A rice bacterial blight monitoring method and system based on multi-source data analysis

Abstract

The present invention discloses a rice bacterial blight monitoring method and system based on multi-source data analysis. The proposed rice bacterial blight monitoring method analyzes multi-source data using a principal factor analysis method to analyze the weight of each influencing factor data on the incidence rate or disease index, thereby screening out the main influencing factors that cause the onset of rice bacterial blight. A monitoring strategy is generated based on the size of the influence weight value. By setting up monitoring units, a real-time monitoring strategy is implemented for the main influencing factors, and an intermittent monitoring strategy is implemented for minor or irrelevant influencing factors. This allows for purposeful and efficient monitoring of the spread trend of rice bacterial blight, facilitating timely implementation of corresponding prevention and control measures for the main influencing factors that cause rice bacterial blight, thereby effectively curbing the rapid spread of rice bacterial blight within rice fields.

Description

Technical Field

[0001] The present invention relates to the technical field of rice bacterial blight monitoring, and in particular to a rice bacterial blight monitoring method and system based on multi-source data analysis. Background Art

[0002] Bacterial leaf blight is one of the three major rice diseases, caused by a pathogenic variant of Xanthomonas oryzae. In indica rice, it manifests as initially yellow or yellow-green spots on the tips and edges of affected leaves, while in japonica rice, it appears gray-green to off-white. Although visible to the naked eye, bacterial leaf blight can cause significant damage to rice leaves when symptoms become apparent, making early detection and prevention crucial for healthy rice growth. Causes of bacterial leaf blight include: 1) poor resistance of the rice variety; 2) rainy and humid weather; 3) high rice density and poor air permeability in rice fields; 4) excessive water depth in rice fields; 5) seed contamination; and 6) residual pathogenic bacteria in previously infected fields.

[0003] Currently, existing technologies mostly use hyperspectral imaging technology to obtain spectral information from rice canopies and leaves, and then monitor rice bacterial blight through spectral analysis. However, since rice bacterial blight has multiple causes, these methods can monitor whether rice is diseased, but they cannot determine the specific cause, making it difficult to implement corresponding prevention and control measures. To address this issue, we propose a method and system for monitoring rice bacterial blight based on multi-source data analysis. Summary of the Invention

[0004] The main purpose of the present invention is to provide a rice bacterial blight monitoring method and system based on multi-source data analysis, which can effectively solve the problems in the background technology.

[0005] To achieve the above object, the technical solution adopted by the present invention is:

[0006] A method for monitoring rice bacterial blight based on multi-source data analysis comprises the following steps:

[0007] Step 1: Select paddy fields with different degrees of damage as sampling objects, use the 5-point sampling method to sample and test each sampling object, record the total number of sampled leaves, the number of diseased leaves and the severity data, and calculate the incidence rate and disease index of the sampling object, where:

[0008] Incidence rate (%) = (number of diseased leaves / total number of leaves) × 100%

[0009] Disease index = [∑(number of diseased leaves at each level × representative value of each level) / (total number of leaves × highest representative value)] × 100;

[0010] Step 2: Collect data on influencing factors of the sampled objects during the disease period, including variety disease resistance evaluation data, total precipitation during the disease period, field planting density, rice field water volume, seed bacterial content, and bacterial residue in the rice field;

[0011] Step 3: Using the principal factor analysis method, analyze the influence weight of each influencing factor data on the incidence rate or disease index;

[0012] Step 4: Determine the impact weight values ​​of the morbidity rate and disease index of the sampled objects based on the analysis results of step 3, generate a monitoring strategy based on the size of the impact weight values, and execute the monitoring strategy by setting a monitoring unit;

[0013] The specific steps of step three include:

[0014] Step 31) The data set sequence of the incidence rate and disease index of the sampled subjects is used as the parent sequence E, and the data set sequence of the various influencing factors of the sampled subjects during the disease period is used as the subsequence F. Its structural expression is:

[0015] E={E1,E2}

[0016] F={F1,F2,F3,F4,F5,F6}

[0017] Where, E1 and E2 are the data sets of the incidence rate and disease index of the sampled objects, respectively; F1, F2, F3, F4, F5, and F6 are the data sets of the disease resistance evaluation data of the varieties of the sampled objects during the disease period, the total precipitation during the disease period, the field planting density, the amount of water accumulated in the rice field, the bacterial content of the seeds, and the bacterial residue in the rice field, respectively;

[0018] Step 32) Use the mean method to perform dimensionless operation on the data in the parent sequence E and the child sequence F. The calculation formula is:

[0019]

[0020]

[0021] Where, E ik , F jk are the data numbers of each factor in the parent sequence E and the child sequence F respectively; n and m are the data amounts of each factor; mean() is the average value operation;

[0022] Step 33) Calculate the correlation coefficient ζ between each factor data point in the subsequence F and the index in the parent sequence E respectively jk , and its calculation formula is:

[0023]

[0024] Δmin=mini (min k (|E ik -F jk |))

[0025] Δmax=max i (max k (|E ik -F jk |))

[0026] Where min i (min k ()) is the first subsequence factor |E ik -F jk | minimum value, taking the minimum value of all factors; max i (max k ()) is the first subsequence factor |E ik -F jk The maximum value of | is taken when all factors are maximized; ρ is the discrimination coefficient, which is a constant between 0 and 1;

[0027] Step 34) Calculate the correlation degree R between each factor data in the parent sequence E and each factor data in the child sequence F ij , and its calculation formula is:

[0028]

[0029] Furthermore, the disease grading standard in the disease index is:

[0030] Level 0: no disease;

[0031] Level 1: The lesion area is less than 1 / 5 of the leaf area;

[0032] Level 2: The lesion area is less than 1 / 3 of the leaf area;

[0033] Level 3: The lesion area is less than 1 / 2 of the leaf area;

[0034] Level 4: The lesion area is more than 3 / 5 of the leaf area.

[0035] Furthermore, the specific steps of step four are as follows:

[0036] Step 41), obtain the correlation degree R ij After the value of ij Create a sample set with the value of , and obtain the mean and standard deviation in the sample set;

[0037] Step 42) Standardize the data using mean and standard deviation. The standardization formula is: In this formula, z is the standard parameter, σ is the variance of the sample data, and μ is the mean of the sample data.

[0038] Step 43), after completing the standardization, the standard parameters are used Adjust the numerical interval to [0,1] and use the function value of f(k) to classify the coincidence rate. The classification mechanism is:

[0039] when When , the degree of association is classified as level one;

[0040] when When , the degree of association is classified as level 2;

[0041] Among them, f(k)min and f(k)max are the minimum and maximum values ​​of the function value of f(k) respectively.

[0042] Further, when the association degree is classified as level one, a real-time monitoring strategy is generated, and the monitoring unit executes the real-time monitoring strategy;

[0043] When the association degree is classified as level 2, an intermittent monitoring strategy is generated, and the monitoring unit executes the intermittent monitoring strategy.

[0044] A rice bacterial blight monitoring system based on multi-source data analysis, comprising:

[0045] Leaf sampling module, used to sample and test rice fields with different degrees of damage, obtain the total number of sampled leaves, the number of diseased leaves and the severity data, and calculate the incidence rate and disease index of the rice fields;

[0046] A monitoring unit, which is used to implement the monitoring strategy, including: a variety disease resistance assessment module, a total precipitation measurement module during the disease period, a field planting density measurement module, a rice field water volume measurement module, a seed bacterial content measurement module, and a rice field bacterial residue measurement module;

[0047] The variety disease resistance evaluation module is used to quantitatively evaluate the rice seed resistance to bacterial blight and obtain variety disease resistance evaluation data;

[0048] The total amount of precipitation during the disease period measurement module is used to measure the total amount of water in the rice field during the disease period and obtain the total amount of precipitation data in the rice field during the disease period;

[0049] The field planting density value measurement module is used to measure the field planting density of the rice field and obtain the field planting density value data of the rice field during the disease period;

[0050] The paddy field water accumulation measurement module is used to measure the paddy field water accumulation in the paddy field and obtain paddy field water accumulation data during the disease period;

[0051] The seed bacterial content measurement module is used to measure the seed bacterial content and obtain bacterial content data of diseased rice field seeds;

[0052] The rice field bacterial residue measurement module is used to measure the bacterial residue in the old diseased area of ​​the rice field and obtain the rice field bacterial residue data during the disease period;

[0053] The data analysis module is used to analyze the influence weights of the data of various influencing factors on the incidence of rice field leaf blight on the incidence rate or disease index, and obtain the influence weight values ​​of various influencing factors on the incidence rate and disease index of rice field leaf blight;

[0054] The monitoring control module is in communication with the data analysis module, and is used to receive the analysis results of the influence weight values ​​of various influencing factors on the incidence rate and disease index of rice field leaf blight, and generate a monitoring strategy based on the analysis results.

[0055] Furthermore, the variety disease resistance evaluation module, the total precipitation measurement module during the disease period, the field planting density value measurement module, the rice field water accumulation measurement module, the seed bacteria content measurement module and the rice field bacterial residue measurement module are all communicatively connected to the monitoring and control module.

[0056] Furthermore, in response to the monitoring strategy generated by the monitoring control module, the variety disease resistance evaluation module, the total precipitation measurement module during the disease period, the field planting density value measurement module, the rice field water accumulation measurement module, the seed bacteria content measurement module and the rice field bacterial residue measurement module respectively execute corresponding monitoring strategies.

[0057] Furthermore, the system includes a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0058] Furthermore, the system is specifically implemented as follows:

[0059] Step 1) When bacterial blight is found in rice fields in a certain area, the leaf sampling module is used to sample and test rice fields with different degrees of damage, obtain the total number of sampled leaves, the number of diseased leaves and the severity data, and calculate the incidence rate and disease index of the rice fields;

[0060] Step 2) Collect data on influencing factors of the sampling objects during the disease period through the variety disease resistance evaluation module, the total precipitation measurement module during the disease period, the field planting density value measurement module, the paddy field water volume measurement module, the seed bacterial content measurement module, and the paddy field bacterial residue measurement module, including variety disease resistance evaluation data, total precipitation during the disease period, field planting density value, paddy field water volume, seed bacterial content, paddy field bacterial residue and other data;

[0061] Step 3) analyzing the influence weights of the data of various influencing factors of the incidence of rice field leaf blight on the incidence rate or disease index through a data analysis module to obtain the influence weight values ​​of the various influencing factors on the incidence rate and disease index of rice field leaf blight;

[0062] Step 4) receiving, through the monitoring and control module, analysis results of the influence weight values ​​of various influencing factors on the incidence rate and disease index of rice field leaf blight, and generating a monitoring strategy based on the analysis results;

[0063] Step 5) In response to the monitoring strategy generated by the monitoring control module, the modules corresponding to the impact weight values ​​in descending order respectively execute the real-time monitoring strategy or the intermittent monitoring strategy.

[0064] The present invention has the following beneficial effects:

[0065] (1) Compared with the prior art, the technical solution of the present invention proposes a method for monitoring rice bacterial blight, which analyzes multi-source data and adopts a principal factor analysis method to analyze the influence weight of each influencing factor data on the incidence rate or disease index, thereby screening out the main influencing factors causing the onset of rice bacterial blight, and generating a monitoring strategy according to the size of the influence weight value. By setting a monitoring unit, a real-time monitoring strategy is implemented for the main influencing factors, and an intermittent monitoring strategy is implemented for the secondary or irrelevant influencing factors, thereby purposefully and efficiently realizing the monitoring of the spread trend of rice bacterial blight, facilitating timely taking corresponding prevention and control measures for the main influencing factors causing rice bacterial blight, thereby effectively curbing the rapid spread of rice bacterial blight in rice fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 Schematic diagram of a flow chart of a method for monitoring rice bacterial blight based on multi-source data analysis according to the present invention;

[0067] Figure 2 The diagram is a structural diagram of a rice bacterial blight monitoring system based on multi-source data analysis according to the present invention. DETAILED DESCRIPTION

[0068] The present invention will be further described below in conjunction with specific embodiments. The accompanying drawings are for illustrative purposes only and represent only schematic diagrams rather than actual drawings. They should not be understood as limiting the present invention. In order to better illustrate the specific embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0069] Example 1

[0070] like Figure 1-2As shown, a rice bacterial blight monitoring method based on multi-source data analysis includes the following steps:

[0071] Step 1: Select paddy fields with different degrees of damage as sampling objects, use the 5-point sampling method to sample and test each sampling object, record the total number of sampled leaves, the number of diseased leaves and the severity data, and calculate the incidence rate and disease index of the sampling object;

[0072] Step 2: Collect data on influencing factors of the sampled objects during the disease period, including variety disease resistance evaluation data, total precipitation during the disease period, field planting density, rice field water volume, seed bacterial content, and bacterial residue in the rice field;

[0073] Step 3: Use the principal factor analysis method to analyze the influence weight of each influencing factor data on the incidence rate or disease index;

[0074] Step 4: Determine the impact weight value of the morbidity rate and disease index of the sampled objects based on the analysis results of step 3, generate a monitoring strategy based on the size of the impact weight value, and execute the monitoring strategy by setting the monitoring unit.

[0075] A rice bacterial blight monitoring system based on multi-source data analysis, comprising:

[0076] Leaf sampling module, used to sample and test rice fields with different degrees of damage, obtain the total number of sampled leaves, the number of diseased leaves and the severity data, and calculate the incidence rate and disease index of the rice fields;

[0077] The monitoring unit is used to implement the monitoring strategy, including: variety disease resistance assessment module, total precipitation measurement module during the disease period, field planting density value measurement module, rice field water volume measurement module, seed bacterial content measurement module, and rice field bacterial residue measurement module;

[0078] The variety disease resistance evaluation module is used to quantitatively evaluate the resistance of rice seeds to bacterial blight and obtain variety disease resistance evaluation data;

[0079] The total amount of precipitation during the disease period measurement module is used to measure the total amount of water in the rice field during the disease period and obtain the total amount of precipitation data in the rice field during the disease period;

[0080] The field planting density value measurement module is used to measure the field planting density of the rice field and obtain the field planting density value data of the rice field during the disease period;

[0081] The paddy field water accumulation measurement module is used to measure the paddy field water accumulation in the paddy field and obtain the paddy field water accumulation data during the disease period;

[0082] The seed bacterial content measurement module is used to measure the seed bacterial content and obtain the bacterial content data of diseased rice field seeds;

[0083] The rice field bacterial residue measurement module is used to measure the bacterial residue in the old diseased area of ​​the rice field and obtain the data of the bacterial residue in the rice field during the disease period;

[0084] The data analysis module is used to analyze the influence weights of the data of various influencing factors on the incidence of rice field leaf blight on the incidence rate or disease index, and obtain the influence weight values ​​of various influencing factors on the incidence rate and disease index of rice field leaf blight;

[0085] The monitoring control module and the detection control module are in communication with the data analysis module, and are used to receive the analysis results of the weighted values ​​of the influence factors on the incidence rate and disease index of rice field leaf blight, and generate a monitoring strategy based on the analysis results.

[0086] The specific implementation steps of the plan are as follows:

[0087] Step 1) When bacterial blight is found in rice fields in a certain area, the leaf sampling module adopts a 5-point sampling method to sample and test rice fields with different degrees of damage, obtain the total number of sampled leaves, the number of diseased leaves and the severity data, and calculate the incidence rate and disease index of the rice fields, where:

[0088] Incidence rate (%) = (number of diseased leaves / total number of leaves) × 100%

[0089] Disease index = [∑(number of diseased leaves at each level × representative value of each level) / (total number of leaves × highest representative value)] × 100;

[0090] Step 2) Collect data on influencing factors of the sampling objects during the disease period through the variety disease resistance evaluation module, the total precipitation measurement module during the disease period, the field planting density value measurement module, the paddy field water volume measurement module, the seed bacterial content measurement module, and the paddy field bacterial residue measurement module, including variety disease resistance evaluation data, total precipitation during the disease period, field planting density value, paddy field water volume, seed bacterial content, paddy field bacterial residue and other data;

[0091] Step 3) The data analysis module uses the principal factor analysis method to analyze the influence weights of the various influencing factors of the incidence of rice field leaf blight on the incidence rate or disease index, and obtains the influence weight values ​​of the various influencing factors on the incidence rate and disease index of rice field leaf blight. The specific steps are as follows:

[0092] Step 31) The data set sequence of the incidence rate and disease index of the sampled subjects is used as the parent sequence E, and the data set sequence of the various influencing factors of the sampled subjects during the disease period is used as the subsequence F. Its structural expression is:

[0093] E={E1,E2}

[0094] F={F1,F2,F3,F4,F5,F6}

[0095] Where, E1 and E2 are the data sets of the incidence rate and disease index of the sampled objects, respectively; F1, F2, F3, F4, F5, and F6 are the data sets of the disease resistance evaluation data of the varieties of the sampled objects during the disease period, the total precipitation during the disease period, the field planting density, the amount of water accumulated in the rice field, the bacterial content of the seeds, and the bacterial residue in the rice field, respectively;

[0096] Step 32) Use the mean method to perform dimensionless operation on the data in the parent sequence E and the child sequence F. The calculation formula is:

[0097]

[0098]

[0099] Where, E ik , F jk are the data numbers of each factor in the parent sequence E and the child sequence F, E 11 It represents the incidence data of the first sampling object, F 11 It represents the disease resistance evaluation data of the sample with the first number; n, m are the data volume of each factor; mean() is the average value operation;

[0100] Step 33) Calculate the correlation coefficient ζ between each factor data point in the subsequence F and the index in the parent sequence E respectively jk , and its calculation formula is:

[0101]

[0102] Δmin=min i (min k (|E ik -F jk |))

[0103] Δmax=max i (max k (|E ik -F jk |))

[0104] Where min i (min k ()) is the first subsequence factor |E ik -F jk | minimum value, taking the minimum value of all factors; max i (max k ()) is the first subsequence factor |E ik -F jkThe maximum value of | is taken when all factors are maximized; ρ is the discrimination coefficient, which is a constant between 0 and 1, and the value of ρ is usually 0.5;

[0105] Step 34) Calculate the correlation degree R between each factor data in the parent sequence E and each factor data in the child sequence F ij , and its calculation formula is:

[0106]

[0107] Step 4) The monitoring and control module receives the analysis results of the influence weight values ​​of various influencing factors on the incidence rate and disease index of rice field leaf blight, and generates a monitoring strategy based on the analysis results. The specific steps are as follows:

[0108] Step 41), obtain the correlation degree R ij After the value of ij Create a sample set with the value of , and obtain the mean and standard deviation in the sample set;

[0109] Step 42) Standardize the data using mean and standard deviation. The standardization formula is: In this formula, z is the standard parameter, σ is the variance of the sample data, and μ is the mean of the sample data.

[0110] Step 43), after completing the standardization, the standard parameters are used Adjust the numerical interval to [0,1] and use the function value of f(k) to classify the coincidence rate. The classification mechanism is:

[0111] when When , the degree of association is classified as level one;

[0112] when When , the degree of association is classified as level 2;

[0113] Among them, f(k)min and f(k)max are the minimum and maximum values ​​of the function value of f(k) respectively.

[0114] Among them, when the correlation degree is classified as level one, a real-time monitoring strategy is generated;

[0115] When the degree of association is classified as level 2, an intermittent monitoring strategy is generated;

[0116] Step 5), in response to the monitoring strategy generated by the monitoring and control module, the modules corresponding to the order of the influence weight values ​​from large to small respectively execute the real-time monitoring strategy or the intermittent monitoring strategy. When the correlation degree is classified as level one, it means that the correlation degree between this influencing factor and the incidence rate and the morbidity index is high, so it is necessary to pay close attention to the changing trend of this influencing factor. When the correlation degree is classified as level two, it means that the correlation degree between this influencing factor and the incidence rate and the morbidity index is low, so the data collection density and frequency of such influencing factors can be appropriately relaxed. For example, when the influence weight value is the largest for the amount of water in the paddy field, it means that the main cause of rice leaf blight is excessive water in the paddy field, so it is necessary to monitor the amount of water in the paddy field in real time. In response to the real-time monitoring strategy generated by the monitoring and control module, the paddy field water volume measurement module monitors the amount of water in the paddy field in real time.

[0117] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring rice bacterial blight based on multi-source data analysis, characterized by: The following steps are involved: Step 1: Select paddy fields with different degrees of damage as sampling objects, use the 5-point sampling method to sample and test each sampling object, record the total number of sampled leaves, the number of diseased leaves and the severity data, and calculate the incidence rate and disease index of the sampling object, where: Incidence rate (%) = (number of diseased leaves / total number of leaves) × 100% Disease index = [∑(number of diseased leaves at each level × representative value of each level) / (total number of leaves × highest representative value)] × 100; Step 2: Collect data on influencing factors of the sampled objects during the disease period, including variety disease resistance evaluation data, total precipitation during the disease period, field planting density, rice field water volume, seed bacterial content, and bacterial residue in the rice field; Step 3: Using the principal factor analysis method, analyze the influence weight of each influencing factor data on the incidence rate or disease index; Step 4: Determine the impact weight values ​​of the morbidity rate and disease index of the sampled objects based on the analysis results of step 3, generate a monitoring strategy based on the size of the impact weight values, and execute the monitoring strategy by setting a monitoring unit; The specific steps of step three include: Step 31) The data set sequence of the incidence rate and disease index of the sampled subjects is used as the parent sequence E, and the data set sequence of the various influencing factors of the sampled subjects during the disease period is used as the subsequence F. Its structural expression is: E={E1,E2} F={F1,F2,F3,F4,F5,F6} Where, E1 and E2 are the data sets of the incidence rate and disease index of the sampled objects, respectively; F1, F2, F3, F4, F5, and F6 are the data sets of the disease resistance evaluation data of the varieties of the sampled objects during the disease period, the total precipitation during the disease period, the field planting density, the amount of water accumulated in the rice field, the bacterial content of the seeds, and the bacterial residue in the rice field, respectively; Step 32) Use the mean method to perform dimensionless operation on the data in the parent sequence E and the child sequence F. The calculation formula is: Where, E ik , F jk are the data numbers of each factor in the parent sequence E and the child sequence F respectively; n and m are the data amounts of each factor; mean() is the average value operation; Step 33) Calculate the correlation coefficient ζ between each factor data point in the subsequence F and the index in the parent sequence E respectively jk , and its calculation formula is: Δmin=min i (my k (|E ik -F jk |)) Δmax=max i (max k (|E ik -F jk |)) Where min i (min k ()) is the first subsequence factor |E ik -F jk | minimum value, taking the minimum value of all factors; max i (max k ()) is the first subsequence factor |E ik -F jk The maximum value of | is taken when all factors are maximized; ρ is the discrimination coefficient, which is a constant between 0 and 1; Step 34) Calculate the correlation degree R between each factor data in the parent sequence E and each factor data in the child sequence F ij , and its calculation formula is:

2. The method for monitoring rice bacterial blight based on multi-source data analysis according to claim 1, characterized in that: The disease grading standards in the disease index are: Level 0: no disease; Level 1: The lesion area is less than 1 / 5 of the leaf area; Level 2: The lesion area is less than 1 / 3 of the leaf area; Level 3: The lesion area is less than 1 / 2 of the leaf area; Level 4: The lesion area is more than 3 / 5 of the leaf area.

3. The method for monitoring rice bacterial blight based on multi-source data analysis according to claim 1, characterized in that: The specific steps of step four are as follows: Step 41), obtain the correlation degree R ij After the value of ij Create a sample set with the value of , and obtain the mean and standard deviation in the sample set; Step 42) Standardize the data using mean and standard deviation. The standardization formula is: In this formula, z is the standard parameter, σ is the variance of the sample data, and μ is the mean of the sample data. Step 43), after completing the standardization, the standard parameters are used Adjust the numerical interval to [0,1] and use the function value of f(k) to classify the coincidence rate. The classification mechanism is: when When , the degree of association is classified as level one; when When , the degree of association is classified as level 2; Among them, f(k)min and f(k)max are the minimum and maximum values ​​of the function value of f(k) respectively.

4. The method for monitoring rice bacterial blight based on multi-source data analysis according to claim 3, characterized in that: When the association degree is classified as level one, a real-time monitoring strategy is generated, and the monitoring unit executes the real-time monitoring strategy; When the association degree is classified as level 2, an intermittent monitoring strategy is generated, and the monitoring unit executes the intermittent monitoring strategy.

5. A rice bacterial blight monitoring system based on multi-source data analysis, characterized by: include: Leaf sampling module, used to sample and test rice fields with different degrees of damage, obtain the total number of sampled leaves, the number of diseased leaves and the severity data, and calculate the incidence rate and disease index of the rice fields; A monitoring unit, which is used to implement the monitoring strategy, including: a variety disease resistance assessment module, a total precipitation measurement module during the disease period, a field planting density measurement module, a rice field water volume measurement module, a seed bacterial content measurement module, and a rice field bacterial residue measurement module; The variety disease resistance evaluation module is used to quantitatively evaluate the rice seed resistance to bacterial blight and obtain variety disease resistance evaluation data; The total amount of precipitation during the disease period measurement module is used to measure the total amount of water in the rice field during the disease period and obtain the total amount of precipitation data in the rice field during the disease period; The field planting density value measurement module is used to measure the field planting density of the rice field and obtain the field planting density value data of the rice field during the disease period; The paddy field water accumulation measurement module is used to measure the paddy field water accumulation in the paddy field and obtain paddy field water accumulation data during the disease period; The seed bacterial content measurement module is used to measure the seed bacterial content and obtain bacterial content data of diseased rice field seeds; The rice field bacterial residue measurement module is used to measure the bacterial residue in the old diseased area of ​​the rice field and obtain the rice field bacterial residue data during the disease period; The data analysis module is used to analyze the influence weights of the data of various influencing factors on the incidence of rice field bacterial blight on the incidence rate or disease index, and obtain the influence weight values ​​of various influencing factors on the incidence rate and disease index of rice field bacterial blight; The monitoring and control module is in communication with the data analysis module and is used to receive analysis results of the influence weight values ​​of various influencing factors on the incidence rate and disease index of rice field bacterial blight, and generate a monitoring strategy based on the analysis results.

6. The rice bacterial blight monitoring system based on multi-source data analysis according to claim 5, characterized in that: The variety disease resistance evaluation module, the total precipitation measurement module during the disease period, the field planting density value measurement module, the rice field water accumulation measurement module, the seed bacteria content measurement module and the rice field bacterial residue measurement module are all communicatively connected to the monitoring and control module.

7. The rice bacterial blight monitoring system based on multi-source data analysis according to claim 5, characterized in that: In response to the monitoring strategy generated by the monitoring control module, the variety disease resistance evaluation module, the total precipitation measurement module during the disease period, the field planting density value measurement module, the rice field water accumulation measurement module, the seed bacteria content measurement module and the rice field bacterial residue measurement module respectively execute corresponding monitoring strategies.

8. The rice bacterial blight monitoring system based on multi-source data analysis according to claim 5, characterized in that: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 4 when executing the program.

Images