Crop disease remote sensing monitoring and early warning system based on time sequence spectral information analysis

Abstract

The invention discloses a crop disease remote sensing monitoring and early warning system based on time sequence spectral information analysis, and relates to the technical field of agricultural disease and insect pest monitoring. Computer drawing software is utilized to divide a corn planting field in equal proportion, and sensors are deployed to monitor the growth environment change in each grid in real time and generate microenvironment data information; the method comprises the following steps: calculating a microenvironment difference index Xbd according to microenvironment data, identifying a microenvironment difference aggregation area and sending a risk analysis instruction, after receiving the risk analysis instruction, capturing related spectral data information of the microenvironment difference aggregation area by using an unmanned aerial vehicle and a multispectral sensor, and constructing a multispectral fluctuation coefficient Xgp by analyzing related spectral data, and comparing the calculated rust disease risk assessment index Zpg with a preset threshold W in combination with the microenvironment difference index Xbd and the trained risk assessment model, and obtaining corresponding grade early warning according to the rust disease risk degree.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural pest monitoring, and in particular to a crop disease remote sensing monitoring and early warning system based on time series spectral information analysis. Background Art

[0002] In the field of agricultural pest and disease monitoring, with the advancement of global agricultural production modernization and intelligentization, the application of precise monitoring and early warning technology has received increasing attention. Early detection and rapid response to pests and diseases are important links in ensuring crop yield and quality, especially in the field of corn pest and disease monitoring. Since corn is one of the main food crops, pests and diseases in its growth process have a significant impact on yield and quality. Therefore, it is particularly important to carry out pest and disease monitoring for corn. Southern corn rust is a major disease affecting corn production. After infection, it will cause rust spots on corn leaves, water loss, and decreased photosynthetic capacity, thereby reducing corn yields. In addition, the disease conditions are complex and spread rapidly, seriously threatening the safety of corn planting. Therefore, monitoring and early warning research on southern corn rust is imminent to improve prevention and control efficiency and reduce economic losses.

[0003] Traditional monitoring and early warning methods for corn rust in the south mainly rely on manual inspections and ground sample testing. This method is not only time-consuming and labor-intensive, but also has a low monitoring frequency and insufficient spatial coverage. Ground sample testing requires laboratory analysis of samples, which is a cumbersome and time-consuming process. It is impossible to quickly feedback changes in the disease, and subjective judgments lead to misjudgments and missed judgments. It is impossible to capture the subtle changes of rust in different growth stages of corn in a timely manner, which makes it difficult to detect rust in its early stages, leading to the spread of rust. In addition, changes in the microenvironment, leaf color and moisture content of corn caused by rust are often overlooked, making it difficult to fully assess the risk of rust. In response to these shortcomings, a crop disease remote sensing monitoring and early warning system based on time-series spectral information analysis uses remote sensing technology to integrate microenvironment change information and spectral data based on the impact of rust on the growth status of corn, and realizes accurate monitoring and dynamic early warning of corn fields, which helps disease control personnel take scientific and effective prevention and control measures, thereby increasing corn yields. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a crop disease remote sensing monitoring and early warning system based on time series spectral information analysis, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a crop disease remote sensing monitoring and early warning system based on time series spectral information analysis, including a grid division module, a microenvironment monitoring module, a difference analysis module, a remote sensing capture module, a rust risk assessment module and an early warning module;

[0006] The grid division module is used to draw the target corn planting field in proportion through computer drawing software, and obtain several groups of plane grid units by combining the grid division function of the computer drawing software and the pre-set grid size and density, and deploy sensors on the obtained several groups of plane grid units;

[0007] The microenvironment monitoring module is used to monitor the changes in the corn growth microenvironment in the plurality of groups of plane grid units in real time according to the influence of rust on the photosynthesis of corn leaves, so as to construct microenvironment data information;

[0008] The difference analysis module is used to construct a microenvironment difference index Xbd in a plurality of groups of plane grid units according to the microenvironment data information, determine the microenvironment difference clustering area in the corn planting field according to the value of the microenvironment difference index Xbd in the plurality of groups of plane grid units, and issue a risk analysis instruction;

[0009] The remote sensing capture module is used to, after receiving the risk analysis instruction, combine the drone remote sensing technology and use the multispectral sensor to capture the spectral reflectance information of corn in the microenvironment difference clustering area in real time, so as to monitor the chlorophyll content level and leaf moisture status in the microenvironment difference clustering area and obtain relevant spectral data information;

[0010] The rust risk assessment module is used to analyze the relevant spectral data information of each time period to construct a multi-spectral fluctuation coefficient Xgp, and to obtain the rust risk assessment index Zpg by fitting by associating it with the microenvironment difference index Xbd and combining it with the trained rust risk assessment model;

[0011] The early warning module is used to pre-set an assessment threshold W, and by comparing and analyzing the rust risk assessment index Zpg with the assessment threshold W, a corresponding level of early warning is obtained according to the degree of rust risk in the current microenvironment difference aggregation area.

[0012] Preferably, the grid division module includes a plane division unit and a deployment unit;

[0013] The plane division unit is used to determine the area and shape of the target corn planting field by drawing in proportion according to the satellite high-definition image of the target corn planting field through computer drawing software, and generate a grid of the two-dimensional model by combining the grid division function of the computer drawing software and the pre-set grid size and density, and obtain a plurality of groups of plane grid units through uniform grid division; wherein the grid size and density are set according to the area size of the target corn planting field, crop growth characteristics and monitoring requirements;

[0014] The deployment unit is used to deploy sensors for the acquired groups of plane grid units. It is required that at least one non-dispersed infrared sensor be deployed at the center of each plane grid unit, and the deployment positions are evenly distributed. The non-dispersed infrared sensor transmits data via wireless communication, and establishes a cloud server for data storage and processing.

[0015] Preferably, the microenvironment monitoring module includes a monitoring unit and a data preprocessing unit;

[0016] The monitoring unit is used to monitor the changes in the corn growth microenvironment in a plurality of groups of plane grid units in real time according to the influence of rust on the photosynthesis of corn leaves, in combination with non-dispersive infrared sensors deployed in a plurality of groups of plane grid units, so as to construct microenvironment data information, wherein the microenvironment data information includes carbon dioxide concentration values ​​Cyt in the corresponding monitoring time periods in the plurality of groups of plane grid units, and features are extracted from the carbon dioxide concentration values ​​Cyt in the corresponding monitoring time periods in the plurality of groups of plane grid units to obtain the minimum carbon dioxide concentration values ​​Cyt in the corresponding monitoring time periods in the plurality of groups of plane grid units. min and the maximum carbon dioxide concentration Cyt max ;

[0017] The data preprocessing unit is used to preprocess the relevant data information in the microenvironment data information, and the preprocessing includes noise removal, missing value filling and data smoothing operations, wherein the missing value filling methods include mean filling, median filling, interpolation filling and regression filling; using dimensionless processing technology, the relevant data information in the disease data set is scaled so that the range of the relevant data information in the microenvironment data information falls between [0,1].

[0018] Preferably, the difference analysis module is used to construct a microenvironment difference index Xbd in a plurality of groups of plane grid units according to the microenvironment data information, and the microenvironment difference index Xbd in the i-th group of plane grid units is i For example, it is obtained in the following way:

[0019]

[0020] In the formula, It is expressed as the maximum carbon dioxide concentration in the i-th group of plane grid cells, It is expressed as the minimum value of carbon dioxide concentration in the i-th group of plane grid cells;

[0021] According to the above, the microenvironment difference index Xbd in the i-th group of plane grid units is obtained i The microenvironment difference index Xbd in several groups of plane grid units is obtained respectively, and the mean value of the microenvironment difference index is calculated according to the statistical mean value algorithm.

[0022] By comparing the microenvironment difference index Xbd in several groups of plane grid cells with the mean Compare the size to get the value above the mean The microenvironment difference index Xbd in the corresponding plane grid unit is calculated, and they are all marked as microenvironment difference aggregation areas. When the microenvironment difference aggregation area exceeds 5% of the total number of plane grid units, a risk analysis instruction is issued through the cloud server.

[0023] Preferably, after receiving the risk analysis instruction issued by the cloud server, the remote sensing capture module combines the drone remote sensing technology and uses the multi-spectral sensor carried by the drone to capture the spectral reflectance information of corn in the microenvironment difference aggregation area in real time, so as to monitor the chlorophyll content level and leaf moisture status in the microenvironment difference aggregation area, and construct relevant spectral data information, which includes the visible light band Bkj and the near-infrared light band Bjh of the corresponding time period.

[0024] Preferably, the rust risk assessment module includes a time series spectrum analysis unit, a model training unit and a rust risk comprehensive assessment unit;

[0025] The time series spectrum analysis unit is used to extract features from the relevant spectrum data information, and obtain the visible light fluctuation coefficient Xkj and the near infrared light fluctuation coefficient Xjh after linear normalization processing. The visible light fluctuation coefficient Xkj and the near infrared light fluctuation coefficient Xjh are obtained by the following formulas respectively;

[0026]

[0027] In the formula, Bkj j Represented as the visible light band of the jth period of the microenvironment difference aggregation area, It is expressed as the mean value of the visible light band in the microenvironment difference clustering area, Bjh j It is represented by the near-infrared light band of the jth period in the microenvironment difference aggregation area, It is represented by the mean value of the near-infrared light band in the microenvironment difference aggregation area, j=1, 2, 3, ..., n, and n represents the monitoring period.

[0028] Preferably, the obtained visible light fluctuation coefficient Xkj and near infrared light fluctuation coefficient Xjh are associated to construct a multi-spectral fluctuation coefficient Xgp, and the multi-spectral fluctuation coefficient Xgp is obtained by the following formula;

[0029]

[0030] Wherein, γ and δ represent the weight values ​​of the visible light fluctuation coefficient Xkj and the near-infrared light fluctuation coefficient Xjh, respectively, and A represents the first correction constant.

[0031] Preferably, the model training unit is used to construct a basic model using convolutional neural network technology, and train and test the basic model with microenvironment data information and related spectral data information, and use the trained basic model as the relevant rust association model, respectively obtain feature information in the relevant rust association model, and use the acquired feature information to train and test the relevant rust association model, and issue a risk analysis instruction in conjunction with the cloud server, and use the trained relevant rust association model as the rust risk assessment model.

[0032] Preferably, the rust risk comprehensive assessment unit is used to associate the multi-spectral fluctuation coefficient Xgp of the microenvironment difference aggregation area with the microenvironment difference index Xbd of the corresponding area, and to obtain the rust risk assessment index Zpg by fitting in combination with the trained rust risk assessment model. The rust risk assessment index Zpg is obtained by the following formula:

[0033]

[0034] In the formula, and σ are both weight values, and B is the second correction constant.

[0035] Preferably, the early warning module is used to pre-set an assessment threshold W, and compare and analyze the rust risk assessment index Zpg with the assessment threshold W, and obtain a corresponding level of early warning according to the degree of rust risk in the current microenvironment difference aggregation area, the specific contents are as follows;

[0036] If the rust risk assessment index Zpg>assessment threshold W, it means that the corn in the current microenvironment difference clustering area is infected with rust, and a first risk warning is generated, and the disease control personnel are notified that the corn in the current area is infected with rust. At the same time, an on-site investigation of the corn in the microenvironment difference clustering area is required to confirm the actual situation and the extent of spread, and remedial measures such as spraying fungicides and fertilizing are taken in the microenvironment difference clustering area to prevent the further spread of rust;

[0037] If the rust risk assessment index Zpg ≤ the assessment threshold W, it means that the corn in the current microenvironment difference clustering area does not suffer from rust, a second risk warning is generated, and the current area is continuously monitored.

[0038] The present invention provides a crop disease remote sensing monitoring and early warning system based on time series spectral information analysis, which has the following beneficial effects:

[0039] (1) By integrating grid division, microenvironment monitoring, difference analysis, remote sensing capture, rust risk assessment and early warning modules, accurate monitoring of corn rust in the south and early dynamic warning of rust are achieved, overcoming the shortcomings of traditional monitoring methods. First, through efficient grid division and sensor deployment, the coverage of corn fields and real-time data collection are ensured, thereby enhancing the frequency and spatial resolution of monitoring. Second, the microenvironment monitoring module combined with difference analysis can timely identify potential risk areas, provide early warnings, and reduce the possibility of disease spread. In addition, the rust risk assessment module targets microenvironment difference clustering areas, combines multispectral data and microenvironment data information, and uses training models for risk fitting, thereby improving the accuracy and reliability of rust risk assessment. In general, this series of improvements effectively identifies rust risk areas, provides timely warning information, and achieves accurate monitoring of corn rust in the south and early dynamic warning of rust. It improves the accuracy and response speed of monitoring, which helps disease control personnel take scientific and effective prevention and control measures to prevent the further spread of rust, thereby increasing corn yields, reducing economic losses and ensuring food security.

[0040] (2) Through precise grid division and sensor deployment, real-time monitoring and data collection of the corn growth microenvironment are achieved, overcoming the problems of insufficient coverage and response delay in traditional monitoring methods. The microenvironment monitoring module uses the carbon dioxide concentration information obtained by the non-dispersive infrared sensor to ensure the accuracy and reliability of the data through feature extraction and data preprocessing. The microenvironment difference index Xbd is obtained to identify the microenvironment difference clustering area. When the microenvironment difference clustering area exceeds 5% of the total number of plane grid units, a risk analysis instruction is issued. This systematic and automated monitoring method can not only identify potential risk areas in a timely manner, provide early warnings, and reduce the possibility of disease spread, but also effectively prevent and reduce the risk of corn rust spread in the south.

[0041] (3) Through the multi-spectral sensors carried by drones and the analysis of time-series spectral information, efficient monitoring and assessment of corn rust in the south was achieved. The advantage of this system is that it can capture the spectral data of the micro-environment difference clustering area in real time, extract the chlorophyll content and leaf moisture status, and then calculate the visible light fluctuation coefficient Xkj and the near-infrared light fluctuation coefficient Xjh, construct the multi-spectral fluctuation coefficient Xgp, and improve the assessment accuracy of disease risk. The rust risk assessment model constructed using convolutional neural networks makes risk prediction more scientific and reliable, and can generate risk warnings in real time to guide disease prevention and control personnel to take timely measures, thereby effectively preventing the further spread of the disease. This systematic monitoring and early warning method solves the problems of slow response and insufficient coverage in traditional methods, and also improves the efficiency of corn rust prevention and control in the south, ensuring food production safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 The present invention is a block diagram of a crop disease remote sensing monitoring and early warning system based on time series spectral information analysis. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Example 1

[0045] See also Figure 1 , the present invention provides a crop disease remote sensing monitoring and early warning system based on time series spectral information analysis, including a grid division module, a microenvironment monitoring module, a difference analysis module, a remote sensing capture module, a rust risk assessment module and an early warning module;

[0046] The grid division module is used to draw the target corn planting field in proportion through computer drawing software, and obtain several groups of plane grid units by combining the grid division function of the computer drawing software and the pre-set grid size and density, and deploy sensors on the obtained several groups of plane grid units;

[0047] The microenvironment monitoring module is used to monitor the changes in the corn growth microenvironment in the plurality of groups of plane grid units in real time according to the influence of rust on the photosynthesis of corn leaves, so as to construct microenvironment data information;

[0048] The difference analysis module is used to construct a microenvironment difference index Xbd in a plurality of groups of plane grid units according to the microenvironment data information, determine the microenvironment difference clustering area in the corn planting field according to the value of the microenvironment difference index Xbd in the plurality of groups of plane grid units, and issue a risk analysis instruction;

[0049] The remote sensing capture module is used to, after receiving the risk analysis instruction, combine the drone remote sensing technology and use the multispectral sensor to capture the spectral reflectance information of corn in the microenvironment difference clustering area in real time, so as to monitor the chlorophyll content level and leaf moisture status in the microenvironment difference clustering area and obtain relevant spectral data information;

[0050] The rust risk assessment module is used to analyze the relevant spectral data information of each time period to construct a multi-spectral fluctuation coefficient Xgp, and to obtain the rust risk assessment index Zpg by fitting by associating it with the microenvironment difference index Xbd and combining it with the trained rust risk assessment model;

[0051] The early warning module is used to pre-set an assessment threshold W, and by comparing and analyzing the rust risk assessment index Zpg with the assessment threshold W, a corresponding level of early warning is obtained according to the degree of rust risk in the current microenvironment difference aggregation area.

[0052] In this embodiment, accurate monitoring of corn rust in the south and early dynamic warning of rust are achieved through the comprehensive application of multiple modules. First, the grid division module ensures the refined monitoring of the planting field, so that the microenvironment changes in each area can be captured in real time, enhancing the accuracy of the data. The microenvironment monitoring module tracks key growth parameters in real time, including the carbon dioxide concentration value Cyt, which helps to timely identify the health status of crops. The difference analysis module can quickly identify potential disease risk areas by constructing the microenvironment difference index Xbd, issue risk analysis instructions, and ensure rapid response. Subsequently, the remote sensing capture module uses drones and multispectral The sensor monitors spectral reflectance information in real time, providing important data on chlorophyll content and moisture conditions, laying the foundation for subsequent risk assessment. The rust risk assessment module combines the microenvironment difference index Xbd with multi-spectral data to generate a rust risk assessment index Zpg, which can provide clear early warning information by comparing it with the set threshold. This series of measures not only enables disease control personnel to take effective prevention and control measures in a timely manner to reduce economic losses, but also improves the scientific and intelligent level of monitoring and early warning of corn rust in the south, especially in the context of climate change and frequent diseases, showing important practical application value.

[0053] Example 2

[0054] Please refer to Figure 1 ,Specifically: the grid division module includes a plane division unit and a deployment unit;

[0055] The plane division unit is used to determine the area and shape of the target corn planting field by drawing in proportion according to the satellite high-definition image of the target corn planting field through computer drawing software, and generate a grid of the two-dimensional model by combining the grid division function of the computer drawing software and the pre-set grid size and density, and obtain a plurality of groups of plane grid units through uniform grid division; wherein the grid size and density are set according to the area size of the target corn planting field, crop growth characteristics and monitoring requirements;

[0056] The deployment unit is used to deploy sensors for the acquired groups of plane grid units. It is required that at least one non-dispersed infrared sensor be deployed at the center of each plane grid unit, and the deployment positions are evenly distributed. The non-dispersed infrared sensor transmits data via wireless communication, and establishes a cloud server for data storage and processing.

[0057] The microenvironment monitoring module includes a monitoring unit and a data preprocessing unit;

[0058] Specifically, the monitoring unit is used to monitor the changes in the corn growth microenvironment in a plurality of groups of plane grid units in real time according to the impact of rust on the photosynthesis of corn leaves, in combination with non-dispersive infrared sensors deployed in a plurality of groups of plane grid units, so as to construct microenvironment data information, wherein the microenvironment data information includes carbon dioxide concentration values ​​Cyt in the corresponding monitoring period in the plurality of groups of plane grid units, and features are extracted from the carbon dioxide concentration values ​​Cyt in the corresponding monitoring period in the plurality of groups of plane grid units to obtain the minimum carbon dioxide concentration values ​​Cyt in the corresponding monitoring period in the plurality of groups of plane grid units. min and the maximum carbon dioxide concentration Cyt max ;

[0059] It should be noted that the microenvironment in which corn is located refers to the environmental conditions in a small range, including temperature, humidity, light, soil properties and gas concentrations. These factors will be different from the surrounding environment in a smaller space. In particular, the difference in carbon dioxide concentration in the microenvironment in which corn is located can reflect the rust situation of corn, because carbon dioxide is an important raw material for plant photosynthesis. Healthy corn plants absorb carbon dioxide and release oxygen during photosynthesis, while rust infection can cause leaf damage and reduce photosynthesis efficiency, thereby reducing the absorption of carbon dioxide. As the disease worsens, the metabolic activity of the plant is severely inhibited. Therefore, monitoring the difference in carbon dioxide concentration can provide early warning signals, help identify potential rust risks, and provide a basis for timely prevention and control measures.

[0060] The data preprocessing unit is used to preprocess the relevant data information in the microenvironment data information, and the preprocessing includes noise removal, missing value filling and data smoothing operations, wherein the missing value filling methods include mean filling, median filling, interpolation filling and regression filling; using dimensionless processing technology, the relevant data information in the disease data set is scaled so that the range of the relevant data information in the microenvironment data information falls between [0,1].

[0061] In this embodiment, the plane division unit uses high-definition satellite images and computer drawing software to generate a uniform and reasonable two-dimensional grid model according to the actual situation of the target planting field, thereby ensuring that each plane grid unit can cover the growth characteristics and health status of the crop. The deployment unit ensures that at least one non-dispersive infrared sensor is configured in each grid, ensuring the comprehensiveness and uniformity of data collection. The microenvironment monitoring module provides important information on crop photosynthesis and growth status by real-time tracking of the carbon dioxide concentration value Cyt in the microenvironment data information, which is crucial for timely discovery of potential risks of rust. In addition, the data preprocessing unit ensures the accuracy and reliability of monitoring data by removing noise and filling missing values, and improves the scientific nature of subsequent analysis. Through these means, not only can the health status of crops be effectively monitored, but also the disease risk can be quickly identified and responded to, providing scientific and accurate decision-making support for disease prevention and control personnel. This efficient monitoring and early warning mechanism reduces the common labor costs and information lag problems in traditional monitoring methods, making crop disease prevention and control more intelligent and systematic, thereby improving the yield and quality of corn and protecting the economic interests of farmers.

[0062] Example 3

[0063] Please refer to Figure 1 Specifically: the difference analysis module is used to construct a microenvironment difference index Xbd in a plurality of groups of plane grid units according to the microenvironment data information, and the microenvironment difference index Xbd in the i-th group of plane grid units i For example, it is obtained in the following way:

[0064]

[0065] In the formula, It is expressed as the maximum carbon dioxide concentration in the i-th group of plane grid cells, It is expressed as the minimum carbon dioxide concentration in the i-th group of plane grid cells;

[0066] According to the above, the microenvironment difference index Xbd in the i-th group of plane grid units is obtained i The microenvironment difference index Xbd in several groups of plane grid units is obtained respectively, and the mean value of the microenvironment difference index is calculated according to the statistical mean algorithm.

[0067] By comparing the microenvironment difference index Xbd in several groups of plane grid cells with the mean Compare the size to get the value above the mean The microenvironment difference index Xbd in the corresponding plane grid unit is calculated, and they are all marked as microenvironment difference aggregation areas. When the microenvironment difference aggregation area exceeds 5% of the total number of plane grid units, a risk analysis instruction is issued through the cloud server.

[0068] In this embodiment, through in-depth analysis of microenvironmental data information, a microenvironmental difference index Xbd within a plane grid unit is constructed, thereby achieving accurate monitoring of crop growth status. Specifically, by calculating the difference in carbon dioxide concentration within each plane grid unit, the microenvironmental difference index Xbd is obtained, and the mean value of the microenvironmental difference index is further obtained. This process enables the system to identify which plane grid units' microenvironmental conditions deviate from the mean, thereby marking the areas where microenvironmental differences are concentrated. When the areas where microenvironmental differences are concentrated exceed 5% of the total number of plane grid units, a risk analysis instruction will be automatically issued. This process not only improves the ability to warn of potential risks of disease occurrence, but this systematic and automated monitoring method can not only identify potential risk areas in a timely manner, provide early warnings, and reduce the possibility of disease spread, but also effectively prevent and reduce the risk of the spread of corn rust in the south.

[0069] Example 4

[0070] Please refer to Figure 1 Specifically: after receiving the risk analysis instruction issued by the cloud server, the remote sensing capture module combines the drone remote sensing technology and uses the multi-spectral sensor carried by the drone to capture the spectral reflectance information of corn in the micro-environment difference aggregation area in real time, so as to monitor the chlorophyll content level and leaf moisture status in the micro-environment difference aggregation area, and construct relevant spectral data information, which includes the visible light band Bkj and the near-infrared light band Bjh in the corresponding time period.

[0071] In this embodiment, by combining UAV remote sensing technology with multi-spectral sensors, the spectral reflectance information of corn in the micro-environment difference clustering area can be obtained efficiently and in real time, especially the monitoring of chlorophyll content and leaf moisture status. This precise data collection not only improves the ability to evaluate the impact of rust on the health of corn, but also can timely identify potential growth problems. By obtaining the visible light band Bkj and near-infrared light band Bjh in a specific period of time, disease control personnel can make more accurate decisions based on scientific data. This real-time monitoring method effectively supplements the deficiencies of traditional monitoring methods, reduces labor costs and time consumption, and at the same time enhances the monitoring ability of the impact of rust on the health of corn.

[0072] Example 5

[0073] Please refer to Figure 1,Specifically: the rust risk assessment module includes a time series spectrum analysis unit, a model training unit and a rust risk comprehensive assessment unit;

[0074] The time series spectrum analysis unit is used to extract features from the relevant spectrum data information, and obtain the visible light fluctuation coefficient Xkj and the near infrared light fluctuation coefficient Xjh after linear normalization processing. The visible light fluctuation coefficient Xkj and the near infrared light fluctuation coefficient Xjh are obtained by the following formulas respectively;

[0075]

[0076] In the formula, Bkj j Represented as the visible light band of the jth period of the microenvironment difference aggregation area, It is expressed as the mean value of the visible light band in the microenvironment difference clustering area, Bjh j It is represented by the near-infrared light band of the jth period in the microenvironment difference aggregation area, It is represented by the mean value of the near-infrared light band in the microenvironment difference aggregation area, j=1, 2, 3, ..., n, and n represents the monitoring period.

[0077] Specifically, the obtained visible light fluctuation coefficient Xkj and near infrared light fluctuation coefficient Xjh are associated to construct a multi-spectral fluctuation coefficient Xgp, and the multi-spectral fluctuation coefficient Xgp is obtained by the following formula;

[0078]

[0079] Wherein, γ and δ represent the weight values ​​of the visible light fluctuation coefficient Xkj and the near-infrared light fluctuation coefficient Xjh, respectively, and A represents the first correction constant.

[0080] Specifically, the model training unit is used to construct a basic model using convolutional neural network technology, and train and test the basic model with microenvironment data information and related spectral data information, and use the trained basic model as the related rust association model, respectively obtain feature information in the related rust association model, and use the acquired feature information to train and test the related rust association model, and issue a risk analysis instruction in conjunction with the cloud server, and use the trained related rust association model as the rust risk assessment model.

[0081] Specifically, the rust risk comprehensive assessment unit is used to associate the multi-spectral fluctuation coefficient Xgp of the microenvironment difference aggregation area with the microenvironment difference index Xbd of the corresponding area, and to obtain the rust risk assessment index Zpg by fitting in combination with the trained rust risk assessment model. The rust risk assessment index Zpg is obtained by the following formula:

[0082]

[0083] In the formula, and σ are both weight values, and B is the second correction constant.

[0084] In this embodiment, the monitoring and early warning capabilities of corn rust are improved through the synergistic effect of the three units of time series spectral analysis, model training and comprehensive evaluation. First, the time series spectral analysis unit extracts features from relevant spectral data to obtain the visible light fluctuation coefficient Xkj and the near-infrared light fluctuation coefficient Xjh, thereby capturing the chlorophyll content level and leaf moisture status in the microenvironment difference clustering area. This precise data processing enables the timely identification of potential disease risks and provides a data basis for subsequent decision-making. Then, the model training unit uses convolutional neural network technology to construct a rust association model, combining microenvironment data and spectral information for in-depth analysis, which not only The prediction accuracy of the model is improved and its adaptability is stronger. Finally, the comprehensive rust risk assessment unit combines the multi-spectral fluctuation coefficient Xgp with the microenvironment difference index Xbd of the corresponding area, and fits a more reliable rust risk assessment index Zpg through scientific weight distribution and correction. This comprehensive assessment method can not only provide real-time risk analysis instructions and help disease control personnel take prevention and control measures in time, but also effectively reduce the economic losses caused by diseases and realize refined agricultural management. In summary, the implementation of this process has enhanced the early warning and response capabilities for crop diseases such as rust, and promoted the sustainable development of agricultural production and the increase of benefits.

[0085] Example 6

[0086] Please refer to Figure 1 Specifically: the early warning module is used to pre-set an evaluation threshold W, and compare and analyze the rust risk assessment index Zpg with the evaluation threshold W, and obtain a corresponding level of early warning according to the degree of rust risk in the current microenvironment difference clustering area. The specific contents are as follows;

[0087] If the rust risk assessment index Zpg>assessment threshold W, it means that the corn in the current microenvironment difference clustering area is infected with rust, and a first risk warning is generated, and the disease control personnel are notified that the corn in the current area is infected with rust. At the same time, an on-site investigation of the corn in the microenvironment difference clustering area is required to confirm the actual situation and the extent of spread, and remedial measures such as spraying fungicides and fertilizing are taken in the microenvironment difference clustering area to prevent the further spread of rust;

[0088] If the rust risk assessment index Zpg ≤ the assessment threshold W, it means that the corn in the current microenvironment difference clustering area does not suffer from rust, a second risk warning is generated, and the current area is continuously monitored.

[0089] In this embodiment, an assessment threshold W is set in advance. By comparing and analyzing the rust risk assessment index Zpg with the assessment threshold W, the real-time response capability and accuracy of the rust warning are enhanced. When the rust risk assessment index Zpg exceeds the assessment threshold W, the system immediately generates a first risk warning and promptly notifies the disease control personnel, thereby prompting them to take quick remedial measures, effectively preventing the further spread of rust and reducing potential economic losses. When the rust risk assessment index Zpg does not exceed the assessment threshold W, the system generates a second risk warning to ensure continuous monitoring and provide safety protection. This dual warning mechanism not only improves the efficiency of monitoring the health status of corn crops, but also provides a scientific basis for disease control personnel, helping to formulate more reasonable disease prevention and control strategies, and ultimately achieving higher agricultural output and quality.

[0090] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A crop disease remote sensing monitoring and early warning system based on time series spectral information analysis, characterized in that: It includes grid division module, microenvironment monitoring module, difference analysis module, remote sensing capture module, rust risk assessment module and early warning module; The grid division module is used to draw the target corn planting field in proportion through computer drawing software, and obtain several groups of plane grid units by combining the grid division function of the computer drawing software and the pre-set grid size and density, and deploy sensors on the obtained several groups of plane grid units; The microenvironment monitoring module is used to monitor the changes in the corn growth microenvironment in the plurality of groups of plane grid units in real time according to the influence of rust on the photosynthesis of corn leaves, so as to construct microenvironment data information; The difference analysis module is used to construct a microenvironment difference index Xbd in a plurality of groups of plane grid units according to the microenvironment data information, determine the microenvironment difference clustering area in the corn planting field according to the value of the microenvironment difference index Xbd in the plurality of groups of plane grid units, and issue a risk analysis instruction; The remote sensing capture module is used to, after receiving the risk analysis instruction, combine the drone remote sensing technology and use the multispectral sensor to capture the spectral reflectance information of corn in the microenvironment difference clustering area in real time, so as to monitor the chlorophyll content level and leaf moisture status in the microenvironment difference clustering area and obtain relevant spectral data information; The rust risk assessment module is used to analyze the relevant spectral data information of each time period to construct a multi-spectral fluctuation coefficient Xgp, and to obtain the rust risk assessment index Zpg by fitting by associating it with the microenvironment difference index Xbd and combining it with the trained rust risk assessment model; The early warning module is used to pre-set an assessment threshold W, and by comparing and analyzing the rust risk assessment index Zpg with the assessment threshold W, a corresponding level of early warning is obtained according to the degree of rust risk in the current microenvironment difference aggregation area.

2. The crop disease remote sensing monitoring and early warning system based on time series spectral information analysis according to claim 1 is characterized by: The grid division module includes a plane division unit and a deployment unit; The plane division unit is used to determine the area and shape of the target corn planting field by drawing in proportion according to the satellite high-definition image of the target corn planting field through computer drawing software, and generate a grid of the two-dimensional model by combining the grid division function of the computer drawing software and the pre-set grid size and density, and obtain a plurality of groups of plane grid units through uniform grid division; wherein the grid size and density are set according to the area size of the target corn planting field, crop growth characteristics and monitoring requirements; The deployment unit is used to deploy sensors for the acquired groups of plane grid units. It is required that at least one non-dispersed infrared sensor be deployed at the center of each plane grid unit, and the deployment positions are evenly distributed. The non-dispersed infrared sensor transmits data via wireless communication, and establishes a cloud server for data storage and processing.

3. The crop disease remote sensing monitoring and early warning system based on time series spectral information analysis according to claim 2 is characterized by: The microenvironment monitoring module includes a monitoring unit and a data preprocessing unit; The monitoring unit is used to monitor the changes in the corn growth microenvironment in a plurality of groups of plane grid units in real time according to the influence of rust on the photosynthesis of corn leaves, in combination with non-dispersive infrared sensors deployed in a plurality of groups of plane grid units, so as to construct microenvironment data information, wherein the microenvironment data information includes carbon dioxide concentration values ​​Cyt in the corresponding monitoring time periods in the plurality of groups of plane grid units, and features are extracted from the carbon dioxide concentration values ​​Cyt in the corresponding monitoring time periods in the plurality of groups of plane grid units to obtain the minimum carbon dioxide concentration values ​​Cyt in the corresponding monitoring time periods in the plurality of groups of plane grid units. min and the maximum carbon dioxide concentration Cyt max ; The data preprocessing unit is used to preprocess the relevant data information in the microenvironment data information, and the preprocessing includes noise removal, missing value filling and data smoothing operations, wherein the missing value filling methods include mean filling, median filling, interpolation filling and regression filling; using dimensionless processing technology, the relevant data information in the disease data set is scaled so that the range of the relevant data information in the microenvironment data information falls between [0,1].

4. The crop disease remote sensing monitoring and early warning system based on time series spectral information analysis according to claim 3 is characterized by: The difference analysis module is used to construct a microenvironment difference index Xbd in a plurality of groups of plane grid units according to the microenvironment data information, and the microenvironment difference index Xbd in the i-th group of plane grid units is used as the i For example, it is obtained in the following way: In the formula, It is expressed as the maximum carbon dioxide concentration in the i-th group of plane grid cells, It is expressed as the minimum carbon dioxide concentration in the i-th group of plane grid cells; According to the above, the microenvironment difference index Xbd in the i-th group of plane grid units is obtained i The microenvironment difference index Xbd in several groups of plane grid units is obtained respectively, and the mean value of the microenvironment difference index is calculated according to the statistical mean value algorithm. By comparing the microenvironment difference index Xbd in several groups of plane grid cells with the mean Compare the size to get the value above the mean The microenvironment difference index Xbd in the corresponding plane grid unit is calculated, and they are all marked as microenvironment difference aggregation areas. When the microenvironment difference aggregation area exceeds 5% of the total number of plane grid units, a risk analysis instruction is issued through the cloud server.

5. The crop disease remote sensing monitoring and early warning system based on time series spectral information analysis according to claim 4 is characterized in that: After receiving the risk analysis instruction issued by the cloud server, the remote sensing capture module combines the drone remote sensing technology and uses the multi-spectral sensor carried by the drone to capture the spectral reflectance information of corn in the micro-environment difference aggregation area in real time, so as to monitor the chlorophyll content level and leaf moisture status in the micro-environment difference aggregation area, and construct relevant spectral data information, which includes the visible light band Bkj and the near-infrared light band Bjh of the corresponding time period.

6. The crop disease remote sensing monitoring and early warning system based on time series spectral information analysis according to claim 5 is characterized by: The rust risk assessment module includes a time series spectrum analysis unit, a model training unit and a rust risk comprehensive assessment unit; The time series spectrum analysis unit is used to extract features from the relevant spectrum data information, and obtain the visible light fluctuation coefficient Xkj and the near infrared light fluctuation coefficient Xjh after linear normalization processing. The visible light fluctuation coefficient Xkj and the near infrared light fluctuation coefficient Xjh are obtained by the following formulas respectively; In the formula, Bkj j Represented as the visible light band of the jth period of the microenvironment difference aggregation area, It is expressed as the mean value of the visible light band in the microenvironment difference clustering area, Bjh j It is represented by the near-infrared light band of the jth period in the microenvironment difference aggregation area, It is represented by the mean value of the near-infrared light band in the microenvironment difference aggregation area, j=1, 2, 3, ..., n, and n represents the monitoring period.

7. The crop disease remote sensing monitoring and early warning system based on time series spectral information analysis according to claim 6 is characterized by: The obtained visible light fluctuation coefficient Xkj and near infrared light fluctuation coefficient Xjh are associated to construct a multi-spectral fluctuation coefficient Xgp, and the multi-spectral fluctuation coefficient Xgp is obtained by the following formula; Wherein, γ and δ represent the weight values ​​of the visible light fluctuation coefficient Xkj and the near-infrared light fluctuation coefficient Xjh, respectively, and A represents the first correction constant.

8. The crop disease remote sensing monitoring and early warning system based on time series spectral information analysis according to claim 6 is characterized by: The model training unit is used to construct a basic model using convolutional neural network technology, and train and test the basic model with microenvironment data information and related spectral data information, and use the trained basic model as a related rust association model, respectively obtain feature information in the related rust association model, and train and test the related rust association model with the acquired feature information, and issue a risk analysis instruction in conjunction with the cloud server, and use the trained related rust association model as a rust risk assessment model.

9. The crop disease remote sensing monitoring and early warning system based on time series spectral information analysis according to claim 6, characterized in that: The rust risk comprehensive assessment unit is used to associate the multi-spectral fluctuation coefficient Xgp of the microenvironment difference aggregation area with the microenvironment difference index Xbd of the corresponding area, and to obtain the rust risk assessment index Zpg by fitting in combination with the trained rust risk assessment model. The rust risk assessment index Zpg is obtained by the following formula; In the formula, and σ are both weight values, and B is the second correction constant.

10. The crop disease remote sensing monitoring and early warning system based on time series spectral information analysis according to claim 9, characterized in that: The early warning module is used to pre-set an assessment threshold W, and compare and analyze the rust risk assessment index Zpg with the assessment threshold W, and obtain a corresponding level of early warning according to the degree of rust risk in the current microenvironment difference clustering area. The specific contents are as follows; If the rust risk assessment index Zpg>assessment threshold W, it means that the corn in the current microenvironment difference clustering area is infected with rust, and a first risk warning is generated, and the disease control personnel are notified that the corn in the current area is infected with rust. At the same time, an on-site investigation of the corn in the microenvironment difference clustering area is required to confirm the actual situation and the extent of spread, and remedial measures such as spraying fungicides and fertilizing are taken in the microenvironment difference clustering area to prevent the further spread of rust; If the rust risk assessment index Zpg ≤ the assessment threshold W, it means that the corn in the current microenvironment difference clustering area does not suffer from rust, a second risk warning is generated, and the current area is continuously monitored.

Images