control effectiveness coefficient are relatively high, it indicates that the drone spraying operations have good effects and high reliability; if one or both of the coefficients are relatively low, it indicates that there are problems with the spraying operations and corresponding optimization measures need to be taken, thereby realizing the technology of drone spraying for potato late blight integrating meteorological data.

[0070] Please refer to Figure 2 , Figure 2It is a flowchart for obtaining the late blight risk level coefficient of the potato late blight drone spraying method integrating meteorological data in some embodiments of the present application. According to the embodiments of the present invention, the obtaining of the meteorological characteristic data of the area where the target potato field is located and the processing to obtain the late blight risk level coefficient include:

[0071] S21. Obtain the meteorological characteristic data of the area where the target potato field is located, including temperature, humidity, wind speed, wind direction and precipitation;

[0072] S22. Process according to the temperature, humidity, wind speed, wind direction and precipitation through a preset late blight prediction model to obtain the late blight risk level coefficient.

[0073] It should be noted that by scientifically arranging automatic weather stations around the field, these devices collect temperature, humidity, wind speed, wind direction and precipitation data in real time at a minute-level frequency; then input them into a preset late blight prediction model for processing; this model is constructed based on years of field test data and historical disease incidence records, using the random forest algorithm in machine learning to deeply explore the internal relationship between meteorological factors and the incidence of late blight. The model performs complex operations and analyses on the input data according to the weights and thresholds of these meteorological factors, and finally outputs the late blight risk level coefficient.

[0074] According to the embodiments of the present invention, the judging whether to perform drone spraying operation according to the late blight risk level coefficient includes:

[0075] Compare the late blight risk level coefficient with a preset late blight risk level threshold to obtain a threshold comparison result;

[0076] Judge whether to perform drone spraying operation according to the threshold comparison result;

[0077] If the late blight risk level coefficient is greater than the preset late blight risk level threshold, drone spraying operation needs to be performed.

[0078] It should be noted that after calculating the late blight risk level coefficient, it is necessary to conduct a rigorous threshold comparison with the preset late blight risk level threshold to obtain an accurate threshold comparison result. Based on the threshold comparison result, it is possible to scientifically determine whether to perform drone spraying operations. If the late blight risk level coefficient is in the low-risk range, that is, less than or equal to the preset minimum risk threshold, it indicates that the probability of late blight occurring in the current potato field is relatively low, and there is no need to perform drone spraying operations for the time being. Only the meteorological data and the growth status of the plants in the field need to be continuously and closely monitored. If the late blight risk level coefficient is greater than the preset late blight risk level threshold and enters the medium-risk, high-risk, or extremely high-risk range, it indicates that the field faces a relatively high risk of late blight. At this time, it is necessary to immediately perform drone spraying operations, and by spraying targeted pesticides, prevent and control late blight in advance, reduce the possibility of pathogenic bacteria infecting potato plants, and ensure the yield and quality of potatoes to the greatest extent.

[0079] Please refer to Figure 3 , Figure 3 is a flowchart for obtaining the optimal spraying parameters of a drone for a potato late blight drone spraying method integrating meteorological data in some embodiments of the present application. According to an embodiment of the present invention, if it is necessary to perform drone spraying operations, obtain the characteristic data of the target potato field, and process it in combination with the meteorological characteristic data to obtain the optimal spraying parameters of the drone, including:

[0080] S31. If it is necessary to perform drone spraying operations, obtain the characteristic data of the target potato field, including the field area, field shape, field terrain, potato growth stage, and the degree of occurrence of pests and diseases;

[0081] S32. According to the field area, field shape, field terrain, potato growth stage, and the degree of occurrence of pests and diseases, process it in combination with the temperature, humidity, wind speed, and wind direction through a preset spraying parameter setting model to obtain the optimal spraying parameters of the drone;

[0082] S33. The spraying parameters include spraying height, spraying width, spraying volume, and flight speed.

[0083] It should be noted that once it is determined that drone spraying operations need to be carried out, obtaining the characteristic data of the target potato field becomes a crucial step. The area of the field is measured using high-precision satellite remote sensing mapping technology. Through multi-spectral image analysis and combined with Geographic Information System (GIS), the actual area of the field can be accurately calculated, and the error can be controlled within a very small range. The shape of the field is obtained by relying on the high-resolution camera carried by the drone for low-altitude aerial photography. Using image recognition algorithms to digitally process the field contour, accurately depicting whether the field is a regular rectangle, an irregular polygon, or other special shapes. For the terrain of the field, with the help of Light Detection and Ranging (LiDAR) technology, a high-precision Digital Elevation Model (DEM) is generated to present in detail the terrain undulations within the field, including information such as slope and aspect. The judgment of the potato growth stage is carried out in two ways. On the one hand, agricultural experts conduct on-site observations of the morphological characteristics of the plants, such as plant height, leaf color and quantity, and flowering situation, etc. On the other hand, spectral analysis technology is used to detect the changes in the reflected spectrum of the plants to accurately determine its specific stage, such as the seedling stage, budding stage, tuber bulking stage, etc. The assessment of the degree of pest and disease occurrence is carried out by professional personnel randomly selecting multiple sample points to investigate indicators such as the proportion of diseased plants and the area of disease spots, and combining the detection results of pathogens under the microscope to quantify the severity of pests and diseases. After obtaining the above-mentioned field characteristic data, combined with the meteorological data such as temperature, humidity, wind speed, and wind direction collected in the early stage, all this information is input into a preset spray parameter setting model. This model is an intelligent algorithm model constructed based on a large amount of field test data and the experience of agricultural experts. Using regression analysis and neural network algorithms in machine learning, it deeply mines the internal relationship between various factors and spray parameters. After complex operations and optimizations of the model, the optimal spray parameters of the drone are finally output, including spray height, spray width, spray volume, and flight speed.

[0084] Please refer to Figure 4 , Figure 4 is a flowchart for obtaining the spray compliance coefficient and the control effectiveness coefficient of the potato late blight drone spraying method integrating meteorological data in some embodiments of the present application. According to the embodiments of the present invention, obtaining the spray state data after the drone spraying operation is completed and processing to obtain the spray compliance coefficient; obtaining the control effect index data after a preset time period after completion and processing to obtain the control effectiveness coefficient, including:

[0085] S41. Obtain the spray state data after the drone spraying operation is completed, including spray coverage rate and spray uniformity;

[0086] S42. Perform weighted processing according to the spray coverage rate and spray uniformity to obtain the spray compliance coefficient;

[0087] S43, obtaining control effect index data after a preset time period, including pest and disease incidence and potato growth index;

[0088] S44, obtaining potato growth indicators before spraying, and performing comparative processing on the potato growth indicators to obtain a growth difference index;

[0089] S45. Perform weighted processing according to the disease and insect pest incidence rate and growth difference index to obtain a control effectiveness coefficient.

[0090] It should be noted that the determination of spray coverage is achieved by combining multispectral remote sensing technology with low-altitude inspection by drones. The drone is equipped with a multispectral camera and takes a second flight to shoot the target field after the operation is completed. By analyzing the differences in the vegetation reflectance spectra in different bands, the covered and uncovered areas are identified, and the image recognition algorithm is used to accurately calculate the proportion of the pesticide coverage area to the total area of the field, thereby obtaining the spray coverage rate. The acquisition of spray uniformity depends on the high-precision sensor array installed on the drone. These sensors monitor the pesticide flow and spray intensity at different points in real time during the spraying process. After the operation is completed, the system grids the massive data collected, and quantitatively evaluates the spray uniformity of the pesticide in the field by calculating the standard deviation and coefficient of variation of the pesticide distribution in each grid. Based on the acquired spray coverage and spray uniformity data, a scientific weighted processing method is used to obtain the spray compliance coefficient. Based on agricultural production practice experience and a large amount of test data, different weights are assigned to spray coverage and spray uniformity. The two indicators are integrated and calculated through a weighted summation formula, and finally a spray compliance coefficient between 0 and 1 is obtained; in the preset time period after the spraying operation is completed (such as 7-14 days), the collection of prevention and control effect indicator data is started; among them, the incidence of pests and diseases is calculated by investigating the number of infected plants or infected areas of pests and diseases in potato fields before and after spraying; in addition, it is necessary to obtain the potato growth index data before spraying and compare it with the index after spraying. By calculating the difference between the various growth indicators before and after spraying and dividing it by the index value before spraying, the growth difference rate of each indicator is obtained. These growth difference rates are comprehensively calculated to finally obtain the growth difference index. According to the incidence of pests and diseases and the growth difference index, the weighted processing method is used again to obtain the prevention and control effectiveness coefficient.

[0091] According to an embodiment of the present invention, the reliability of the drone spraying operation is judged based on the spray compliance coefficient and the prevention and control effectiveness coefficient, and corresponding optimization measures are taken, including:

[0092] Obtain a preset spray reliability threshold set, including a spray compliance threshold and a control effectiveness threshold;

[0093] Compare the two thresholds corresponding to the spray compliance coefficient and the control effectiveness coefficient with the corresponding preset spray reliability threshold set.

[0094] If the comparison results of both thresholds are greater than the corresponding thresholds in the preset spray reliability threshold set, the reliability of the UAV spraying operation meets the requirements.

[0095] If the comparison results of both thresholds are not both greater than the corresponding thresholds in the preset spray reliability threshold set, the reliability of the UAV spraying operation does not meet the requirements, and corresponding optimization measures need to be taken.

[0096] It should be noted that obtaining the preset spray reliability threshold set includes the spray compliance threshold and the control effectiveness threshold. This threshold set is obtained by agricultural research institutions in cooperation with UAV manufacturing enterprises and plant protection experts through a large number of field tests and data analyses. Compare the two thresholds corresponding to the spray compliance coefficient and the control effectiveness coefficient with the corresponding thresholds in the preset spray reliability threshold set. If the comparison results of both thresholds are greater than the corresponding thresholds in the preset spray reliability threshold set, that is, the spray compliance coefficient is greater than the spray compliance threshold and the control effectiveness coefficient is greater than the control effectiveness threshold, this indicates that the UAV spraying operation has reached or exceeded the expected standards in terms of the chemical coverage effect and the pest control effect, and the reliability of the operation meets the requirements; conversely, if the comparison results of both thresholds are not both greater than the corresponding thresholds in the preset spray reliability threshold set, it means that there are deficiencies in the UAV spraying operation and the reliability does not meet the requirements, and corresponding optimization measures need to be taken in a timely manner; if the spray compliance coefficient does not reach the threshold, it may be due to a malfunction of the UAV spraying equipment, unreasonable spray parameter settings, or improper flight route planning resulting in missed spraying in some areas. At this time, it is necessary to repair and debug the UAV spraying system, re-optimize parameters such as the spray height, spray width, and flight speed, and adjust the flight route in combination with the terrain and shape of the field; if the control effectiveness coefficient does not meet the standard, it may be that the chemical formula is not suitable for the current pest situation, the spray timing is not properly selected, or the chemical dosage is insufficient. At this time, it is necessary to re-screen a suitable chemical according to the actual occurrence of pests, optimize the chemical ratio, and at the same time select the best spray time in combination with the meteorological conditions and the potato growth stage, and appropriately adjust the chemical spraying amount to improve the control effect and reliability of the spraying operation.

[0097] According to an embodiment of the present invention, it further includes:

[0098] Compare the field area with a preset field area threshold to obtain a comparison result.

[0099] If the comparison result is greater than the preset threshold, divide the potato field into multiple sub-potato fields with the same area.

[0100] Obtain the characteristic data of each sub-potato field block, and respectively combine the meteorological characteristic data for processing through the preset spray parameter setting model to obtain the optimal spray parameters of the corresponding unmanned aerial vehicle (UAV).

[0101] Perform UAV spray operations on the sub-potato field block according to the optimal spray parameters of the corresponding UAV.

[0102] It should be noted that by comparing the area of the field block with the preset field block area threshold, it is judged whether the field block area is too large. To more effectively improve the UAV spray efficiency and quality, when the area of the potato field block is too large, the large field block can be cut into several regular sub-field blocks with the same area, and then targeted spraying is carried out according to each sub-field block, including obtaining the corresponding area, shape, terrain, potato growth stage, and the degree of pest and disease occurrence of each sub-potato field block, and then combining temperature, humidity, wind speed, and wind direction for processing through the preset spray parameter setting model to obtain the optimal spray parameters of the UAV corresponding to each sub-field block, setting the UAV according to the optimal spray parameters and performing UAV spray operations on the corresponding sub-field block, and finally completing the spray work of all sub-field blocks.

[0103] In a second aspect, the present invention also discloses a UAV spray system for potato late blight integrating meteorological data, including a memory and a processor. The memory includes a program for the UAV spray method for potato late blight integrating meteorological data. When the program for the UAV spray method for potato late blight integrating meteorological data is executed by the processor, the following steps are implemented:

[0104] Obtain the meteorological characteristic data of the area where the target potato field block is located, and process to obtain the late blight risk level coefficient;

[0105] Judge whether UAV spray operations need to be performed according to the late blight risk level coefficient;

[0106] If UAV spray operations need to be performed, obtain the characteristic data of the target potato field block, combine the meteorological characteristic data for processing to obtain the optimal spray parameters of the UAV;

[0107] Perform UAV spray operations on the target potato field block;

[0108] Obtain the spray state data after the UAV spray operations are completed, and process to obtain the spray compliance coefficient; obtain the control effect index data after a preset time period after completion, and process to obtain the control effectiveness coefficient;

[0109] Judge the reliability of the UAV spray operations according to the spray compliance coefficient and the control effectiveness coefficient, and take corresponding optimization measures.

[0110] It should be noted that through a professional meteorological monitoring network, including weather stations, satellite remote sensing equipment, and meteorological radars distributed around the target potato fields, meteorological characteristic data of the area where the target potato fields are located are comprehensively obtained. These data cover multiple dimensions such as temperature, humidity, wind speed, wind direction, and precipitation. After obtaining the data, professional data processing algorithms are used to deeply analyze and process the meteorological characteristic data in combination with the incidence law model of potato late blight, so as to obtain the late blight risk level coefficient. Then, according to the calculated late blight risk level coefficient, it is compared with a pre-set risk threshold to determine whether to perform drone spraying operations. If the late blight risk level coefficient exceeds the set high-risk threshold, it indicates that the potato fields face a relatively high risk of late blight, and at this time, drone spraying operations need to be carried out; conversely, if it does not exceed the threshold, there is no need to perform drone spraying operations temporarily. When it is determined that drone spraying operations need to be carried out, through a high-precision geographic information system (GIS) and on-site survey equipment, characteristic data of the target potato fields are obtained, including information such as the field area, field shape, field terrain, potato growth stage, and the degree of pest and disease occurrence. Then, these field characteristic data are combined with the previously obtained meteorological characteristic data and processed using a special drone spraying parameter calculation model. This model comprehensively considers factors such as the impact of wind speed on spray diffusion, the limitation of field terrain on flight paths, and the demand for chemical dosage at different potato growth stages, so as to obtain the optimal spraying parameters for the drone, such as spraying height, spray width, spraying volume, and flight speed. After obtaining the optimal spraying parameters, the drone is controlled to perform spraying operations on the target potato fields according to the set parameters. After the drone spraying operations are completed, spray status data are obtained through various sensors installed on the drone, such as spray pressure sensors, flow sensors, and high-definition cameras. These data are processed and analyzed, and a spray compliance coefficient is obtained using specific calculation methods. This coefficient reflects the degree of compliance between the actual spraying operation parameters and the optimal spraying parameters. At the same time, within a preset time period (such as 7 days, 14 days, etc.) after the spraying operations are completed, through on-site investigations, sample detections, etc., control effect index data are obtained. These control effect index data are processed and analyzed, and a control effectiveness coefficient is obtained using specific calculation methods. This coefficient reflects the actual control effect of the spraying operations on potato late blight. Finally, based on the calculated spray compliance coefficient and control effectiveness coefficient, the reliability of the drone spraying operations is comprehensively judged. If both the spray compliance coefficient and the control effectiveness coefficient are relatively high, it indicates that the drone spraying operations have good effects and high reliability; if one or both of the coefficients are relatively low, it indicates that there are problems with the spraying operations and corresponding optimization measures need to be taken, so as to realize the technology of drone spraying for potato late blight integrating meteorological data.

[0111] According to an embodiment of the present invention, obtaining meteorological characteristic data of the area where the target potato field is located and processing to obtain a late blight risk level coefficient includes:

[0112] Obtaining meteorological characteristic data of the area where the target potato field is located, including temperature, humidity, wind speed, wind direction, and precipitation;

[0113] Processing according to the temperature, humidity, wind speed, wind direction, and precipitation through a preset late blight prediction model to obtain a late blight risk level coefficient.

[0114] It should be noted that by scientifically arranging automatic weather stations around the field, these devices collect temperature, humidity, wind speed, wind direction, and precipitation data in real time at a minute-level frequency; then input them into a preset late blight prediction model for processing; this model is constructed based on years of field test data and historical disease incidence records, using the random forest algorithm in machine learning to deeply explore the internal relationship between meteorological factors and the occurrence of late blight. The model performs complex operations and analyses on the input data according to the weights and thresholds of these meteorological factors, and finally outputs a late blight risk level coefficient.

[0115] According to an embodiment of the present invention, judging whether to perform drone spraying operation according to the late blight risk level coefficient includes:

[0116] Performing a threshold comparison between the late blight risk level coefficient and a preset late blight risk level threshold to obtain a threshold comparison result;

[0117] Judging whether to perform drone spraying operation according to the threshold comparison result;

[0118] If the late blight risk level coefficient is greater than the preset late blight risk level threshold, then drone spraying operation needs to be performed.

[0119] It should be noted that after calculating the late blight risk level coefficient, a rigorous threshold comparison needs to be made with the preset late blight risk level threshold to obtain an accurate threshold comparison result. Based on the threshold comparison result, it can be scientifically judged whether to perform drone spraying operation. If the late blight risk level coefficient is in the low-risk interval, that is, less than or equal to the preset lowest risk threshold, it indicates that the probability of late blight occurring in the current potato field is relatively low, and there is no need to perform drone spraying operation temporarily. Only the meteorological data of the field and the growth status of the plants need to be continuously and closely monitored; if the late blight risk level coefficient is greater than the preset late blight risk level threshold and enters the medium-risk, high-risk, or extremely high-risk interval, it indicates that the field faces a relatively high risk of late blight occurrence. At this time, drone spraying operation needs to be immediately performed, and by spraying targeted pesticides, the prevention and control of late blight can be carried out in advance, reducing the possibility of the pathogen infecting potato plants, and ensuring the yield and quality of potatoes to the greatest extent.

[0120] According to an embodiment of the present invention, if it is necessary to perform drone spraying operation, the characteristic data of the target potato field is obtained and processed in combination with the meteorological characteristic data to obtain the optimal spraying parameters of the drone, including:

[0121] If it is necessary to perform drone spraying operation, the characteristic data of the target potato field is obtained, including the field area, field shape, field terrain, potato growth stage, and the degree of pest and disease occurrence;

[0122] According to the field area, field shape, field terrain, potato growth stage, and the degree of pest and disease occurrence, in combination with the temperature, humidity, wind speed, and wind direction, it is processed through a preset spraying parameter setting model to obtain the optimal spraying parameters of the drone;

[0123] The spraying parameters include spraying height, spraying width, spraying volume, and flight speed.

[0124] It should be noted that once it is determined that it is necessary to perform drone spraying operation, obtaining the characteristic data of the target potato field becomes a key step; the measurement of the field area uses high-precision satellite remote sensing mapping technology. Through multi-spectral image analysis and in combination with the Geographic Information System (GIS), the actual area of the field can be accurately calculated, and the error can be controlled within a very small range; the acquisition of the field shape depends on the high-resolution camera carried by the drone for low-altitude aerial photography. Using image recognition algorithms to digitally process the field contour, accurately depict whether the field is a regular rectangle, an irregular polygon, or other special shapes; for the field terrain, with the help of Light Detection and Ranging (LiDAR) technology, a high-precision Digital Elevation Model (DEM) is generated to present the terrain undulation in the field in detail, including information such as slope and aspect; the judgment of the potato growth stage is, on the one hand, through agricultural experts' on-site observation of the morphological characteristics of the plants, such as plant height, leaf color and quantity, flowering situation, etc.; on the other hand, using spectral analysis technology to detect the changes in the reflected spectrum of the plants to accurately determine its specific stage such as the seedling stage, budding stage, tuber swelling stage, etc.; the assessment of the degree of pest and disease occurrence is carried out by professional personnel randomly selecting multiple sample points, investigating indicators such as the proportion of diseased plants and the area of disease spots, and combining the detection results of pathogens under the microscope to quantify the severity of pests and diseases; after obtaining the above field characteristic data, combined with the meteorological data such as temperature, humidity, wind speed, and wind direction collected earlier, all this information is input into the preset spraying parameter setting model; this model is an intelligent algorithm model constructed based on a large amount of field test data and agricultural experts' experience, using regression analysis and neural network algorithms in machine learning to deeply explore the internal relationship between various factors and spraying parameters; through the complex operation and optimization of the model, the optimal spraying parameters of the drone are finally output, including spraying height, spraying width, spraying volume, and flight speed.

[0125] According to an embodiment of the present invention, obtaining spray status data after the UAV spraying operation is completed, and processing to obtain a spray compliance coefficient; obtaining prevention and control effect index data after a preset time period after completion, and processing to obtain a prevention and control effectiveness coefficient, including:

[0126] Obtaining spray status data after the UAV spraying operation is completed, including spray coverage rate and spray uniformity;

[0127] Performing weighted processing according to the spray coverage rate and the spray uniformity to obtain a spray compliance coefficient;

[0128] Obtaining prevention and control effect index data after a preset time period after completion, including the incidence of pests and diseases and potato growth indexes;

[0129] Obtaining potato growth indexes before spraying, and performing comparison processing in combination with the potato growth indexes to obtain a growth difference index;

[0130] Performing weighted processing according to the incidence of pests and diseases and the growth difference index to obtain a prevention and control effectiveness coefficient.

[0131] It should be noted that the determination of the spray coverage rate is carried out by combining multi-spectral remote sensing technology with low-altitude drone patrol. The drone is equipped with a multi-spectral camera and conducts a second flight over the target field after the operation to take pictures. By analyzing the differences in the vegetation reflection spectra in different bands, the areas covered by the agent and the non-covered areas are identified, and the proportion of the area covered by the agent in the total area of the field is accurately calculated using an image recognition algorithm, thereby obtaining the spray coverage rate. The acquisition of the spray uniformity depends on the high-precision sensor array installed on the drone. These sensors monitor the agent flow rate and spraying intensity at different points in real time during the spraying process. After the operation, the system performs grid processing on the massive data collected. By calculating the standard deviation and coefficient of variation of the agent distribution in each grid, the spraying uniformity of the agent in the field is quantitatively evaluated. Based on the obtained spray coverage rate and spray uniformity data, a scientific weighted processing method is used to obtain the spray compliance coefficient. According to agricultural production practice experience and a large amount of experimental data, different weights are assigned to the spray coverage rate and spray uniformity. Through the weighted summation formula, the two indicators are integrated and calculated to finally obtain a spray compliance coefficient between 0 and 1. In a preset time period (such as 7 - 14 days) after the spraying operation, the collection of the control effect index data is started. Among them, the incidence of pests and diseases is calculated by investigating the number of infected plants or the infected area of pests and diseases in the potato field before and after spraying. In addition, the potato growth index data before spraying needs to be obtained and compared with the index after spraying. By calculating the difference in each growth index before and after spraying and then dividing it by the index value before spraying, the growth difference rate of each index is obtained. These growth difference rates are comprehensively calculated to finally obtain the growth difference index. Based on the incidence of pests and diseases and the growth difference index, the control effectiveness coefficient is obtained again by using the weighted processing method.

[0132] According to an embodiment of the present invention, judging the reliability of the drone spraying operation based on the spray compliance coefficient and the control effectiveness coefficient, and taking corresponding optimization measures, including:

[0133] Obtain a preset spray reliability threshold set, including a spray compliance threshold and a control effectiveness threshold;

[0134] Compare the spray compliance coefficient and the control effectiveness coefficient with the two corresponding thresholds of the preset spray reliability threshold set for threshold comparison;

[0135] If the results of the two threshold comparisons are both greater than the corresponding thresholds of the preset spray reliability threshold set, the reliability of the drone spraying operation meets the requirements;

[0136] If the results of the two threshold comparisons are not both greater than the corresponding thresholds of the preset spray reliability threshold set, the reliability of the drone spraying operation does not meet the requirements and corresponding optimization measures need to be taken.

[0137] It should be noted that obtaining the preset spray reliability threshold set, including the spray compliance threshold and the control effectiveness threshold, is obtained by agricultural research institutions in conjunction with UAV manufacturing enterprises and plant protection experts through a large number of field tests and data analysis; comparing the spray compliance coefficient and the control effectiveness coefficient with the two thresholds of the corresponding preset spray reliability threshold set, if the comparison results of the two thresholds are both greater than the corresponding thresholds of the preset spray reliability threshold set, that is, the spray compliance coefficient is greater than the spray compliance threshold, and the control effectiveness coefficient is greater than the control effectiveness threshold, this indicates that the UAV spray operation has reached or exceeded the expected standard in terms of the chemical coverage effect and the pest control effect, and the reliability of the operation meets the requirements; otherwise, if the comparison results of the two thresholds are not both greater than the corresponding thresholds of the preset spray reliability threshold set, it means that there are deficiencies in the UAV spray operation and the reliability does not meet the requirements, and corresponding optimization measures need to be taken in a timely manner; if the spray compliance coefficient does not reach the threshold, it may be due to a malfunction of the UAV spray equipment, unreasonable spray parameter settings, or improper flight route planning resulting in missed spraying in some areas. At this time, it is necessary to repair and debug the spray system of the UAV, re-optimize parameters such as the spray height, spray width, and flight speed, and adjust the flight route in combination with the terrain and shape of the field; if the control effectiveness coefficient does not meet the standard, it may be that the chemical formulation is not suitable for the current pest situation, the spray timing is not properly selected, or the chemical dosage is insufficient. At this time, it is necessary to re-screen a suitable chemical according to the actual occurrence of pests and diseases, optimize the chemical ratio, and at the same time select the best spray time in combination with the meteorological conditions and the growth stage of the potato, and appropriately adjust the chemical spraying amount to improve the control effect and reliability of the spray operation.

[0138] According to an embodiment of the present invention, it further includes:

[0139] Compare the area of the field with a preset field area threshold to obtain a comparison result;

[0140] If the comparison result is greater than the preset threshold, divide the potato field into multiple sub-potato fields with the same area;

[0141] Obtain the characteristic data of each sub-potato field, and respectively process them through the preset spray parameter setting model in combination with the meteorological characteristic data to obtain the optimal spray parameters of the corresponding UAV;

[0142] Perform UAV spray operation on the sub-potato fields according to the optimal spray parameters of the corresponding UAV.

[0143] It should be noted that by comparing the area of the field with the preset threshold of the field area, it is determined whether the field area is too large. To more effectively improve the spraying efficiency and quality of the drone, when the area of the potato field is too large, the large field can be cut into several sub-fields with the same and regular area, and then targeted spraying can be carried out according to each sub-field, including obtaining the area, shape, terrain, potato growth stage and the degree of pest and disease occurrence corresponding to each sub-potato field, and then processing through a preset spraying parameter setting model in combination with temperature, humidity, wind speed and wind direction to obtain the optimal spraying parameters of the drone corresponding to each sub-field, setting the drone according to the optimal spraying parameters and performing the drone spraying operation on the corresponding sub-field, and finally completing the spraying work of all sub-fields.

[0144] The method and system for spraying potato late blight by drones integrating meteorological data disclosed in the present invention obtain the meteorological characteristic data of the area where the target potato field is located, and process to obtain the late blight risk level coefficient, and judge whether it is necessary to perform the drone spraying operation according to the late blight risk level coefficient. If it is necessary to perform the drone spraying operation, obtain the characteristic data of the target potato field, process in combination with the meteorological characteristic data to obtain the optimal spraying parameters of the drone, perform the drone spraying operation on the target potato field, obtain the spraying state data after the drone spraying operation is completed, and process to obtain the spraying compliance coefficient; obtain the prevention and control effect index data after a preset time period after completion, process to obtain the prevention and control effectiveness coefficient, and judge the reliability of the drone spraying operation according to the spraying compliance coefficient and the prevention and control effectiveness coefficient, and take corresponding optimization measures, so as to realize the technology of spraying potato late blight by drones integrating meteorological data.

[0145] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed with each other can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0146] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units; they may be located in one place or 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.

[0147] In addition, each functional unit in the embodiments of the present invention may be entirely integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0148] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the foregoing storage medium includes: removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks and other various media that can store program codes.

[0149] Alternatively, if the above-mentioned integrated units of the present invention are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a readable storage medium. Based on such an understanding, the technical solutions of the embodiments of the present invention essentially or the parts that contribute to the prior art can be embodied in the form of a software product. The software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. And the foregoing storage medium includes: removable storage devices, ROM, RAM, magnetic disks, or optical disks and other various media that can store program codes.

Claims

1. A method for spraying potato late blight by an unmanned aerial vehicle integrating meteorological data, characterized in that, It includes the following steps: Obtain the meteorological characteristic data of the area where the target potato field is located, and process it to obtain the late blight risk level coefficient; Judge whether it is necessary to perform drone spraying operation according to the late blight risk level coefficient; If it is necessary to perform drone spraying operation, obtain the characteristic data of the target potato field, and process it in combination with the meteorological characteristic data to obtain the optimal spraying parameters of the drone; Perform drone spraying operation on the target potato field; Obtain the spraying state data after the drone spraying operation is completed, and process it to obtain the spraying compliance coefficient; obtain the control effect index data after a preset time period after completion, and process it to obtain the control effectiveness coefficient; Judge the reliability of the drone spraying operation according to the spraying compliance coefficient and the control effectiveness coefficient, and take corresponding optimization measures.

2. The potato late blight drone spraying method integrating meteorological data according to claim 1 is characterized in that: The obtaining the meteorological characteristic data of the area where the target potato field is located, and processing it to obtain the late blight risk level coefficient includes: Obtain the meteorological characteristic data of the area where the target potato field is located, including temperature, humidity, wind speed, wind direction and precipitation; Process the temperature, humidity, wind speed, wind direction and precipitation through a preset late blight prediction model to obtain the late blight risk level coefficient.

3. The method for spraying potato late blight by an unmanned aerial vehicle integrating meteorological data according to claim 2, wherein The judging whether it is necessary to perform drone spraying operation according to the late blight risk level coefficient includes: Compare the late blight risk level coefficient with a preset late blight risk level threshold to obtain a threshold comparison result; Judge whether it is necessary to perform drone spraying operation according to the threshold comparison result; If the late blight risk level coefficient is greater than the preset late blight risk level threshold, it is necessary to perform drone spraying operation.

4. The method for spraying potato late blight by an unmanned aerial vehicle integrating meteorological data according to claim 3, wherein, The if it is necessary to perform drone spraying operation, obtain the characteristic data of the target potato field, and process it in combination with the meteorological characteristic data to obtain the optimal spraying parameters of the drone includes: If it is necessary to perform drone spraying operation, obtain the characteristic data of the target potato field, including the field area, field shape, field terrain, potato growth stage and the degree of pest and disease occurrence; Process the field area, field shape, field terrain, potato growth stage and the degree of pest and disease occurrence, and process it in combination with the temperature, humidity, wind speed and wind direction through a preset spraying parameter setting model to obtain the optimal spraying parameters of the drone; The spraying parameters include spraying height, spraying width, spraying volume and flight speed.

5. The method for spraying potato late blight by an unmanned aerial vehicle integrating meteorological data according to claim 4, characterized in that, Obtain the spraying state data after the drone spraying operation is completed, and process it to obtain the spraying compliance coefficient; Obtain the control effect index data after a preset time period after completion, and process it to obtain the control effectiveness coefficient, including: Obtain the spraying state data after the drone spraying operation is completed, including spraying coverage rate and spraying uniformity; Perform weighted processing according to the spraying coverage rate and spraying uniformity to obtain the spraying compliance coefficient; Obtain the control effect index data after a preset time period after completion, including the pest and disease incidence rate and the potato growth index; Obtain the potato growth index before spraying, and perform comparison processing in combination with the potato growth index to obtain the growth difference index; Perform weighted processing based on the incidence of pests and diseases and the growth difference index to obtain a control effectiveness coefficient.

6. The method for spraying potato late blight by drone with integrated meteorological data according to claim 5, wherein Judge the reliability of the UAV spraying operation according to the spraying compliance coefficient and the control effectiveness coefficient, and take corresponding optimization measures, including: Obtain a preset spraying reliability threshold set, including a spraying compliance threshold and a control effectiveness threshold; Perform threshold comparison on the spraying compliance coefficient and the control effectiveness coefficient with the two thresholds corresponding to the preset spraying reliability threshold set; If the results of the two threshold comparisons are both greater than the corresponding thresholds of the preset spraying reliability threshold set, the reliability of the UAV spraying operation meets the requirements; If the results of the two threshold comparisons are not both greater than the corresponding thresholds of the preset spraying reliability threshold set, the reliability of the UAV spraying operation does not meet the requirements and corresponding optimization measures need to be taken.

7. A potato late blight drone spraying system integrating meteorological data, characterized in that, The system includes: a memory and a processor. The memory includes a program of the UAV spraying method for potato late blight integrating meteorological data. When the program of the UAV spraying method for potato late blight integrating meteorological data is executed by the processor, the following steps are implemented: Obtain the meteorological characteristic data of the area where the target potato field is located, and process it to obtain a late blight risk level coefficient; Judge whether UAV spraying operation needs to be performed according to the late blight risk level coefficient; If UAV spraying operation needs to be performed, obtain the characteristic data of the target potato field, and process it in combination with the meteorological characteristic data to obtain the best spraying parameters of the UAV; Perform UAV spraying operation on the target potato field; Obtain the spraying state data after the UAV spraying operation is completed, and process it to obtain a spraying compliance coefficient; obtain the control effect index data after a preset time period after completion, and process it to obtain a control effectiveness coefficient; Judge the reliability of the UAV spraying operation according to the spraying compliance coefficient and the control effectiveness coefficient, and take corresponding optimization measures.

8. The potato late blight drone spraying system integrating meteorological data according to claim 7, characterized in that, The obtaining of the meteorological characteristic data of the area where the target potato field is located, and processing it to obtain a late blight risk level coefficient includes: Obtain the meteorological characteristic data of the area where the target potato field is located, including temperature, humidity, wind speed, wind direction and precipitation; Process the temperature, humidity, wind speed, wind direction and precipitation through a preset late blight prediction model to obtain a late blight risk level coefficient.

9. The potato late blight drone spraying system integrating meteorological data according to claim 8, characterized in that The judging whether UAV spraying operation needs to be performed according to the late blight risk level coefficient includes: Perform threshold comparison on the late blight risk level coefficient and a preset late blight risk level threshold to obtain a threshold comparison result; Judge whether UAV spraying operation needs to be performed according to the threshold comparison result; If the late blight risk level coefficient is greater than the preset late blight risk level threshold, UAV spraying operation needs to be performed.

10. The potato late blight drone spraying system integrating meteorological data according to claim 9, characterized in that, The if UAV spraying operation needs to be performed, obtaining the characteristic data of the target potato field, and processing it in combination with the meteorological characteristic data to obtain the best spraying parameters of the UAV includes: If it is necessary to perform drone spraying operations, obtain the characteristic data of the target potato field block, including the field block area, field block shape, field block terrain, potato growth stage, and the degree of pest and disease occurrence; According to the field block area, field block shape, field block terrain, potato growth stage, and the degree of pest and disease occurrence, and combined with the temperature, humidity, wind speed, and wind direction, perform processing through a preset spray parameter setting model to obtain the optimal spray parameters for the drone; The spray parameters include spray height, spray width, spray volume, and flight speed.

Images