Disaster prediction system and device for pest crawler

Abstract

The invention relates to the technical field of computer systems of biological models, in particular to a disaster prediction system and device for pest crawlers. A camera support rod; a device housing; a temperature sensor; a humidity sensor; the system comprises an MCU processor, a disaster prediction system for pest crawlers, a loudspeaker and a power supply. The pest crawler information is collected through the camera, the temperature sensor and the humidity sensor, and the pest crawler information is processed, predicted and alarmed through the disaster prediction system for the pest crawler, so that the disaster prediction precision of the pest crawler is improved, and the disaster prediction accuracy of the pest crawler is improved. Normal operation of the early warning system is guaranteed, and the effect of accurately predicting disasters of pest crawlers is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of computer systems for biological models, and particularly to a disaster prediction system and device for pest crawlers. Background Art

[0002] In the field of pest control, for disasters caused by reptilian pests, such as crop yield reduction and ecological environment damage, traditional prediction methods have many limitations. Currently, most predictions rely on experience and simple environmental monitoring data. This approach lacks in-depth understanding and accurate analysis of the biological characteristics of crawlers. Reptilian pests have unique life cycles, reproduction laws, and behavior patterns, which are not fully considered by traditional methods.

[0003] Chinese Patent with publication number CN103616482A discloses a pest occurrence period automatic warning device, characterized in that: a wireless transmitter is arranged above a solar panel and transmits data to a microcomputer placed indoors via wireless signals. An electronic circuit board and a lead-acid battery are arranged inside the chassis. The electronic circuit board is connected to a temperature sensor, and the temperature sensor probe is inserted into the plant medium to collect real-time temperature parameters; the environmental temperature acquisition system collects real-time temperature parameters and transmits the collected data to the pest occurrence period automatic prediction system in the microcomputer for data analysis here. The lead-acid battery continuously powers the electronic circuit board, and the temperature sensor connected to the electronic circuit board collects real-time ambient temperature data and transmits the data to the microcomputer placed indoors via wireless signals through the wireless transmitter. It solves the problems existing in the current method of predicting the occurrence period of stem-boring pests using the effective accumulated temperature prediction method; and can accurately calculate the effective accumulated temperature of each instar and the entire generation of stem-boring pests, and predict their development progress in the field through real-time collection and transmission of external data, playing a warning role for the peak occurrence period of stem-boring pests. However, this solution lacks comprehensive consideration of the overall ecological environment within the region and cannot accurately predict the disasters of pest crawlers based on the complex and diverse ecological environments and the number of natural enemies in different regions. Summary of the Invention

[0004] Therefore, the present invention provides a disaster prediction system and device for pest crawlers to overcome the problem in the prior art that the disasters of pest crawlers cannot be accurately predicted based on the complex and diverse ecological environments and the number of natural enemies in different regions.

[0005] To achieve the above object, the present invention provides a disaster prediction device for pest crawlers, comprising:

[0006] A camera, connected to a camera support rod, a power supply, and an MCU processor, for obtaining environmental information;

[0007] The camera support rod is connected to the camera, power supply, device housing, and MUC processor, and is used to support the camera to rotate 360°;

[0008] The device housing is used to protect the camera support rod, power supply, and MCU processor;

[0009] The temperature sensor is connected to the device housing and is used to monitor the ambient temperature;

[0010] The humidity sensor is connected to the device housing and is used to monitor the ambient humidity;

[0011] The MCU processor is connected to the camera, camera support rod, speaker, and power supply, and is used to process the information collected by the camera, temperature sensor, and humidity sensor;

[0012] The disaster prediction system for pest crawlers is provided in the MCU processor and is used to give early warnings of pest crawler disasters;

[0013] The speaker is connected to the MCU processor and power supply and is used to emit alarm sounds;

[0014] The power supply is connected to the camera, camera support rod, MCU processor, and speaker and is used to provide power.

[0015] Further, the disaster prediction system for pest crawlers includes:

[0016] The data collection module collects pest crawler information;

[0017] The quantity prediction module is used to construct a Leslie matrix model based on pest crawler information, predict the quantity of pest crawlers through the Leslie matrix model to obtain the quantity of pest crawlers, and is also used to judge the intraspecific competition situation of pest crawlers according to the population density in the pest crawler information and adjust the Leslie matrix model according to the judgment result. It is also used to judge the environmental impact situation according to the environmental impact value in the pest crawler information and correct the judgment process of the intraspecific competition situation of pest crawlers according to the judgment result;

[0018] The population diffusion prediction module is used to predict the diffusion prediction behavior of pest crawlers according to the quantity of pest crawlers, and is also used to judge the influence situation of population natural enemies according to the population natural enemy influence factor in the pest crawler information and revise the prediction result of the diffusion prediction behavior of pest crawlers according to the judgment result. It is also used to judge the influence situation of the quantity of pest crawlers and the number of population natural enemies according to the human activity value in the pest crawler information and calibrate the judgment process of the influence situation of population natural enemies according to the judgment result;

[0019] A real-time monitoring and feedback module, which is used to judge the performance of the Leslie matrix model according to the actual pest quantity and the pest crawler quantity in the pest crawler information, and correct the Leslie matrix model according to the judgment result;

[0020] An alarm module, which is used to judge the quantity suitability according to the pest crawler quantity, and give an alarm according to the judgment result. It is also used to judge the population diffusion behavior according to the prediction result of the pest crawler diffusion situation, and give an alarm according to the judgment result.

[0021] Further, the quantity prediction module inputs the pest crawler information into the Leslie matrix model to predict the quantity of pest crawlers, and obtains the pest crawler quantity. The Leslie matrix model is constructed by the Leslie matrix model construction method, and the Leslie matrix model construction method includes:

[0022] Step A1: Divide the pest crawler biological age in the pest crawler information into n age stages, and fill the reproduction rate fi of the historical age i in the pest crawler information into the first row F of the Leslie matrix, and set the first row F of the Leslie matrix = [f1, f2, f3,... fn], i = 1, 2, 3,... n;

[0023] Step A2: Design a diagonal matrix p related to the survival rate according to the survival rate Pi from the historical age i to the age i + 1 in the pest crawler information, and set where P1 is the survival rate from age 1 to age 2, P2 is the survival rate from age 2 to age 3, Pn - 1 is the survival rate from age n - 2 to age n - 1, and the individuals at age n do not survive to the next age, that is, there is no Pn in the diagonal matrix related to the survival rate;

[0024] Step A3: Design a diagonal matrix M related to the migration rate according to the migration rate mi of the individuals at the historical age i in the observation period in the pest crawler information, and set where m1 is the migration rate of the individuals at age 1 in the observation period, m2 is the migration rate of the individuals at age 2 in the observation period, and mn is the migration rate of the individuals at age n in the unit time;

[0025] Step A4: Combine the first row F of the Leslie matrix in Step A1, the diagonal matrix p related to the survival rate in Step A2, and the diagonal matrix M related to the migration rate in Step A3 into a prediction matrix L, and set And the Leslie matrix model is constituted by the prediction matrix L.

[0026] Further, the prediction matrix calculates the predicted quantity \(N_{0t1}\) at time \(t1\) based on the initial quantity \(N0\) in the pest crawler information and the prediction matrix \(L\), calculates the predicted quantity \(N_{0t2}\) at time \(t2\) based on the predicted quantity \(N_{0t1}\) at time \(t1\) and the prediction matrix \(L\), and repeats the calculation until the predicted quantity \(N_{0tz}\) at time \(tz\) is obtained, where \(z = 1, 2,\cdots,v\), and \(v\) is the number of unit prediction times. Here, \(t1\) is one unit prediction time, \(t2\) is two unit prediction times, and \(tz\) is \(z\) unit prediction times input by the user.

[0027] Further, the quantity prediction module compares the current population density \(\rho\) in the pest crawler information with the preset population density \(\rho0\), where \(0.12\leqslant\rho0\leqslant0.38\), judges the intraspecific competition situation of the current pest crawlers according to the comparison result, and adjusts the prediction matrix according to the judgment result.

[0028] Further, the quantity prediction module calculates the environmental impact value \(D\) according to the environmental food quantity \(A\), environmental suitability \(B\) and the number of population natural enemies \(C\) in the pest crawler information, sets \(D = a\times A + b\times B+1 / C\), where \(a = 0.6\), \(b = 0.4\), compares the environmental impact value \(D\) with the preset environmental impact value \(D0\), where \(0.43\leqslant D0\leqslant0.52\), judges the environmental impact situation according to the comparison result, and corrects the judgment process of the intraspecific competition situation of the current pest crawlers according to the judgment result.

[0029] Further, the population diffusion prediction module uses the reaction-diffusion prediction model to predict the population diffusion trend of the pest crawlers, and obtains the population diffusion trend of the pest crawlers. The reaction-diffusion prediction model predicts the diffusion trend of the pest crawler population according to the partial differential equation of the population diffusion trend, where \(D\) is the diffusion coefficient, \(\nabla\) 2 \(u\) is the Laplace operator, \(r\) is the population growth rate, \(N_{0tz}\) is the predicted quantity corresponding to time \(tz\) predicted by the Leslie matrix model, and \(K\) is the environmental carrying capacity. The population diffusion prediction module inputs the population diffusion trend of the pest crawlers into the harmful crawler prediction behavior model and outputs the diffusion prediction behavior of the harmful crawlers.

[0030] Further, the population diffusion prediction module calculates the regional population natural enemy influence factor \(g\) according to the number of population natural enemies \(C\) and the reproduction speed \(H\) of the natural enemies in the region in the pest crawler information, compares the regional population natural enemy influence factor \(g\) with the preset regional population natural enemy influence factor \(g0\), where \(0.46\leqslant g0\leqslant0.69\), judges the influence of the natural enemies on the population diffusion of the harmful crawlers according to the comparison result, and revises the prediction result of the reaction-diffusion prediction model according to the judgment result.

[0031] Further, the population diffusion prediction module compares the human activity value Z in the pest crawler information with a preset human activity value Z0, where 0.62 ≤ Z0 ≤ 0.81. Based on the comparison result, the human activity situation is judged, and the judgment process of the influence of natural enemies on the population diffusion of harmful crawlers is calibrated according to the judgment result.

[0032] Further, the real-time monitoring and feedback module calculates the prediction deviation L1 by comparing the actual pest quantity Ns at time t2 in the biological crawler information with the predicted pest quantity N0t2 at time t2 by the Leslie matrix model. The prediction deviation L1 is compared with a preset deviation L01, where 0.26 ≤ L01 ≤ 0.38. Based on the comparison result, the performance of the Leslie matrix model is judged, and the Leslie matrix model is corrected according to the judgment result.

[0033] Compared with the prior art, the beneficial effects of the present invention are as follows. The system is applied to a disaster prediction device for pest crawlers. The system collects pest crawler information through a data acquisition module to predict the disaster of pest crawlers based on the pest crawler information. The system predicts the quantity of pest crawlers at a future time through a quantity prediction module, judges the intraspecific competition situation of pest crawlers based on the population density in the pest crawler information, and adjusts the prediction process of the quantity of pest crawlers at a future time according to the judgment result, improving the accuracy of the disaster prediction of pest crawlers. The system also judges the environmental impact situation based on the environmental impact value in the pest crawler information, and corrects the judgment process of the intraspecific competition situation of pest crawlers according to the judgment result, thereby improving the accuracy of the disaster prediction of pest crawlers. The system also predicts the diffusion prediction behavior of harmful crawlers through a population diffusion prediction module, judges the influence of population natural enemies based on the population natural enemy influence factor in the pest crawler information, and revises the prediction result of the diffusion prediction behavior of harmful crawlers according to the judgment result. It is also used to judge the influence of the human activity value in the pest crawler information on the quantity of pest crawlers and the number of population natural enemies, and calibrate the judgment process of the influence of population natural enemies according to the judgment result, greatly improving the prediction accuracy of the diffusion prediction behavior of harmful crawlers and enhancing the accuracy of the disaster prediction of pest crawlers, so as to issue an alarm according to the disaster prediction of pest crawlers subsequently. The system also corrects the prediction result of the quantity prediction module through a real-time monitoring and feedback module, improving the accuracy of the disaster prediction of pest crawlers by the quantity prediction module. The system issues an alarm for the disaster prediction of pest crawlers through an alarm module. The entire system improves the accuracy of the disaster prediction of pest crawlers while ensuring the normal operation of the early warning system, achieving the effect of accurately predicting the disaster of pest crawlers. Description of the Drawings

[0034] Figure 1 It is a schematic structural diagram of the disaster prediction device for pest crawlers in this embodiment;

[0035] Figure 2 It is a schematic structural diagram of the disaster prediction system for pest crawlers in this embodiment. Detailed Embodiments

[0036] In order to make the objectives and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0037] The preferred embodiments of the present invention will be described below with reference to the drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0038] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0039] In addition, it should also be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installation", "connection", "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0040] Please refer to Figure 1 shown, which is a schematic structural diagram of the disaster prediction device for pest crawlers in this embodiment. The device includes:

[0041] A camera 1, connected to a camera support rod 2, a power supply 6, and an MCU processor 4, for acquiring environmental information;

[0042] A camera support rod 2, connected to the camera 1, the power supply 6, the device housing 3, and the MUC processor 4, for supporting the camera 1 to rotate 360°;

[0043] A device housing 3, for protecting the camera support rod 3, the power supply 6, and the MCU processor 4;

[0044] A temperature sensor (not shown in the figure), connected to the device housing 3, for monitoring the ambient temperature;

[0045] A humidity sensor (not shown in the figure), connected to the device housing 3, for monitoring the ambient humidity;

[0046] An MCU processor 4, connected to the camera 1, the camera support rod 2, the speaker 5, and the power supply 6, for processing the information collected by the camera 1, the temperature sensor, and the humidity sensor;

[0047] A disaster prediction system for harmful pest crawlers (not shown in the figure), provided in the MCU processor, for warning of disasters caused by harmful pest crawlers;

[0048] The speaker 5, connected to the MCU processor 4 and the power supply 6, for emitting an alarm sound;

[0049] The power supply 6, connected to the camera 1, the camera support rod 2, the MCU processor 4, and the speaker 5, for providing power.

[0050] Specifically, this device is applied to outdoor mountainous areas for disaster warning of harmful pest crawlers. This device collects harmful pest crawler information through the camera 1, the temperature sensor, and the humidity sensor. And the disaster prediction system for harmful pest crawlers in the MCU processor processes and predicts the harmful pest crawler information, and warns of disasters caused by harmful pest crawlers according to the prediction results, achieving the effect of early warning of disasters caused by harmful pest crawlers, enabling users to prevent disasters caused by harmful pest crawlers in advance.

[0051] Please refer to Figure 2 As shown, it is a schematic structural diagram of the disaster prediction system for harmful pest crawlers in this embodiment. The system includes:

[0052] A data acquisition module, for collecting harmful pest crawler information;

[0053] A quantity prediction module, for constructing a Leslie matrix model according to the harmful pest crawler information, predicting the quantity of harmful pest crawlers through the Leslie matrix model to obtain the quantity of harmful pest crawlers, and also for judging the intraspecific competition situation of harmful pest crawlers according to the population density in the harmful pest crawler information and adjusting the Leslie matrix model according to the judgment result, and also for judging the environmental impact situation according to the environmental impact value in the harmful pest crawler information and correcting the judgment process of the intraspecific competition situation of harmful pest crawlers according to the judgment result. The quantity prediction module is connected to the data acquisition module;

[0054] A real-time monitoring and feedback module is used to judge the performance of the Leslie matrix model according to the actual pest quantity and the pest crawler quantity in the pest crawler information, and to correct the Leslie matrix model according to the judgment result. The real-time monitoring and feedback module is respectively connected to the quantity prediction module and the data acquisition module;

[0055] A population diffusion prediction module is used to predict the diffusion prediction behavior of harmful crawlers according to the pest crawler quantity, and is also used to judge the influence of population natural enemies according to the population natural enemy influence factor in the pest crawler information, and to revise the prediction result of the diffusion prediction behavior of harmful crawlers according to the judgment result. It is also used to judge the influence of the human activity value in the pest crawler information on the pest crawler quantity and the population natural enemy quantity, and to calibrate the judgment process of the influence of population natural enemies according to the judgment result. The population diffusion prediction module is connected to the quantity prediction module;

[0056] An alarm module is used to judge the quantity suitability according to the pest crawler quantity and to give an alarm according to the judgment result. It is also used to judge the population diffusion behavior situation according to the prediction result of the diffusion situation of the pest crawlers and to give an alarm according to the judgment result. The alarm module is connected to the population diffusion prediction module.

[0057] Specifically, the system is applied to a disaster prediction device for pest crawlers. The system collects pest crawler information through a data collection module to predict the disasters of pest crawlers based on the pest crawler information. The system predicts the number of pest crawlers in the future time through a quantity prediction module, judges the intraspecific competition situation of pest crawlers according to the population density in the pest crawler information, and adjusts the prediction process of the number of pest crawlers in the future time according to the judgment result to improve the accuracy of disaster prediction of pest crawlers. The system also judges the environmental impact situation according to the environmental impact value in the pest crawler information, and corrects the judgment process of the intraspecific competition situation of pest crawlers according to the judgment result, thereby improving the accuracy of disaster prediction of pest crawlers. The system also predicts the diffusion prediction behavior of harmful crawlers through a population diffusion prediction module, judges the influence situation of population natural enemies according to the population natural enemy influence factor in the pest crawler information, and revises the prediction result of the diffusion prediction behavior of harmful crawlers according to the judgment result. It is also used to judge the influence situation of the number of pest crawlers and the number of population natural enemies according to the human activity value in the pest crawler information, and calibrate the judgment process of the influence situation of population natural enemies according to the judgment result, greatly improving the prediction accuracy of the diffusion prediction behavior of harmful crawlers and enhancing the accuracy of disaster prediction of pest crawlers, so as to alarm according to the disaster prediction of pest crawlers subsequently. The system also corrects the prediction result of the quantity prediction module through a real-time monitoring feedback module to improve the accuracy of the quantity prediction module in predicting the disasters of pest crawlers. The system alarms the disaster prediction of pest crawlers through an alarm module. The entire system improves the accuracy of disaster prediction of pest crawlers while ensuring the normal operation of the early warning system, achieving the effect of accurately predicting the disasters of pest crawlers.

[0058] Specifically, the data acquisition module is used to collect pest information, where the pest information includes the age of harmful crawling pests, the reproduction rate at historical age i, the survival rate from historical age i to age i + 1, the migration rate of individuals at historical age i within the observation period, the initial quantity, the current population density, the environmental food quantity, the environmental suitability, the number of population natural enemies, the human activity value, and the actual pest quantity at time t2. The data acquisition module collects the age of harmful crawling pests, the initial quantity, the environmental food quantity, the current population density, the human activity value, the number of population natural enemies, and the actual pest quantity at time t2 through a camera. The data acquisition module inputs the reproduction rate at historical age i, the survival rate from historical age i to age i + 1, and the migration rate of individuals at historical age i within the observation period into the data acquisition module manually. The data acquisition module collects the environmental temperature through a temperature sensor and the environmental humidity through a humidity sensor. The data acquisition module calculates the environmental suitability B based on the collected environmental temperature Q and the collected environmental humidity P, and sets B = (Q / 100) + (P / 100).

[0059] Specifically, the quantity prediction module inputs the pest crawling information into the Leslie matrix model to predict the quantity of pest crawlers, and obtains the quantity of pest crawlers. The Leslie matrix model is constructed through the Leslie matrix model construction method, and the Leslie matrix model construction method includes:

[0060] Step A1: Divide the age of harmful crawling pests in the pest crawling information into n age stages, and fill the reproduction rate fi at historical age i in the pest crawling information into the first row F of the Leslie matrix, and set the first row F of the Leslie matrix = [f1, f2, f3,... fn], where i = 1, 2, 3,... n;

[0061] Step A2: Design a diagonal matrix p related to the survival rate according to the survival rate Pi from historical age i to age i + 1 in the pest crawling information, and set where P1 refers to the survival rate from age 1 to age 2, P2 refers to the survival rate from age 2 to age 3, Pn - 1 refers to the survival rate from age n - 2 to age n - 1, and individuals at age n do not survive to the next age, that is, Pn does not exist in the diagonal matrix related to the survival rate;

[0062] Step A3: Design a diagonal matrix M related to the migration rate according to the migration rate mi of individuals at historical age i within the observation period in the pest crawling information, and set Among them, m1 refers to the migration rate of individuals of age 1 within the observation period, m2 refers to the migration rate of individuals of age 2 within the observation period, and mn refers to the migration rate of individuals of age n per unit time;

[0063] Step A4: Combine the first row F of the Leslie matrix in Step A1, the diagonal matrix p related to the survival rate in Step A2, and the diagonal matrix M related to the migration rate in Step A3 to form a prediction matrix L, and set And form a Leslie matrix model from the said prediction matrix L.

[0064] Specifically, the reproduction rate of the historical age i refers to the reproduction efficiency of the pest crawlers of this population at the age i stage in the historical data. The survival rate from the historical age i to age i + 1 refers to the proportion of the number of pest crawlers that survived from age i to age i + 1 to the original number of pest crawlers in this population of pest crawlers in the historical data. The migration rate of individuals of the historical age i within the observation period refers to the proportion of pest crawlers at the age i stage that migrated out of the monitoring area during the observation period. In this embodiment, the specific value of the observation period is not limited, and those skilled in the art can set it according to actual needs, as long as it meets the calculation requirements for the migration rate of individuals of the historical age i within the observation period. For example, the observation period can be set to 5 days.

[0065] Specifically, by constructing a Leslie matrix model, this system can predict the number of pest crawlers in the monitoring area, and enable this system to give an early warning according to the predicted number of pest crawlers, achieving the effect of preventing disasters caused by pest crawlers in advance.

[0066] Specifically, the prediction matrix calculates the predicted quantity N0t1 at time t1 according to the initial quantity N0 in the pest crawler information and the prediction matrix L, and sets N0t1 = L × NO. According to the predicted quantity N0t1 at time t1 and the prediction matrix L, calculate the predicted quantity N0t2 at time t2, and set NOt2 = L × N0t1. Repeat the calculation until the predicted quantity NOtz at time tz is obtained, where z = 1, 2,... v, and v is the number of unit prediction times. Among them, t1 is one unit prediction time, t2 is two unit prediction times, and tz is z unit prediction times input by the user.

[0067] Specifically, the initial quantity refers to the number of pest crawlers in the monitoring area when predicting the number of pest crawlers. The unit prediction time refers to the time for prediction with a period of a certain time. In this embodiment, the specific value of the unit prediction time is not limited, and those skilled in the art can set it according to actual needs, as long as it meets the prediction requirements for the number of pest crawlers. For example, the unit prediction time can be set to 7 days.

[0068] Specifically, the quantity prediction module compares the current population density ρ in the pest crawler information with a preset population density ρ0, where 0.12 ≤ ρ0 ≤ 0.38. It determines the intraspecific competition situation of the current pest crawlers based on the comparison result and adjusts the prediction matrix according to the determination result, where:

[0069] When ρ ≤ ρ0, the quantity prediction module determines that the intraspecific competition situation of the current pest crawlers is non-competition and does not adjust the prediction matrix;

[0070] When ρ > ρ0, the quantity prediction module determines that the intraspecific competition situation of the current pest crawlers is competition and adjusts the prediction matrix. The adjustment method is to adjust the reproduction rate fi at historical age i, the migration rate mi of individuals at historical age i within the observation period, and the survival rate Pi from historical age i to age i + 1 according to the reproduction rate influence coefficient α, the survival rate influence coefficient β, and the migration rate influence coefficient γ to obtain the adjusted reproduction rate fi`, the adjusted survival rate Pi`, and the adjusted migration rate mi`. It is set that fi` = fi × (1 - α × ρ0), Pi` = Pi × (1 - β × ρ0), mi` = mi + γ × ρ0; 0.7 ≤ α ≤ 0.9, 0.62 ≤ β ≤ 0.88, 1.1 ≤ γ ≤ 1.4, and the prediction matrix is reconstructed according to the adjusted reproduction rate fi`, the adjusted survival rate Pi`, and the adjusted migration rate mi` to obtain the adjusted Leslie matrix model.

[0071] Specifically, the current population density refers to the population density of pest crawlers monitored in real time in the monitoring area within the area. The preset population density refers to a preset value used to determine the intraspecific competition situation of the current pest crawlers. The intraspecific competition situation of the current pest crawlers refers to whether there will be competition within the species of pest crawlers under the current population density. The intraspecific competition situation of the current pest crawlers includes competition and non-competition.

[0072] Specifically, by comparing the current population density with the preset population density, the intraspecific competition situation of the current pest crawlers can be obtained, and the prediction matrix can be adjusted according to the intraspecific competition situation of the current pest crawlers, which can improve the prediction accuracy of the Leslie matrix model, enable the system to predict the quantity of pest crawlers more accurately, and achieve the effect of accurate alarm.

[0073] Specifically, the quantity prediction module calculates the environmental impact value D based on the environmental food quantity A, environmental suitability B, and the number of natural enemies C of the population in the area in the pest crawler information, and sets D = a×A + b×B + 1 / C, where a = 0.6 and b = 0.4. The environmental impact value D is compared with the preset environmental impact value D0, where 0.43 ≤ D0 ≤ 0.52. The environmental impact situation is judged based on the comparison result, and the judgment process of the intraspecific competition situation of the current pest crawler is corrected according to the judgment result, where:

[0074] When D ≤ D0, the quantity prediction module determines that the environmental impact situation has no impact and does not correct the judgment process of the intraspecific competition situation of the current pest crawler;

[0075] When D > D0, the quantity prediction module determines that the environmental impact situation has an impact and corrects the judgment process of the intraspecific competition situation of the current pest crawler. The correction coefficient Y = 0.7 + 0.3e -(D-D0) is used to correct the preset population density ρ0, where e is the base of the natural logarithm, to obtain the corrected preset population density ρ0`. Set ρ0` = Y×ρ0, and compare the population density ρ with the corrected preset population density ρ0` again. The intraspecific competition situation of the current pest crawler is judged based on the comparison result, and the prediction matrix is adjusted according to the judgment result.

[0076] Specifically, the environmental food quantity refers to the quantity of food that the pest crawler can eat in the monitored environment. The maximum value of the environmental food quantity is 1, and the closer it is to 1, the more abundant the food is. The environmental suitability refers to the degree of suitability of the environment in the monitored environment for the pest crawler. The maximum value of the environmental suitability is 1, and the closer it is to 1, the more suitable the environment is for the growth of the pest crawler. The preset environmental impact value refers to the preset value used to judge the environmental impact situation. The environmental impact situation refers to the impact of environmental factors in the monitored area on the number of pest crawlers. The environmental impact situation includes the environmental impact situation of no impact and the environmental impact situation of having an impact.

[0077] Specifically, by calculating the environmental impact value and comparing it with the preset environmental impact value, the impact of environmental factors in the monitored area on the number of pest crawlers can be obtained, and the judgment process of the intraspecific competition situation of the current pest crawler can be corrected according to the impact situation, making the quantity prediction module more accurate in judging the intraspecific competition situation of the current pest crawler, and thus making the entire system more accurate in predicting the number of pest crawlers.

[0078] Specifically, the population diffusion prediction module uses a reaction-diffusion prediction model to predict the population diffusion trend of harmful pest crawlers, obtaining the population diffusion trend of harmful pest crawlers. The reaction-diffusion prediction model is based on the partial differential equation of population diffusion trend to predict the diffusion trend of the harmful pest crawler population. Among them, D is the diffusion coefficient, and ▽ 2 u is the Laplace operator, r is the population growth rate, N0tz is the predicted quantity corresponding to the tz moment predicted by the Leslie matrix model, and K is the environmental carrying capacity.

[0079] Specifically, the population diffusion trend of the harmful pest crawlers refers to the diffusion development trend of the harmful pest crawler population. The reaction-diffusion prediction model refers to a mathematical model used to describe the change of population density over time and space. The Laplace operator refers to the second-order spatial derivative of the population density, which reflects the change rate of the density in space. In this embodiment, the specific value of the Laplace operator is not limited, and those skilled in the art can calculate it according to the actual situation, as long as it satisfies the construction of the partial differential equation of the population diffusion trend. For example, the Laplace operator can be calculated according to the population density q(x, y) in the two-dimensional space. Set x as the abscissa of the two-dimensional space, y as the ordinate of the two-dimensional space. The diffusion coefficient refers to the diffusion influence coefficient used to describe the partial differential equation of the population diffusion trend. In this embodiment, the specific value of the diffusion coefficient is not limited, and those skilled in the art can set it according to the actual situation, as long as it satisfies the construction of the partial differential equation of the population diffusion trend. For example, the specific value of the diffusion coefficient can be set according to the geographical environment of the monitoring area. The population growth rate refers to the population growth rate of the harmful pest crawlers. In this embodiment, the specific value of the population growth rate is not limited, and those skilled in the art can set it according to the actual situation, as long as it satisfies the construction of the partial differential equation of the population diffusion trend. For example, the specific value of the population growth rate can be set according to the type of harmful pest crawlers and the geographical environment. The environmental carrying capacity refers to the maximum density that the harmful pest crawler population can reach under the monitoring environmental conditions. In this embodiment, the specific value of the environmental carrying capacity is not limited, and those skilled in the art can set it according to the actual situation, as long as it satisfies the construction of the partial differential equation of the population diffusion trend. For example, the specific value of the environmental carrying capacity can be set according to the type of harmful pest crawlers and the geographical environment.

[0080] Specifically, predicting the population diffusion trend of harmful pest crawlers through the reaction-diffusion prediction model can obtain the population diffusion trend of harmful pest crawlers, providing a data basis for the next prediction of the diffusion prediction behavior of harmful crawlers, enabling the population diffusion prediction module to accurately predict the diffusion prediction behavior of harmful crawlers.

[0081] Specifically, the population diffusion prediction module inputs the harmful pest crawler population diffusion trend into the harmful crawler prediction behavior model and outputs the diffusion prediction behavior of the harmful crawlers.

[0082] Specifically, the harmful crawler prediction behavior model refers to a neural network learning model that takes the harmful pest crawler population diffusion trend as the input and the diffusion prediction behavior of the harmful crawlers as the output. The harmful crawler prediction behavior model is constructed by the harmful crawler prediction behavior model construction method. The harmful crawler prediction behavior model construction method includes:

[0083] Dividing 70% of the historical harmful crawler behavior data set into a data recognition training set, 15% of the historical harmful crawler behavior data set into a data recognition verification set, and 15% of the historical harmful crawler behavior data set into a data recognition test set. Training the convolutional neural network model according to the data recognition training set, updating the weights of the convolutional neural network model through the backpropagation algorithm, and after each epoch, using the data recognition verification set to verify the convolutional neural network model to obtain the recognition verification loss value and the recognition verification accuracy rate. When the verification loss value and the verification accuracy rate meet the preset verification conditions, testing the convolutional neural network model according to the data recognition test set to obtain the recognition test accuracy rate, and when the recognition test accuracy rate reaches the preset accuracy rate, outputting the convolutional neural network model as the harmful crawler prediction behavior model;

[0084] Among them, the historical harmful crawler behavior data set refers to a learning data set stored in the form of historical harmful pest crawler population diffusion trend - historical harmful crawler diffusion behavior for training the convolutional neural network model. The epoch refers to the process of the convolutional neural network model completing one forward propagation and one backpropagation on the data recognition training set. The verification loss value refers to the loss value of the loss function in the convolutional neural network model when the data recognition verification set is input into the convolutional neural network model for verification. The verification accuracy rate refers to the ratio of the number of historical harmful crawler diffusion behaviors that are consistent with the historical harmful crawler diffusion behaviors in the data recognition verification set to the total number of samples in the data recognition verification set after the data recognition verification set is input into the convolutional neural network model. The preset verification condition refers to that the verification loss value does not decrease for 7 consecutive epochs and the verification accuracy rate does not increase. The recognition test accuracy rate refers to the ratio of the number of data test results that are consistent with the historical harmful crawler diffusion behaviors in the data recognition test set to the total number of samples in the data recognition test set after the data recognition test set is input into the convolutional neural network model. The preset accuracy rate refers to the preset value of the recognition test accuracy rate for judging that the convolutional neural network model reaches the output standard, such as the preset accuracy rate can be set to 95%. The diffusion behavior of the harmful crawlers refers to the behavior when the harmful pest crawler population diffuses.

[0085] Specifically, the population diffusion prediction module calculates the influence factor g of natural enemies in the area on the population according to the number C of natural enemies of the population in the area of the pest crawler information and the reproduction rate H of natural enemies in the area, sets g = ω×C + λ×H, where ω = 0.7 and λ = 0.3, compares the influence factor g of natural enemies in the area with the preset influence factor g0 of natural enemies, 0.46 ≤ g0 ≤ 0.69, judges the influence of natural enemies on the population diffusion of harmful crawlers according to the comparison result, and revises the prediction result of the reaction-diffusion prediction model according to the judgment result, where:

[0086] When g < g0, the population diffusion prediction module determines that the influence of natural enemies on the population diffusion of harmful crawlers is not significant and does not revise the prediction result of the reaction-diffusion prediction model;

[0087] When g ≥ g0, the population diffusion prediction module determines that the influence of natural enemies on the population diffusion of harmful crawlers is significant and revises the prediction result of the reaction-diffusion prediction model. The partial differential equation of the population diffusion situation is revised through the revision coefficient W = r×NOtz×g×C / K to obtain the revised partial differential equation of the population diffusion situation Set and use the revised partial differential equation of the population diffusion situation to replace the population diffusion trend of the pest crawler, obtain the revised population diffusion trend of the pest crawler, and input the revised population diffusion trend of the pest crawler into the harmful crawler prediction behavior model to obtain the revised diffusion prediction behavior of the harmful crawler.

[0088] Specifically, the number of natural enemies of the population in the area refers to the number of natural enemies corresponding to the pest crawler within the monitoring range of the disaster prediction device of the pest crawler. The reproduction rate of natural enemies in the area refers to the reproduction rate of natural enemies corresponding to the pest crawler within the monitoring range of the disaster prediction device. The preset influence factor of natural enemies of the population is a preset value used to judge the influence of natural enemies on the population diffusion of harmful crawlers. The influence of natural enemies on the population diffusion of harmful crawlers refers to the influence of the presence of natural enemies of harmful crawlers on the population diffusion of harmful crawlers. The influence of natural enemies on the population diffusion of harmful crawlers includes that the influence of natural enemies on the population diffusion of harmful crawlers is significant and the influence of natural enemies on the population diffusion of harmful crawlers is not significant.

[0089] Specifically, by calculating the influencing factors of natural enemies of the population within the region and comparing the influencing factors of natural enemies of the population within the region with the preset influencing factors of natural enemies of the population, the influence of natural enemies on the spread of harmful crawler populations can be obtained, and the prediction results of the reaction-diffusion prediction model can be revised according to the influence situation, so that the predicted spread trend of harmful pest crawler populations by the reaction-diffusion prediction model is more accurate, thereby improving the accuracy of the spread prediction behavior of harmful crawlers output by the harmful crawler prediction behavior model.

[0090] Specifically, the population spread prediction module compares the human activity value Z in the harmful pest crawler information with the preset human activity value Z0, where 0.62 ≤ Z0 ≤ 0.81. According to the comparison result, the human activity situation is judged, and the judgment process of the influence of natural enemies on the spread of harmful crawler populations is calibrated according to the judgment result, where:

[0091] When Z < Z0, the population spread prediction module determines that the human activity situation is that human activities are not frequent, and does not calibrate the judgment process of the influence of natural enemies on the spread of harmful crawler populations;

[0092] When Z ≥ Z0, the population spread prediction module determines that the human activity situation is that human activities are frequent, and calibrates the judgment process of the influence of natural enemies on the spread of harmful crawler populations. Through the calibration factor ∈ = 0.52 + 0.48e -(Z-Z0) calibrates the preset influencing factor of natural enemies g0, where e is the base of the natural logarithm, to obtain the calibrated preset influencing factor of natural enemies g0z. Set g0z = ∈ × g0, and compare the influencing factor of natural enemies g within the region with the calibrated preset influencing factor of natural enemies g0z again, and judge the influence of natural enemies on the spread of harmful crawler populations according to the comparison result, and revise the prediction result of the reaction-diffusion prediction model according to the judgment result.

[0093] Specifically, the human activity value refers to the number of times humans appear within the monitoring region per unit time. In this embodiment, the specific value of the unit time is not limited, and those skilled in the art can set it according to their needs as long as the calculation of the human activity value is satisfied. For example, the unit time can be set according to the distance between the monitoring region and the human activity region. The preset human activity value refers to the preset value used to judge the human activity situation. The human activity situation refers to the frequency of human activities in the monitoring region, which can affect the survival situation of organisms within the region. The human activity situation includes frequent human activities and infrequent human activities.

[0094] Specifically, by comparing the human activity value Z with the preset human activity value Z0, the frequency of human activities in the area can be judged. When human activities are frequent, it will affect the number of natural enemies in the area, thus affecting the judgment process of the impact of natural enemies on the spread of harmful crawler populations. By calibrating the judgment process of the impact of natural enemies on the spread of harmful crawler populations, the spread prediction behavior of harmful crawlers can be obtained more accurately through the population spread prediction module.

[0095] Specifically, the real-time monitoring and feedback module calculates the prediction deviation L1 based on the actual number of harmful organisms Ns at time t2 in the biological crawler information and the predicted number of harmful organisms N0t2 at time t2 by the Leslie matrix model, and sets L1 = |Ns - N0t2| / Ns. Then, the prediction deviation L1 is compared with the preset deviation L01, where 0.26 ≤ L01 ≤ 0.38. According to the comparison result, the performance of the Leslie matrix model is judged, and the Leslie matrix model is corrected based on the judgment result, where:

[0096] When L1 ≤ L01, the real-time monitoring and feedback module determines that the performance of the Leslie matrix model is qualified and does not correct the Leslie matrix model;

[0097] When L1 > L01, the real-time monitoring and feedback module determines that the performance of the Leslie matrix model is unqualified and corrects the Leslie matrix model. The correction scheme is to replace the predicted number at time t2 in the prediction matrix with the actual number of harmful organisms at time t2, and recalculate the predicted number at time tz to obtain the corrected predicted number at time tz.

[0098] Specifically, the actual number of harmful organisms at time t2 refers to all the actual harmful organisms in the monitored area at time t2 monitored in real time. The preset deviation refers to the preset value used to judge the performance of the Leslie matrix model. The performance of the Leslie matrix model refers to whether the predicted value of the Leslie matrix model fits the actual value. The performance of the Leslie matrix model includes that the performance of the Leslie matrix model is qualified and the performance of the Leslie matrix model is unqualified.

[0099] Specifically, the real-time monitoring and feedback module calculates the prediction deviation, compares the prediction deviation with the preset deviation, judges the performance of the Leslie matrix model according to the comparison result, and corrects the Leslie matrix model according to the judgment result, further ensuring the prediction accuracy of the Leslie matrix model, improving the prediction accuracy of harmful biological crawler disasters, predicting disasters in advance, and facilitating users to take measures in advance for the predicted disasters.

[0100] Specifically, the alarm module compares the predicted quantity NOtz at time tz with the preset quantity Ny0, where 27 ≤ Ny0 ≤ 39. It determines the suitability of the quantity based on the comparison result and triggers an alarm according to the determination result, where:

[0101] When NOtz ≤ Ny0, the alarm module determines that the quantity suitability is appropriate and does not trigger an alarm;

[0102] When NOtz > Ny0, the alarm module determines that the quantity suitability is inappropriate and triggers an alarm.

[0103] Specifically, the preset quantity refers to the preset value used to determine the quantity suitability. The quantity suitability refers to whether the pest quantity at time tz will cause a disaster. The quantity suitability includes appropriate quantity suitability and inappropriate quantity suitability.

[0104] Specifically, by comparing the predicted quantity corresponding to time tz with the preset quantity, it can timely predict whether the pest quantity will cause a disaster at the future time tz and give an alarm, reminding the staff to prevent the disaster in advance before the disaster occurs.

[0105] Specifically, the alarm module compares the predicted diffusion behavior of harmful crawlers with the preset population diffusion behavior, determines the future diffusion behavior situation of the population based on the comparison result, and triggers an alarm according to the determination result, where:

[0106] When the predicted diffusion behavior of the harmful crawlers is consistent with the preset population diffusion behavior, the alarm module determines that the future diffusion behavior situation of the population is normal and does not trigger an alarm;

[0107] When the predicted diffusion behavior of the harmful crawlers is inconsistent with the preset population diffusion behavior, the future diffusion behavior situation of the population is abnormal and an alarm is triggered.

[0108] Specifically, the preset population diffusion behavior refers to the preset diffusion behavior used to determine the future diffusion behavior situation of the population. In this embodiment, the specific behavior of the preset population diffusion behavior is not limited, and those skilled in the art can set it by themselves as long as it meets the judgment requirements for the future diffusion behavior situation of the population. For example, it can be set according to the types of harmful pest crawlers. The future diffusion behavior situation of the population refers to whether the future diffusion behavior of the population will cause a disaster. The disasters include crop yield reduction and ecological environment damage. The future diffusion behavior situation of the population includes normal and abnormal.

[0109] Specifically, by comparing the diffusion prediction behavior of harmful crawlers with the preset population diffusion behavior, it is possible to timely predict whether the harmful pest crawlers will cause a disaster and give an alarm, and remind the staff to prevent the disaster in advance before the disaster occurs.

[0110] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A disaster prediction device for pest crawlers, characterized in that, Including: A camera, connected to a camera support rod, a power supply, and an MCU processor, for acquiring environmental information; A camera support rod, connected to the camera, the power supply, the device housing, and the MUC processor, for supporting the 360° rotation of the camera; The device housing, for protecting the camera support rod, the power supply, and the MCU processor; A temperature sensor, connected to the device housing, for monitoring the environmental temperature; A humidity sensor, connected to the device housing, for monitoring the environmental temperature; The MCU processor, connected to the camera, the camera support rod, a speaker, and the power supply, for processing the information collected by the camera, the temperature sensor, and the humidity sensor; A disaster prediction system for pest crawlers, provided in the MCU processor, for warning of pest crawler disasters; A speaker, connected to the MCU processor and the power supply, for emitting an alarm sound; The power supply, connected to the camera, the camera support rod, the MCU processor, and the speaker, for providing power.

2. The pest crawler disaster prediction system according to claim 1, wherein, The disaster prediction system for pest crawlers includes: A data collection module, for collecting pest crawler information; A quantity prediction module, for constructing a Leslie matrix model according to the pest crawler information, predicting the quantity of pest crawlers through the Leslie matrix model to obtain the quantity of pest crawlers, for judging the intraspecific competition situation of pest crawlers according to the population density in the pest crawler information, and adjusting the Leslie matrix model according to the judgment result, for judging the environmental impact situation according to the environmental impact value in the pest crawler information, and correcting the judgment process of the intraspecific competition situation of pest crawlers according to the judgment result; A population diffusion prediction module, for predicting the diffusion prediction behavior of harmful crawlers according to the quantity of pest crawlers, for judging the population natural enemy influence situation according to the population natural enemy influence factor in the pest crawler information, and revising the prediction result of the diffusion prediction behavior of harmful crawlers according to the judgment result, for judging the influence situation of the quantity of pest crawlers and the number of population natural enemies according to the human activity value in the pest crawler information, and calibrating the judgment process of the population natural enemy influence situation according to the judgment result; A real-time monitoring and feedback module, for judging the performance of the Leslie matrix model according to the actual pest quantity and the pest crawler quantity in the pest crawler information, and correcting the Leslie matrix model according to the judgment result; An alarm module, for judging the quantity suitability according to the quantity of pest crawlers and giving an alarm according to the judgment result, for judging the population diffusion behavior situation according to the prediction result of the diffusion situation of pest crawlers, and giving an alarm according to the judgment result.

3. The pest crawler disaster prediction system according to claim 2, characterized in that, The quantity prediction module inputs the pest crawler information into the Leslie matrix model to predict the quantity of pest crawlers, and obtains the quantity of pest crawlers. The Leslie matrix model is constructed by a Leslie matrix model construction method. The Leslie matrix model construction method includes: Step A1: Divide the age of harmful crawling pests in the harmful pest crawling information into n age stages, and fill the reproduction rate fi of historical age i in the harmful pest crawling information into the first row F of the Leslie matrix. Set the first row F of the Leslie matrix as F = [f1, f2, f3,... fn], where i = 1, 2, 3,... n; Step A2: Design a diagonal matrix p related to survival rate according to the survival rate Pi from historical age i to age i+1 in the pest crawler information, and set where P1 refers to the survival rate from age 1 to age 2, P2 refers to the survival rate from age 2 to age 3, Pn-1 refers to the survival rate from age n-2 to age n-1, and individuals at age n do not survive to the next age, that is, Pn does not exist in the diagonal matrix related to the survival rate; Step A3, design a diagonal matrix M related to the migration rate according to the migration rate mi of individuals with historical age i in the pest crawler information, and set where m1 refers to the migration rate of individuals of age 1 within the observation period, m2 refers to the migration rate of individuals of age 2 within the observation period, and mn refers to the migration rate of individuals of age n per unit time; Step A4, combine the first row F of the Leslie matrix in Step A1, the diagonal matrix p related to the survival rate in Step A2, and the diagonal matrix M related to the migration rate in Step A3 to form a prediction matrix L, and set and construct a Leslie matrix model from the prediction matrix L.

4. The pest crawler disaster prediction system according to claim 3, wherein The prediction matrix calculates the predicted quantity N0t1 at time t1 based on the initial quantity N0 in the harmful pest crawling information and the prediction matrix L, calculates the predicted quantity N0t2 at time t2 based on the predicted quantity N0t1 at time t1 and the prediction matrix L, and repeats the calculation until the predicted quantity NOtz at time tz is obtained, where z = 1, 2,... v, and v is the number of unit prediction times. Among them, t1 is one unit prediction time, t2 is two unit prediction times, and tz is z unit prediction times input by the user.

5. The disaster prediction system for pest crawlers according to claim 4, characterized in that, The quantity prediction module compares the current population density ρ in the harmful pest crawling information with the preset population density ρ0, where 0.12 ≤ ρ0 ≤ 0.38, judges the intraspecific competition situation of the current harmful pests according to the comparison result, and adjusts the prediction matrix according to the judgment result.

6. The pest crawler disaster prediction system according to claim 5, characterized in that, The quantity prediction module calculates the environmental impact value D according to the environmental food quantity A, environmental suitability B, and the number of population natural enemies C in the harmful pest crawling information. Set D = a × A + b × B + 1 / C, where a = 0.6 and b = 0.

4. Compare the environmental impact value D with the preset environmental impact value D0, where 0.43 ≤ D0 ≤ 0.52, judge the environmental impact situation according to the comparison result, and correct the judgment process of the intraspecific competition situation of the current harmful pests according to the judgment result.

7. The pest crawler disaster prediction system according to claim 6, characterized in that, The population diffusion prediction module uses a reaction-diffusion prediction model to predict the population diffusion trend of pest crawlers, obtaining the population diffusion trend of pest crawlers. The reaction-diffusion prediction model is based on the partial differential equation of population diffusion trend to predict the diffusion trend of the population of pest crawlers. Among them, D is the diffusion coefficient, is the Laplace operator, r is the population growth rate, N0tz is the L es l predicted quantity corresponding to the tz moment predicted by the ie matrix model, and K is the environmental carrying capacity. The population diffusion prediction module inputs the population diffusion trend of the pest crawlers into the harmful crawler prediction behavior model and outputs the diffusion prediction behavior of the harmful crawlers.

8. The pest crawler disaster prediction system according to claim 7, characterized in that, The population diffusion prediction module calculates the regional population natural enemy influence factor g according to the number of population natural enemies C in the harmful pest crawling information and the reproduction speed H of the natural enemies in the region. Compare the regional population natural enemy influence factor g with the preset regional population natural enemy influence factor g0, where 0.46 ≤ g0 ≤ 0.69, judge the influence of natural enemies on the population diffusion of harmful crawling pests according to the comparison result, and revise the prediction result of the reaction-diffusion prediction model according to the judgment result.

9. The pest crawler disaster prediction system according to claim 8, characterized in that, The population diffusion prediction module compares the human activity value Z in the harmful pest crawling information with the preset human activity value Z0, where 0.62 ≤ Z0 ≤ 0.81, judges the human activity situation according to the comparison result, and calibrates the judgment process of the influence of natural enemies on the population diffusion of harmful crawling pests according to the judgment result.

10. The pest crawler disaster prediction system according to claim 9, characterized in that, The real-time monitoring and feedback module calculates the prediction deviation L1 according to the actual harmful pest quantity Ns at time t2 in the biological crawling information and the predicted harmful pest quantity N0t2 at time t2 by the Leslie matrix model. Compare the prediction deviation L1 with the preset deviation L01, where 0.26 ≤ L01 ≤ 0.38, judge the performance of the Leslie matrix model according to the comparison result, and correct the Leslie matrix model according to the judgment result.

Images