Intelligent monitoring and precise pesticide application integrated rice bakanae disease prevention and control system

Abstract

The invention discloses an intelligent monitoring and precise pesticide application integrated rice bakanae disease prevention and control system, and relates to the technical field of agricultural disease prevention and control, the prevention and control system comprises a data acquisition module used for acquiring rice related data through a data monitoring device, and fusing the acquired data through a space-time weight fusion formula; through the data acquisition module, the data processing and analysis module and the pesticide application decision module, real-time monitoring, accurate identification and effective prevention and control of the rice bakanae disease are achieved, the data processing and analysis module comprehensively analyzes the acquired data, the disease type and degree can be accurately identified, the development trend of the disease can be predicted, and the pesticide application decision module can be applied to the rice bakanae disease. The disease identification and prediction capability enables the pesticide application decision-making module to dynamically determine the optimal pesticide application scheme based on the current disease state, the environmental condition and the historical prevention and control effect, thereby effectively improving the accuracy and efficiency of disease prevention and control, and reducing pesticide waste and environmental pollution.

Description

Technical Field

[0001] This invention relates to the field of agricultural disease control technology, specifically to an integrated intelligent monitoring and precision pesticide application system for the control of rice seedling blight. Background Technology

[0002] With the rapid development of modern agriculture, rice, as one of the world's most important food crops, has its yield and quality directly related to food security and social stability. However, rice is often attacked by various diseases during its growth process. Among them, rice bakanae disease, a serious disease caused by fungi, not only affects the normal growth and development of rice, but may also lead to a significant reduction in yield or even crop failure, causing huge losses to agricultural production. Traditionally, farmers mainly rely on experience to judge the occurrence of diseases and take measures to control them by spraying pesticides on a large scale.

[0003] However, traditional rice bakanae disease control techniques have many shortcomings. They rely on manual experience to judge the occurrence of the disease, lack comprehensive analysis and in-depth mining of multi-source data such as environmental and meteorological data, making it difficult to accurately identify the type and severity of the disease, easily leading to misjudgment or omission, and failing to predict the development trend of the disease. In terms of pesticide application decisions, traditional methods often use fixed application plans, lacking dynamic evaluation of the current disease status, environmental conditions, and historical control effectiveness. They cannot adjust control strategies in a timely manner according to the actual situation of the disease, resulting in unreasonable application plans. This not only easily leads to pesticide waste and environmental pollution, but also has an adverse effect on rice growth due to untimely or excessive application, resulting in poor control effect. Furthermore, the lack of comprehensive consideration of multiple factors such as environment and meteorology cannot provide strong support for precision pesticide application.

[0004] Therefore, it is necessary to develop an integrated intelligent monitoring and precision pesticide application system for the prevention and control of rice bakanae disease. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and provide an integrated intelligent monitoring and precision pesticide application system for the prevention and control of rice bakanae disease. Through the data processing and analysis module, the collected data is comprehensively analyzed to accurately identify the type and severity of the disease and predict its development trend. This disease identification and prediction capability enables the pesticide application decision module to dynamically determine the optimal pesticide application plan based on the current disease status, environmental conditions, and historical control effectiveness, thereby effectively improving the accuracy and efficiency of disease control and reducing pesticide waste and environmental pollution.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an integrated intelligent monitoring and precision spraying system for the prevention and control of rice bakanae disease, the system comprising:

[0007] Data acquisition module: Collects rice-related data through data monitoring equipment and fuses the collected data using a spatiotemporal weighted fusion formula;

[0008] Data transmission module: transmits the collected images, environmental data, topographic data, and weather data in real time;

[0009] Data processing and analysis module: Receives transmitted data, preprocesses and extracts features, identifies whether rice is infected with bakanae disease and the type and severity of the disease using the bakanae disease feature identification index formula method, integrates the identification results with other data to establish a correlation model, predicts the disease development trend, and simulates the pathogen transmission path using the pathogen transmission simulation formula.

[0010] Application decision module: Combining knowledge base and historical prevention and control data, the application decision comprehensive evaluation algorithm is used to determine the application plan, and the preliminary application plan is adjusted based on the simulation and prediction results of pathogen transmission path;

[0011] The pesticide application execution module controls the operation of intelligent spraying equipment, monitors parameters and evaluates the effects in real time, and provides feedback to the pesticide application decision module to adjust the plan if the effect is not satisfactory.

[0012] Furthermore, the data monitoring equipment used in the data acquisition module is:

[0013] High-definition camera: captures images of rice plants;

[0014] Environmental data acquisition sensors: Temperature and humidity sensor: collects temperature and humidity data of soil and air; Light sensor: monitors parameters such as light intensity and duration of light exposure; Rainfall sensor: measures rainfall amount and duration of rainfall; Soil nutrient sensor: monitors nitrogen, phosphorus, and potassium content, pH value, and organic matter content in soil; Wind speed and direction sensor: monitors wind speed and direction; Water flow velocity and direction sensor: monitors water flow velocity and direction in irrigation channels and drainage outlets.

[0015] Topographic mapping equipment: LiDAR: By scanning with ground-based LiDAR, three-dimensional topographic data of paddy field elevation, slope, and ridge location are obtained;

[0016] Satellite remote sensing equipment: docks with Sentinel satellites to acquire multispectral remote sensing images with a spatial resolution of 10-30 meters, and extracts data on the boundaries of rice planting areas, vegetation coverage, and leaf area index;

[0017] Meteorological data acquisition unit: Connects to the meteorological department via API interface to acquire routine meteorological data such as temperature, air pressure, humidity, precipitation, sunshine hours, wind speed and direction in real time.

[0018] Furthermore, in the data acquisition module, the acquired data is fused using a spatiotemporal weighted fusion formula, which is as follows: ,in, for The integrated data vector after time-mapping for High-definition camera images of rice plants are captured in real time. for Data collected by environmental sensors at all times Data on the topography and geomorphology of paddy fields. for Real-time weather data, For time, These are dynamic weighting coefficients, and .

[0019] Furthermore, the data processing and analysis module receives and preprocesses the transmitted data, extracting features such as leaf elongation rate, stem distortion, and lesion color threshold from rice plant images, as well as features of temperature, humidity, and light from environmental data, features of topographic data, and features of wind speed and water flow speed from meteorological data. The extracted plant image features are then substituted into the bakanae disease feature recognition formula to obtain disease identification results, determining whether the rice is suffering from bakanae disease and the type and severity of the disease. The disease identification results are integrated with environmental, topographic, and meteorological data to construct a correlation model between environmental factors, meteorological factors, and disease occurrence. Based on the correlation model, the disease development trend is predicted, and combined with real-time airflow, water flow, and topographic information, the pathogen transmission path is simulated using a pathogen transmission simulation formula to predict its transmission direction and speed.

[0020] Furthermore, in the data processing and analysis module, the extracted plant image features are substituted into the bakanae disease feature recognition formula to calculate the disease recognition result. The bakanae disease feature recognition formula is then: ,in, The comprehensive identification index for bakanae disease. For the rate of excessive leaf growth, The degree of stem distortion, The threshold for lesion color. These are the dynamic weighting coefficients for each feature.

[0021] Furthermore, in the data processing and analysis module, a correlation model is constructed between environmental factors, meteorological factors, and disease occurrence. The calculation formula for this correlation model is as follows: ,in, For the future The incidence rate of rice bakanae disease within a day ranges from 0 to 1. The average temperature. The average humidity. To accumulate the duration of illumination, data is collected using a light sensor. The comprehensive identification index for bakanae disease. For wind speed, Based on the offset coefficient, Temperature effect coefficient, Humidity influence coefficient The influence coefficient of illumination duration, The coefficient representing the impact of the current state of the disease. This represents the wind speed influence coefficient.

[0022] Furthermore, in the data processing and analysis module, the formula for simulating pathogen transmission is: ,in, To the speed of pathogen transmission, For wind speed, For water flow velocity, Based on the speed of propagation, The weights of the effects of wind and water flow on propagation, and , , The angle of direction of pathogen transmission. Wind direction angle This represents the angle of the water flow direction.

[0023] Furthermore, the pesticide application decision module retrieves knowledge about rice bakanae disease control stored in the knowledge base, as well as past pesticide application cases and the correspondence between disease development and control effects from historical control data. Using a comprehensive evaluation algorithm for pesticide application decision, it integrates the current state of the disease, environmental conditions, and historical control effectiveness factors to initially determine the pesticide application plan, including the type of pesticide to be selected, the basic dosage, and the initial application time.

[0024] Furthermore, in the drug application decision module, a drug application decision comprehensive evaluation algorithm is used to initially determine the drug application plan. The formula for the drug application decision comprehensive evaluation algorithm is as follows: ,in, This is a comprehensive index for medication application decisions, ranging from 0 to 1. A higher value indicates a greater need for immediate medication application. The number of influencing factors, For the first The weight coefficients of each factor For the first Standardized score functions for each factor This is an index representing the historical effectiveness of prevention and control. This represents the highest prevention and control effectiveness index in history. It is the index variable for the summation operation.

[0025] Compared with existing technologies, this integrated intelligent monitoring and precision application system for rice bakanae disease control has the following beneficial effects:

[0026] I. This invention achieves real-time monitoring, accurate identification, and effective control of rice bakanae disease through a data acquisition module, a data processing and analysis module, and a pesticide application decision module. The data processing and analysis module comprehensively analyzes the collected data, accurately identifying the disease type and severity, and predicting the disease's development trend. This disease identification and prediction capability enables the pesticide application decision module to dynamically determine the optimal pesticide application plan based on the current disease status, environmental conditions, and historical control effectiveness, thereby effectively improving the accuracy and efficiency of disease control and reducing pesticide waste and environmental pollution.

[0027] Second, this invention controls the operation of intelligent spraying equipment through a pesticide application execution module, and monitors parameters and evaluates the effect in real time. If the effect is not good, it feeds back to the pesticide application decision module to adjust the plan, forming a closed-loop control. This intelligent and automated prevention and control method not only reduces the reliance on human experience and reduces labor costs, but also improves the timeliness and accuracy of prevention and control operations. At the same time, it can dynamically adjust the pesticide application plan based on real-time monitoring data to ensure the maximization of prevention and control effect, providing strong support for agricultural production.

[0028] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0030] Figure 1 A flowchart of an integrated intelligent monitoring and precision spraying system for the prevention and control of rice bakanae disease;

[0031] Figure 2 This is a framework diagram of an integrated intelligent monitoring and precision pesticide application system for the prevention and control of rice bakanae disease. Detailed Implementation

[0032] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0033] Example 1:

[0034] Data Acquisition Module: High-definition cameras are deployed at the four corners and center of the field to capture images of rice plants during the tillering stage every 20 minutes. Simultaneously, soil temperature and humidity sensors (buried 10cm deep), air temperature and humidity sensors (1.5m above ground), light sensors, rainfall sensors, wind speed and direction sensors, and water flow velocity and direction sensors are installed to collect environmental data such as soil moisture (range 0-100%) and air temperature (-20℃-60℃) in real time. A lidar scanner is used to scan the entire field, acquiring elevation data and field ridge location information with an accuracy of 5cm. Meteorological data (including wind speed and air pressure) is accessed from the central meteorological station via an API interface. The collected data is fused using a spatiotemporal weighted fusion formula, which is as follows: ,in, for The integrated data vector after time-mapping for High-definition camera images of rice plants are captured in real time. for Data collected by environmental sensors at all times Data on the topography and geomorphology of paddy fields. for Real-time weather data, For time, These are dynamic weighting coefficients, and .

[0035] Data transmission module: Through the base's self-built 5G private network, images (approximately 8MB per frame) and environmental data (1 set per second) are transmitted in real time, with transmission latency controlled within 100ms.

[0036] Data processing and analysis module: Receives transmitted data, preprocesses it, and extracts features such as leaf elongation rate (exceeding 15% of normal plant height is considered abnormal) and stem distortion (bending angle > 10°). These features are then substituted into the bakanae disease feature identification formula to calculate the identification index. The bakanae disease feature identification formula is as follows: ,in, The comprehensive identification index for bakanae disease. For the rate of excessive leaf growth, The degree of stem distortion, The threshold for lesion color. The dynamic weighting coefficients for each feature are used. When the D value of a certain block exceeds 0.6 three times consecutively, it is judged as a moderate incidence. This is calculated using the association model formula. ,in, For the future The incidence rate of rice bakanae disease within a day ranges from 0 to 1. The average temperature is collected from temperature sensors in the environmental data. The average humidity is collected from a humidity sensor within the environmental data. To accumulate the duration of illumination, data is collected using a light sensor. The comprehensive identification index for bakanae disease. For wind speed, Based on the offset coefficient, Temperature effect coefficient, Humidity influence coefficient The influence coefficient of illumination duration, The coefficient representing the impact of the current state of the disease. Using wind speed as the influence coefficient, and based on environmental parameters such as daily average temperature >25℃ and air humidity >85%, the potential spread of the disease within a 50-meter radius over the next 3 days is predicted. The pathogen spread path under the prevailing wind direction (southeast wind, wind speed 3-4 m / s) is determined using a pathogen transmission simulation formula. The pathogen transmission simulation formula is as follows: ,in, To the speed of pathogen transmission, For wind speed, For water flow velocity, Based on the speed of propagation, The weights of the effects of wind and water flow on propagation, and , , The angle of direction of pathogen transmission. Wind direction angle This represents the angle of the water flow direction.

[0037] Application decision module: Retrieves bakanae disease control programs from the knowledge base, compares them with application cases in the same region (using 25% cyazofamid suspension), and utilizes the comprehensive evaluation algorithm formula for application decision: ,in, This is a comprehensive index for medication application decisions, ranging from 0 to 1. A higher value indicates a greater need for immediate medication application. The number of influencing factors, For the first The weight coefficients of each factor For the first Standardized score functions for each factor This is an index representing the historical effectiveness of prevention and control. This represents the highest prevention and control effectiveness index in history. This is the index variable for the summation operation. The calculated Ω = 0.82, indicating that the medication should be administered immediately. Figure 1 As shown, the basic dosage was adjusted to 180g / mu (considering the current high humidity), and the initial application time was set at 10:00 am the next day (avoiding the dew period). Based on the results of pathogen transmission simulation, the core prevention and control area (within an 80-meter radius of the disease center) and the prevention area were delineated.

[0038] Application execution module: Four drones (with a payload of 20L) were activated to operate along the planned route, and parameters such as spray width (8 meters) and droplet size (150-200μm) were monitored in real time. After 24 hours of operation, the disease rate was reduced to 3%. However, the effect was not as expected in the edge area due to sudden changes in wind speed. The system automatically fed back to the decision module, and the application was adjusted to a ground self-propelled sprayer (with more uniform droplets) when reapplying.

[0039] In summary, in a thousand-acre rice paddy in the plains, by deploying high-definition cameras, various environmental sensors, and lidar, multi-dimensional data is collected and processed using a spatiotemporal weighted fusion formula. The data processing module, combined with formulas for identifying bakanae disease characteristics, correlation models, and pathogen transmission simulation, accurately determines the severity and development trend of the disease. The pesticide application decision module determines the plan based on the evaluation algorithm and adjusts it in conjunction with the transmission path. The execution module operates in conjunction with drones and ground equipment, achieving closed-loop control from data collection to pesticide application feedback, effectively controlling the spread of bakanae disease and improving prevention and control efficiency.

[0040] Example 2:

[0041] Data Acquisition Module: Fixed-mount high-definition cameras (4K resolution, with infrared night vision) are installed at different altitudes (every 10 meters) along the ridges of the terraced fields. Images of rice plants are captured hourly from 6:00 AM to 6:00 PM daily. Soil temperature and humidity sensors (15cm depth), air temperature and humidity sensors (1.2m above ground), as well as light sensors and wind speed sensors (equipped with windproof covers to cope with valley winds) are buried in the soil of each terrace platform to collect environmental data in real time. Ground-based lidar scans the terraces to obtain 3D topographic data such as slope and ridge location with an accuracy of 10cm. Satellite remote sensing equipment is connected to Sentinel satellites to acquire 15-meter resolution remote sensing images, extracting data such as rice planting area boundaries and vegetation coverage. The collected data is then fused using a spatiotemporal weighting formula. To integrate.

[0042] Data transmission module: Due to insufficient network coverage in mountainous areas, a hybrid networking method of 4G wireless transmission and fiber optic is adopted to transmit image data (compressed to 3MB per frame) and environmental data (1 set per minute) in real time.

[0043] Data processing and analysis module: Receives transmitted data, preprocesses the data, extracts features such as lesion color threshold (RGB values ​​R > 210, G < 160, B < 110) and leaf elongation rate, and substitutes them into the bakanae disease feature recognition formula: The calculated value of D is 0.73 (local high value area), and the formula is calculated using the correlation model: Combining real-time monitoring data of valley winds (south wind 2-4 m / s during the day, north wind 1-3 m / s at night) and water accumulation in the terraced fields, it was predicted that the disease might spread downstream along the direction of water flow (following the drop in elevation of the terraced fields). Then, a pathogen transmission simulation formula was used. It was determined that under the combined influence of water flow velocity (0.08 m / s) and wind direction, the pathogen could spread to the downstream second-level terraced fields within 48 hours. Figure 2 As shown.

[0044] Application decision module: Retrieves control plans for bakanae disease in hilly areas from the knowledge base, compares application cases (using 10% difenoconazole water-dispersible granules) with similar terrain, and utilizes the comprehensive evaluation algorithm formula for application decision: The calculated Ω=0.78, and the pesticide dosage was determined to be 200g / mu. Considering the difference in pesticide deposition caused by the difference in terrace elevation, the initial application time was set at 17:00 (during the period when the valley wind weakens). Based on the simulated path of pathogen transmission, the application sequence was adjusted to "segmented spraying from the upstream diseased field to the middle and downstream terraces against the direction of water flow".

[0045] Application execution module: A tracked sprayer with terrain-following function (25° climbing ability) is used, equipped with a variable spray system. The spraying pressure (0.25-0.35MPa) and travel speed (1.2-1.8km / h) are automatically adjusted according to the slope of the terrace. The system monitors the droplet size (180-220μm) and spray width (6-8 meters) in real time. After the first application, a follow-up check is performed 24 hours later. The control effect in the upstream diseased field reaches 85%, but the downstream second-level terrace has been infected by secondary infection due to the pathogen carried by the water flow. After the system feeds the data back to the application decision module, it is adjusted to a low dose (120g / mu) for supplementary application, which ultimately controls the spread of the disease.

[0046] In summary, by installing fixed cameras and sensors at different altitudes in hilly terraced fields, and combining data from lidar and satellite remote sensing, and after spatiotemporal weighted fusion, the disease is analyzed using formulas such as bakanae disease feature identification. The pesticide application decision module references the knowledge base and the comprehensive evaluation algorithm formula for pesticide application decisions, and adjusts the plan based on terrain and pathogen transmission simulation. Tracked sprayers are used to achieve terrain-adaptive operations, forming an integrated prevention and control process that specifically solves the problem of bakanae disease prevention and control in fragmented hilly areas.

[0047] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. An integrated system for monitoring and precise application of rice seedling disease prevention and control, characterized in that, The system comprises: a data acquisition module: collecting rice-related data through data monitoring equipment and fusing the collected data through a spatio-temporal weight fusion formula; a data transmission module: real-time transmission of collected image, environmental, topographical and meteorological data; a data processing and analysis module: receiving transmitted data, preprocessing and extracting features, identifying whether the rice is suffering from bakanae disease and the type and degree of the disease through a bakanae disease feature recognition index formula, establishing a correlation model by comprehensively analyzing the identification results and other data, predicting the disease development trend, and simulating the path of disease transmission through a disease transmission simulation formula; a pesticide application decision module: combining the knowledge base and historical prevention data, determining the pesticide application scheme using a pesticide application decision comprehensive evaluation algorithm, and adjusting the initially determined pesticide application scheme according to the simulation and prediction results of the disease transmission path; a pesticide application execution module: controlling the operation of intelligent pesticide spraying equipment, and monitoring parameters and evaluating effects in real time, and feeding back to the pesticide application decision module to adjust the scheme if the effect is not good.

2. The intelligent monitoring and precise application integrated system for controlling rice seedling blight according to claim 1, characterized in that, In the data acquisition module, the data monitoring equipment used is: a high-definition camera: to collect rice plant images; environmental data acquisition sensors: temperature and humidity sensors to collect soil and air temperature and humidity data; light sensors to monitor light intensity and light duration parameters; rain sensors to measure rainfall and rainfall duration; soil nutrient sensors to monitor nitrogen, phosphorus, potassium content, pH value, and organic matter content in the soil; wind speed and direction sensors to monitor wind speed and direction; water flow speed and direction sensors to monitor the water flow speed and direction of irrigation channels and drainage outlets; topographical surveying and mapping equipment: laser radar: through ground-based laser radar scanning, three-dimensional topographical data of rice field elevation, slope, and ridge position are obtained; satellite remote sensing equipment: interfacing with the Sentinel satellite to obtain multispectral remote sensing images with a spatial resolution of 10-30 meters, and extracting data on rice planting area boundaries, vegetation coverage, and leaf area index; a meteorological data acquisition unit: connected to the meteorological department through an API interface to obtain real-time conventional meteorological data such as air temperature, air pressure, humidity, precipitation, sunshine duration, and wind speed and direction. 3.The intelligent monitoring and precision application integrated system for controlling rice seedling blight according to claim 1, characterized in that, In the data acquisition module, the collected data is fused through a space-time weight fusion formula, which is: wherein, is a comprehensive data vector fused at the moment, is image data of a rice plant captured by a high-definition camera at the moment, is data collected by an environmental sensor at the moment, is paddy field topography data, is meteorological data at the moment, is time, is a dynamic weight coefficient, and .

4. The intelligent monitoring and precise application integrated system for controlling rice seedling blight according to claim 1, characterized in that, In the data processing and analysis module, the transmitted data is received and preprocessed, the features of leaf elongation rate, stem distortion degree, and disease spot color threshold in the rice plant image, as well as the features of temperature and humidity and light in the environmental data, the features of topographical data, and the features of wind speed and water flow speed in the meteorological data are extracted, the extracted plant image features are substituted into the bakanae disease feature recognition formula to obtain the disease identification result, it is determined whether the rice is suffering from bakanae disease and the type and degree of the disease, the disease identification result is integrated with the environmental, topographical, and meteorological data to build a correlation model between environmental factors, meteorological factors, and disease occurrence, the disease development trend is predicted based on the correlation model, and the path of disease transmission is simulated through a disease transmission simulation formula based on real-time air flow, water flow, and topographical information to predict the direction and speed of transmission.

5. The intelligent monitoring and precise application integrated system for controlling rice seedling blight according to claim 4, characterized in that, In the data processing and analysis module, the extracted plant image features are substituted into the characteristic recognition formula of the wheat yellow mosaic disease, and the disease recognition result is calculated, and the characteristic recognition formula of the wheat yellow mosaic disease is: wherein, is a comprehensive recognition index of the wheat yellow mosaic disease, is a leaf elongation rate, is a stem distortion degree, is a disease spot color threshold value, is a dynamic weight coefficient of each feature. 6.The intelligent monitoring and precision application integrated system for controlling rice seedling blight according to claim 5, characterized in that, The data processing and analysis module, the correlation model between the environmental factors, weather factors and disease occurrence is constructed, and the calculation formula of the correlation model is wherein, is the incidence probability of rice foul brood in the future days, ranging between 0 and 1, is the average temperature, is the average humidity, is the cumulative light duration, collected by a light sensor, is the comprehensive identification index of foul brood, is the wind speed, is the basic offset coefficient, temperature influence coefficient, humidity influence coefficient, light duration influence coefficient, is the disease status influence coefficient, is the wind speed influence coefficient.

7. The intelligent monitoring and precision application integrated system for controlling rice seedling disease according to claim 1, characterized in that, The data processing and analysis module, pathogen transmission simulation formula is: Wherein, is the pathogen transmission speed, is the wind speed, is the water flow speed, is the basic transmission speed, is the wind, water flow on the transmission of the influence weight, and , , is the direction angle of pathogen transmission, is the wind direction angle, is the water flow direction angle. 8.The intelligent monitoring and precision application integrated system for controlling rice seedling blight according to claim 1, characterized in that, The application discloses a rice sheath blight disease prevention and treatment method based on a big data analysis platform, and belongs to the technical field of rice sheath blight disease prevention and treatment. The application discloses a rice sheath blight disease prevention and treatment method based on a big data analysis platform, and belongs to the technical field of rice sheath blight disease prevention and treatment. 9.The intelligent monitoring and precision application integrated system for controlling rice seedling blight according to claim 1, characterized in that, In the medication decision module, the medication scheme is preliminarily determined by using a medication decision comprehensive evaluation algorithm, and the formula of the medication decision comprehensive evaluation algorithm is: Wherein, is a medication decision comprehensive index, ranging from 0 to 1, and the higher the value, the more immediate medication is needed, is the number of influencing factors, is the weight coefficient of the th factor, is the standardized score function of the th factor, is a historical prevention and control effectiveness index, is a historical maximum prevention and control effectiveness index, is an index variable of summation operation.

Images