A UAV-based pest monitoring method based on intelligent path planning

Abstract

This invention relates to the field of drone path adjustment and discloses a drone pest monitoring method based on intelligent path planning. This method addresses the problem of failing to monitor pests in a timely manner when their distribution changes dynamically. The method includes: dividing the area to be monitored into n regions, denoted as monitoring sub-regions; detecting meteorological data for each monitoring sub-region and calculating a meteorological influence coefficient; acquiring illumination condition data for each monitoring sub-region and calculating an illumination influence coefficient; acquiring historical pest infestation data for each monitoring sub-region and evaluating a historical disaster coefficient; comprehensively evaluating a disaster index; dividing the monitoring sub-regions in real time based on the disaster index; using Algorithm A to perform real-time path planning based on the divided regions; and enabling the drone to monitor pests based on the real-time path planning. This effectively improves the effectiveness of drone route planning and reduces crop damage rates.

Description

Technical Field

[0001] This invention relates to the field of drone path adjustment, and more specifically to a drone pest monitoring method based on intelligent path planning. Background Technology

[0002] Intelligent path planning for drones uses algorithms and real-time data analysis to dynamically optimize flight paths based on environmental conditions, mission requirements, and flight limitations, thereby efficiently covering target areas. It combines pest distribution data, meteorological information, and terrain features to automatically plan and adjust flight routes, ensuring maximum monitoring accuracy and efficiency while reducing energy consumption and flight time.

[0003] Most existing drone pest monitoring methods rely on historical data or prior knowledge to identify key areas where pests are prevalent. Drones then focus their coverage on these key areas to save unnecessary flight time and energy. However, the distribution of pests is usually not fixed and may change dynamically. If only the previously identified key areas are covered, the pest situation may not be detected in time, leading to crop damage.

[0004] To address the above problems, this invention proposes a solution. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a method for monitoring pests by unmanned aerial vehicles based on intelligent path planning, so as to solve the problems existing in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A drone-based pest monitoring method based on intelligent path planning includes the following steps:

[0008] Step 1: Divide the area where pest monitoring needs to be carried out into n equal regions, denoted as monitoring sub-regions;

[0009] Step 2: Detect meteorological data for each monitoring sub-area, including wind speed, wind direction, temperature, and humidity data, and obtain the meteorological influence coefficient based on the meteorological data;

[0010] Step 3: Obtain the illumination condition data for each monitoring sub-area, including sunshine duration and diurnal temperature range, and calculate the illumination influence coefficient based on the illumination condition data;

[0011] Step 4: Obtain historical pest infestation data for each monitored sub-area. The historical pest infestation data includes the frequency of pest occurrence, duration of pest occurrence, and severity of pest infestation. The historical pest infestation coefficient is evaluated based on the historical pest infestation data.

[0012] Step 5: Calculate the disaster index based on the meteorological impact coefficient, the sunshine impact coefficient, and the historical disaster impact coefficient. The calculation formula is as follows: DT represents the disaster index, MI represents the meteorological impact coefficient, LE represents the sunshine impact coefficient, HD represents the historical disaster coefficient, and a1, a2, and a3 represent the weighting coefficients of the meteorological impact coefficient, sunshine impact coefficient, and historical disaster coefficient.

[0013] Step 6: Divide the monitoring sub-regions in real time according to the disaster index;

[0014] Step 7: Use Algorithm A to perform real-time path planning based on the divided areas, and enable the drone to monitor pests based on the real-time path planning;

[0015] The steps for assessing and obtaining the historical disaster coefficient based on historical insect infestation data are as follows:

[0016] Get the number of pest occurrences within the detection time period for each monitored sub-region; get the duration of each pest occurrence within the detection time period;

[0017] Acquire the loss data for each pest infestation and calculate the degree of damage based on the loss data;

[0018] The historical damage coefficient is calculated based on the number of pest occurrences, duration, and degree of damage. The calculation formula is as follows: Where HD represents the historical disaster coefficient, j represents the number of insect infestations, and sj i For the duration of the i-th infestation, ph i The degree of damage caused by the i-th pest infestation;

[0019] The steps for obtaining loss data for each pest infestation and calculating the degree of damage based on the loss data are as follows:

[0020] The method for collecting data on crop yield reduction rate and affected area in the monitored sub-regions after each pest infestation, and then determining the degree of damage based on these data, is as follows: , where ph is the degree of damage, sa is the affected area, and jc is the crop yield reduction rate.

[0021] Preferably, the step of obtaining the meteorological influence coefficient based on meteorological data is as follows:

[0022] Obtain the wind speed and direction for each monitoring sub-region, and calculate the wind force impact.

[0023] The temperature and humidity data of each monitoring sub-area are standardized, and the temperature and humidity influence is obtained based on the standardized temperature and humidity data.

[0024] The method for obtaining the meteorological influence coefficient based on the influence of wind force and the influence of temperature and humidity is as follows: , where MI represents the meteorological influence coefficient, WF represents the wind force influence degree, and TH represents the temperature and humidity influence degree.

[0025] Preferably, the step of obtaining the wind speed and direction of each monitoring sub-region and calculating the wind force influence is as follows:

[0026] Real-time wind speed data of the monitored sub-region is collected, and all monitored sub-regions adjacent to the monitored sub-region are selected and recorded as adjacent sub-regions. The wind speed data of the adjacent sub-regions is collected in real time.

[0027] Collect wind direction data for the monitored sub-region and adjacent sub-regions, and convert the wind direction into radians;

[0028] The method for calculating the vector components of wind in the monitored sub-region is as follows: , ,in To monitor the components of the horizontal vector in the sub-region, To monitor the components of the vertical vector in the sub-region, Represented in radians, This is represented as wind speed data for a monitored sub-region; the method for calculating the vector components of wind for adjacent sub-regions is as follows: , ,in Let be the component of the horizontal vector of the i-th adjacent sub-region. Let be the components of the vertical vector of the i-th adjacent sub-region. It is represented by the radians of the wind direction in the i-th adjacent sub-region. This is represented as the wind speed data of the i-th adjacent sub-region;

[0029] The average level component is obtained by averaging the wind speed vectors on the horizontal components of the monitored sub-region and its adjacent sub-regions. The calculation formula is as follows: ,in Represented as the average level component, To monitor the components of the horizontal vector in the sub-region, Let be the component of the horizontal vector of the i-th adjacent sub-region, and m represent the number of adjacent sub-regions. The average vertical component is obtained by averaging the wind speed vectors of the monitored sub-region and its adjacent sub-regions. The calculation formula is as follows: , This is represented as the average vertical component. To monitor the components of the vertical vector in the sub-region, These are the components of the vertical vector of the i-th adjacent sub-region;

[0030] The method for obtaining wind influence based on the average horizontal component and the average vertical component. Where WF represents the wind impact degree, Represented as the average level component, It is represented as the average vertical component.

[0031] Preferably, the step of calculating the illumination influence coefficient based on illumination condition data is as follows:

[0032] The average sunshine duration is calculated by averaging the sunshine duration of the monitored sub-regions within the monitoring period.

[0033] The average diurnal temperature range is obtained by averaging the diurnal temperature range of the monitored sub-regions within the monitoring period.

[0034] The light impact coefficient is calculated based on the average sunshine duration and average diurnal temperature range. The formula for its calculation is as follows: Where LE represents the light impact coefficient, S is the average sunshine duration, and T is the average sunshine duration. d This represents the average diurnal temperature range.

[0035] Preferably, the step of dividing the monitoring sub-regions in real time according to the disaster index is as follows:

[0036] The disaster index is compared with a preset threshold. If the disaster index is less than the preset threshold, the probability of insect infestation in the area is low, and the area is recorded as a secondary area. If the disaster index is greater than the preset threshold, the probability of insect infestation in the area is high, and the area is recorded as a key area.

[0037] Preferably, the step of real-time path planning based on the acquired key areas is as follows:

[0038] By adding a "priority weight" parameter to Algorithm A, an optimized Algorithm A is obtained. Low path costs are set for key areas, allowing drones to fly to these areas first; at the same time, high path costs are set for secondary areas to reduce the frequency of flights.

[0039] An optimized A algorithm is used to generate monitoring routes based on key and secondary areas;

[0040] It also acquires new data in real time during flight, re-divides the area, and updates the monitoring route.

[0041] The technical effects and advantages of this invention are as follows:

[0042] The area requiring pest monitoring is divided into n regions, denoted as monitoring sub-regions. Meteorological data for each monitoring sub-region is collected, and the meteorological influence coefficient is calculated. Lighting condition data for each monitoring sub-region is obtained, and the lighting influence coefficient is calculated. Historical pest infestation data for each monitoring sub-region is obtained, and the historical disaster coefficient is evaluated. A comprehensive evaluation is then performed to obtain the disaster index. Based on the disaster index, the monitoring sub-regions are divided in real time. The A algorithm is used to perform real-time path planning based on the divided regions, and the drones are used to monitor pests according to the real-time path planning. This effectively improves the effectiveness of drone route planning and reduces crop damage rates. Attached Figure Description

[0043] Figure 1 This is the overall flowchart of the present invention. Detailed Implementation

[0044] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. In addition, the forms of the various structures described in the following embodiments are merely illustrative. The UAV pest monitoring method based on intelligent path planning involved in the present invention is not limited to the structures described in the following embodiments. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] This invention provides a drone-based pest monitoring method based on intelligent path planning, comprising the following steps:

[0046] Step 1: Divide the area where pest monitoring needs to be carried out into n equal regions, denoted as monitoring sub-regions;

[0047] By dividing a large area into smaller sub-regions, drones can monitor each region systematically, avoiding the long flight times required to cover the entire area at once, thus improving monitoring speed and efficiency. The sub-regions facilitate detailed monitoring and data collection and analysis, enabling the identification of pest infestation points or trends in specific sub-regions, and helping to more accurately identify and locate pest distribution. Sub-regional monitoring allows for frequent monitoring in key areas and periodic monitoring in secondary areas, achieving tiered monitoring. Furthermore, the division of regions allows for more flexible path planning and real-time adjustments, more effectively optimizing drone flight paths and energy consumption. Regional monitoring also establishes historical data for each sub-region, facilitating comparative analysis of long-term pest trends and providing a scientific basis for future pest prediction and prevention.

[0048] Step 2: Detect meteorological data for each monitoring sub-area, including wind speed, wind direction, temperature, and humidity data, and obtain the meteorological influence coefficient based on the meteorological data;

[0049] In this embodiment, it should be specifically explained that the step of obtaining the meteorological influence coefficient based on meteorological data is as follows:

[0050] Obtain the wind speed and direction for each monitoring sub-region, and calculate the wind force impact.

[0051] The temperature and humidity data for each monitoring sub-region are standardized. The method for obtaining the temperature and humidity influence degree based on the standardized temperature and humidity data is as follows: TH represents the influence of temperature and humidity, t represents the temperature data of the monitored sub-region, and h represents the humidity data of the monitored sub-region. Many pests grow and reproduce most rapidly within a suitable temperature range. Higher temperatures usually accelerate their life cycle, leading to a rapid increase in population size; high humidity environments are conducive to the survival of many pests; high humidity may also affect the health of plants, making them more susceptible to pest attacks, as plants may become more vulnerable under stress.

[0052] The method for obtaining the meteorological influence coefficient based on the influence of wind force and the influence of temperature and humidity is as follows: , where MI represents the meteorological influence coefficient, WF represents the wind force influence degree, and TH represents the temperature and humidity influence degree.

[0053] In this embodiment, it should be specifically explained that the step of obtaining the wind speed and direction of each monitoring sub-region and calculating the wind force influence is as follows:

[0054] Real-time wind speed data of the monitored sub-region is collected, and all monitored sub-regions adjacent to the monitored sub-region are selected and recorded as adjacent sub-regions. The wind speed data of the adjacent sub-regions is collected in real time.

[0055] Collect wind direction data from the monitoring sub-region and adjacent sub-regions, and convert the wind direction into radians using the following formula: ,in Represented in radians, Wind direction;

[0056] The method for calculating the vector components of wind in the monitored sub-region is as follows: , ,in To monitor the components of the horizontal vector in the sub-region, To monitor the components of the vertical vector in the sub-region, This is represented as wind speed data for a monitored sub-region; the method for calculating the vector components of wind for adjacent sub-regions is as follows: , ,in Let be the component of the horizontal vector of the i-th adjacent sub-region. Let be the components of the vertical vector of the i-th adjacent sub-region. This is represented as the wind speed data of the i-th adjacent sub-region;

[0057] The average level component is obtained by averaging the wind speed vectors on the horizontal components of the monitored sub-region and its adjacent sub-regions. The calculation formula is as follows: ,in Represented as the average level component, To monitor the components of the horizontal vector in the sub-region, Let be the component of the horizontal vector of the i-th adjacent sub-region, and m represent the number of adjacent sub-regions. The average vertical component is obtained by averaging the wind speed vectors of the monitored sub-region and its adjacent sub-regions. The calculation formula is as follows: , This is represented as the average vertical component. To monitor the components of the vertical vector in the sub-region, These are the components of the vertical vector of the i-th adjacent sub-region;

[0058] The method for obtaining wind influence based on the average horizontal component and the average vertical component. Where WF represents the wind impact degree, Represented as the average level component, It is represented as the average vertical component.

[0059] Pests are typically influenced by wind and move between regions. By combining wind speed and direction data from each region and adjacent regions, the impact of wind on pest spread can be captured more accurately, leading to more precise predictions of pest distribution across areas. Wind influence factors help identify areas where pests are more likely to spread. Drones can prioritize monitoring high-risk sub-regions, rationally allocating monitoring resources to reduce waste of manpower and materials, ensuring timely control in key areas. Wind speed and direction are dynamically changing; wind influence factors generated based on this real-time data can help drones adjust their flight paths to cover areas where new pests may emerge, enabling dynamic monitoring and rapid response.

[0060] Step 3: Obtain the illumination condition data for each monitoring sub-area, including sunshine duration and diurnal temperature range, and calculate the illumination influence coefficient based on the illumination condition data;

[0061] Sunshine duration affects plant photosynthesis and growth environment, directly impacting pest reproduction and activity. Diurnal temperature variation influences pest physiology and behavior, affecting their growth cycle and activity level; light conditions directly affect pest activity and reproduction. By using the light impact coefficient, the likelihood of pest occurrence in a specific area can be predicted more accurately, allowing for proactive control measures. Sunshine duration and diurnal temperature variation are common parameters in meteorological data, typically easily obtainable from weather stations or services. This simplifies data acquisition and makes it suitable for monitoring and analysis in different regions.

[0062] In this embodiment, it should be specifically explained that the step of calculating the illumination influence coefficient based on illumination condition data is as follows:

[0063] The average sunshine duration is calculated by averaging the sunshine duration of the monitored sub-regions within the monitoring period.

[0064] The average diurnal temperature range is obtained by averaging the diurnal temperature range of the monitored sub-regions within the monitoring period.

[0065] The light impact coefficient is calculated based on the average sunshine duration and average diurnal temperature range. The formula for its calculation is as follows: Where LE represents the light impact coefficient, S is the average sunshine duration, and T is the average sunshine duration. d This represents the average diurnal temperature range.

[0066] Step 4: Obtain historical pest infestation data for each monitored sub-area. The historical pest infestation data includes the frequency of pest occurrence, duration of pest occurrence, and severity of pest infestation. The historical pest infestation coefficient is evaluated based on the historical pest infestation data.

[0067] In this embodiment, it should be specifically explained that the step of obtaining the historical disaster coefficient based on historical insect infestation data is as follows:

[0068] The number of pest occurrences in each monitored sub-area within a monitoring period can be one or two years. A high frequency of pest occurrences may indicate that the area is more sensitive to pests. The duration of each pest occurrence within the monitoring period is also obtained. A longer pest duration usually indicates greater damage.

[0069] Acquire the loss data for each pest infestation and calculate the degree of damage based on the loss data;

[0070] The historical damage coefficient is calculated based on the number of pest occurrences, duration, and degree of damage. The calculation formula is as follows: Where HD represents the historical disaster coefficient, j represents the number of insect infestations, and sj i For the duration of the i-th infestation, ph i The degree of damage caused by the i-th pest infestation.

[0071] In this embodiment, it should be specifically explained that the step of obtaining the loss data for each pest infestation and calculating the degree of damage based on the loss data is as follows:

[0072] The method for collecting data on crop yield reduction rate and affected area in the monitored sub-regions after each pest infestation, and then determining the degree of damage based on these data, is as follows: , where ph is the degree of damage, sa is the affected area, and jc is the crop yield reduction rate.

[0073] Crop yield reduction rate reflects the direct impact of pests, while affected area indicates the extent of the impact. Combining the two allows for a more comprehensive assessment of the degree of damage caused by pests, reflecting both the depth (yield reduction rate) and the breadth (affected area) of the infestation. Both yield reduction rate and affected area are relatively easy-to-obtain basic data, and farmers and monitoring personnel can usually quickly measure or estimate these two indicators after a pest outbreak. Because yield reduction rate and affected area do not depend on the physical characteristics of a specific crop, this calculation method can be adapted to various crop types. Whether it is food crops, cash crops, or other vegetation, these two parameters can be used to assess the impact of pests, demonstrating strong adaptability.

[0074] Step 5: Calculate the disaster index based on the meteorological impact coefficient, the sunshine impact coefficient, and the historical disaster impact coefficient. The calculation formula is as follows: The equations DT (Disaster Indices) and MI (Meteorological Influence Coefficient) represent the risk of insect infestations. Different meteorological conditions have a significant impact on and drive the risk of insect infestations. As wind speed increases or wind direction becomes more favorable for insect migration, high temperature and high humidity environments become more conducive to insect reproduction and activity, leading to an increase in the meteorological influence coefficient and consequently, an increase in the insect infestation index. This direct correlation indicates that when unfavorable meteorological conditions intensify, the risk of insect outbreaks and spread is higher. The meteorological influence coefficient can serve as a key parameter, reflecting the degree to which meteorological conditions in a specific area affect insect infestations, thus providing a scientific basis for insect infestation early warning, monitoring strategy adjustment, and precision control. LE (Light Influence Coefficient) represents the light impact coefficient. Increased sunshine duration and widening diurnal temperature ranges typically stimulate the reproduction, activity, and spread of certain insects. For example, prolonged sunshine may accelerate insect metabolism and growth, while larger diurnal temperature ranges may affect the activity time or frequency of insects. In this case, the higher the light impact coefficient, the higher the insect infestation index, indicating an increased risk of insect infestations in the area. The light impact coefficient, as an indicator for assessing insect infestation risk, reflects the driving role of light factors on the ecological behavior of pests, providing a scientific reference for pest monitoring and control. HD represents the historical damage coefficient, and past insect infestation situations have a guiding role in current insect infestation risk. The historical damage coefficient reflects the frequency and severity of insect infestations in the region in different years. A higher historical damage coefficient means that the region has experienced frequent insect infestations in the past, and environmental conditions were suitable for pest breeding or spread; therefore, the insect infestation index will increase accordingly. a1, a2, and a3 represent the weighting coefficients of the meteorological impact coefficient, the light impact coefficient, and the historical damage coefficient, respectively. The specific values ​​of a1, a2, and a3 are determined by professionals based on the actual situation. For example, a1, a2, and a3 can be 0.4, 0.4, and 0.2, respectively.

[0075] Step 6: Divide the monitoring sub-regions in real time according to the disaster index;

[0076] In this embodiment, it should be specifically explained that the step of dividing the monitoring sub-area in real time according to the disaster index is as follows:

[0077] The disaster index is compared with a preset threshold. If the disaster index is less than the preset threshold, the probability of insect infestation in the area is low, and the area is recorded as a secondary area. If the disaster index is greater than the preset threshold, the probability of insect infestation in the area is high, and the area is recorded as a key area.

[0078] By dividing regions into key and secondary areas, limited monitoring and control resources can be allocated more effectively. Key areas can receive more attention and intervention measures, while secondary areas can be subject to relatively simple monitoring measures. Threshold-based assessment of the disaster index can promptly identify high-risk areas, enabling rapid and targeted implementation of control measures, thereby reducing the spread and losses of pests. Data-driven regional division allows for precision agricultural management, enabling differentiated management based on actual conditions, effectively improving the safety and profitability of agricultural production. This method bases decisions on objective data, reducing the influence of subjective judgment and thus improving the scientific rigor and reliability of decisions. Furthermore, this method allows for the establishment of standardized monitoring procedures, facilitating evaluation and comparison by agricultural management departments at all levels, thereby improving the efficiency of the entire monitoring system.

[0079] Step 7: Use Algorithm A to perform real-time path planning based on the key areas obtained, and let the drone monitor pests according to the real-time path planning;

[0080] Algorithm A is a heuristic search-based path planning algorithm used to find the optimal path from a starting point to a target point on a map. It estimates the sum of the actual cost (distance from the starting point to the node) and the heuristic cost (estimated distance from the node to the target point) of each path node, prioritizing the node with the lowest cost for expansion, thus quickly finding the shortest or lowest-cost path. Algorithm A is widely used in path planning and navigation, especially suitable for scenarios with many obstacles or requiring dynamically updated paths.

[0081] In this embodiment, it should be specifically explained that the step of real-time path planning based on the acquired key areas is as follows:

[0082] By adding a "priority weight" parameter to the cost function of Algorithm A, an optimized Algorithm A is obtained. Lower path costs are set for key areas, allowing drones to fly to these areas first; at the same time, higher costs are set for secondary areas to reduce flight frequency.

[0083] An optimized A algorithm is used to prioritize coverage of key areas when planning routes, and then generate routes to secondary areas to save energy. A monitoring threshold is set so that after the UAV completes the monitoring task of the key areas, it will switch to the secondary areas for auxiliary monitoring.

[0084] If new data on densely populated pest areas are acquired during flight, the regions are re-divided. Based on the region division results, the algorithm automatically adjusts their priorities and paths, enabling the UAV to dynamically adjust its flight plan. The UAV flies on the real-time updated path, achieving high-frequency monitoring of key areas and low-frequency monitoring of secondary areas, thereby improving monitoring efficiency.

[0085] The distribution of pests is random and mobile, and can change with wind direction, climate, or other factors. By acquiring and updating data on pest-dense areas in real time, drones can dynamically adapt to the latest pest situation, ensuring timely monitoring and control of high-density pest areas. Adjusting monitoring priorities and flight paths based on new data allows drones to concentrate on the most infested areas, avoiding excessive time spent in low-risk areas. This path optimization effectively reduces battery, power, and pesticide consumption, improving drone mission efficiency. Dynamically adjusting flight plans enables drones to cover newly infested areas more promptly, preventing further pest spread and improving the overall effectiveness of pest control. Drones can respond quickly at critical times and locations, achieving more effective pest control; dynamic path planning allows drones to automatically adjust priorities and paths, reducing reliance on manual commands. Thus, drones can autonomously handle complex pest situations without human intervention, enhancing their intelligence and automation.

[0086] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0087] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for monitoring pests using unmanned aerial vehicles (UAVs) based on intelligent path planning, characterized in that, Includes the following steps: Step 1: Divide the area where pest monitoring needs to be carried out into n equal regions, denoted as monitoring sub-regions; Step 2: Detect meteorological data for each monitoring sub-area, including wind speed, wind direction, temperature, and humidity data, and obtain the meteorological influence coefficient based on the meteorological data; Step 3: Obtain the illumination condition data for each monitoring sub-area, including sunshine duration and diurnal temperature range, and calculate the illumination influence coefficient based on the illumination condition data; Step 4: Obtain historical pest infestation data for each monitored sub-area. The historical pest infestation data includes the frequency of pest occurrence, duration of pest occurrence, and severity of pest infestation. The historical infestation coefficient is evaluated based on the historical pest infestation data. Step 5: Calculate the disaster index based on the meteorological impact coefficient, the sunshine impact coefficient, and the historical disaster impact coefficient. The calculation formula is as follows: DT represents the disaster index, MI represents the meteorological impact coefficient, LE represents the sunshine impact coefficient, HD represents the historical disaster coefficient, and a1, a2, and a3 represent the weighting coefficients of the meteorological impact coefficient, sunshine impact coefficient, and historical disaster coefficient. Step 6: Divide the monitoring sub-regions in real time according to the disaster index; Step 7: Use Algorithm A to perform real-time path planning based on the divided areas, and enable the drone to monitor pests based on the real-time path planning; The steps for assessing and obtaining the historical disaster coefficient based on historical insect infestation data are as follows: Get the number of pest occurrences within the detection time period for each monitored sub-region; get the duration of each pest occurrence within the detection time period; Acquire the loss data for each pest infestation and calculate the degree of damage based on the loss data; The historical damage coefficient is calculated based on the number of pest occurrences, duration, and degree of damage. The calculation formula is as follows: Where HD represents the historical disaster coefficient, j represents the number of insect infestations, and sj i For the duration of the i-th infestation, ph i The degree of damage caused by the i-th pest infestation; The steps for obtaining loss data for each pest infestation and calculating the degree of damage based on the loss data are as follows: The method for collecting data on crop yield reduction rate and affected area in the monitored sub-regions after each pest infestation, and then determining the degree of damage based on these data, is as follows: , where ph is the degree of damage, sa is the affected area, and jc is the crop yield reduction rate.

2. The method for monitoring pests using unmanned aerial vehicles (UAVs) based on intelligent path planning according to claim 1, characterized in that: The steps for obtaining the meteorological impact coefficient based on meteorological data are as follows: Obtain the wind speed and direction for each monitoring sub-region, and calculate the wind force impact. The temperature and humidity data of each monitoring sub-area are standardized, and the temperature and humidity influence is obtained based on the standardized temperature and humidity data. The method for obtaining the meteorological influence coefficient based on the influence of wind force and the influence of temperature and humidity is as follows: , where MI represents the meteorological influence coefficient, WF represents the wind force influence degree, and TH represents the temperature and humidity influence degree.

3. The method for monitoring pests using unmanned aerial vehicles (UAVs) based on intelligent path planning according to claim 2, characterized in that: The steps for obtaining the wind speed and direction of each monitoring sub-region and calculating the wind force influence are as follows: Real-time wind speed data of the monitored sub-region is collected, and all monitored sub-regions adjacent to the monitored sub-region are selected and recorded as adjacent sub-regions. The wind speed data of the adjacent sub-regions is collected in real time. Collect wind direction data for the monitored sub-region and adjacent sub-regions, and convert the wind direction into radians; The method for calculating the vector components of wind in the monitored sub-region is as follows: , ,in To monitor the components of the horizontal vector in the sub-region, To monitor the components of the vertical vector in the sub-region, Represented in radians, This is represented as wind speed data for a monitored sub-region; the method for calculating the vector components of wind for adjacent sub-regions is as follows: , ,in Let be the component of the horizontal vector of the i-th adjacent sub-region. Let be the components of the vertical vector of the i-th adjacent sub-region. It is represented by the radians of the wind direction in the i-th adjacent sub-region. This is represented as the wind speed data of the i-th adjacent sub-region; The average level component is obtained by averaging the wind speed vectors on the horizontal components of the monitored sub-region and its adjacent sub-regions. The calculation formula is as follows: ,in Represented as the average level component, To monitor the components of the horizontal vector in the sub-region, Let be the component of the horizontal vector of the i-th adjacent sub-region, and m represent the number of adjacent sub-regions. The average vertical component is obtained by averaging the wind speed vectors of the monitored sub-region and its adjacent sub-regions. The calculation formula is as follows: , This is represented as the average vertical component. To monitor the components of the vertical vector in the sub-region, These are the components of the vertical vector of the i-th adjacent sub-region; The method for obtaining the wind force influence based on the average horizontal component and the average vertical component. Where WF represents the wind impact degree, Represented as the average level component, It is represented as the average vertical component.

4. The method for monitoring pests using unmanned aerial vehicles (UAVs) based on intelligent path planning according to claim 1, characterized in that: The steps for calculating the illumination influence coefficient based on illumination condition data are as follows: The average sunshine duration is calculated by averaging the sunshine duration of the monitored sub-regions within the monitoring period. The average diurnal temperature range is obtained by averaging the diurnal temperature range of the monitored sub-regions within the monitoring period. The light impact coefficient is calculated based on the average sunshine duration and average diurnal temperature range. The formula for its calculation is as follows: Where LE represents the light impact coefficient, S is the average sunshine duration, and T is the average sunshine duration. d This represents the average diurnal temperature range.

5. The method for monitoring pests using unmanned aerial vehicles (UAVs) based on intelligent path planning according to claim 1, characterized in that: The steps for dividing the monitoring sub-regions in real time based on the disaster index are as follows: The disaster index is compared with a preset threshold. If the disaster index is less than the preset threshold, the probability of insect infestation in the area is low, and the area is recorded as a secondary area. If the disaster index is greater than the preset threshold, the probability of insect infestation in the area is high, and the area is recorded as a key area.

6. The method for monitoring pests using unmanned aerial vehicles (UAVs) based on intelligent path planning according to claim 5, characterized in that: The steps for real-time path planning based on the obtained key areas are as follows: By adding a "priority weight" parameter to Algorithm A, an optimized Algorithm A is obtained. Low path costs are set for key areas, allowing drones to fly to these areas first; at the same time, high path costs are set for secondary areas to reduce the frequency of flights. An optimized A algorithm is used to generate monitoring routes based on key and secondary areas; It also acquires new data in real time during flight, re-divides the area, and updates the monitoring route.

Images