CN117113030A - Rice bacterial leaf blight monitoring method and system based on multisource data analysis - Google Patents
Rice bacterial leaf blight monitoring method and system based on multisource data analysis Download PDFInfo
- Publication number
- CN117113030A CN117113030A CN202311100024.XA CN202311100024A CN117113030A CN 117113030 A CN117113030 A CN 117113030A CN 202311100024 A CN202311100024 A CN 202311100024A CN 117113030 A CN117113030 A CN 117113030A
- Authority
- CN
- China
- Prior art keywords
- disease
- data
- paddy field
- monitoring
- rice
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 91
- 235000007164 Oryza sativa Nutrition 0.000 title claims abstract description 61
- 235000009566 rice Nutrition 0.000 title claims abstract description 61
- 230000001580 bacterial effect Effects 0.000 title claims abstract description 59
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000007405 data analysis Methods 0.000 title claims abstract description 28
- 240000007594 Oryza sativa Species 0.000 title 1
- 201000010099 disease Diseases 0.000 claims abstract description 118
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 118
- 241000209094 Oryza Species 0.000 claims abstract description 60
- 238000004458 analytical method Methods 0.000 claims abstract description 15
- 238000005259 measurement Methods 0.000 claims description 46
- 238000005070 sampling Methods 0.000 claims description 46
- 241000894006 Bacteria Species 0.000 claims description 35
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 27
- 208000035240 Disease Resistance Diseases 0.000 claims description 25
- 238000011156 evaluation Methods 0.000 claims description 24
- 238000001556 precipitation Methods 0.000 claims description 17
- 238000009825 accumulation Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 6
- 230000003902 lesion Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 2
- 230000002265 prevention Effects 0.000 abstract description 4
- 230000007480 spreading Effects 0.000 abstract description 4
- 238000000556 factor analysis Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000001717 pathogenic effect Effects 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 240000002582 Oryza sativa Indica Group Species 0.000 description 1
- 240000008467 Oryza sativa Japonica Group Species 0.000 description 1
- 241000589652 Xanthomonas oryzae Species 0.000 description 1
- 244000052616 bacterial pathogen Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Business, Economics & Management (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Agronomy & Crop Science (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Apparatus Associated With Microorganisms And Enzymes (AREA)
Abstract
The invention discloses a rice bacterial leaf blight monitoring method and system based on multi-source data analysis. According to the provided rice bacterial leaf blight monitoring method, based on analysis of multi-source data, a main factor analysis method is adopted to analyze the influence weight of each influence factor data on morbidity or disease index, so that main influence factors causing the disease of the rice field bacterial leaf blight are screened out, a monitoring strategy is generated according to the magnitude of influence weight values, a real-time monitoring strategy is executed on the main influence factors by setting a monitoring unit, and an intermittent monitoring strategy is executed on secondary or irrelevant influence factors, so that the monitoring of the spreading trend of the rice field bacterial leaf blight is realized purposefully and efficiently, corresponding prevention measures are conveniently taken timely for the main influence factors causing the rice field bacterial leaf blight, and the rapid spreading of the bacterial leaf blight in the rice field is effectively restrained.
Description
Technical Field
The invention relates to the technical field of rice bacterial leaf blight monitoring, in particular to a rice bacterial leaf blight monitoring method and system based on multi-source data analysis.
Background
Bacterial leaf blight is one of three diseases of rice, is a rice disease caused by a xanthomonas oryzae pathogenic variety, is expressed as yellow or yellow-green spots on leaf tips and edges of a disease plant on indica rice, and is expressed as grayish green to gray white on japonica rice. Although bacterial leaf blight can be seen by naked eyes, when symptoms are obvious, damage to rice leaves is huge, so early prevention is found to be of great significance to healthy growth of rice. The causes of bacterial leaf blight of rice are: 1) The disease resistance of the varieties is poor; 2) Rainy and high-humidity weather; 3) The rice has high field density and poor permeability; 4) The paddy field is too deep; 5) Carrying out seed bacteria; 6) The pathogenic bacteria remained in the field of the old disease area and then dip-dyed, etc.
At present, in the prior art, the hyperspectral imaging technology is adopted to acquire the spectral information of rice canopy and leaf, and the rice bacterial leaf blight is monitored through spectral analysis, so that the reasons for the occurrence of the rice bacterial leaf blight are various, and although the method can monitor whether the rice is in an occurrence state, the specific pathogenic reason cannot be determined, so that corresponding prevention and treatment measures cannot be taken aiming at the cause of the disease. Therefore, we propose a rice bacterial leaf blight monitoring method and system based on multi-source data analysis.
Disclosure of Invention
The invention mainly aims to provide a rice bacterial leaf blight monitoring method and system based on multi-source data analysis, which can effectively solve the problems in the background technology.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
a rice bacterial leaf blight monitoring method based on multi-source data analysis comprises the following steps:
firstly, selecting paddy fields with different victims as sampling objects, sampling and detecting each sampling object by adopting a 5-point sampling method, recording data of total number of sampled leaves, number of diseased leaves and severity, and calculating morbidity and disease index of the sampling object, wherein:
incidence (%) = (number of diseased leaves/total number of leaves) ×100%
Disease index = [ Σ (leaf number of each stage×representative value of each stage)/(total leaf number×representative value of highest stage) ]×100;
step two, collecting influence factor data of a sampling object in the disease period, wherein the influence factor data comprise variety disease resistance evaluation data, total precipitation amount in the disease period, field planting density value, paddy field water yield, seed bacterial content and paddy field bacteria residual quantity;
analyzing the influence weight of each influence factor data on the morbidity or the disease index by adopting a principal component analysis method;
determining the incidence rate of the sampling object and the influence weight value of the disease index according to the analysis result of the step three, generating a monitoring strategy according to the influence weight value, and executing the monitoring strategy by setting a monitoring unit;
the specific steps of the third step comprise:
step 31), taking a data set sequence of the morbidity and the disease index of the sampling object as a parent sequence E, and taking a data set sequence of each influencing factor of the sampling object in the morbidity period as a subsequence F, wherein the structural expression is as follows:
E＝{E 1 ,E 2 }
F＝{F 1 ,F 2 ,F 3 ,F 4 ,F 5 ,F 6 }
wherein E is 1 ，E 2 Data sets of morbidity and disease index of the sampled subjects, F 1 ，F 2 ，F 3 ，F 4 ，F 5 ，F 6 Respectively collecting variety disease resistance evaluation data of a sampling object in a disease period, total precipitation amount in the disease period, a field planting density value, paddy field water yield, seed bacterial content and paddy field bacterial residue;
step 32), carrying out dimensionless operation on the data in the parent sequence E and the child sequence F by adopting a mean value method, wherein the calculation formula is as follows:
wherein E is ik ，F jk The data numbers of all factors in the parent sequence E and the child sequence F are respectively given; n, m is the data amount of each factor; mean () is an averaging operation;
step 33), calculating association coefficients ζ of each factor data point in the subsequence F and the index in the parent sequence E respectively jk The calculation formula is as follows:
Δmin＝min i (min k (|E ik -F jk |))
Δmax＝max i (max k (|E ik -F jk |))
in the formula, min i (min k () For |E in the factor of the pre-fetch subsequence ik -F jk The minimum value of the I is taken as the minimum value for all factors; max (max) i (max k () For |E in the factor of the pre-fetch subsequence ik -F jk The maximum value of I, which is the maximum value for all factors; ρ is a resolution coefficient, ρ is a constant between 0 and 1;
step 34) calculating the degree of correlation R between the factor data in the parent sequence E and the factor data in the child sequence F ij The calculation formula is as follows:
further, the disease grading criteria in the disease index are:
level 0: no disease;
stage 1: the area of the lesion is less than 1/5 of the area of the leaf;
2 stages: the area of the lesion is less than 1/3 of the area of the leaf;
3 stages: the area of the lesion is less than 1/2 of the area of the leaf;
4 stages: the area of the disease spots is more than 3/5 of the area of the leaves.
Further, the specific steps of the fourth step are as follows:
step 41), obtaining the association degree R ij After the value of (2), the association degree R is utilized ij Creating a sample set, and acquiring the mean value and standard deviation in the sample set;
step 42), the data are standardized by means of the mean value and the standard deviation, and the standardized formula is thatWhere z is a standard parameter, σ is the variance of the sample data, μ is the mean of the sample data,
step 43), after normalization, the standard parameters are utilizedAdjust the value interval to [0,1 ]]The coincidence rate is classified by using the function value of f (k), and the classification mechanism is as follows:
when (when)When the association degree is classified as a first level;
when (when)The association degree is classified into a second level;
wherein f (k) min and f (k) max are the minimum and maximum values of the function values of f (k), respectively.
Further, when the association degree is classified as a first level, a real-time monitoring strategy is generated, and the monitoring unit executes the real-time monitoring strategy;
when the degree of association is classified as secondary, an intermittent monitoring strategy is generated, and the monitoring unit executes the intermittent monitoring strategy.
A rice bacterial leaf blight monitoring system based on multi-source data analysis, comprising:
the blade sampling module is used for sampling and detecting paddy fields with different damage degrees, acquiring data of total number of sampled blades, number of diseased blades and severity degree, and calculating morbidity and disease index of the paddy fields;
a monitoring unit for executing a monitoring strategy, comprising: the system comprises a variety disease resistance evaluation module, a rainfall total amount measurement module during disease occurrence, a field planting density value measurement module, a paddy field ponding measurement module, a seed bacteria content measurement module and a paddy field bacteria residue measurement module;
the variety disease resistance evaluation module is used for quantitatively evaluating the bacterial blight resistance of rice seeds to obtain variety disease resistance evaluation data;
the total precipitation amount measuring module is used for measuring the total water amount of the paddy field in the attack period and acquiring the total precipitation amount data of the paddy field in the attack period;
the field planting density value measuring module is used for measuring field planting density of the paddy field and acquiring field planting density value data of the paddy field in the disease period;
the paddy field water accumulation measuring module is used for measuring paddy field water accumulation of the paddy field and acquiring paddy field water accumulation data of the paddy field in the disease period;
the seed bacteria content measuring module is used for measuring seed bacteria content and acquiring bacteria content data of the disease-causing paddy field seeds;
the paddy field bacterial residue amount measuring module is used for measuring the bacterial residue amount of old disease areas of the paddy field and obtaining paddy field bacterial residue amount data of the paddy field in the disease period;
the data analysis module is used for analyzing the influence weight of each influence factor data of the disease occurrence of the rice field shutter disease on the disease occurrence rate or the disease index and obtaining the influence weight value of each influence factor on the disease occurrence rate and the disease index of the rice field shutter disease;
the monitoring control module is in communication connection with the data analysis module and is used for receiving analysis results of influence weight values of all influence factors on the incidence rate and the disease index of the rice field shutter disease and generating a monitoring strategy according to the analysis results.
Further, the variety disease resistance evaluation module, the rainfall total amount measurement module during disease occurrence, the field planting density value measurement module, the paddy field water yield measurement module, the seed bacteria content measurement module and the paddy field bacteria residual amount measurement module are all in communication connection with the monitoring control module.
Further, in response to the monitoring policy generated by the monitoring control module, the variety disease resistance evaluation module, the total precipitation amount measurement module during disease occurrence, the field planting density value measurement module, the paddy field water yield measurement module, the seed bacteria content measurement module and the paddy field bacteria residue measurement module execute corresponding monitoring policies respectively.
Further, the system includes a memory, a processor, and a computer program stored on the memory and executable on the processor.
Further, the system comprises the following specific implementation steps:
step 1), when bacterial leaf blight occurs in a rice field in a certain area, sampling and detecting the rice field with different damage degrees through a leaf sampling module, acquiring data of total number of leaves, number of diseased leaves and severity degree of sampling, and calculating morbidity and disease index of the rice field;
step 2), acquiring influence factor data of a sampling object in the period of attack by a variety disease resistance evaluation module, a total precipitation amount measurement module in the period of attack, a field planting density value measurement module, a paddy field ponding measurement module, a seed bacteria content measurement module and a paddy field bacteria residue measurement module respectively, wherein the influence factor data comprises variety disease resistance evaluation data, total precipitation amount in the period of attack, a field planting density value, paddy field ponding, seed bacteria content, paddy field bacteria residue and the like;
step 3), analyzing the influence weight of each influence factor data of the disease occurrence of the rice field shutter disease on the disease occurrence rate or the disease index through a data analysis module, and obtaining the influence weight value of each influence factor on the disease occurrence rate and the disease index of the rice field shutter disease;
step 4), receiving analysis results of influence weight values of incidence rate and disease index of the rice field shutter disease by each influence factor through a monitoring control module, and generating a monitoring strategy according to the analysis results;
and step 5), responding to the monitoring strategy generated by the monitoring control module, and correspondingly executing the real-time monitoring strategy or the intermittent monitoring strategy respectively by the modules corresponding to the sequence from big to small influencing weight values.
The invention has the following beneficial effects:
(1) Compared with the prior art, the technical scheme of the invention is characterized in that the method for monitoring the bacterial leaf blight of the paddy rice is based on analysis of multi-source data, a main factor analysis method is adopted to analyze the influence weight of each influence factor data on the morbidity or the disease index, so that the main influence factors causing the disease of the bacterial leaf blight of the paddy field are screened out, a monitoring strategy is generated according to the magnitude of the influence weight value, a real-time monitoring strategy is executed on the main influence factors by arranging the monitoring unit, and an intermittent monitoring strategy is executed on the secondary or irrelevant influence factors, so that the monitoring of the spreading trend of the bacterial leaf blight of the paddy field is realized purposefully and efficiently, and corresponding prevention measures are conveniently and timely adopted for the main influence factors causing the bacterial leaf blight of the paddy field, thereby effectively preventing the rapid spreading of the bacterial leaf blight of the paddy field in the paddy field.
Drawings
FIG. 1 is a schematic flow chart of a rice bacterial blight monitoring method based on multi-source data analysis;
fig. 2 is a schematic structural diagram of a rice bacterial leaf blight monitoring system based on multi-source data analysis.
Detailed Description
The present invention will be further described with reference to the following detailed description, wherein the drawings are for illustrative purposes only and are presented as schematic drawings, rather than physical drawings, and are not to be construed as limiting the invention, and wherein certain components of the drawings are omitted, enlarged or reduced in order to better illustrate the detailed description of the present invention, and are not representative of the actual product dimensions.
Example 1
As shown in fig. 1-2, the method for monitoring bacterial leaf blight of rice based on multi-source data analysis comprises the following steps:
firstly, selecting paddy fields with different damage degrees as sampling objects, sampling and detecting each sampling object by adopting a 5-point sampling method, recording data of total number of sampled leaves, number of diseased leaves and severity degree, and calculating morbidity and disease index of the sampling object;
step two, collecting influence factor data of a sampling object in the disease period, wherein the influence factor data comprise variety disease resistance evaluation data, total precipitation amount in the disease period, field planting density value, paddy field water yield, seed bacterial content and paddy field bacteria residual quantity;
analyzing the influence weight of the influence factor data on the morbidity or the disease index by adopting a principal factor analysis method;
and step four, determining the incidence rate of the sampling object and the influence weight value of the disease index according to the analysis result of the step three, generating a monitoring strategy according to the magnitude of the influence weight value, and executing the monitoring strategy by setting a monitoring unit.
A rice bacterial leaf blight monitoring system based on multi-source data analysis, comprising:
the blade sampling module is used for sampling and detecting paddy fields with different damage degrees, acquiring data of total number of sampled blades, number of diseased blades and severity degree, and calculating morbidity and disease index of the paddy fields;
the monitoring unit, the monitoring unit is used for carrying out the monitoring tactics, include: the system comprises a variety disease resistance evaluation module, a rainfall total amount measurement module during disease occurrence, a field planting density value measurement module, a paddy field ponding measurement module, a seed bacteria content measurement module and a paddy field bacteria residue measurement module;
the variety disease resistance evaluation module is used for quantitatively evaluating the bacterial blight resistance of rice seeds to obtain variety disease resistance evaluation data;
the total precipitation amount measuring module is used for measuring the total amount of water in the paddy field in the attack period and acquiring the total precipitation amount data of the paddy field in the attack period;
the field planting density value measuring module is used for measuring the field planting density of the paddy field and acquiring the field planting density value data of the paddy field in the disease period;
the paddy field water accumulation measuring module is used for measuring paddy field water accumulation of the paddy field and acquiring paddy field water accumulation data of the paddy field in the disease period;
the seed bacteria content measuring module is used for measuring the bacteria content of seeds and obtaining the bacteria content data of the disease-causing paddy seeds;
the paddy field bacterial residue measurement module is used for measuring the bacterial residue of old disease areas of the paddy field and acquiring paddy field bacterial residue data of the paddy field in the disease period;
the data analysis module is used for analyzing the influence weight of each influence factor data of the disease occurrence of the rice field shutter disease on the disease occurrence rate or the disease index and obtaining the influence weight value of each influence factor on the disease occurrence rate and the disease index of the rice field shutter disease;
the monitoring control module is in communication connection with the data analysis module and is used for receiving the analysis results of the influence weight values of the influence factors on the incidence rate and the disease index of the rice field shutter disease and generating a monitoring strategy according to the analysis results.
The specific implementation steps of the scheme are as follows:
step 1), when bacterial leaf blight occurs in a rice field in a certain area, sampling and detecting the rice field with different damage degrees by a leaf sampling module through a 5-point sampling method, acquiring data of total number of leaves, number of diseased leaves and severity degree of sampling, and calculating morbidity and disease index of the rice field, wherein:
incidence (%) = (number of diseased leaves/total number of leaves) ×100%
Disease index = [ Σ (leaf number of each stage×representative value of each stage)/(total leaf number×representative value of highest stage) ]×100;
step 2), acquiring influence factor data of a sampling object in the period of attack by a variety disease resistance evaluation module, a total precipitation amount measurement module in the period of attack, a field planting density value measurement module, a paddy field ponding measurement module, a seed bacteria content measurement module and a paddy field bacteria residue measurement module respectively, wherein the influence factor data comprises variety disease resistance evaluation data, total precipitation amount in the period of attack, a field planting density value, paddy field ponding, seed bacteria content, paddy field bacteria residue and the like;
and 3) analyzing the influence weight of each influence factor data of the disease occurrence of the rice field blind spot to the disease occurrence rate or the disease index by a data analysis module by adopting a principal component analysis method, and obtaining the influence weight value of each influence factor to the disease occurrence rate and the disease index of the rice field blind spot, wherein the specific steps are as follows:
step 31), taking a data set sequence of the morbidity and the disease index of the sampling object as a parent sequence E, and taking a data set sequence of each influencing factor of the sampling object in the morbidity period as a subsequence F, wherein the structural expression is as follows:
E＝{E 1 ,E 2 }
F＝{F 1 ,F 2 ,F 3 ,F 4 ,F 5 ,F 6 }
wherein E is 1 ，E 2 Data sets of morbidity and disease index of the sampled subjects, F 1 ，F 2 ，F 3 ，F 4 ，F 5 ，F 6 Respectively collecting variety disease resistance evaluation data of a sampling object in a disease period, total precipitation amount in the disease period, a field planting density value, paddy field water yield, seed bacterial content and paddy field bacterial residue;
step 32), carrying out dimensionless operation on the data in the parent sequence E and the child sequence F by adopting a mean value method, wherein the calculation formula is as follows:
wherein E is ik ，F jk Data numbers of each factor in the parent sequence E and the child sequence F respectively, E 11 Representative is the morbidity data of the first sample, F 11 Representative is variety disease resistance evaluation data of the sampling object numbered first; n, m is the data amount of each factor; mean () is an averaging operation;
step 33), calculating association coefficients ζ of each factor data point in the subsequence F and the index in the parent sequence E respectively jk The calculation formula is as follows:
Δmin＝min i (min k (|E ik -F jk |))
Δmax＝max i (max k (|E ik -F jk |))
in the formula, min i (min k () For |E in the factor of the pre-fetch subsequence ik -F jk The minimum value of the I is taken as the minimum value for all factors; max (max) i (max k () For |E in the factor of the pre-fetch subsequence ik -F jk The maximum value of I, which is the maximum value for all factors; ρ is a resolution coefficient, ρ is a constant between 0 and 1, and typically the value of ρ takes 0.5;
step 34) calculating the degree of correlation R between the factor data in the parent sequence E and the factor data in the child sequence F ij The calculation formula is as follows:
and 4) receiving analysis results of influence weight values of the incidence rate and the disease index of the rice field shutter disease by each influence factor through a monitoring control module, and generating a monitoring strategy according to the analysis results, wherein the specific steps are as follows:
step 41), obtaining the association degree R ij After the value of (2), the association degree R is utilized ij Creating a sample set, and acquiring the mean value and standard deviation in the sample set;
step 42), the data are standardized by means of the mean value and the standard deviation, and the standardized formula is thatWhere z is a standard parameter, σ is the variance of the sample data, μ is the mean of the sample data,
step 43), after normalization, the standard parameters are utilizedAdjust the value interval to [0,1 ]]The coincidence rate is classified by using the function value of f (k), and the classification mechanism is as follows:
when (when)When the association degree is classified as a first level;
when (when)The association degree is classified into a second level;
wherein f (k) min and f (k) max are the minimum and maximum values of the function values of f (k), respectively.
When the association degree is classified as a first level, generating a real-time monitoring strategy;
generating an intermittent monitoring strategy when the degree of association is classified as secondary;
and 5) responding to the monitoring strategy generated by the monitoring control module, correspondingly executing a real-time monitoring strategy or an intermittent monitoring strategy respectively by the modules corresponding to the sequence from big to small in influence weight value, when the association degree is classified as first level, indicating that the association degree of the influence factor and the morbidity and morbidity index is higher, thus needing to pay close attention to the change trend of the influence factor, when the association degree is classified as second level, indicating that the association degree of the influence factor and the morbidity index is lower, thus the data acquisition density and frequency of the influence factor can be properly relaxed, for example, when the influence weight value is the paddy field water accumulation amount with the largest influence weight value, indicating that the main cause of the paddy field shutter disease is excessive water accumulation amount, thus needing to monitor the paddy field water accumulation amount in real time, and responding to the real-time monitoring strategy generated by the monitoring control module, and the paddy field water accumulation amount measuring module monitors the paddy field water accumulation amount in real time.
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. A rice bacterial leaf blight monitoring method based on multisource data analysis is characterized by comprising the following steps of: the method comprises the following steps:
firstly, selecting paddy fields with different victims as sampling objects, sampling and detecting each sampling object by adopting a 5-point sampling method, recording data of total number of sampled leaves, number of diseased leaves and severity, and calculating morbidity and disease index of the sampling object, wherein:
incidence (%) = (number of diseased leaves/total number of leaves) ×100%
Disease index = [ Σ (leaf number of each stage×representative value of each stage)/(total leaf number×representative value of highest stage) ]×100;
step two, collecting influence factor data of a sampling object in the disease period, wherein the influence factor data comprise variety disease resistance evaluation data, total precipitation amount in the disease period, field planting density value, paddy field water yield, seed bacterial content and paddy field bacteria residual quantity;
analyzing the influence weight of each influence factor data on the morbidity or the disease index by adopting a principal component analysis method;
determining the incidence rate of the sampling object and the influence weight value of the disease index according to the analysis result of the step three, generating a monitoring strategy according to the influence weight value, and executing the monitoring strategy by setting a monitoring unit;
the specific steps of the third step comprise:
step 31), taking a data set sequence of the morbidity and the disease index of the sampling object as a parent sequence E, and taking a data set sequence of each influencing factor of the sampling object in the morbidity period as a subsequence F, wherein the structural expression is as follows:
E＝{E 1 ,E 2 }
F＝{F 1 ,F 2 ,F 3 ,F 4 ,F 5 ,F 6 }
wherein E is 1 ，E 2 Data sets of morbidity and disease index of the sampled subjects, F 1 ，F 2 ，F 3 ，F 4 ，F 5 ，F 6 Respectively collecting variety disease resistance evaluation data of a sampling object in a disease period, total precipitation amount in the disease period, a field planting density value, paddy field water yield, seed bacterial content and paddy field bacterial residue;
step 32), carrying out dimensionless operation on the data in the parent sequence E and the child sequence F by adopting a mean value method, wherein the calculation formula is as follows:
wherein E is ik ，F jk The data numbers of all factors in the parent sequence E and the child sequence F are respectively given; n, m is the data amount of each factor; mean () is an averaging operation;
step 33), calculating subsequences respectivelyCorrelation coefficient ζ of each factor data point in F and index in parent sequence E jk The calculation formula is as follows:
Δmin＝min i (min k (|E ik -F jk |))
Δmax＝max i (max k (|E ik -F jk |))
in the formula, min i (min k () For |E in the factor of the pre-fetch subsequence ik -F jk The minimum value of the I is taken as the minimum value for all factors; max (max) i (max k () For |E in the factor of the pre-fetch subsequence ik -F jk The maximum value of I, which is the maximum value for all factors; ρ is a resolution coefficient, ρ is a constant between 0 and 1;
step 34) calculating the degree of correlation R between the factor data in the parent sequence E and the factor data in the child sequence F ij The calculation formula is as follows:
2. the method for monitoring bacterial leaf blight of rice based on multi-source data analysis according to claim 1, wherein the method comprises the following steps: the disease classification criteria in the disease index are:
level 0: no disease;
stage 1: the area of the lesion is less than 1/5 of the area of the leaf;
2 stages: the area of the lesion is less than 1/3 of the area of the leaf;
3 stages: the area of the lesion is less than 1/2 of the area of the leaf;
4 stages: the area of the disease spots is more than 3/5 of the area of the leaves.
3. The method for monitoring bacterial leaf blight of rice based on multi-source data analysis according to claim 1, wherein the method comprises the following steps: the specific steps of the fourth step are as follows:
step 41), obtaining the association degree R ij After the value of (2), the association degree R is utilized ij Creating a sample set, and acquiring the mean value and standard deviation in the sample set;
step 42), the data are standardized by means of the mean value and the standard deviation, and the standardized formula is thatWhere z is a standard parameter, σ is the variance of the sample data, μ is the mean of the sample data,
step 43), after normalization, the standard parameters are utilizedAdjust the value interval to [0,1 ]]The coincidence rate is classified by using the function value of f (k), and the classification mechanism is as follows:
when (when)When the association degree is classified as a first level;
when (when)The association degree is classified into a second level;
wherein f (k) min and f (k) max are the minimum and maximum values of the function values of f (k), respectively.
4. The method for monitoring bacterial leaf blight of rice based on multi-source data analysis according to claim 3, wherein the method comprises the following steps:
when the association degree is classified as a first level, a real-time monitoring strategy is generated, and the monitoring unit executes the real-time monitoring strategy;
when the degree of association is classified as secondary, an intermittent monitoring strategy is generated, and the monitoring unit executes the intermittent monitoring strategy.
5. A rice bacterial leaf blight monitoring system based on multisource data analysis is characterized in that: comprising the following steps:
the blade sampling module is used for sampling and detecting paddy fields with different damage degrees, acquiring data of total number of sampled blades, number of diseased blades and severity degree, and calculating morbidity and disease index of the paddy fields;
a monitoring unit for executing a monitoring strategy, comprising: the system comprises a variety disease resistance evaluation module, a rainfall total amount measurement module during disease occurrence, a field planting density value measurement module, a paddy field ponding measurement module, a seed bacteria content measurement module and a paddy field bacteria residue measurement module;
the variety disease resistance evaluation module is used for quantitatively evaluating the bacterial blight resistance of rice seeds to obtain variety disease resistance evaluation data;
the total precipitation amount measuring module is used for measuring the total water amount of the paddy field in the attack period and acquiring the total precipitation amount data of the paddy field in the attack period;
the field planting density value measuring module is used for measuring field planting density of the paddy field and acquiring field planting density value data of the paddy field in the disease period;
the paddy field water accumulation measuring module is used for measuring paddy field water accumulation of the paddy field and acquiring paddy field water accumulation data of the paddy field in the disease period;
the seed bacteria content measuring module is used for measuring seed bacteria content and acquiring bacteria content data of the disease-causing paddy field seeds;
the paddy field bacterial residue amount measuring module is used for measuring the bacterial residue amount of old disease areas of the paddy field and obtaining paddy field bacterial residue amount data of the paddy field in the disease period;
the data analysis module is used for analyzing the influence weight of each influence factor data of the disease occurrence of the rice field shutter disease on the disease occurrence rate or the disease index and obtaining the influence weight value of each influence factor on the disease occurrence rate and the disease index of the rice field shutter disease;
the monitoring control module is in communication connection with the data analysis module and is used for receiving analysis results of influence weight values of all influence factors on the incidence rate and the disease index of the rice field shutter disease and generating a monitoring strategy according to the analysis results.
6. The multi-source data analysis-based rice bacterial blight monitoring system of claim 5, wherein: the disease resistance evaluation module, the rainfall total amount measurement module during disease occurrence, the field planting density value measurement module, the paddy field water yield measurement module, the seed bacteria content measurement module and the paddy field bacteria residual amount measurement module are all in communication connection with the monitoring control module.
7. The multi-source data analysis-based rice bacterial blight monitoring system of claim 5, wherein: responding to the monitoring strategies generated by the monitoring control module, and respectively executing corresponding monitoring strategies by the variety disease resistance evaluation module, the rainfall total amount measurement module during disease occurrence, the field planting density value measurement module, the paddy field water yield measurement module, the seed bacteria content measurement module and the paddy field bacteria residue measurement module.
8. The multi-source data analysis-based rice bacterial blight monitoring system of claim 5, wherein: the system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any of claims 1-4 when the program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311100024.XA CN117113030A (en) | 2023-08-30 | 2023-08-30 | Rice bacterial leaf blight monitoring method and system based on multisource data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311100024.XA CN117113030A (en) | 2023-08-30 | 2023-08-30 | Rice bacterial leaf blight monitoring method and system based on multisource data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117113030A true CN117113030A (en) | 2023-11-24 |
Family
ID=88812478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311100024.XA Pending CN117113030A (en) | 2023-08-30 | 2023-08-30 | Rice bacterial leaf blight monitoring method and system based on multisource data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117113030A (en) |
-
2023
- 2023-08-30 CN CN202311100024.XA patent/CN117113030A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Strawberry maturity classification from UAV and near-ground imaging using deep learning | |
| CN102621118B (en) | Early warning method of greenhouse vegetable diseases and insect pests | |
| CN111062251A (en) | Monitoring method of farmland cotton aphid pest grade model based on unmanned aerial vehicle imaging | |
| CN102072885A (en) | Machine vision-based paddy neck blast infection degree grading method | |
| Huang et al. | Detection of scab in wheat ears using in situ hyperspectral data and support vector machine optimized by genetic algorithm | |
| Jin et al. | Predicting the nutrition deficiency of fresh pear leaves with a miniature near-infrared spectrometer in the laboratory | |
| CN114113471A (en) | Method and system for detecting food freshness of artificial nose refrigerator based on machine learning | |
| Chen et al. | Online field performance evaluation system of a grain combine harvester | |
| WO2024099475A1 (en) | Soil heavy metal stress identification method based on long time series ndvi | |
| CN102788796B (en) | Nutrient diagnosis device and nutrient diagnosis method for nitrogen of crops based on multi-information integration of high spectral images and fluorescent images | |
| CN109034450B (en) | Method for establishing potato late blight forecasting model in north China based on meteorological conditions | |
| CN114219795A (en) | Hyperspectral imaging system-based tea tree drought induction component and drought degree assessment prediction method and system | |
| CN113267458A (en) | Method for establishing quantitative prediction model of soluble protein content of sweet potatoes | |
| CN117113030A (en) | Rice bacterial leaf blight monitoring method and system based on multisource data analysis | |
| Zhou et al. | Hyperspectral imaging technology for detection of moisture content of tomato leaves | |
| CN112528726A (en) | Aphis gossypii insect pest monitoring method and system based on spectral imaging and deep learning | |
| CN117057946A (en) | Intelligent agricultural park data monitoring device and method | |
| Chen et al. | Sugarcane stem node detection based on wavelet analysis | |
| Zhao et al. | A backlight and deep learning based method for calculating the number of seeds per silique | |
| CN111223002B (en) | Corn area dry matter yield or silage yield evaluation method and system | |
| CN115049902A (en) | Citrus leaf water content visual prediction method, system, equipment and storage medium | |
| CN112488230A (en) | Crop water stress degree judging method and device based on machine learning | |
| CN112034912A (en) | Greenhouse crop disease control method based on real-time feedback | |
| Zhang et al. | A comparative study on wheat leaf area index by different measurement methods | |
| An et al. | Classification of wheat powdery mildew based on hyperspectral: From leaves to canopy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |