Green prevention and control system and method for plant diseases and insect pests in corn tasseling period based on environmental self-adaption

Abstract

The invention relates to the technical field of intelligent agriculture and green plant protection, and discloses a corn tasseling period pest and disease damage green prevention and control system and method based on environment self-adaption, and the system comprises a prevention and control system which comprises an environment simulation unit, a pest and disease damage simulation database, a prediction analysis module, an early warning decision module and an acquisition unit. According to the method, a nonlinear mapping model of five-dimensional environment vectors (temperature, humidity, illumination intensity, rainfall and wind speed) and pest and disease damage activities is constructed, multiple regression analysis and Monte Carlo simulation are combined, pest and disease damage occurrence probability distribution under different climate scenes is generated, the limitation of a single threshold model is effectively overcome, and the method is suitable for popularization and application. The prediction reliability in a complex environment is obviously enhanced; according to the method, the disease and insect pest outbreak risk can be early warned 72 hours in advance, and the disaster loss is reduced by at least 30%; the dosage of chemical pesticides is reduced by more than 40% through a graded green prevention and control strategy, and the biodiversity of farmland and the ecological health of soil are protected.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of smart agriculture and green plant protection technology, more particularly to a corn tasseling stage pest and disease green prevention and control system and method based on environmental adaptation, which realizes the precision and ecological friendly pest and disease prevention and control in the key growth period of corn through real-time collection of multi-source environmental data, dynamic prediction of pest and disease occurrence probability and hierarchical early warning response mechanism. BACKGROUND

[0002] The corn tasseling stage is a sensitive stage of high incidence of pests and diseases, and the traditional prevention and control method relying on chemical pesticides is easy to cause pesticide residues, ecological environment destruction and pest resistance enhancement. The existing technology has the following pain points: Poor environmental adaptability: the occurrence of pests and diseases is strongly related to environmental factors (temperature, humidity, light, etc.), but lacks dynamic environmental modeling capability, and cannot adjust the prevention and control strategy according to real-time weather changes; Early warning lag: manual patrol is low in efficiency and difficult to capture the premonitory signs of pest and disease outbreak in time; Over-reliance on chemical control: existing automatic systems mostly directly trigger pesticide spraying, and lack intelligent cooperation of green means such as biological control; Insufficient data fusion: the heterogeneous environmental data (such as canopy temperature, humidity, wind speed) collected by the sensor network are not effectively associated with the occurrence regularity of pests and diseases, resulting in limited prediction accuracy; Therefore, there is an urgent need for a corn tasseling stage pest and disease green prevention and control system and method based on environmental adaptation to solve the above technical problems. SUMMARY

[0003] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a corn tasseling stage pest and disease green prevention and control system and method based on environmental adaptation to solve the technical problems proposed in the background art.

[0004] To achieve the above-mentioned purpose, the present application provides the following technical scheme: a corn tasseling stage pest and disease green prevention and control system based on environmental adaptation, comprising a control system, wherein the control system comprises an environmental simulation unit, a pest and disease simulation database, a prediction analysis module, an early warning decision module and a collection unit; The environmental simulation unit is combined with the pest and disease simulation database to construct a mapping relationship model of pest and disease biological activity under different environmental variables; The collection unit is deployed in the monitoring area to collect a data set of the area in real time, and the data set is respectively: temperature T, humidity H, light intensity L, rainfall R and wind speed W; The early warning analysis module calculates the pest occurrence probability of the monitoring area through the data set collected by the collection unit, and obtains a pest probability occurrence value Q; The early warning decision module generates a corresponding decision signal according to the pest probability occurrence value Q, which is used to make early prevention.

[0005] In a preferred embodiment, the environment simulation unit is combined with the pest simulation database to construct the mapping relationship between the activities of pest organisms and different environmental variables. The specific process is as follows: Historical data retrieval step: Extract historical environmental pest data sets from the pest simulation database, which contains a five-dimensional environmental vector of time-stamped temperature T, humidity H, light intensity L, rainfall R, and wind speed W; Nonlinear correlation modeling step: Establish a mapping function of the five-dimensional environmental vector and pest activity intensity using multivariate regression analysis; Probability distribution generation step: Generate pest occurrence probability distribution under different climate scenarios through Monte Carlo simulation.

[0006] In a preferred embodiment, the collection unit includes a collection end, wherein the collection end includes a canopy temperature sensor, a relative humidity sensor, a light intensity meter, a tipping bucket rain gauge, and an ultrasonic anemometer; The collection end is deployed between corn rows, and the sampling interval is set to 15 minutes / time. The collection unit collects temperature T, humidity H, light intensity L, rainfall R, and wind speed W and transmits them to the early warning analysis module through a wireless communication system; The canopy temperature sensor is suspended in the middle of the corn plant canopy and uses a radiation-proof ventilation structure. The measurement range is -10℃ to 60℃, and the accuracy is ±0.5℃. The relative humidity sensor is coaxially packaged with the temperature sensor and is equipped with a high-molecular capacitive sensing element. The measurement range is 0% to 100% RH, and the accuracy is ±2%. The light intensity meter is installed 30 cm above the canopy and is equipped with a cosine corrector and a spectral response filter (400-700 nm). The measurement range is 0 to 200 klux, and the accuracy is ±5%. The tipping bucket rain gauge is laid out in the open field and has a non-blocking drainage funnel and a magnetic reed switch metering mechanism with a resolution of 0.2 mm. The ultrasonic anemometer is fixed to a bracket 1.5 m above the ground and uses the time difference method for three-dimensional wind speed measurement. The range is 0 to 30 m / s, and the accuracy is ±0.2 m / s.

[0007] In a preferred embodiment, the wireless communication module includes a multi-modal wireless communication system, and the collection unit transmits data sets through the multi-modal wireless communication system. The multi-modal wireless communication system includes: Local sensing layer: Star network using LoRa modulation technology; Wide area backhaul layer: Dual-channel redundant architecture; Edge computing layer: deployed in the embedded processing unit of LoRa gateway, to perform: environmental data preprocessing, communication protocol conversion and off-network cache.

[0008] In a preferred embodiment, the calculation method of the early warning analysis module comprises: a: outlier rejection and moving average processing on the collected raw data; b: input environmental parameters into the trained support vector machine classification model; c: combined with the occurrence cycle characteristics of pests and diseases, output the pest probability value Q in the next 72 hours.

[0009] In a preferred embodiment, the method for judging outliers comprises: S1, the early warning analysis module generates a threshold range of normal state of data set; S2, the early warning analysis module compares the real-time data set with the threshold range; S3, when the real-time data set at a certain time end is not within the threshold range, it is judged that a certain group of data in the data set at the time end is an outlier; The simulation range includes: temperature: -20℃≤T≤45℃ (out of the extreme range of corn growth) Humidity: 0%≤RH≤100% (excluding negative or supersaturated data) Light intensity: 0lux≤L≤120,000lux (consistent with natural light range).

[0010] Among them, the temperature-humidity coupling relationship is: when T> 30℃, RH should not be sustained <20% (exclude contradictory data of high temperature and low humidity in arid areas) Rainfall-wind speed correlation: strong rainfall (> 50mm / h) should be accompanied by wind speed > 1m / s (exclude sensor water accumulation false alarm).

[0011] In a preferred embodiment, the calculation formula of the pest probability value Q is: ; Where T 1 is the temperature T after range normalization processing; H 1 is the humidity H after range normalization processing; L 1 is the light intensity L after range normalization processing; R 1 is the rainfall R after range normalization processing; W 1 is the wind speed W after range normalization processing.

[0012] In a preferred embodiment, the judgment process of the decision module is: When 0.6≤Q≤0.8, the decision module judges that the probability of occurrence of the plant diseases and insect pests is in a yellow early warning state, and the decision module generates a first decision instruction; When 0.8≤Q≤0.95, the decision module judges that the probability of occurrence of the plant diseases and insect pests is in an orange early warning state, and the decision module generates a second decision instruction; When Q>0.95, the decision module judges that the probability of occurrence of the plant diseases and insect pests is in a red early warning state, and the decision module generates a third decision instruction.

[0013] In a preferred embodiment, the decision module receives the first decision instruction, remotely sends a wireless signal to remind a staff to arrive at the scene to release natural enemy insects and carry out biological intervention; The decision module receives the second decision instruction, remotely sends a wireless signal to remind a staff to arrive at the scene to start a frequency vibration type insect killing lamp; The decision module receives the third decision instruction, remotely sends a wireless signal to remind a staff to arrive at the scene to start a sex attractant trapping device.

[0014] In a preferred embodiment, the application is applied to a corn detasseling period plant disease and insect pest green prevention and control system based on environmental self-adaptation, and includes the following operation steps: Step one, the environment simulation unit is combined with a plant disease and insect pest simulation database, and is used for constructing a mapping relationship model of biological activities of plant diseases and insect pests under different environmental variables; Step two, a collection unit is deployed in a monitoring area, and is used for collecting a data group of the area in real time; Step three, a warning analysis module calculates the occurrence probability of the plant diseases and insect pests of the monitoring area through the data group collected by the collection unit, and obtains a plant disease and insect pest occurrence probability value Q; Step four, a warning decision module generates a corresponding decision signal according to the plant disease and insect pest occurrence probability value Q.

[0015] Technical effects and advantages of the application: 1. The application constructs a five-dimensional environmental vector (temperature, humidity, light intensity, rainfall, and wind speed) and a nonlinear mapping model of plant disease and insect pest activities, adopts multiple regression analysis and Monte Carlo simulation, generates plant disease and insect pest occurrence probability distribution under different climate scenarios, effectively overcomes the limitation of a single threshold model, and significantly enhances the prediction reliability under complex environments; 2. The application establishes a three-level early warning response mechanism, when the plant disease and insect pest occurrence probability value Q is in a yellow early warning interval (0.6≤Q≤0.8), a natural enemy insect release instruction is triggered; when Q is in an orange early warning interval (0.8≤Q≤0.95), a frequency vibration type insect killing lamp starting operation is triggered; when Q reaches a red early warning threshold (Q>0.95), a sex attractant trapping device is triggered; through the hierarchical response strategy, the prevention and control intensity is dynamically matched, chemical pesticides are replaced to the maximum extent, and the ecological environment pollution is reduced; 3、The present application can early warning 72 hours before the outbreak of disease and pest risk, reduce disaster loss by at least 30%; by hierarchical green prevention and control strategy to reduce the amount of chemical pesticides by more than 40%, protect the biodiversity and soil ecological health of farmland. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 The overall flowchart of the corn tasseling period disease and pest green prevention and control system of the present application.

[0017] Figure 2 The overall flowchart of the corn tasseling period disease and pest green prevention and control method of the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application, and in addition, the forms of each structure described in the following embodiments are only examples, and the corn tasseling period disease and pest green prevention and control system and method based on environmental adaptation involved in the present application are not limited to each structure described in the following embodiments, all other embodiments obtained by those skilled in the art without making creative efforts belong to the scope of protection of the present application.

[0019] Referring to Figure 1 The present application provides a corn tasseling period disease and pest green prevention and control system based on environmental adaptation, comprising a prevention and control system; the control system comprises an environmental simulation unit, a disease and pest simulation database, a prediction analysis module, a warning decision module and an acquisition unit; The environmental simulation unit is combined with the disease and pest simulation database, and is used to construct a mapping relationship model of disease and pest biological activities under different environmental variables; The acquisition unit is deployed in a monitoring area, and is used to acquire a data group of the area in real time, and the data group is respectively: temperature T, humidity H, light intensity L, rainfall R and wind speed W; The warning analysis module calculates the occurrence probability of pests in the monitoring area through the data group acquired by the acquisition unit, and obtains a pest occurrence probability value Q; The warning decision module generates a corresponding decision signal according to the pest occurrence probability value Q, which is used for early prevention.

[0020] In the embodiments of the present application, by constructing a five-dimensional environmental vector (temperature, humidity, light intensity, rainfall, wind speed) and a nonlinear mapping model of disease and pest activities, a multivariate regression analysis and a Monte Carlo simulation are combined to generate a disease and pest occurrence probability distribution under different climate scenarios, effectively overcoming the limitations of a single threshold model, and significantly enhancing the prediction reliability under complex environments.

[0021] Referring toFigure 1 As shown, this invention provides a green control system for maize tasseling stage diseases and pests based on environmental adaptation. The specific process for constructing the mapping relationship between different environmental variables and the biological activities of diseases and pests, by combining the environmental simulation unit with the disease and pest simulation database, is as follows: Historical data retrieval steps: Extract historical environmental disease data pairs from the pest and disease simulation database. The data pairs contain a five-dimensional environmental vector with timestamp aligned: temperature T, humidity H, light intensity L, rainfall R, and wind speed W. Nonlinear correlation modeling steps: Use multiple regression analysis to establish a mapping function between a five-dimensional environmental vector and the intensity of pest and disease activity; Probability distribution generation steps: Generate the probability distribution of pest and disease occurrence under different climate scenarios through Monte Carlo simulation.

[0022] The acquisition unit includes an acquisition end, which includes a canopy temperature sensor, a relative humidity sensor, a light intensity meter, a tipping bucket rain gauge, and an ultrasonic anemometer. The data acquisition unit is deployed between the corn rows, with a sampling interval of 15 minutes per time. The data acquisition unit collects temperature T, humidity H, light intensity L, rainfall R, and wind speed W and transmits them to the early warning analysis module via a wireless communication system.

[0023] In this application embodiment, the following are some examples: a canopy temperature sensor, suspended in the middle of the corn plant canopy, with a radiation-proof and ventilated structure, measuring range -10℃ to 60℃, accuracy ±0.5℃; a relative humidity sensor, coaxially packaged with the temperature sensor, equipped with a polymer capacitive sensitive element, measuring range 0% to 100%RH, accuracy ±2%; a light intensity meter, installed 30cm above the canopy, equipped with a cosine corrector and a spectral response filter (400-700nm), measuring range 0 to 200klux, accuracy ±5%; a tipping bucket rain gauge, deployed in an open area of ​​the field, with an anti-clogging drainage funnel and a magnetic reed switch measuring mechanism, resolution 0.2mm; and an ultrasonic anemometer, fixed on a bracket 1.5m above the ground, using a time-difference method for three-dimensional wind speed measurement, measuring range 0 to 30m / s, accuracy ±0.2m / s.

[0024] Reference Figure 1 As shown, this invention provides a green control system for corn tasseling stage diseases and pests based on environmental adaptation. The wireless communication module includes a multimodal wireless communication system, and the acquisition unit transmits data groups through the multimodal wireless communication system. The multimodal wireless communication system includes: Local sensing layer: The star network employing LoRa modulation technology includes: Terminal nodes deployed in the acquisition unit (e.g., Class A devices); LoRa gateway installed on the field high point, receiving radius ≥ 500m; Adaptive spreading factor mechanism, power dynamic adjustment range 14-20dBm; Wide area backhaul layer: adopt dual-channel redundant architecture, including: 4G / LTE Cat.1 cellular communication module; Beidou RDSS short message communication module; Edge computing layer: deployed in the embedded processing unit of LoRa gateway, and performs: environmental data preprocessing, communication protocol conversion and network outage cache.

[0025] Referring to Figure 1 The present application provides a kind of based on environmental adaptation's corn tassel period disease and pest green prevention and control system, the calculation method of early warning analysis module includes: Step one: the original data collected are excluded and sliding average processing is carried out to abnormal value; Step two: environmental parameters are input into the trained support vector machine classification model; Step three: combined with the cycle characteristics of disease and pest occurrence, output future 72 hours pest probability value Q.

[0026] In the application embodiment, in part of the application embodiment, the abnormal value judging method step is: S1, the threshold range when the data group of early warning analysis module is in normal state is generated; S2, early warning analysis module compares real-time data group with threshold range; S3, when the real-time data group of a certain time end is not in threshold range, it is judged that the data of the data group in the time end is abnormal value.

[0027] Simulation range includes: temperature: -20℃≤T≤45℃ (out of the limit range of corn growth) Humidity: 0%≤RH≤100% (exclude negative or supersaturated data) Irradiance: 0lux≤L≤120,000lux (in line with natural light range).

[0028] Wherein the temperature-humidity coupling relationship: when T>30℃, RH should not be sustained <20% (exclude arid area high temperature low humidity contradictory data) Rainfall-wind speed correlation: heavy rainfall (>50mm / h) needs to be accompanied by wind speed >1m / s (exclude sensor water accumulation false alarm); The calculation formula of the pest probability occurrence value Q is: ; Where T1 is the temperature T after range normalization; H1 is the humidity H after range normalization; L1 is the light intensity L after range normalization; R1 is the rainfall R after range normalization; and W1 is the wind speed W after range normalization. The process for normalizing the range of the original environmental parameters is as follows: Here, temperature T is used as an example. T 均 This refers to the average value of temperature T collected within 1 hour. max T represents the maximum value generated within this time range. min It refers to the minimum value generated within this range.

[0029] Reference Figure 1 As shown, the present invention provides a green prevention and control system for corn tasseling stage diseases and pests based on environmental adaptation. When 0.6≤Q≤0.8, the decision module judges that the probability of disease and pest occurrence is in a yellow warning state, and the decision module generates the first decision instruction. When 0.8≤Q≤0.95, the decision module determines that the probability of pest and disease occurrence is in an orange alert state, and the decision module generates a second decision instruction; When Q > 0.95, the decision module determines that the probability of pests and diseases occurring is in a red alert state, and the decision module generates a third decision instruction; Upon receiving the first decision instruction, the decision module remotely sends a wireless signal to remind staff to arrive at the site to release predatory insects and conduct biological intervention. The decision module receives the second decision instruction and remotely sends a wireless signal to remind staff to arrive at the site and turn on the frequency-vibration insecticidal lamp. The decision module receives a third decision instruction and remotely sends a wireless signal to remind staff to arrive at the site and activate the sex pheromone trapping device.

[0030] Reference Figure 2 The method for green control of maize tasseling stage diseases and pests, as shown, is applied to a green control system for maize tasseling stage diseases and pests based on environmental adaptation and includes the following operational steps: Step 1: The environmental simulation unit is combined with the pest and disease simulation database to construct a mapping model between different environmental variables and pest and disease biological activities; Step 2: The data acquisition unit is deployed in the monitoring area to collect data sets from that area in real time. Step 3: The early warning analysis module calculates the probability of pest occurrence in the monitored area using the data collected by the acquisition unit, and obtains the pest probability value Q. Step 4: The early warning decision module generates a corresponding decision signal based on the pest probability occurrence value Q.

[0031] The above-described embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. Those of ordinary skill in the art can be aware that the units and algorithm steps described in connection with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solutions. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application. Those skilled in the art can clearly understand that, for the sake of brevity and conciseness, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described here.

[0032] In several embodiments provided in the present application, it should be understood that the disclosed system, device, and method can be implemented in other ways. For example, the device embodiments described above are merely schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices, or units, and can be electrical, mechanical, or other forms.

[0033] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0034] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically, or two or more units can be integrated into one unit.

[0035] The above is merely a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0036] Finally: the above only for the preferred embodiments of the present application, and not for limiting the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application, should be included in the scope of protection of the present application.

Claims

1. A green control system for maize diseases and pests during the tasseling stage based on environmental adaptation, comprising a control system, characterized in that: The control system includes an environmental simulation unit, a pest and disease simulation database, a predictive analysis module, an early warning decision module, and a data acquisition unit. The environmental simulation unit is combined with the pest and disease simulation database to construct a mapping relationship model between different environmental variables and pest and disease biological activities. The data acquisition unit is deployed in the monitoring area to collect data sets of the area in real time, which are: temperature T, humidity H, light intensity L, rainfall R, and wind speed W. The early warning analysis module calculates the probability of pest occurrence in the monitored area using the data collected by the acquisition unit, and obtains the pest occurrence probability value Q. The early warning decision module generates a corresponding decision signal based on the pest probability occurrence value Q, which is used to make early prevention measures.

2. The environmentally adaptive green control system for maize tasseling stage diseases and pests according to claim 1, characterized in that: The specific process for combining environmental simulation units with pest and disease simulation databases to construct mapping relationships between different environmental variables and pest and disease biological activities is as follows: Historical data retrieval steps: Extract historical environmental disease data sets from the pest and disease simulation database. The data sets contain a five-dimensional environmental vector with timestamp aligned: temperature T, humidity H, light intensity L, rainfall R, and wind speed W. Nonlinear correlation modeling steps: Use multiple regression analysis to establish a mapping function between a five-dimensional environmental vector and the intensity of pest and disease activity; Probability distribution generation steps: Generate the probability distribution of pest and disease occurrence under different climate scenarios through Monte Carlo simulation.

3. The environmentally adaptive green control system for maize tasseling stage diseases and pests according to claim 1, characterized in that: The acquisition unit includes an acquisition end, which includes a canopy temperature sensor, a relative humidity sensor, a light intensity meter, a tipping bucket rain gauge, and an ultrasonic anemometer. The data acquisition unit is deployed between the corn rows, with a sampling interval of 15 minutes per time. The data acquisition unit collects temperature T, humidity H, light intensity L, rainfall R, and wind speed W and transmits them to the early warning analysis module via a wireless communication system.

4. The environmentally adaptive green control system for maize tasseling stage diseases and pests according to claim 3, characterized in that: The wireless communication module includes a multimodal wireless communication system, and the acquisition unit transmits data groups through the multimodal wireless communication system, which includes: Local sensing layer: Star network using LoRa modulation technology; Wide Area Backhaul Layer: Employs a dual-channel redundant architecture; Edge computing layer: An embedded processing unit deployed on the LoRa gateway, performing tasks such as environmental data preprocessing, communication protocol conversion, and network outage caching.

5. The environmentally adaptive green control system for maize tasseling stage diseases and pests according to claim 1, characterized in that: The calculation method of the early warning analysis module includes: a: Perform outlier removal and moving average processing on the collected raw data; b: Input the environmental parameters into the trained support vector machine classification model; c: Based on the characteristics of the pest and disease occurrence cycle, output the pest probability value Q for the next 72 hours.

6. The environmentally adaptive green control system for maize tasseling stage diseases and pests according to claim 1, characterized in that: The steps for determining outliers are as follows: S1. The threshold range for data groups to be in a normal state is generated by the early warning analysis module. S2, the early warning analysis module compares the real-time data set with the threshold range; S3. When a real-time data group at a certain time point is not within the threshold range, it is determined that a certain data group in the data group at that time point is an outlier.

7. The environmentally adaptive green control system for maize tasseling stage diseases and pests according to claim 1, characterized in that: The formula for calculating the pest probability occurrence value Q is: ; Where T 1 The temperature T after range normalization; H 1 The humidity H; L is the humidity after range normalization. 1 The light intensity L and R are the light intensities after range normalization. 1 The rainfall amount R after range normalization; W 1 It is the wind speed W after range normalization.

8. The environmentally adaptive green control system for maize tasseling stage diseases and pests according to claim 7, characterized in that: The decision-making process of the decision module is as follows: When 0.6≤Q≤0.8, the decision module determines that the probability of pest and disease occurrence is in a yellow warning state, and the decision module generates the first decision instruction; When 0.8≤Q≤0.95, the decision module determines that the probability of pest and disease occurrence is in an orange alert state, and the decision module generates a second decision instruction; When Q > 0.95, the decision module determines that the probability of pests and diseases occurring is in a red alert state, and the decision module generates a third decision instruction.

9. The environmentally adaptive green control system for maize tasseling stage diseases and pests according to claim 8, characterized in that: Upon receiving the first decision instruction, the decision module remotely sends a wireless signal to remind staff to arrive at the site to release predatory insects and conduct biological intervention. The decision module receives the second decision instruction and remotely sends a wireless signal to remind staff to arrive at the site and turn on the frequency-vibration insecticidal lamp. The decision module receives a third decision instruction and remotely sends a wireless signal to remind staff to arrive at the site and activate the sex pheromone trapping device.

10. A green control method for maize tasseling stage diseases and pests based on environmental adaptation, applied to the green control system for maize tasseling stage diseases and pests based on environmental adaptation as described in any one of claims 1-9, characterized in that, The following steps are included: Step 1: The environmental simulation unit is combined with the pest and disease simulation database to construct a mapping model between different environmental variables and pest and disease biological activities; Step 2: The data acquisition unit is deployed in the monitoring area to collect data sets from that area in real time. Step 3: The early warning analysis module calculates the probability of pest occurrence in the monitored area using the data collected by the acquisition unit, and obtains the pest probability value Q. Step 4: The early warning decision module generates a corresponding decision signal based on the pest probability occurrence value Q.

Images