Black shank early warning model construction method and black shank early warning method and system

Abstract

The invention relates to the technical field of microbiology, soil ecology and disease early warning, and provides a black shank early warning model construction method, a black shank early warning method and a black shank early warning system. According to the method disclosed by the invention, key characteristics which have important influences on the incidence of the black shank are determined by means of standardized soil sample collection, physicochemical index measurement, high-throughput sequencing analysis, microbial community evaluation and the like, so that the tobacco black shank early warning model is constructed. On the basis of deploying the tobacco black shank early warning model, the early warning of the tobacco black shank is realized through the tobacco black shank early warning system. Through scientific prevention and control of early warning, the occurrence rate and the harm degree of the tobacco black shank can be effectively reduced, the tobacco leaf quality is improved, and agricultural intelligent development is promoted.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of microbiology, soil ecology and disease early warning, and in particular to a black shank disease early warning model construction method, a black shank disease early warning method and system. BACKGROUND

[0002] Tobacco black shank disease is one of the most serious soil-borne diseases that threatens tobacco yield worldwide, and has the characteristics of fast transmission, strong soil transmission and difficult prevention and control.

[0003] Traditional tobacco black shank disease prevention and control methods mainly rely on applying chemical pesticides and replacing disease-resistant varieties. However, the prevention and control of applying chemical pesticides is lagging behind, and has a negative impact on the environment; the cost of replacing disease-resistant varieties is too high. In recent years, microbiome analysis and high-throughput sequencing technology have developed rapidly, and can analyze soil microbial communities. However, there is still a lack of related technology for applying soil microbial community analysis to tobacco black shank disease occurrence early warning.

[0004] Therefore, it is urgent to propose a method for integrating standardized sampling and intelligent data analysis to early warn tobacco black shank disease. SUMMARY

[0005] To solve the above problems, the present application provides a black shank disease early warning model construction method, a black shank disease early warning method and system, which determines the key features that have an important influence on the occurrence of black shank disease through standardized soil sample collection, physicochemical index determination, high-throughput sequencing analysis, microbial community evaluation and other means, and then constructs a tobacco black shank disease early warning model to realize early warning of tobacco black shank disease and provide a scientific basis for precision agriculture.

[0006] The present application adopts the following technical solutions:

[0007] In a first aspect, the present application provides a black shank disease early warning model construction method, which comprises:

[0008] Collecting multiple soil samples from tobacco planting areas where black shank disease has not occurred and tobacco planting areas where black shank disease has occurred at different levels, respectively;

[0009] Physicochemical index determination is performed on the multiple soil samples to obtain physicochemical index data of the multiple soil samples;

[0010] Microbiome analysis is performed on the multiple soil samples to obtain a microbial community feature table;

[0011] According to the physicochemical index data and the microbial community feature table, the key features that have an important influence on the occurrence of black shank disease are determined;

[0012] The characteristic values of the key features of the multiple soil samples are used as training samples to train a classification model to obtain a tobacco black shank disease early warning model.

[0013] In a second aspect, the present application provides a black shank disease early warning model construction system, which comprises:

[0014] A soil sample collection module is configured to collect multiple soil samples from a tobacco planting area where no black shank disease occurs and tobacco planting areas where different degrees of black shank disease occur, respectively.

[0015] A physicochemical index determination module is configured to determine physicochemical indexes of the multiple soil samples to obtain physicochemical index data of the multiple soil samples.

[0016] A microbiome analysis module is configured to analyze the multiple soil samples to obtain a microbial community feature table.

[0017] A data processing module is configured to determine key features that have an important influence on the occurrence of black shank disease according to the physicochemical index data and the microbial community feature table.

[0018] A model training module is configured to train a classification model by taking the feature values of the key features of the multiple soil samples as training samples to obtain a tobacco black shank disease early warning model.

[0019] In a third aspect, the present application provides a black shank disease early warning method, which comprises:

[0020] Collecting a target soil sample from a tobacco planting area;

[0021] Determining physicochemical indexes and performing microbiome analysis on the target soil sample, determining the feature values of the key features of the target soil sample according to the input requirements of the tobacco black shank disease early warning model, inputting the feature values of the key features of the target soil sample into the tobacco black shank disease early warning model, and obtaining a tobacco black shank disease occurrence probability prediction result.

[0022] Generating early warning information and control strategies based on the tobacco black shank disease occurrence probability prediction result;

[0023] Visually displaying the physicochemical index determination result and the microbiome analysis result, the early warning information, and the control strategies.

[0024] In a fourth aspect, the present application provides a black shank disease early warning system, which comprises:

[0025] A target soil sample collection module is configured to collect a target soil sample from a tobacco planting area.

[0026] An integrated analysis module is configured to determine physicochemical indexes and perform microbiome analysis on the target soil sample, determine the feature values of the key features of the target soil sample according to the input requirements of the tobacco black shank disease early warning model, input the feature values of the key features of the target soil sample into the tobacco black shank disease early warning model, and obtain a tobacco black shank disease occurrence probability prediction result.

[0027] an early warning module, configured to generate early warning information and prevention and control strategies based on the probability prediction result of occurrence of the black shank disease;

[0028] an interaction module, configured to visually display the physicochemical index determination result and the microbiome analysis result, the early warning information and the prevention and control strategies.

[0029] The above-mentioned at least one technical solution adopted by the present application can achieve the following beneficial effects:

[0030] The present application determines the key features that have important influence on the occurrence of the black shank disease through standardized soil sample collection, physicochemical index determination, high-throughput sequencing analysis and microbial community evaluation, and then constructs a tobacco black shank disease early warning model. On the basis of deploying the tobacco black shank disease early warning model, the tobacco black shank disease early warning system is used to realize early warning of the tobacco black shank disease. Through scientific prevention and control of early warning, the occurrence rate and harm degree of the tobacco black shank disease can be effectively reduced, the quality of tobacco leaves can be improved, and the development of agricultural intelligence can be promoted. BRIEF DESCRIPTION OF DRAWINGS

[0031] The accompanying drawings, which are included to provide a further understanding of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and together with the description serve to explain the present application. In the drawings:

[0032] Figure 1 a flowchart of a method for constructing a black shank disease early warning model provided by an embodiment of the present application;

[0033] Figure 2 a structural diagram of a system for constructing a black shank disease early warning model provided by an embodiment of the present application;

[0034] Figure 3 a flowchart of a method for early warning of the black shank disease provided by an embodiment of the present application;

[0035] Figure 4 a structural diagram of a system for early warning of the black shank disease provided by an embodiment of the present application;

[0036] Figure 5 a structural diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0037] Exemplary embodiments of the present application will be described in greater detail below. It should be understood, however, that the present application can be practiced in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.

[0038] The present disclosure provides a number of different implementations or examples to implement different structures of the present application. To simplify the disclosure of the present application, the components and arrangements of the specific examples in the present application are described. Of course, they are only examples, and the purpose is not to limit the present application. In addition, the present application can repeatedly refer to numbers and / or letters in different examples, and such repetition is for the purpose of simplification and clarity, which does not indicate the relationship between the various embodiments and / or arrangements discussed. In addition, the present application provides examples of various specific processes and materials, but those skilled in the art can realize the application of other processes and / or the use of other materials.

[0039] Generally, the terms can be understood at least in part according to the usage above the present application. For example, the term "one or more" used in the present application can be used to describe any component, structure or feature in singular form at least in part depending on the usage above the present application, or can be used to describe the combination of components, structures or features in plural form. Similarly, terms such as "a", "an" or "the" can also be understood at least in part depending on the usage above the present application to convey singular usage or to convey plural usage. In addition, the term "based on" can be understood as not necessarily intended to convey a set of exclusive factors, but can be replaced at least in part depending on the context, allowing the existence of additional factors that are not necessarily explicitly described.

[0040] The present application provides a black leg disease early warning model construction method, as shown in the figure, the method comprises the following steps: Figure 1

[0041] Step S110, respectively collecting a plurality of soil samples of tobacco planting areas without black leg disease and tobacco planting areas with different degrees of black leg disease.

[0042] The present embodiment first carries out standardized soil sample collection. The collected soil samples at least include tobacco planting areas without black leg disease and tobacco planting areas with black leg disease. For tobacco planting areas with black leg disease, according to the degree of disease, it is divided into several grades, and standardized soil sampling is carried out respectively for different grades.

[0043] In some optional embodiments, step S110 comprises: in the tobacco planting areas without black leg disease and the tobacco planting areas with different degrees of black leg disease, a plurality of soil samples are collected according to the "S" shaped sampling method respectively; wherein the sampling points avoid abnormal areas, and 5-10g of soil samples are taken at a soil depth of 5-20cm at each sampling point; the collection environment data of each soil sample is recorded, and each soil sample is divided into two parts and sealed for low temperature preservation.

[0044] ​The sampling principle of the standardized soil sample collection is: in the tobacco planting area where the black shank disease does not occur and the tobacco planting area where the black shank disease occurs in different degrees, the "S" shaped sampling method is used for sampling respectively to ensure the representativeness of the soil samples; 5-10 g of rhizosphere soil is taken at each sampling point, and the sampling depth is 5-20 cm; and the sampling point avoids the abnormal area, and the abnormal area is not limited to including waterlogged land, chemical fertilizer stacking place and the like.

[0045] For example: the tobacco planting area where the black shank disease occurs is divided into mild, moderate and severe degrees according to different degrees. Then, multiple soil samples are collected in the tobacco planting area where the black shank disease does not occur according to the sampling principle of the standardized soil sample collection, multiple soil samples are collected in the tobacco planting area where the mild black shank disease occurs according to the sampling principle of the standardized soil sample collection, multiple soil samples are collected in the tobacco planting area where the moderate black shank disease occurs according to the sampling principle of the standardized soil sample collection, and multiple soil samples are collected in the tobacco planting area where the severe black shank disease occurs according to the sampling principle of the standardized soil sample collection.

[0046] In actual situations, the soil sample collection is carried out in the field of the tobacco planting area, and the subsequent physicochemical index determination and microbiome analysis are carried out in a special laboratory, so the soil sample needs to be transferred from the field to the laboratory.

[0047] After collecting a soil sample, the collection environment data of the soil sample are recorded. The collection environment data are not limited to including temperature, humidity and the like. The soil sample is divided into two parts, which are respectively sealed by sterile bags and transported to the laboratory at-4°C to avoid the change of the microbial community structure and ensure the authenticity and stability of the microbial community structure. One part of the soil sample is used for the physicochemical index determination, and the other part of the soil sample is used for the microbiome analysis.

[0048] In step S120, the physicochemical index determination is carried out on the multiple soil samples to obtain the physicochemical index data of the multiple soil samples.

[0049] The physicochemical index determination of the multiple soil samples is carried out in this embodiment to determine the physicochemical index data of each soil sample.

[0050] In some optional embodiments, step S120 includes: using a corresponding detection kit to determine the physicochemical index of each soil sample to obtain the physicochemical index data of each soil sample; wherein the physicochemical index includes: pH value, organic matter content, total nitrogen content, total phosphorus content and total potassium content.

[0051] According to the physicochemical indexes to be determined, corresponding detection kits are selected for determination. The physicochemical indexes are not limited to including pH value, organic matter content, total nitrogen content, total phosphorus content and total potassium content, and can also include available nitrogen, available phosphorus, available potassium, conductivity, cation exchange capacity and the like. The physicochemical index data of each soil sample obtained at least include pH value result, organic matter content result, total nitrogen content result, total phosphorus content result and total potassium content result.

[0052] In step S130, microbiome analysis is performed on the multiple soil samples to obtain a microbial community characteristic table.

[0053] The microbiome analysis of the multiple soil samples is then performed to obtain a microbial community characteristic table. The microbial community characteristic table can be a matrix file, the rows of which represent each soil sample, the columns of which represent microbial units, and the values of which represent abundance ratios.

[0054] In some optional embodiments, step S130 comprises: extracting DNA of each soil sample respectively by using a soil microbial DNA extraction kit; wherein the concentration and purity of the extracted DNA are monitored by ultraviolet spectrophotometry and fluorescent dye method, to ensure that the concentration and purity of the extracted DNA meet the preset standards; bacterial community is amplified in the V3-V4 region of 16S rRNA gene, and fungal community is amplified in the ITS region, to perform double-end high-throughput sequencing and obtain sequencing data of each soil sample; quality control, dechimerization, denoising and species annotation are performed on the sequencing data to obtain a microbial community characteristic table.

[0055] For a soil sample, rhizosphere soil DNA is extracted by using a soil microbial DNA extraction kit. The soil microbial DNA extraction kit can use MOBIO's PowerSoil® DNA Isolation Kit. In order to ensure the reliability of the results, multiple repeated DNA extraction can be performed on a soil sample. DNA Isolation Kit. In order to ensure the reliability of the results, multiple repeated DNA extraction can be performed on a soil sample.

[0056] During the extraction of DNA, the concentration and purity of the extracted DNA are monitored by ultraviolet spectrophotometry and fluorescent dye method. The monitoring indexes of ultraviolet spectrophotometry (NanoDrop) are concentration and purity A260 / A280 and purity A260 / A230. The monitoring index of fluorescent dye method (Qubit) is concentration.

[0057] The preset standards are not limited to including Qubit concentration qualification standards, A260 / A280 qualification standards, A260 / A230 qualification standards, concentration range standards of DNA of different soil samples, concentration difference standards of DNA of multiple repetitions of the same soil sample, and the like. For example: when the Qubit monitoring index is <0.5 ng / μL, subsequent paired-end high-throughput sequencing cannot be performed, and therefore ≥0.5 ng / μL is taken as the Qubit concentration qualification standard; when A260 / A230 is <1.5, the subsequent paired-end high-throughput sequencing adapter ligation efficiency is reduced, and therefore ≥1.5 is taken as the A260 / A230 qualification standard. The above preset standards are only illustrative examples, and the standard values are not limited to the above examples.

[0058] If the concentration and purity of the DNA of a soil sample do not meet the preset standards, the DNA needs to be re-extracted until DNA with a concentration and purity meeting the preset standards is obtained.

[0059] After the DNA is extracted, primers are used to amplify the bacterial community in the V3-V4 region of the 16S rRNA gene and the fungal community in the ITS region. Illumina NovaSeq6000 is used for paired-end high-throughput sequencing to obtain sequencing data for each soil sample.

[0060] After sequencing is completed, the sequencing data is subjected to quality control, dechimerization, and denoising using bioinformatics tools such as QIIME2 and DADA2. Based on the SILVA database, the bacteria are annotated for species, and based on the UNITE database, the fungi are annotated for species to obtain operational taxonomic units (OTUs) or unassembled amplicon sequence variants (ASVs), which in turn form a microbial community feature table.

[0061] Table 1 illustrates a possible form of the microbial community feature table using OTUs as an example.

[0062] Table 1:

[0063]

[0064]

[0065] wherein i in Pi j corresponds to the soil sample serial number, j in Pi j corresponds to the serial number of the operational taxonomic unit, and Pi j represents the proportion of the abundance of OTU-j (species annotation) of soil sample i to the total microbial abundance of soil sample i.

[0066] Step S140, according to the physicochemical index data and the microbial community feature table, determine the key features that have important influence on the occurrence of black shank disease.

[0067] The soil samples have a large number of physicochemical indexes and complex microbial communities. Therefore, it is necessary to reduce the dimensionality of the physicochemical indexes, the microbial community indexes related to the microbial community, and the like, and determine the key features that have an important influence on the occurrence of black foot disease.

[0068] In some optional embodiments, step S140 comprises: performing alpha diversity analysis according to the microbial community feature table to determine alpha diversity index data of each soil sample; performing beta diversity analysis according to the microbial community feature table to determine beta diversity index data of each soil sample; performing function prediction according to the microbial community feature table to determine function index data of each soil sample; and using correlation analysis to screen the key features that have an important influence on the occurrence of black foot disease from the physicochemical index data, the alpha diversity index data, the beta diversity index data, and the function index data.

[0069] Alpha diversity analysis is used to evaluate the diversity of the microbial community in each soil sample. It generally includes the following core alpha diversity indexes.

[0070] Species richness: represents the total number of microbial community species in each soil sample. The total number of microbial community species in each soil sample can be evaluated by counting the number of operational taxonomic units in each soil sample.

[0071] Microbial community diversity: the microbial community diversity in each soil sample can be evaluated by calculating the Shannon index.

[0072] For a soil sample i, the mathematical expression of the Shannon index is:

[0073] H ′ = -∑pi j Inpi j , (1).

[0074] Microbial community concentration: the microbial community concentration in each soil sample can be evaluated by calculating the Simpson index.

[0075] For a soil sample i, the mathematical expression of the Simpson index is:

[0076]

[0077] The alpha diversity index can also include other contents, which are not described here.

[0078] The species richness data, the microbial community diversity data, and the microbial community concentration data of each soil sample are recorded as the alpha diversity index data of each soil sample.

[0079] The beta diversity analysis is used to measure the difference in microbial community composition between different soil samples. Through the beta diversity analysis, the microbial community related to the occurrence of black root rot can be determined, and the environmental driving factor can be determined.

[0080] The abundance-based (Bray-Curtis) distance matrix can be used to calculate the difference in microbial community composition between different soil samples based on the difference in microbial community abundance in the microbial community feature table. In addition, in the case of providing a phylogenetic tree, the phylogenetic (Unifrac) distance matrix can also be used to calculate the difference in microbial community composition between different soil samples.

[0081] The Bray-Curtis distance matrix between different soil samples is input into principal coordinate analysis (PCoA), which maps the high-dimensional distance matrix to a low-dimensional space, and determines the microbial community with significant difference between different soil samples and the microbial community with the largest contribution to the difference between different soil samples. These different microbial communities can be used as beta diversity indicators.

[0082] For example: through analysis, it is determined that the soil samples without black root rot are enriched with beneficial bacteria A, beneficial bacteria B, and the like, and the soil samples with different degrees of black root rot are enriched with pathogenic bacteria a, pathogenic bacteria b, and the like. The abundance ratio of the above beneficial bacteria and pathogenic bacteria in each soil sample is used as the beta diversity indicator data.

[0083] On the basis of collecting soil samples and recording the collection environment data of the soil samples, the microbial community feature table and the collection environment data are input into redundancy analysis (RDA), so as to reveal the explanatory power of the environmental factors on the variation of the microbial community, and then determine the environmental driving factor as the beta diversity indicator.

[0084] For example: the humidity environmental factor is significantly related to the difference in microbial community structure between different soil samples, and then the humidity value of each soil sample is determined as the beta diversity indicator data.

[0085] That is, the beta diversity indicator data is not limited to including the abundance ratio of the different microbial communities of each soil sample and the value of the environmental driving factor.

[0086] Based on the microbial community feature table, the bacterial metabolic pathways are predicted by PICRUSt2, and the fungal ecological functions are annotated by FUNGuild, so as to compare the functional spectrum of the soil samples without black root rot and the soil samples with different degrees of black root rot, and screen at least one pathogenic bacteria with potential to cause black root rot and at least one antagonistic bacteria with potential to inhibit pathogenic bacteria.

[0087] The abundance proportion of at least one pathogenic fungus potentially causing black shank and the abundance proportion of at least one antagonistic fungus potentially inhibiting the pathogenic fungus are taken as functional index data for each soil sample.

[0088] So far, for each soil sample, at least the physicochemical index data (not limited to including pH value results, organic matter content results, total nitrogen content results, total phosphorus content results, and total potassium content results, etc.), the alpha diversity index data (not limited to including species richness data, microbial community diversity data, and microbial community concentration data, etc.), the beta diversity index data (not limited to including the abundance proportion of different microbial communities and environmental driving factor values, etc.), and the functional index data (including the abundance proportion of at least one pathogenic fungus potentially causing black shank and the abundance proportion of at least one antagonistic fungus potentially inhibiting the pathogenic fungus) are prepared.

[0089] The tobacco black shank early warning model can be directly trained based on the above index data, but since there are many above-mentioned indexes, in order to reduce the training computing power, the above-mentioned indexes can be screened to determine the key features that have a critical impact on the occurrence of black shank.

[0090] The critical impact includes positive impact and negative impact, that is, the key features include features that have a critical positive impact on the occurrence of black shank and features that have a critical negative impact on the occurrence of black shank. When screening, correlation analysis can be used to screen part of the indexes with high correlation with the occurrence of black shank as key features. The correlation analysis can use the Spearman correlation analysis method.

[0091] Taking the calculation of the correlation between species richness and the occurrence of black shank as an example. For each soil sample, its species richness data can be ranked according to size, such as the smallest species richness data is ranked the smallest, and the largest species richness data is ranked the largest. Its disease degree can be ranked according to size, such as the smallest is no black shank, and the largest is severe black shank. The difference between the richness data ranking and the disease degree ranking of each soil sample is calculated, and then the difference is brought into the Spearman formula to calculate the correlation between species richness and the occurrence of black shank.

[0092] After other indexes are calculated according to the same method, the correlation between each index and the occurrence of black shank is obtained. The value of the correlation between each index and the occurrence of black shank is in the range of [0, 1].

[0093] In the screening, a positive selection threshold (greater than 0) and a negative selection threshold (less than 0) can be set. When the correlation of an index with the occurrence of black shank is greater than the positive selection threshold or less than the negative selection threshold, the index is screened as a key index. For example, the positive selection threshold is 0.05, and the negative selection threshold is -0.05. When the correlation of an index with the occurrence of black shank is > 0.05 or <- 0.05, the index is screened as a key index.

[0094] In the screening, the correlation of each index with the occurrence of black shank can also be taken as an absolute value and ranked from large to small, and the pre-set number of indexes with the largest absolute value are screened as key indexes.

[0095] In step S150, the characteristic values of the key characteristics of the multiple soil samples are used as training samples to train a classification model, and a tobacco black shank early warning model is obtained.

[0096] Since each soil sample corresponds to a determined disease degree, the characteristic values of the key characteristics of the multiple soil samples are input into the classification model to train the classification model, and then a tobacco black shank early warning model that can be used for tobacco black shank early warning is obtained.

[0097] In some optional embodiments, step S150 includes: constructing a classification model; using the characteristic values of the key characteristics of each soil sample as training samples, and using a 10-fold cross-validation method to train the classification model; using the characteristic values of the key characteristics of the historical soil samples as a test set to independently test the trained classification model, and obtaining a tobacco black shank early warning model.

[0098] The classification model can use a random forest or a support vector machine.

[0099] The characteristic values of the key characteristics of the multiple soil samples are used as training samples. The characteristic values of the key characteristics are the values corresponding to the key characteristics. For example, when the key characteristics include pH values, the characteristic values of the pH values are specific pH value results; when the key characteristics include beneficial bacteria A, the characteristic values of the beneficial bacteria A are specific abundance ratios, etc.

[0100] The training samples are divided into 10 similar subsets. Each time, 9 of them are used as a training set, and the remaining 1 is used as a validation set. The training set is used to train the classification model, and the validation set is used to adjust the hyperparameters of the classification model. Each time, a different subset is replaced as the validation set, and the above process is repeated 10 times. A trained classification model is obtained.

[0101] The historical soil samples are obtained, and the historical soil samples are different from the training samples, and can include historical soil samples of tobacco planting areas without black shank disease and historical soil samples of tobacco planting areas with different degrees of black shank disease. The characteristic values of the key characteristics of the historical soil samples are obtained by physical and chemical index determination and microbiome analysis. The characteristic values of the key characteristics of the historical soil samples are used as a test set to independently test the trained classification model, and the performance of the trained classification model is evaluated, so as to obtain the tobacco black shank disease early warning model.

[0102] The tobacco black shank disease early warning model construction method provided in the embodiment determines the key characteristics that have an important influence on the occurrence of black shank disease through standardized soil sample collection, physical and chemical index determination, high-throughput sequencing analysis, and microbial community evaluation, and then constructs a tobacco black shank disease early warning model, so as to realize early warning of tobacco black shank disease and provide a scientific basis for precision agriculture.

[0103] The application provides a black shank disease early warning model construction system, as shown in Figure 2 The system 200 comprises:

[0104] The soil sample collection module 201 is used to collect multiple soil samples in tobacco planting areas without black shank disease and tobacco planting areas with different degrees of black shank disease, respectively.

[0105] The physical and chemical index determination module 202 is used to determine the physical and chemical indexes of the multiple soil samples, so as to obtain the physical and chemical index data of the multiple soil samples.

[0106] The microbiome analysis module 203 is used to analyze the microbiome of the multiple soil samples, so as to obtain a microbial community characteristic table.

[0107] The data processing module 204 is used to determine the key characteristics that have an important influence on the occurrence of black shank disease according to the physical and chemical index data and the microbial community characteristic table.

[0108] The model training module 205 is used to train a classification model by taking the characteristic values of the key characteristics of the multiple soil samples as training samples, so as to obtain a tobacco black shank disease early warning model.

[0109] In some optional embodiments, the soil sample collection module 201 is specifically used to collect multiple soil samples in tobacco planting areas without black shank disease and tobacco planting areas with different degrees of black shank disease according to the “S” sampling method, respectively; wherein the sampling points avoid abnormal areas, and 5-10g of soil samples are taken at a soil depth of 5-20cm at each sampling point; the collection environment data of each soil sample is recorded, each soil sample is divided into two parts, and is sealed and stored at low temperature, respectively.

[0110] In some optional embodiments, the physicochemical index determination module 202 is specifically configured to: determine the physicochemical index of each soil sample by using a corresponding detection kit, to obtain physicochemical index data of each soil sample; wherein the physicochemical index includes pH value, organic matter content, total nitrogen content, total phosphorus content, and total potassium content.

[0111] In some optional embodiments, the microbiome analysis module 203 is specifically configured to: extract DNA of each soil sample by using a soil microbial DNA extraction kit; wherein the concentration and purity of the extracted DNA are monitored by using ultraviolet spectrophotometry and fluorescent dye method, to ensure that the concentration and purity of the extracted DNA meet preset standards; amplify bacterial community in the V3-V4 region of 16S rRNA gene, and amplify fungal community in the ITS region, to perform double-end high-throughput sequencing, to obtain sequencing data of each soil sample; perform quality control, chimeric removal, noise removal, and species annotation on the sequencing data, to obtain a microbial community feature table.

[0112] In some optional embodiments, the data processing module 204 is specifically configured to: perform alpha diversity analysis according to the microbial community feature table, to determine alpha diversity index data of each soil sample; perform beta diversity analysis according to the microbial community feature table, to determine beta diversity index data of each soil sample; perform function prediction according to the microbial community feature table, to determine function index data of each soil sample; and use correlation analysis to screen key features that have important influence on occurrence of black shank disease from the physicochemical index data, the alpha diversity index data, the beta diversity index data, and the function index data.

[0113] In some optional embodiments, the model training module 205 is specifically configured to: construct a classification model; use feature values of the key features of the plurality of soil samples as training samples, and train the classification model by using a 10-fold cross-validation method; use feature values of the key features of the historical soil samples as a test set to independently test the trained classification model, to obtain a tobacco black shank disease early warning model.

[0114] For specific limitations of the black shank disease early warning model construction system, reference can be made to the limitations of the black shank disease early warning model construction method in the foregoing, which will not be described herein again. Each module in the above black shank disease early warning model construction system can be realized by software, hardware, and combinations thereof, in whole or in part. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform operations corresponding to each module.

[0115] The present application provides a black shank disease early warning method, as shown in FIG. 1, the method comprises the following steps: Figure 3

[0116] ​Step S310, collect the target soil sample of the tobacco planting area.

[0117] The embodiment first collects the target soil sample. The collected target soil sample corresponds to a tobacco planting area with an unclear occurrence of black shank.

[0118] In some optional embodiments, step S310 includes: collecting a target soil sample in a tobacco planting area to be warned; wherein the sampling point avoids the abnormal area, and 5-10 g of the target soil sample is taken at a soil depth of 5-20 cm; recording the collection environment data of the target soil sample, and dividing the target soil sample into two parts for low-temperature preservation.

[0119] Step S320, performing physicochemical index determination and microbiome analysis on the target soil sample, determining the characteristic value of the key characteristics of the target soil sample according to the input requirement of the tobacco black shank early warning model, inputting the characteristic value of the key characteristics of the target soil sample into the tobacco black shank early warning model, and obtaining the tobacco black shank occurrence probability prediction result.

[0120] The collected target soil sample is subjected to physicochemical index determination and microbiome analysis, and then the characteristic value of the key characteristics is screened and input into the tobacco black shank early warning model, and the tobacco black shank occurrence probability prediction result is output based on the tobacco black shank early warning model.

[0121] In some optional embodiments, step S320 includes: using a corresponding detection kit to determine the physicochemical index of the target soil sample, and obtaining the physicochemical index data of the target soil sample; wherein the physicochemical index includes: pH value, organic matter content, total nitrogen content, total phosphorus content and total potassium content.

[0122] In some optional embodiments, step S320 includes: using a soil microbial DNA extraction kit to extract the DNA of the target soil sample; wherein the concentration and purity of the extracted DNA are monitored by ultraviolet spectrophotometry and fluorescent dye method, and the concentration and purity of the extracted DNA are ensured to meet the preset standard; the bacterial community is amplified in the V3-V4 region of the 16S rRNA gene, and the fungal community is amplified in the ITS region, and double-end high-throughput sequencing is performed to obtain the sequencing data of the target soil sample; the sequencing data is subjected to quality control, dechimerization, denoising and species annotation to obtain a microbial community characteristic table; the alpha diversity index data of the target soil sample is determined by performing alpha diversity analysis according to the microbial community characteristic table.

[0123] In some optional embodiments, step S320 comprises: determining the characteristic values of the key characteristics of the target soil sample from the collection environment data, the physicochemical index data, the alpha diversity index data, and the microbial community characteristic table of the target soil sample according to the input requirements of the tobacco black shank disease early warning model; and inputting the characteristic values of the key characteristics of the target soil sample into the tobacco black shank disease early warning model to obtain the tobacco black shank disease occurrence probability prediction result.

[0124] In order to improve the accuracy of the prediction result, multiple target soil samples can be collected in the tobacco planting area to be warned. Physicochemical index determination and microbiome analysis are performed on each target soil sample, the characteristic values of the key characteristics of each target soil sample are determined according to the input requirements of the tobacco black shank disease early warning model, the characteristic values of the key characteristics of each target soil sample are input into the tobacco black shank disease early warning model, and the tobacco black shank disease occurrence probability prediction result of each target soil sample is obtained. Then, the tobacco black shank disease occurrence probability prediction results of each target soil sample are statistically processed (such as taking the average value, etc.), and the potential probability of the tobacco black shank disease occurring in the tobacco planting area to be warned is obtained.

[0125] Step S330, generating early warning information and control strategies based on the tobacco black shank disease occurrence probability prediction result.

[0126] Based on the tobacco black shank disease occurrence probability prediction result, the potential probability of the tobacco black shank disease occurring in the tobacco planting area to be warned can be determined. In combination with the prediction result, targeted prevention and control strategies including biological control, crop rotation management, and precise fertilization can be generated.

[0127] Step S340, visualizing and displaying the physicochemical index determination result and the microbiome analysis result, the early warning information, and the control strategies.

[0128] In the tobacco black shank disease early warning process, the collection environment data, the physicochemical index data, the alpha diversity index data, and the microbial community characteristic table of the target soil sample involved in the data processing process are displayed through the visual interactive platform. The tobacco black shank disease occurrence probability prediction result predicted based on the tobacco black shank disease early warning model is displayed, and the prediction result can be converted into a tobacco black shank disease risk index. The early warning information and the control strategies are visualized and displayed in the form of risk alerts and graphical reports.

[0129] The present application provides a black shank disease early warning system, as shown in Figure 4 The system 400 comprises:

[0130] A target soil sample collection module 401 is configured to collect a target soil sample in a tobacco planting area.

[0131] The integrated analysis module 402 is used for physicochemical index determination and microbiome analysis of the target soil sample, determines the characteristic value of the key characteristics of the target soil sample according to the input requirement of the tobacco black shank early warning model, inputs the characteristic value of the key characteristics of the target soil sample into the tobacco black shank early warning model, and obtains a tobacco black shank occurrence probability prediction result.

[0132] The early warning module 403 is used for generating early warning information and prevention and control strategies based on the tobacco black shank occurrence probability prediction result.

[0133] The interaction module 404 is used for visualizing and displaying the physicochemical index determination result and the microbiome analysis result, the early warning information and the prevention and control strategies.

[0134] The tobacco black shank early warning system provided in the embodiment supports automatic data import, automatic integrated processing of physicochemical index determination and microbiome analysis. The potential probability of occurrence of the tobacco black shank in the tobacco planting area to be warned is predicted based on the tobacco black shank early warning model, and the early warning information is visualized and displayed in the form of a risk alarm, a graphic report and the like. In combination with the prediction result, targeted prevention and control strategies such as biological control, rotation management and precise fertilization are provided, so that the precision and timeliness of disease management are improved.

[0135] The specific limitation of the tobacco black shank early warning system can be referred to the limitation of the tobacco black shank early warning method in the above, and will not be described here. Each module in the above tobacco black shank early warning system can be realized by software, hardware and a combination thereof in whole or in part. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so as to call and execute the operations corresponding to the above modules by the processor.

[0136] The present application determines the key characteristics that have an important influence on the occurrence of the black shank disease through standardized soil sample collection, physicochemical index determination, high-throughput sequencing analysis, microbial community evaluation and the like, and then constructs a tobacco black shank early warning model. On the basis of deploying the tobacco black shank early warning model, early warning of the tobacco black shank is realized through the tobacco black shank early warning system. Through scientific prevention and control of early warning, the occurrence rate and harm degree of the tobacco black shank can be effectively reduced, the quality of tobacco leaves can be improved, and the development of agricultural intelligence can be promoted.

[0137] In one embodiment, a computer device is provided, and an internal structure diagram of the computer device can be as shown in Figure 5As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile and / or volatile storage media, internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with the outside through the network connection. The computer program is executed by the processor to realize the functions or steps of the black rot early warning model construction method or the black rot early warning method.

[0138] In one embodiment, a computer readable storage medium is provided, and a computer program is stored on the computer readable storage medium. The computer program is executed by the processor to realize the functions or steps of the black rot early warning model construction method or the black rot early warning method.

[0139] It should be noted that the functions or steps that the computer readable storage medium or the computer device can achieve described above can be referred to the related description in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0140] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to memory, storage, database or other medium used in each embodiment provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM) and the like.

[0141] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the system is divided into different functional units or modules to complete all or part of the functions described above.

[0142] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for constructing a black shank early warning model, characterized in that, The method includes: Multiple soil samples were collected from tobacco-growing areas where black shank disease was not present and from tobacco-growing areas where black shank disease was present to varying degrees. Physicochemical indicators were measured on multiple soil samples, and physicochemical indicator data of multiple soil samples were obtained. Microbiome analysis was performed on multiple soil samples to obtain a microbial community characteristic table; Based on physicochemical index data and microbial community characteristic table, key characteristics that have an important impact on the occurrence of black shank were identified. The classification model was trained using the feature values ​​of key features from multiple soil samples as training samples, resulting in an early warning model for tobacco black shank disease.

2. The method for constructing a black shank early warning model according to claim 1, characterized in that, Multiple soil samples were collected from tobacco-growing areas where black shank disease was not present and from tobacco-growing areas where black shank disease was present to varying degrees, including: In tobacco-growing areas where black shank disease has not occurred and in tobacco-growing areas where black shank disease has occurred to varying degrees, multiple soil samples were collected using the "S"-shaped sampling method. The sampling points avoided abnormal areas, and 5 to 10 g of soil samples were collected at each sampling point at a soil depth of 5 to 20 cm. Record the environmental data for each soil sample collection, and divide each soil sample into two parts, which are then sealed and stored at low temperature.

3. The method for constructing a black shank early warning model according to claim 1, characterized in that, The physicochemical index determination of multiple soil samples yielded physicochemical index data for multiple soil samples, including: The physicochemical properties of each soil sample were measured using the corresponding test kits to obtain the physicochemical property data for each soil sample. The physicochemical properties included: pH value, organic matter content, total nitrogen content, total phosphorus content, and total potassium content.

4. The method for constructing a black shank early warning model according to claim 1, characterized in that, The microbiome analysis of multiple soil samples yielded a microbial community characteristic table, including: DNA was extracted from each soil sample using a soil microbial DNA extraction kit. The concentration and purity of the extracted DNA were monitored using ultraviolet spectrophotometry and fluorescent dye method to ensure that the concentration and purity of the extracted DNA met the preset standards. Bacterial communities were amplified in the V3-V4 region of the 16S rRNA gene, and fungal communities were amplified in the ITS region. Paired-end high-throughput sequencing was performed to obtain sequencing data for each soil sample. The sequencing data were subjected to quality control, dechimeric removal, noise reduction, and species annotation to obtain a microbial community characteristic table.

5. The method for constructing a black shank early warning model according to claim 1, characterized in that, Based on physicochemical index data and microbial community characteristic tables, key characteristics that significantly influence the occurrence of black shank disease were identified, including: Alpha diversity analysis was performed based on the microbial community characteristic table to determine the alpha diversity index data for each soil sample. β-diversity analysis was performed based on the microbial community characteristic table to determine the β-diversity index data for each soil sample. Functional prediction was performed based on the microbial community characteristic table to determine the functional index data of each soil sample. Correlation analysis was used to screen key features that have an important impact on the occurrence of black shank disease from physicochemical index data, α diversity index data, β diversity index data and functional index data.

6. The method for constructing a black shank early warning model according to claim 5, characterized in that, Based on physicochemical index data and microbial community characteristic tables, key characteristics that significantly influence the occurrence of black shank disease were identified, including: The Richness index was calculated to determine the species richness data of each soil sample, the Shannon index was calculated to determine the microbial community diversity data of each soil sample, and the Simpson index was calculated to determine the microbial community concentration data of each soil sample. The species richness data, microbial community diversity data, and microbial community concentration data of each soil sample were used as α diversity index data. Distance matrix and principal coordinate analysis were used to determine the differential microbial communities in different soil samples, and redundancy analysis was used to determine the environmental driving factors. The abundance ratio of the differential microbial community and the environmental driving factor value of each soil sample were used as β diversity index data. PICRUSt2 was used to predict bacterial metabolic pathways, and FUNGuild was used to annotate fungal ecological functions. At least one pathogen that could potentially cause black shank disease and at least one antagonistic bacterium that could potentially inhibit the pathogen were screened out. The abundance ratio of at least one pathogen that could potentially cause black shank disease and the abundance ratio of at least one antagonistic bacterium that could potentially inhibit the pathogen were used as functional indicators for each soil sample. Using Spearman correlation analysis, key features that have an important impact on the occurrence of black shank were screened from physicochemical index data, α diversity index data, β diversity index data and functional index data.

7. The method for constructing a black shank early warning model according to claim 1, characterized in that, The method of training a classification model using the feature values ​​of key characteristics from multiple soil samples as training samples to obtain a tobacco black shank early warning model includes: Build a classification model; The classification model was trained using the feature values ​​of key features from multiple soil samples as training samples and a 10-fold cross-validation method. The trained classification model was independently tested using the feature values ​​of key features of historical soil samples as a test set to obtain a tobacco black shank early warning model.

8. A black shank early warning model construction system, characterized in that, The system includes: The soil sample collection module is used to collect multiple soil samples from tobacco planting areas that have not experienced black shank disease and tobacco planting areas that have experienced black shank disease to varying degrees. The physicochemical index determination module is used to determine the physicochemical indexes of multiple soil samples and obtain the physicochemical index data of multiple soil samples. The microbiome analysis module is used to perform microbiome analysis on multiple soil samples and obtain a microbial community characteristic table. The data processing module is used to identify key characteristics that have an important impact on the occurrence of black shank based on physicochemical index data and microbial community characteristic table; The model training module is used to train a classification model using the feature values ​​of key features from multiple soil samples as training samples, thereby obtaining a tobacco black shank early warning model.

9. A method for early warning of black shank disease, characterized in that, The method includes: Collect target soil samples from tobacco-growing areas; Physicochemical indicators and microbiome analysis were performed on the target soil samples. Based on the input requirements of the tobacco black shank early warning model, the characteristic values ​​of the key features of the target soil samples were determined. The characteristic values ​​of the key features of the target soil samples were then input into the tobacco black shank early warning model to obtain the predicted probability of tobacco black shank occurrence. Early warning information and prevention and control strategies are generated based on the predicted probability of tobacco black shank disease. Visualize and display the results of physicochemical index measurement, microbiome analysis, early warning information, and prevention and control strategies; The tobacco black shank early warning model is obtained based on the black shank early warning model construction method described in any one of claims 1 to 7.

10. A black shank early warning system, characterized in that, The system includes: The target soil sample collection module is used to collect target soil samples from tobacco growing areas. The integrated analysis module is used to determine the physicochemical indicators and perform microbiome analysis on the target soil sample. Based on the input requirements of the tobacco black shank early warning model, the feature values ​​of the key features of the target soil sample are determined. The feature values ​​of the key features of the target soil sample are then input into the tobacco black shank early warning model to obtain the predicted probability of tobacco black shank occurrence. The early warning module is used to generate early warning information and prevention and control strategies based on the predicted probability of tobacco black shank disease. The interactive module is used to visually display the results of physicochemical index measurement, microbiome analysis, early warning information, and prevention and control strategies. The tobacco black shank early warning model is obtained based on the black shank early warning model construction method described in any one of claims 1 to 7.

Images