Sugarcane borer field distribution positioning and insect situation prediction method

Abstract

The invention is suitable for the technical field of agricultural information, and provides a sugarcane borer field distribution positioning and insect condition prediction method, which comprises the following steps: collecting historical insect condition data, real-time monitoring data and ecological environment data, and constructing an insect condition database; obtaining a sugarcane field image by aerial photography of an unmanned aerial vehicle, and generating an insect pest distribution thermodynamic diagram by associating geographic coordinates; future insect pest distribution is predicted based on historical data and an environment simulation model (including life cycle and diffusion path modules); a spraying path is optimized by combining the thermodynamic diagram and spraying equipment parameters; finally, a dynamic pesticide spraying scheme is generated, and pesticide spraying time and pesticide dosage distribution are coordinated. Through multi-source data fusion and model analysis, accurate positioning, dynamic prediction and path optimization of insect pests are realized, the control efficiency is remarkably improved, pesticide use is reduced, the sugarcane growth requirements are met, and an efficient solution is provided for scientific control of sugarcane borers.

Description

Technical Field

[0001] The invention belongs to the field of agricultural information technology, and in particular relates to a method for field distribution positioning and insect situation prediction of sugarcane borers. Background Art

[0002] The sugarcane borer is a major pest in sugarcane cultivation. Its larvae bore into the stalks, leading to yield reductions or even complete crop failure. Current monitoring of the pest relies primarily on manual field inspections or data collection using single sensors (such as traps). This presents challenges such as low efficiency, limited coverage, and poor data timeliness.

[0003] In recent years, some technologies have attempted to combine drone aerial photography with geographic information systems (GIS) for insect infestation location, but these technologies are often limited to static image analysis and lack the ability to integrate dynamic data. In the field of insect infestation prediction, existing methods are often based on statistical analysis of historical insect infestation data or linear regression models of simple environmental parameters (such as temperature). They fail to systematically integrate real-time ecological and environmental data (such as humidity and soil conditions) and pest spread patterns, resulting in insufficient prediction accuracy. For pesticide control, traditional methods rely on fixed routes or empirical spraying methods, lacking optimal matching of the dynamic distribution of pests and equipment properties, and can easily lead to pesticide waste or incomplete coverage. Summary of the Invention

[0004] The object of the present invention is to provide a method for locating the field distribution of sugarcane borers and predicting their insect infestation, aiming to solve the technical problems existing in the prior art identified in the background technology.

[0005] The present invention is achieved by providing a method for locating the field distribution of sugarcane borers and predicting their presence, the method comprising: Collect insect-related data, including historical insect data, current insect monitoring data, and ecological environment data, and establish an insect database, storing all collected data with the data collection time as the label; Obtain images of sugarcane fields and, based on the collected current pest monitoring data, correlate the pest data with geographic coordinates, analyze pest density in different areas, generate a current pest distribution heat map, and mark the infested areas; Match the locations and times recorded in pest-related data with the pest-infested areas. Build an environmental simulation model based on historical pest data and ecological environment data to simulate the growth and spread of stem borers in the current growth environment and generate a thermal map of pest distribution changes in the future. Based on the simulated pest growth and spread, as well as the current pest distribution heat map, a path optimization model is established to calculate the spraying path with the goal of spraying all pest-infested areas. Based on the spraying path and combined with the pest distribution thermal change map at future moments, a specific future pest spraying plan is generated.

[0006] As a further solution of the present invention, analyzing the pest density in different areas, generating a pest distribution heat map at the current moment, and marking the pest areas specifically includes: Read sugarcane field image data collected by aerial drones and add metadata to each image, including shooting time, geographic coordinates, and current ecological and environmental data; Match the current insect situation data with the geographic coordinates of the corresponding image data; Based on the matched image data, pest density maps are generated through spatial statistics to analyze pest density data in different areas; Based on the pest density data of different areas, a pest distribution heat map at the current moment is generated, and the pest density map is superimposed to mark each pest area, and the mark color is adjusted according to the density value.

[0007] As a further solution of the present invention, the matching of the pest area with the location and time recorded in the pest-related data, and establishing an environmental simulation model based on historical pest data and ecological environment data, simulating the growth and spread of stem borers in the current growth environment, and generating a thermal change map of pest distribution at future moments, specifically includes: Each pest area is associated with the historical pest data entries in the pest database through geographic coordinates and collection time tags; Filter historical pest data and ecological environment data corresponding to each pest area in the current pest distribution heat map, establish an environmental simulation model, and simulate the life cycle, behavior patterns, and diffusion patterns of sugarcane borers; Using the established environmental simulation model, the current insect monitoring data and ecological environment data are used as input to simulate the growth and spread of stem borers in the current growth environment, and generate a thermal change map of insect pest distribution in the future.

[0008] As a further solution of the present invention, the environmental simulation model includes: Life cycle module: used to simulate the hatching, reproduction and death cycle of stem borers under current environmental conditions; Diffusion module: used to simulate the diffusion path and speed of stem borers by combining ecological environment data; Environmental impact module: used to simulate the impact of ecological and environmental factors on the growth and spread of stem borers; Dynamic update module: used to update simulation results based on real-time data.

[0009] As a further solution of the present invention, the path optimization model is established to calculate the spraying path with the goal of covering all pest-infested areas with spraying, specifically including: A heat map of pest distribution at the current moment, identifying all areas affected by pests and recording the pest density and distribution characteristics in each area; Establish a path optimization model, using the coordinates of the infested area, pest density data, and spraying equipment attributes as input parameters to simulate the actual spraying process, evaluate the spraying coverage and efficiency, and calculate the optimal spraying path; The calculated optimal spraying path is re-evaluated to determine whether it can cover all pest-infested areas at present and in the future based on the growth and spread of stem borers in the current growth environment.

[0010] As a further solution of the present invention, the generation of a specific future pest spraying plan by combining the pest distribution thermal change map at a future moment specifically includes: Based on the pest distribution thermal change map at future moments, read the predicted data of future pests; Based on the forecast data of future pests, we can identify the peak period of pests and set the best time for spraying according to the growth stage of sugarcane. Based on the current pest distribution heat map and pest density, the required amount of pesticide is calculated, and combined with the properties of the spraying equipment, the pesticide demand for each area is allocated.

[0011] As a further embodiment of the present invention, the generating of a specific future pest spraying plan further includes: Integrate the optimal spraying route with the spraying time and dosage, analyze whether the spraying route is coordinated with the spraying time, and whether the spraying time is coordinated with the pesticide demand in each area, and adjust future pest spraying plans.

[0012] The beneficial effects of the present invention are: An insect database is established by collecting historical insect infestation data, current insect monitoring data, and ecological and environmental data, and data is stored using the time of data collection. Aerial drones are used to capture images of sugarcane fields, and metadata is added to link insect infestation data with geographic coordinates. Compared to traditional manual field inspections or single-sensor data collection, drone aerial photography can capture large-scale, high-resolution images, greatly improving data acquisition efficiency and coverage. Storing data using time tags facilitates tracking of insect pest development and changes, improving data timeliness.

[0013] By integrating historical pest data, current pest monitoring data, and ecological environment data, the dynamic update module within the environmental simulation model can update simulation results based on real-time data, enabling dynamic monitoring and analysis of stem borer growth and spread. This overcomes the limitations of existing technologies, which are limited to static image analysis, and can reflect pest changes in real time.

[0014] By collaboratively simulating the growth, reproduction, and diffusion patterns of stem borers and the influence of ecological and environmental factors through multiple modules, various factors affecting the insect situation are comprehensively and systematically considered. Compared with simple statistical analysis based on historical insect situation data or linear regression models that only consider a single environmental parameter, the prediction accuracy is significantly improved.

[0015] A path optimization model was established, aiming to achieve complete spray coverage of infested areas. The optimal spraying path was calculated using infested area coordinates, pest density data, and spraying equipment attributes as input parameters. The optimal spraying path was then generated based on a thermodynamic map of future pest distribution. During the spraying plan development process, comprehensive considerations were taken into account regarding spraying timing, dosage distribution, and coordination of the spraying path. This approach avoids the waste and incomplete coverage associated with traditional fixed-path or empirical spraying, reduces pesticide usage, and improves the efficiency and effectiveness of spraying. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of a method for field distribution positioning and insect infestation prediction of sugarcane borers provided by an embodiment of the present invention; Figure 2 A flowchart for generating a current pest distribution heat map and marking pest-infested areas, provided by an embodiment of the present invention; Figure 3 A flowchart for simulating the growth and spread of stem borers in a current growth environment and generating a thermodynamic change diagram of pest distribution at a future time, provided by an embodiment of the present invention; Figure 4 A flow chart for calculating a spraying path provided by an embodiment of the present invention; Figure 5 A flowchart for generating a specific future pest spraying plan provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] Figure 1 A flow chart of a method for field distribution positioning and insect infestation prediction of sugarcane borers provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the method includes: S100, collecting insect-related data, including historical insect data, current insect monitoring data, and ecological environment data, and establishing an insect database, storing all collected data with data collection time as a label; This step requires collecting various data related to the sugarcane borer to establish a comprehensive pest database. This data consists of three main areas: historical pest data, current pest monitoring data, and ecological and environmental data. Historical pest data refers to the occurrence of sugarcane borers over a period of time, including pest species, occurrence time, distribution area, and abundance. This data provides important context for subsequent pest analysis, helping to identify seasonal variations in pests and potential high-incidence areas. Current pest monitoring data, collected in real time, is typically obtained through drone imagery and ground-based monitoring. It reflects the immediate dynamics of pests and provides a basis for subsequent decision-making. Ecological and environmental data includes factors such as temperature, humidity, precipitation, and soil type. These environmental conditions have a direct impact on the growth and spread of the borer. Therefore, by combining these data, we can better understand the biological behavior and ecological habits of the borer.

[0019] Storing this collected data with a label based on the time of data collection not only clarifies the data structure but also facilitates subsequent querying and analysis. The introduction of time labels allows researchers to easily track changes in pest development, analyze trends in pest infestations at different time points, and make more accurate predictions of pest occurrences. Furthermore, establishing an insect infestation database lays a solid foundation for subsequent model construction, facilitating data mining and pattern recognition in subsequent steps, thereby improving the accuracy of pest infestation predictions.

[0020] This step, through comprehensive data collection, builds a rich database, providing multidimensional data support for subsequent analysis. The integration of historical data with current monitoring data allows for the integration of dynamic monitoring with historical trend analysis, effectively identifying potential pest risks. Furthermore, considering ecological factors makes model construction more scientific and practical, as the growth and spread of stem borers are not solely influenced by the pest population itself, but are closely related to their habitat.

[0021] The systematization and standardization of this process will significantly improve the accuracy and reliability of insect infestation forecasts, thereby providing sugarcane growers with more scientific prevention and control measures and reducing economic losses.

[0022] S200, obtaining an image of a sugarcane field, and based on the collected current pest monitoring data, associating the pest data with geographic coordinates, analyzing pest density in different areas, generating a current pest distribution heat map, and marking the pest-infested areas; This step uses drones to capture images of the sugarcane fields. This method captures high-resolution images of large areas, ensuring both accurate and rich data. Adding metadata to each image, including capture time, geographic coordinates, and current ecological and environmental data, provides essential context for subsequent analysis, ensuring that the image data is clearly identified in time and space.

[0023] By matching the geographic coordinates of current pest monitoring data with image data, we can accurately overlay pest information onto actual geographic locations, providing a more intuitive view of pest distribution in different regions. Using spatial statistical methods, we can generate pest density maps based on the matched image data, analyzing which areas are most densely infested with pests. This provides important guidance for the development of subsequent prevention and control measures.

[0024] Based on pest density data for different areas, a heat map of the current pest distribution is generated. In the heat map, each infested area is marked with a different color. This intuitive visual representation makes data interpretation simple and clear, allowing growers to quickly identify areas with severe pests and take appropriate measures. This process not only improves the efficiency of data utilization but also enhances farmers' ability to respond promptly to pest dynamics.

[0025] Advanced image acquisition and processing technologies enable precise location and quantitative analysis of pest distribution in sugarcane fields. The use of aerial drones significantly expands the scope and efficiency of data acquisition, overcoming the limitations of traditional ground inspection methods. High-resolution imagery provides more detailed pest information. Linking pest data to geographic coordinates transcends statistical data, enhancing its practicality and relevance. The resulting heat maps provide farmers with clear identification of infested areas and support decision-making, significantly improving the efficiency and effectiveness of pest control efforts. This allows for more efficient resource allocation and optimized spraying strategies, ultimately enabling scientific and efficient agricultural production management.

[0026] This method of data integration and intuitive visualization not only improves the accuracy of insect monitoring, but also provides a solid foundation for subsequent insect prediction and prevention and control strategy formulation, and promotes the development of precision agriculture.

[0027] like Figure 2 As shown, the analysis of pest density in different areas, generating a pest distribution heat map at the current moment, and marking the pest areas specifically includes: S210, reading the sugarcane field image data collected by the aerial photography drone, and adding metadata to each image, including the shooting time, geographic coordinates, and ecological environment data at the current moment; S220, matching the insect situation data at the current moment with the geographic coordinates of the corresponding image data; S230, generating an insect pest density map through spatial statistics based on the matched image data, and analyzing insect pest density data in different areas; S240: Based on the pest density data of different areas, a pest distribution heat map at the current moment is generated, and the pest density map is superimposed to mark each pest area, and the mark color is adjusted according to the density value.

[0028] S300: Matching the location and time recorded in the pest-infested area with the pest-related data, and establishing an environmental simulation model based on the historical pest data and ecological environment data to simulate the growth and spread of stem borers in the current growth environment and generate a thermal change map of pest distribution in the future; This step links each infested area to historical pest data entries in the pest database using geographic coordinates and collection time tags. This process ensures the timeliness and spatial accuracy of the data, providing a deeper understanding of pest conditions in specific areas and enabling analysis of historical pest trends and patterns based on past pest data.

[0029] By screening historical pest and ecological data corresponding to each infested area in the current pest distribution heat map, we can identify key ecological and environmental factors influencing the reproduction and spread of sugarcane borers, such as temperature, precipitation, and soil moisture. These factors are crucial in environmental simulation models and can influence the borer's life cycle, behavior patterns, and spread.

[0030] After establishing the environmental simulation model, it includes several key modules: a life cycle module simulates the incubation, reproduction, and death cycle of stem borers under current environmental conditions; a diffusion module simulates the stem borer's spread path and speed based on ecological and environmental data; an environmental impact module analyzes the impact of ecological and environmental factors on stem borer growth and spread; and a dynamic update module continuously adjusts simulation results based on real-time data. This systematic modeling approach enables more accurate predictions of stem borer distribution in the future, helping farmers prepare for prevention and control measures in advance.

[0031] Specifically: Life Cycle Module: This module's core function is to simulate the growth cycle of the sugarcane borer under specific environmental conditions, including hatching, reproduction, and death. Using historical pest data, we can analyze the borer's growth rate under different climatic conditions, such as temperature and humidity. For example, studies have shown that borer reproduction accelerates significantly under warm and humid conditions, while growth slows in cold and dry environments. By simulating life cycle changes under different environmental conditions, farmers can predict trends in borer populations, such as predicting peak seasons, allowing them to take preventive measures in advance.

[0032] Dispersion Module: This module simulates the spread paths and speeds of stem borers. By combining ecological and environmental data, particularly meteorological factors such as wind speed and direction, the module can predict how stem borers will spread across farmland. For example, if the pest density in a particular area is high and the wind is blowing toward adjacent sugarcane fields, the model can predict how the borers will spread to new areas via wind. This predictive capability enables farmers to apply pesticides at the appropriate time and location, effectively reducing the spread of the pest.

[0033] Environmental Impact Module: This module primarily assesses the impact of various environmental factors on the growth and spread of stem borers. For example, soil moisture, temperature fluctuations, and precipitation are all crucial to the stem borer's habitat. Based on real-time monitoring data, this module analyzes how the current ecological environment promotes or inhibits stem borer reproduction. In some cases, the model may reveal that temperature changes in a particular area accelerate stem borer growth, triggering the risk of an insect outbreak. Farmers can use this information to proactively adjust field management strategies, such as timely irrigation or fertilization, to improve crop resistance to insects.

[0034] Dynamic Update Module: This module is designed to continuously update simulation results based on real-time data to ensure model validity and accuracy. For example, as the seasons change, environmental conditions (such as increased or decreased precipitation) can have varying impacts on the growth of stem borers. The Dynamic Update Module can integrate these changes in real time and automatically adjust model parameters to provide more accurate predictions. For example, after a period of drought, the model might adjust the survival and reproduction rates of stem borers to reflect changing trends in the pest situation. This allows farmers to quickly receive early warnings, prompting them to intervene at the appropriate time.

[0035] By integrating these modules, the environmental simulation model enables multi-dimensional analysis of stem borer growth and spread, helping farmers make informed decisions within complex ecological environments. This data-driven approach not only enhances understanding of pest dynamics but also provides strong technical support for precision agriculture practices.

[0036] This step, through the construction of an environmental simulation model, enables comprehensive analysis and prediction of the growth and spread of sugarcane borers. Combining historical data with real-time monitoring data makes the analysis more accurate, enabling the development of more targeted prevention and control measures based on actual conditions. The multi-module environmental simulation model comprehensively considers all factors affecting borer growth, making predictions more scientific and reasonable, and reducing the errors associated with single-factor analysis.

[0037] Furthermore, the introduction of a dynamic update module enables the model to reflect environmental changes in real time, allowing for timely adjustments to predictions and enhancing early warning capabilities. These advantages not only help farmers take preventative measures before pest infestations occur, improving the economic benefits of sugarcane cultivation, but also promote sustainable agricultural production, providing strong support for effectively controlling the damage caused by sugarcane borers. Through this scientific management approach, farmers can make sound decisions in the face of uncertain climate factors and changing pest conditions, ensuring the healthy growth of their crops.

[0038] like Figure 3 As shown, the matching of the pest area with the location and time recorded in the pest-related data, and the establishment of an environmental simulation model based on historical pest data and ecological environment data, simulate the growth and spread of stem borers in the current growth environment, and generate a thermal change map of pest distribution at future moments, specifically including: S310 , associating each insect infestation area with a historical insect infestation data entry in an insect infestation database using geographic coordinates and collection time tags; S320, screening historical pest data and ecological environment data corresponding to each pest area in the current pest distribution heat map, establishing an environmental simulation model, and simulating the life cycle, behavior pattern, and diffusion pattern of the sugarcane borer; S330 uses the established environmental simulation model, takes the current insect monitoring data and ecological environment data as input, simulates the growth and spread of stem borers in the current growth environment, and generates a thermal change map of insect pest distribution at future times.

[0039] In this step, the environmental simulation model includes: Life cycle module: used to simulate the hatching, reproduction and death cycle of stem borers under current environmental conditions; Diffusion module: used to simulate the diffusion path and speed of stem borers by combining ecological environment data; Environmental impact module: used to simulate the impact of ecological and environmental factors on the growth and spread of stem borers; Dynamic update module: used to update simulation results based on real-time data.

[0040] S400: Based on the simulated insect growth and spread and the current insect pest distribution heat map, a path optimization model is established to calculate the spraying path with the goal of spraying all insect pest areas. The current pest distribution heat map provides farmers with detailed information on pest distribution, including pest density and distribution characteristics in each affected area. This heat map allows farmers to quickly identify areas with severe pests, understand the severity and scope of the infestation, and provide data support for subsequent spraying decisions.

[0041] When building a route optimization model, the coordinates of the infested areas, pest density data, and the properties of the spraying equipment are first required as input parameters. The coordinates of the infested areas help the model determine specific target locations for spraying, while the pest density data provides a basis for prioritizing spraying in each area. For example, if a particular area has a high pest density, that area will be prioritized during route optimization to ensure that spraying reaches the areas most in need of intervention. Furthermore, the properties of the spraying equipment, such as spraying coverage and spraying speed, also influence route design.

[0042] The core task of the path optimization model is to simulate the actual spraying process and evaluate its coverage and efficiency. By simulating the spraying path, the model can calculate the optimal route required to spray all infested areas in the shortest possible time. This optimization not only reduces spraying time but also reduces pesticide usage, thereby reducing costs and environmental impact.

[0043] After determining the optimal spraying route, a secondary assessment is also crucial. This process assesses whether the calculated route is sufficient to cover the infested area both now and in the future, based on the current growth and spread of stem borers in the environment. For example, if the model predicts that an infested area may expand into neighboring areas within the next few days, this future change should be factored into the route optimization to ensure the effectiveness and sustainability of the spraying effort.

[0044] By comprehensively considering pest density and equipment properties, the optimization model eliminates random decisions related to spraying and instead makes them scientific and informed. This data-driven, precise spraying strategy not only protects crops but also effectively controls pesticide use and reduces negative environmental impacts.

[0045] The ability to dynamically assess future pest distribution changes ensures proactive spraying measures and provides farmers with more adaptable control strategies. This means farmers are no longer passively responding to pests, but can proactively predict and manage them, thereby improving the scientific nature and effectiveness of overall agricultural management.

[0046] like Figure 4As shown, the path optimization model is established to calculate the spraying path with the goal of covering all pest areas with spraying, specifically including: S410, a heat map of pest distribution at the current moment, identifying all areas affected by pests and recording the pest density and distribution characteristics of each area; S420, establishing a path optimization model, using the coordinates of the pest area, pest density data, and spraying equipment attributes as input parameters, simulating the actual spraying process, evaluating the spraying coverage and efficiency, and calculating the optimal spraying path; S430: A secondary evaluation is performed on the calculated optimal spraying path to determine whether it can cover all pest-infested areas at present and in the future based on the growth and spread of stem borers in the current growth environment.

[0047] S500 generates a specific future pest spraying plan based on the spraying path and the pest distribution thermal change map at future moments.

[0048] Generating future pest spraying plans first requires accessing forecast data on future pest outbreaks. Based on thermal maps of pest distribution at future moments, farmers can clearly understand potential peak pest outbreaks. By analyzing historical and current pest data, combined with the output of environmental simulation models, upcoming peak pest outbreaks can be identified. This peak identification not only facilitates timely formulation of prevention and control strategies but also effectively reduces pesticide use and mitigates negative environmental impacts. For example, during critical periods when a pest outbreak is imminent, farmers can precisely schedule spraying to ensure it is most effective.

[0049] The optimal spraying time is then determined based on the sugarcane's growth stage. This step aims to maximize spraying effectiveness, minimize crop damage, and improve yield and quality, based on an understanding of the sugarcane growth cycle and the peak period of pest resistance.

[0050] After determining the spraying time, the required dosage needs to be calculated. Based on the current pest distribution heat map and pest density, the model accurately calculates the required dosage for each area. By analyzing pest density, farmers can rationally allocate pesticides to ensure that each affected area receives the appropriate amount of control measures. Combined with the properties of the spraying equipment, this process can optimize pesticide distribution, making the spraying process more efficient.

[0051] Finally, the optimal spraying path is integrated with the spraying time and dosage. By analyzing the matching degree between the spraying path and the spraying time, the spraying measures can be guaranteed to achieve maximum coverage in both time and space. At the same time, the coordination between the spraying time and the required amount of pesticide in each area can effectively avoid the situation where the control effect is not ideal due to improper spraying time or uneven distribution of pesticide.

[0052] This step leverages future pest forecast data, allowing farmers to proactively control pest outbreaks before they occur, improving the accuracy of pest management. Furthermore, by rationally calculating pesticide dosages and optimizing spraying routes, pesticide usage can be significantly reduced, lowering production costs and minimizing environmental impact, thus complying with the principles of sustainable agriculture. Properly scheduling spraying ensures that spraying occurs before the peak of pest activity, improving control effectiveness and minimizing the threat to sugarcane yields.

[0053] like Figure 5 As shown, the method combines the pest distribution thermal change map at the future moment to generate a specific future pest spraying plan, which specifically includes: S510, based on the pest distribution thermal change map at the future moment, reading the predicted data of future pests; S520, based on future pest prediction data, identifies the peak period of pest occurrence and sets the optimal spraying time based on the sugarcane growth stage; S530: Calculate the required pesticide dosage based on the current pest distribution heat map and pest density, and allocate the pesticide demand to each area based on the properties of the spraying equipment.

[0054] In this step, generating a specific future pest spraying plan also includes: Integrate the optimal spraying route with the spraying time and dosage, analyze whether the spraying route is coordinated with the spraying time, and whether the spraying time is coordinated with the pesticide demand in each area, and adjust future pest spraying plans.

[0055] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0056] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0057] 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 and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for locating the distribution of sugarcane borers in the field and predicting their presence, characterized in that: The method comprises: Collect insect-related data, including historical insect data, current insect monitoring data, and ecological environment data, and establish an insect database, storing all collected data with the data collection time as the label; Obtain images of sugarcane fields and, based on the collected current pest monitoring data, correlate the pest data with geographic coordinates, analyze pest density in different areas, generate a current pest distribution heat map, and mark the infested areas; Match the locations and times recorded in pest-related data with the pest-infested areas. Build an environmental simulation model based on historical pest data and ecological environment data to simulate the growth and spread of stem borers in the current growth environment and generate a thermal map of pest distribution changes in the future. Based on the simulated pest growth and spread, as well as the current pest distribution heat map, a path optimization model is established to calculate the spraying path with the goal of spraying all pest-infested areas. Based on the spraying path and combined with the pest distribution thermal change map at future moments, a specific future pest spraying plan is generated.

2. The method according to claim 1, characterized in that The analysis of pest density in different areas, generating a pest distribution heat map at the current moment, and marking the pest areas specifically includes: Read sugarcane field image data collected by aerial drones and add metadata to each image, including shooting time, geographic coordinates, and current ecological and environmental data; Match the current insect situation data with the geographic coordinates of the corresponding image data; Based on the matched image data, pest density maps are generated through spatial statistics to analyze pest density data in different areas; Based on the pest density data of different areas, a pest distribution heat map at the current moment is generated, and the pest density map is superimposed to mark each pest area, and the mark color is adjusted according to the density value.

3. The method according to claim 2, characterized in that The matching of the pest area with the location and time recorded in the pest-related data, and the establishment of an environmental simulation model based on historical pest data and ecological environment data, simulate the growth and spread of stem borers in the current growth environment, and generate a thermal change map of pest distribution at future moments, specifically including: Each pest area is associated with the historical pest data entries in the pest database through geographic coordinates and collection time tags; Filter historical pest data and ecological environment data corresponding to each pest area in the current pest distribution heat map, establish an environmental simulation model, and simulate the life cycle, behavior patterns, and diffusion patterns of sugarcane borers; Using the established environmental simulation model, the current insect monitoring data and ecological environment data are used as input to simulate the growth and spread of stem borers in the current growth environment, and generate a thermal change map of insect pest distribution in the future.

4. The method according to claim 3, characterized in that The environmental simulation model includes: Life cycle module: used to simulate the hatching, reproduction and death cycle of stem borers under current environmental conditions; Diffusion module: used to simulate the diffusion path and speed of stem borers by combining ecological environment data; Environmental impact module: used to simulate the impact of ecological and environmental factors on the growth and spread of stem borers; Dynamic update module: used to update simulation results based on real-time data.

5. The method according to claim 4, characterized in that The path optimization model is established to calculate the spraying path with the goal of covering all pest-infested areas with spraying, specifically including: A heat map of pest distribution at the current moment, identifying all areas affected by pests and recording the pest density and distribution characteristics in each area; Establish a path optimization model, using the coordinates of the infested area, pest density data, and spraying equipment attributes as input parameters to simulate the actual spraying process, evaluate the spraying coverage and efficiency, and calculate the optimal spraying path; The calculated optimal spraying path is re-evaluated to determine whether it can cover all pest-infested areas at present and in the future based on the growth and spread of stem borers in the current growth environment.

6. The method according to claim 5, characterized in that The method of generating a specific future pest spraying plan by combining the pest distribution thermal change map at a future moment specifically includes: Based on the pest distribution thermal change map at future moments, read the predicted data of future pests; Based on the forecast data of future pests, we can identify the peak period of pests and set the best time for spraying according to the growth stage of sugarcane. Based on the current pest distribution heat map and pest density, the required amount of pesticide is calculated, and combined with the properties of the spraying equipment, the pesticide demand for each area is allocated.

7. The method according to claim 6, characterized in that The generating of a specific future pest spraying plan also includes: Integrate the optimal spraying route with the spraying time and dosage, analyze whether the spraying route is coordinated with the spraying time, and whether the spraying time is coordinated with the pesticide demand in each area, and adjust future pest spraying plans.

Images