Corn pathogen early warning method and system based on big data

Abstract

The invention discloses a corn pathogen early warning method and system based on big data, and relates to the technical field of agricultural early warning, the method comprises the following steps: comparing sequences in historical small RNA deep sequencing data and verified viral pathogen monitoring data, and establishing a mapping relationship between the two to obtain a pathogen-small RNA reference corresponding relationship library; matching the small RNA deep sequencing data of the current monitoring period with the pathogen-small RNA reference corresponding relationship library, and extracting sequence fragments consistent with the mapping relationship in the library to obtain a target viral pathogen feature sequence; coupling the target viral pathogen feature sequence with the current environmental factor data; according to the method, the core value in the multi-source data can be effectively mined, the early infection signal of the pathogen can be accurately captured, the early accurate prediction of the transmission risk and potential outbreak of the corn viral pathogen is realized, a timely and reliable decision basis is provided for field prevention and control, and the corn production safety is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of agricultural early warning technology, and in particular to a method and system for early warning of corn pathogens based on big data. Background Technology

[0002] With the development of molecular detection technology, small RNA deep sequencing technology has become an important means of monitoring maize pathogens because it can capture specific molecular signals generated during pathogen infection. However, this technology generates massive amounts of multi-source heterogeneous data, which contain a large amount of irrelevant sequence interference and differ significantly from historical pathogen monitoring data in terms of format, dimension, and characteristics.

[0003] Existing technologies lack effective data association and integration mechanisms. On the one hand, they fail to screen key environmental factors based on the biological characteristics of pathogens, and cannot dynamically quantify the compatibility between environmental conditions and the survival and activity of pathogens, making it difficult to determine the transmission potential of pathogens in different environmental scenarios. On the other hand, they fail to fully explore the spatiotemporal path patterns in historical disease transmission records, and the prediction models lack scientific historical references, only providing general risk assessments and failing to accurately simulate the potential spread direction, range, and outbreak probability of pathogens.

[0004] This fragmented and one-sided approach to data processing makes it difficult for existing technologies to accurately predict the early transmission risk and potential outbreak of maize viral pathogens based on multi-source heterogeneous data from deep sequencing of small RNAs. This makes it impossible to provide timely and effective decision support for field control, ultimately leading to passive disease control and severe yield losses. Summary of the Invention

[0005] This invention provides a method and system for early warning of maize pathogens based on big data, in order to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides a maize pathogen early warning method based on big data, comprising:

[0007] S1. Compare the sequences in historical small RNA deep sequencing data with the validated viral pathogen monitoring data, establish the mapping relationship between the two, and obtain the pathogen-small RNA reference correspondence library;

[0008] S2. Match the small RNA deep sequencing data of the current monitoring period with the pathogen-small RNA reference correspondence library, extract the sequence fragments that are consistent with the mapping relationship in the library, and obtain the characteristic sequence of the target viral pathogen;

[0009] S3. Couple the characteristic sequence of the target viral pathogen with the current environmental factor data, and evaluate the degree of influence of environmental conditions on the survival and activity of the pathogen based on the data obtained by coupling, so as to obtain the environment-pathogen adaptability criterion.

[0010] S4. By integrating environmental-pathogen adaptability criteria with spatiotemporal information from historical disease transmission records, potential diffusion trend analysis of target pathogens is conducted to obtain the transmission risk level.

[0011] S5. Based on the transmission risk level, match the preset early warning response strategy and determine the field early warning report.

[0012] Preferably, the step of comparing historical small RNA deep sequencing data with validated viral pathogen monitoring data to establish a mapping relationship between the two, thereby obtaining a pathogen-small RNA reference correspondence library, includes:

[0013] Based on historical small RNA deep sequencing data, small RNA sequence fragments that appear stably in virus-infected samples were screened to obtain candidate small RNA sequence fragments.

[0014] Co-occurrence association analysis was performed on candidate small RNA sequence fragments and validated viral pathogen monitoring data to obtain stable associations between small RNAs and pathogens;

[0015] Based on stable association relationships, a pathogen-small RNA reference correspondence library was constructed.

[0016] Preferably, the method of matching the small RNA deep sequencing data of the current monitoring period with the pathogen-small RNA reference correspondence library, extracting sequence fragments that match the mapping relationship in the library, and obtaining the characteristic sequence of the target viral pathogen includes:

[0017] Based on the small RNA deep sequencing data of the current monitoring period and the pathogen-small RNA reference correspondence database, sequence similarity comparison was performed to obtain a preliminary set of matching sequences;

[0018] The preliminary matching sequence set is clustered according to the homology of the candidate small RNA sequence fragments from which it originates, resulting in a classified sequence set;

[0019] Based on the relative abundance of the classification sequence set in the sample, the characteristic sequences of the target viral pathogen are identified.

[0020] Preferably, the coupling of the target viral pathogen's characteristic sequence with current environmental factor data includes:

[0021] The characteristic sequences of target viral pathogens are analyzed to determine their species and infection characteristics, thereby obtaining a description of the pathogen's biological characteristics.

[0022] Based on the description of the biological characteristics of pathogens, key environmental factors are extracted from the current environmental factor data to obtain a subset of key environmental factors.

[0023] By horizontally and synchronously associating and integrating real-time status data of a subset of key environmental factors with the characteristic sequences of target viral pathogens, a dynamic environmental-pathogen association dataset is obtained.

[0024] Preferably, the assessment of the impact of environmental conditions on pathogen survival and activity based on the coupled data includes:

[0025] Based on the dynamic correlation dataset between environment and pathogen, a consistency analysis was conducted on the status of key environmental factors and the biological requirements of pathogens to obtain the results of the consistency degree judgment.

[0026] Based on the consistency assessment results, the comprehensive promotion potential of the environment on pathogen activity is quantified to obtain the environmental adaptation potential level.

[0027] The environmental adaptability potential level constitutes the environmental-pathogen adaptability criterion.

[0028] Preferably, the spatiotemporal information in the fusion environment-pathogen adaptability criterion and historical disease transmission records includes:

[0029] From historical disease transmission records, spatiotemporal path information of historical events that are homologous to the current pathogen is extracted to obtain a set of historical transmission paths;

[0030] We conducted a weighted historical transmission path analysis based on environmental background similarity between the historical transmission path set and the environment-pathogen adaptability criterion to obtain the weighted historical transmission path.

[0031] Based on weighted historical propagation paths, a potential diffusion corridor prediction map driven by current environmental conditions is generated.

[0032] Preferably, the potential spread trend analysis of the target pathogen includes:

[0033] Identify the main diffusion directions in the potential diffusion corridor prediction map to obtain the preferred diffusion directions;

[0034] By combining the spatial layout of farmland, the pathogen diffusion process was simulated along the preferred diffusion direction, and preliminary diffusion simulation results were obtained.

[0035] Based on the differences in environmental adaptability potential levels of different micro-regions in the preliminary diffusion simulation results, the propagation speed and range are corrected to obtain a dynamic spatial risk distribution map.

[0036] Preferably, obtaining the transmission risk level includes:

[0037] Multidimensional information is aggregated to obtain a multidimensional risk feature vector by analyzing the temporal trends of spatial range, risk intensity, and environmental adaptability potential level in the dynamic spatial risk distribution map.

[0038] A comprehensive risk assessment of agronomic risk is conducted on the multidimensional risk feature vector to obtain the comprehensive risk level.

[0039] Preferably, the step of determining the field early warning report based on the pre-set early warning response strategy matched with the transmission risk level includes:

[0040] For the comprehensive risk level, analyze the risk scope, intensity and urgency information, and generate a preliminary set of response measures based on the analysis results;

[0041] By combining multidimensional risk feature vectors, the initial set of response measures is prioritized and optimized for spatiotemporal adaptability to obtain a personalized list of prevention and control strategies.

[0042] A list of personalized prevention and control strategies constitutes the core content of field early warning reports.

[0043] To address the above problems, this invention also provides a maize pathogen early warning system based on big data, the system comprising:

[0044] The data mapping and library building module is used to compare the sequences in historical small RNA deep sequencing data with the validated viral pathogen monitoring data, establish the mapping relationship between the two, and obtain the pathogen-small RNA reference correspondence library.

[0045] The real-time sequence feature extraction module is used to match the small RNA deep sequencing data of the current monitoring period with the pathogen-small RNA reference correspondence library, extract sequence fragments that are consistent with the mapping relationship in the library, and obtain the characteristic sequence of the target viral pathogen.

[0046] The environment-pathogen coupling analysis module is used to couple the characteristic sequence of the target viral pathogen with the current environmental factor data, and evaluate the degree of influence of environmental conditions on the survival and activity of the pathogen based on the coupled data, so as to obtain the environment-pathogen suitability criterion.

[0047] The dynamic simulation module for transmission risk is used to integrate spatiotemporal information from environmental-pathogen adaptability criteria and historical disease transmission records to analyze the potential spread trend of target pathogens and obtain the transmission risk level.

[0048] The early warning report generation module is used to match the preset early warning response strategy with the transmission risk level and determine the field early warning report.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] 1. By constructing a pathogen-small RNA reference correspondence library, extracting target pathogen characteristic sequences, coupling environmental factor data, integrating historical spatiotemporal information on transmission, and matching early warning strategies, a complete technical solution has been developed. This solution achieves deep correlation and systematic integration of small RNA sequencing data, historical monitoring data, and environmental factors, effectively mining the core value of multi-source data, accurately capturing early infection signals of pathogens, and enabling early and accurate prediction of the risk of transmission and potential outbreaks of viral pathogens in maize. This provides timely and reliable decision-making basis for field control and ensures the safety of maize production.

[0051] 2. Through precise screening of key environmental factors, weighted matching analysis of historical transmission paths, and optimization of the spatiotemporal adaptability of control strategies, the accuracy of pathogen transmission potential assessment and the precision of diffusion trend simulation have been further improved. This makes the generated field early warning reports more targeted and operable, enabling them to guide efficient control in the field and minimize yield losses caused by diseases. Attached Figure Description

[0052] Figure 1 This is a flowchart illustrating a big data-based early warning method for maize pathogens, provided in an embodiment of the present invention.

[0053] Figure 2 This is a schematic diagram of the specific process of S3 provided in an embodiment of the present invention;

[0054] Figure 3 This is a schematic diagram of the specific process of S4 provided in an embodiment of the present invention;

[0055] Figure 4 A functional block diagram of a maize pathogen early warning system based on big data provided in an embodiment of the present invention;

[0056] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0057] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0058] This application provides a method for early warning of maize pathogens based on big data. The executing entity of this method includes, but is not limited to, at least one of the electronic devices that can be configured to execute the method provided in this application, such as a server and a terminal. In other words, the method for early warning of maize pathogens based on big data can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cluster of cloud servers. The server can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0059] Example 1, referring to Figure 1 The diagram shown is a flowchart illustrating a big data-based early warning method for maize pathogens according to an embodiment of the present invention. In this embodiment, the big data-based early warning method for maize pathogens includes:

[0060] S1. Compare the sequences in historical small RNA deep sequencing data with the validated viral pathogen monitoring data, establish the mapping relationship between the two, and obtain the pathogen-small RNA reference correspondence library;

[0061] S2. Match the small RNA deep sequencing data of the current monitoring period with the pathogen-small RNA reference correspondence library, extract the sequence fragments that are consistent with the mapping relationship in the library, and obtain the characteristic sequence of the target viral pathogen;

[0062] S3. Couple the characteristic sequence of the target viral pathogen with the current environmental factor data, and evaluate the degree of influence of environmental conditions on the survival and activity of the pathogen based on the data obtained by coupling, so as to obtain the environment-pathogen adaptability criterion.

[0063] S4. By integrating environmental-pathogen adaptability criteria with spatiotemporal information from historical disease transmission records, potential diffusion trend analysis of target pathogens is conducted to obtain the transmission risk level.

[0064] S5. Based on the transmission risk level, match the preset early warning response strategy and determine the field early warning report.

[0065] In this embodiment of the invention, by comparing the sequences in historical small RNA deep sequencing data with those in validated viral pathogen monitoring data, a mapping relationship is established between the two, resulting in a pathogen-small RNA reference correspondence library, including:

[0066] Based on historical small RNA deep sequencing data, small RNA sequence fragments that appear stably in virus-infected samples were screened to obtain candidate small RNA sequence fragments.

[0067] Co-occurrence association analysis was performed on candidate small RNA sequence fragments and validated viral pathogen monitoring data to obtain stable associations between small RNAs and pathogens;

[0068] Based on stable association relationships, a pathogen-small RNA reference correspondence library was constructed.

[0069] Specifically, multiple batches of virus-infected maize control experiments were conducted, setting up virus treatment groups with different infection levels and healthy control groups. The maize were cultured under the same temperature, light, water, and fertilizer conditions, and the expression of small RNA sequences in each group was continuously monitored. Sequence features that appeared continuously only in all treatment groups and never appeared in the control group were recorded, and these features were extracted as the criteria for stable appearance. Based on historical small RNA deep sequencing data, according to this preset criterion, small RNA sequence fragments that appeared stably in virus-infected samples and did not appear in healthy samples were screened to obtain candidate small RNA sequence fragments.

[0070] Furthermore, virus infection tracking experiments were conducted in different maize planting areas and at different growth stages to record the synchronous occurrence of candidate small RNA sequences and viral pathogens. Co-occurrence characteristics of synchronous occurrence in the same region at the same time were extracted as association criteria. Based on this preset standard, co-occurrence association analysis was performed on candidate small RNA sequence fragments and verified viral pathogen monitoring data to obtain stable association relationships between small RNAs and pathogens.

[0071] Finally, the stable associations between the obtained small RNAs and pathogens were classified and organized according to the types of viral pathogens. For each type of viral pathogen, all corresponding stable associated candidate small RNA sequence fragments were bound to form a complete correspondence list containing the types of viral pathogens and their corresponding stable associated small RNA sequence fragments, thus obtaining a pathogen-small RNA reference correspondence library.

[0072] In summary, this embodiment ensures the stability and specificity of the association between small RNAs and pathogens by screening small RNA sequences that are stably present in virus-infected samples and absent in healthy samples, combined with co-occurrence association analysis across multiple regions and growth cycles. This effectively eliminates interference from irrelevant sequences and significantly improves the accuracy of subsequent pathogen identification. Furthermore, the constructed reference correspondence database is categorized by pathogen species and integrates rich historical data resources, covering pathogen characteristics under different planting scenarios. It possesses strong versatility and scalability and can be adapted to diverse maize planting environments and pathogen types.

[0073] In this embodiment of the invention, the small RNA deep sequencing data of the current monitoring period is matched with a pathogen-small RNA reference correspondence library, and sequence fragments that match the mapping relationship in the library are extracted to obtain the characteristic sequence of the target viral pathogen, including:

[0074] Based on the small RNA deep sequencing data of the current monitoring period and the pathogen-small RNA reference correspondence database, sequence similarity comparison was performed to obtain a preliminary set of matching sequences;

[0075] The preliminary matching sequence set is clustered according to the homology of the candidate small RNA sequence fragments from which it originates, resulting in a classified sequence set;

[0076] Based on the relative abundance of the classification sequence set in the sample, the characteristic sequences of the target viral pathogen are identified.

[0077] Specifically, each small RNA sequence in the maize small RNA deep sequencing data of the current monitoring period is compared with all small RNA sequences in the pathogen-small RNA reference correspondence library one by one at the base pair level. All sequences in the current sequencing data that are completely consistent with the small RNA sequences in the library are retained, and these sequences are integrated to form a preliminary matching sequence set.

[0078] Furthermore, the source of the candidate small RNA sequence fragments in the pathogen-small RNA reference correspondence database corresponding to each sequence in the preliminary matching sequence set is clarified. The preliminary matching sequences are grouped according to the source of the candidate small RNA sequence fragments. All preliminary matching sequences from the same candidate small RNA sequence fragment are grouped into one category. Each category of sequences forms a subset, and all subsets together constitute the classification sequence set.

[0079] Furthermore, it should be noted that relative abundance specifically refers to the proportion of small RNA sequences contained in a single subset of the classification sequence set to the total number of small RNA deep sequencing data in the current monitoring period. This proportion directly reflects the proportion of the corresponding candidate small RNA sequence fragments in the overall sequencing data, providing a core basis for distinguishing between maize virus infection status and healthy status.

[0080] To clarify the criteria for selecting target sequences based on relative abundance characteristics, a gradient experiment involving different virus concentrations infecting maize can be conducted. Gradient concentrations of virus infection treatment groups and healthy control groups are set up. Maize samples are cultivated under the same planting environment and culture conditions. After the samples reach a stable infection state, small RNA deep sequencing data are obtained for each group. Sequence subsets for each group are obtained according to the method for constructing classification sequence sets. The number of sequences in each subset and the total number of sequences in each group are counted. The relative abundance of each subset is calculated. Patterns are extracted from multiple batches of experimental data. The criterion is that "the relative abundance of the sequence subsets in the infection treatment group is consistently higher than the relative abundance baseline value of the healthy control group, and this difference remains consistent across different concentration gradients."

[0081] Furthermore, the number of small RNA sequences contained in each subset of the classification sequence set is counted, and the total number of sequences in the current monitoring period's small RNA deep sequencing data is also counted. The relative abundance of each subset is calculated, and the relative abundance of each subset is compared with the relative abundance of the subset formed by the corresponding candidate small RNA sequence fragments in the small RNA sequencing data of healthy maize samples during the same period according to a preset standard. Classification sequence subsets with a relative abundance that is consistently higher than the corresponding subsets of healthy samples are retained. These retained subsets are the characteristic sequences of the target viral pathogen.

[0082] In summary, this embodiment rapidly screens sequences that match the mapping relationship in the library through complete base pair alignment, avoiding repeated analysis of massive amounts of raw sequencing data, significantly improving the efficiency of feature sequence extraction, and saving time for subsequent early warning processes. Furthermore, by grouping sequences by origin through homology clustering, it effectively classifies related sequence fragments of the same pathogen, making feature information more concentrated and facilitating subsequent biological characteristic analysis. Simultaneously, based on the comparison of relative abundance with healthy samples and according to the pre-set judgment criteria of the gradient experiment, it accurately distinguishes between infected and healthy states, eliminating interference from low-abundance irrelevant sequences, significantly improving the specificity and reliability of target feature sequences, and avoiding misjudgments.

[0083] Example 2, refer to Figure 2 The diagram shown is a schematic diagram of the specific process of S3 provided in an embodiment of the present invention.

[0084] In this embodiment of the invention, coupling the characteristic sequence of a target viral pathogen with current environmental factor data includes:

[0085] The characteristic sequences of target viral pathogens are analyzed to determine their species and infection characteristics, thereby obtaining a description of the pathogen's biological characteristics.

[0086] Based on the description of the biological characteristics of pathogens, key environmental factors are extracted from the current environmental factor data to obtain a subset of key environmental factors.

[0087] By horizontally and synchronously associating and integrating real-time status data of a subset of key environmental factors with the characteristic sequences of target viral pathogens, a dynamic environmental-pathogen association dataset is obtained.

[0088] Specifically, by comparing the characteristic sequence of the target viral pathogen with the characteristic sequence database of known viral pathogens one by one, the specific species of the target pathogen is determined. At the same time, combined with the known infection patterns of the pathogen of this species, information such as the key growth stages of its infection in maize, suitable living conditions, and the environmental support required for its spread is clarified. This information is then integrated to form a description of the biological characteristics of the pathogen.

[0089] Furthermore, based on the environmental conditions required for the survival and activity of pathogens as specified in the description of their biological characteristics, environmental factors directly related to these conditions are screened from the current environmental factor data. For example, if the description of biological characteristics indicates that the pathogen is suitable for activity in high humidity and a specific temperature range, humidity data, temperature data, etc., are screened from the current environmental factor data, and these screened environmental factors are integrated to form a subset of key environmental factors.

[0090] Finally, based on the time node of the current monitoring cycle, the real-time status data of the key environmental factor subset is accurately matched with the detection time of the target viral pathogen characteristic sequence to ensure that the environmental factor data at the same time node corresponds to the corresponding pathogen characteristic sequence. At the same time, the corn planting area information corresponding to both is associated, and these matched and associated information are organized and integrated in chronological order to obtain the environment-pathogen dynamic association dataset.

[0091] In this embodiment of the invention, assessing the impact of environmental conditions on pathogen survival and activity based on coupled data includes:

[0092] Based on the dynamic correlation dataset between environment and pathogen, a consistency analysis was conducted on the status of key environmental factors and the biological requirements of pathogens to obtain the results of the consistency degree judgment.

[0093] Based on the consistency assessment results, the comprehensive promotion potential of the environment on pathogen activity is quantified to obtain the environmental adaptation potential level.

[0094] The environmental adaptability potential level constitutes the environmental-pathogen adaptability criterion.

[0095] Among them, consistency analysis assesses the fit of a single factor by constructing a suitability membership function of key environmental factor values ​​to pathogen activity:

[0096] ;

[0097] Indicates the first element in the key environmental factor subset. The current real-time status values ​​of key environmental factors.

[0098] Indicates the first The theoretical optimal values ​​of key environmental factors for the activity of the target pathogen are derived from the description of the pathogen's biological characteristics.

[0099] Indicates the first The tolerance threshold width parameter of a key environmental factor is used to control the width of the membership function. It is also derived from the description of the biological characteristics of the pathogen and reflects the sensitivity of the pathogen to fluctuations of the factor.

[0100] Indicates the current environmental factor value The degree of membership in a suitable fuzzy set ranges from 0 to 1, with values ​​closer to 1 indicating a more suitable state for pathogen activity. The consistency assessment result is determined by the values ​​of each key factor. Together they constitute.

[0101] Specifically, for each key environmental factor in the environment-pathogen dynamic association dataset, a single-factor gradient influence experiment is conducted. The key environmental factor can be selected as the only variable, and all other key environmental factors are adjusted to the theoretical optimal value of the pathogen. A continuous gradient value interval with sufficient coverage is set around the theoretical optimal value of the environmental factor. The activity intensity indicators such as the pathogen's reproduction rate and infectivity are monitored under different gradient values. The width of the value interval of the environmental factor when the pathogen's activity intensity is maintained at more than 80% of the optimal level is statistically analyzed, and the half-width of the interval width is used as the tolerance threshold width parameter.

[0102] Furthermore, the three parameter values ​​corresponding to the factor are first determined. The current real-time state value comes from the real-time monitoring data of the key environmental factor subset. The theoretical optimal value and the tolerance threshold width parameter are extracted from the pathogen biological characteristic description. The theoretical optimal value is the environmental factor value that is most suitable for the pathogen activity as specified in the biological characteristic description. The tolerance threshold width parameter is a parameter in the biological characteristic description that reflects the pathogen's sensitivity to fluctuations in the environmental factor.

[0103] Specifically, the calculation first calculates the difference between the current real-time state value and the theoretical optimal value, then squares the difference, and simultaneously squares the tolerance threshold width parameter and multiplies it by 2. The squared result of the difference is divided by this product to obtain a calculated value. Then, the negative exponent of the calculated value is taken, and the result is the degree to which the current environmental factor value belongs to the suitable fuzzy set.

[0104] Specifically, this value ranges from 0 to 1 and can be used to determine the suitability of a single key environmental factor state for pathogen activity. The closer the value is to 1, the more suitable the current environmental factor state is for pathogen activity. By integrating this value corresponding to all key environmental factors, the consistency judgment result is obtained.

[0105] Furthermore, all values ​​in the consistency assessment results are comprehensively considered. First, a classification standard for the environmental adaptability potential level is preset. This standard is preset by conducting an experiment on the influence of environmental factor gradients. In the experiment, the single key environmental factor is controlled to change in different ranges, while the other factors are kept in a suitable state. The activity intensity of pathogens, such as reproduction rate and infectivity, is monitored. The correspondence between the activity intensity of pathogens under different environmental factor ranges is recorded. The range standard for the environmental adaptability potential level is divided based on the difference characteristics of activity intensity. Then, different contribution weights are determined according to the size distribution of each value.

[0106] Specifically, the closer the value of a key environmental factor is to 1, the greater its promoting effect on pathogen activity, and the higher its corresponding weight. Each value is multiplied by its corresponding weight and then summed to obtain a comprehensive promoting potential value. Different environmental adaptation potential levels are then classified according to a preset classification standard. For example, the closer the comprehensive promoting potential value is to 1, the higher the corresponding environmental adaptation potential level, indicating that the environment has a stronger comprehensive promoting effect on pathogen activity.

[0107] Furthermore, the environmental adaptability potential levels obtained are used as environmental-pathogen adaptability criteria. These criteria directly reflect the degree of influence of current environmental conditions on the survival and activity of target viral pathogens. The higher the level, the more suitable the current environment is for the survival and activity of pathogens, and the easier it is to cause maize viral diseases.

[0108] In summary, this embodiment first analyzes the species and infection characteristics of the pathogen, accurately identifies the key environmental factors required for its survival, reproduction and spread, avoids indiscriminate analysis of massive amounts of environmental data, greatly improves the targeting of environmental factor screening, effectively eliminates interference from irrelevant factors, and allows subsequent evaluation to focus on core influencing factors.

[0109] Secondly, by horizontally and synchronously integrating real-time data of key environmental factors with pathogen characteristic sequences, precise matching of time points and planting areas was achieved, ensuring a strong correlation between environmental data and pathogen status. This provided a high-quality, highly reliable dynamic dataset for assessment, avoiding assessment bias caused by data misalignment.

[0110] Overall, this embodiment uses a fitness membership function to conduct consistency analysis, quantifying the fit between environmental conditions and pathogen biological needs into an environmental fit potential level, replacing traditional qualitative judgment, making the assessment results more objective, accurate, and intuitively reflecting the degree to which the environment promotes or inhibits pathogen survival activities.

[0111] Example 3, referring to Figure 3 The diagram shown is a schematic diagram of the specific process of S4 provided in an embodiment of the present invention.

[0112] In this embodiment of the invention, the spatiotemporal information in the environmental-pathogen adaptability criterion and historical disease transmission records are integrated to analyze the potential diffusion trend of the target pathogen and obtain the transmission risk level.

[0113] In this embodiment of the invention, the fusion of spatiotemporal information from the environment-pathogen adaptability criterion and historical disease transmission records includes:

[0114] From historical disease transmission records, spatiotemporal path information of historical events that are homologous to the current pathogen is extracted to obtain a set of historical transmission paths;

[0115] We conducted a weighted historical transmission path analysis based on environmental background similarity between the historical transmission path set and the environment-pathogen adaptability criterion to obtain the weighted historical transmission path.

[0116] Based on weighted historical propagation paths, a potential diffusion corridor prediction map driven by current environmental conditions is generated.

[0117] Among them, the weighted matching analysis based on environmental background similarity determines the weight by calculating the cosine similarity between the environmental vector at the time of the historical event and the current environmental vector, as shown in the following formula:

[0118] ;

[0119] This represents a multidimensional vector consisting of observations from a subset of key environmental factors during a specific time period in a historical disease transmission event. This represents a multidimensional vector consisting of the real-time status values ​​of a subset of key environmental factors during the current monitoring period.

[0120] This represents the dot product operation of vectors. This represents the Euclidean length of the vector.

[0121] This represents cosine similarity, with values ​​ranging from -1 to 1. In this application scenario, since all environmental factors are non-negative, its value is between 0 and 1. The larger the value, the more similar the historical environment is to the current environment.

[0122] This indicates the weight assigned to this historical transmission path, directly from... The higher the similarity, the greater its weight in predicting current potential diffusion corridors.

[0123] Specifically, based on the species information of the target pathogen, historical disease events belonging to the same species as the current pathogen are screened from historical disease transmission records. The onset time of each historical event, key time nodes in the spread process, and the geographical coordinates corresponding to each time node are extracted. At the same time, the complete geographical trajectory of the event from the starting area to the spread area is recorded. These information containing time series and geographical trajectory are integrated to form a set of historical transmission paths.

[0124] Furthermore, two types of environmental vectors are constructed: the historical environmental vector consists of the observation values ​​of the key environmental factor subset corresponding to the time period during the occurrence of historical disease transmission events, arranged in a fixed factor order; and the current environmental vector consists of the real-time status values ​​of the key environmental factor subset in the current monitoring period, arranged in the same factor order.

[0125] Specifically, the calculation first involves performing a dot product operation on the two vectors, that is, multiplying the environmental factor values ​​at corresponding positions pairwise and summing the results to obtain the dot product; then, the Euclidean lengths of the two vectors are calculated separately, that is, squaring all factor values ​​in each vector, summing the results, and then taking the square root of the summation to obtain the length of each vector; finally, the dot product result is divided by the product of the Euclidean lengths of the two vectors, and the result is the cosine similarity.

[0126] Specifically, the cosine similarity measures the degree of similarity between the environment when a historical event occurred and the current environment. Since all environmental factors are non-negative, their values ​​range from 0 to 1, and the trend is that the larger the value, the higher the environmental similarity between the two.

[0127] Furthermore, the cosine similarity is directly used as the weight of the corresponding historical propagation path. The higher the similarity of the historical propagation path, the greater the weight. All the historical propagation paths with assigned weights together constitute the weighted historical propagation path.

[0128] Furthermore, based on weighted historical transmission paths and combined with the environmental adaptability potential level in the environmental-pathogen adaptability criterion, the historical transmission paths with higher weights are used as core references. Areas with high adaptability potential levels in the current environment are overlaid. By connecting the core paths with high adaptability areas, a corridor graph that reflects the possible direction and range of pathogen spread under the current environmental conditions is drawn, generating a potential spread corridor prediction map driven by the current environmental conditions.

[0129] In this embodiment of the invention, the potential spread trend analysis of the target pathogen includes:

[0130] Identify the main diffusion directions in the potential diffusion corridor prediction map to obtain the preferred diffusion directions;

[0131] By combining the spatial layout of farmland, the pathogen diffusion process was simulated along the preferred diffusion direction, and preliminary diffusion simulation results were obtained.

[0132] Based on the differences in environmental adaptability potential levels of different micro-regions in the preliminary diffusion simulation results, the propagation speed and range are corrected to obtain a dynamic spatial risk distribution map.

[0133] Specifically, the diffusion corridors in the potential diffusion corridor prediction map are analyzed. First, the criteria for determining the main diffusion direction are preset. The preset criteria can be achieved by conducting field pathogen diffusion tracking experiments. In the experiment, the initial infection point of the pathogen is set in plots with different maize planting layouts. The natural diffusion trajectory of the pathogen is continuously tracked, and the relationship between the extension length, coverage width and diffusion speed of different diffusion trajectories is recorded. The characteristics of the trajectory with the largest diffusion range are analyzed. Based on these characteristics, the criteria for determining the main diffusion direction are determined. Then, the extension length and coverage width of each corridor are counted. According to the preset criteria, the direction pointed to by the corridor with the longest extension length and the widest coverage width is determined as the main diffusion direction. All main diffusion directions are integrated to obtain the priority diffusion direction.

[0134] Furthermore, information on the spatial layout of farmland in the current maize planting area is collected, including the distribution range of planting plots, the connecting channels between plots such as field ridges and irrigation channels, and the planting density of plots. Guided by the priority direction of diffusion, starting from the area where the target pathogen has been detected, the spread process of the pathogen between different plots is gradually deduced according to the connection relationship of the plots. The spread range and time required at each stage of the spread process are recorded to obtain preliminary spread simulation results.

[0135] Finally, the environmental adaptability potential levels of different micro-regions in the preliminary diffusion simulation results are extracted. For micro-regions with high environmental adaptability potential levels, it is determined that the pathogen spreads faster and has a wider diffusion range in the region, and the diffusion speed parameter of the region is adjusted accordingly to increase the diffusion range. For micro-regions with low environmental adaptability potential levels, it is determined that the pathogen spreads slower and has a limited diffusion range, and the diffusion speed parameter of the region is adjusted to reduce the diffusion range. After the above adjustments, a dynamic spatial risk distribution map is obtained.

[0136] In this embodiment of the invention, the transmission risk level is obtained, including:

[0137] Multidimensional information is aggregated to obtain a multidimensional risk feature vector by analyzing the temporal trends of spatial range, risk intensity, and environmental adaptability potential level in the dynamic spatial risk distribution map.

[0138] A comprehensive risk assessment of agronomic risk is conducted on the multidimensional risk feature vector to obtain the comprehensive risk level.

[0139] Specifically, the spatial range of the spread, i.e. the geographical area that the pathogen may cover, and the risk intensity, i.e. the probability of pathogen infection in different regions, are extracted from the dynamic spatial risk distribution map. At the same time, the changes in the environmental adaptability potential level at different time points, i.e. the time sequence change trend, are combined with these three types of information according to fixed dimensions to form a multidimensional risk feature vector that can comprehensively reflect the risk of pathogen spread.

[0140] Furthermore, by combining the tolerance of maize to target pathogens at different growth stages with the extent of damage caused by similar pathogens in the past, an agronomic risk assessment standard was established. The standard was pre-set through multi-growth stage maize pathogen infection experiments. In the experiments, different pathogen infection gradients were set at key growth stages of maize, and the disease incidence and yield loss data of maize under each gradient were monitored. At the same time, the occurrence and loss data of diseases under different risk characteristics in history were summarized, and the correspondence between risk characteristics and disease losses was analyzed. Based on experimental data and historical patterns, the risk level corresponding to different characteristic combinations was determined, and an agronomic risk assessment standard was established.

[0141] Furthermore, based on this standard, the information in the multidimensional risk feature vector is comprehensively considered. If the diffusion space is large, the risk intensity is high, and the environmental adaptability potential level continues to rise, it is judged as a high-risk level. Otherwise, it is judged as a medium-low risk level based on the specific combination of features. The final comprehensive risk level is the transmission risk level.

[0142] In summary, this embodiment prioritizes extracting historical spatiotemporal transmission paths that are homologous to the current pathogen, ensuring the relevance and specificity of historical data and avoiding interference from irrelevant transmission cases in the analysis results. This provides a reliable historical reference basis for predicting diffusion trends. Cosine similarity calculation is used to achieve environmental background similarity weight matching, accurately associating historical transmission paths with current environmental conditions. Higher similarity results in greater weight, making the reuse of historical experience more scientific and significantly improving the accuracy of diffusion predictions.

[0143] Furthermore, this embodiment generates a potential diffusion corridor prediction map based on weighted historical paths and environmental adaptability criteria, transforming abstract propagation patterns into visual spatial guidance, clearly presenting the possible diffusion directions of pathogens, and providing an intuitive basis for subsequent simulation analysis. By combining the simulation of the diffusion process with the spatial layout of farmland, and adjusting the propagation speed and range according to the differences in environmental adaptability potential levels of different micro-regions, the diffusion simulation takes into account both macro-trends and micro-regional characteristics, resulting in a dynamic spatial risk distribution map that better reflects the actual field scenario.

[0144] Overall, by aggregating spatial range, risk intensity, and temporal trends of environmental adaptability to form a multidimensional risk feature vector, and combining maize growth tolerance and historical disease losses to establish agronomic risk assessment criteria, the transformation from data level to actual agricultural risk has been achieved. The resulting transmission risk level is comprehensive and objective, quantifying the degree of risk and clarifying the spatiotemporal characteristics of risk impact.

[0145] S5. Based on the transmission risk level, match the preset early warning response strategy and determine the field early warning report, including:

[0146] For the comprehensive risk level, analyze the risk scope, intensity and urgency information, and generate a preliminary set of response measures based on the analysis results;

[0147] By combining multidimensional risk feature vectors, the initial set of response measures is prioritized and optimized for spatiotemporal adaptability to obtain a personalized list of prevention and control strategies.

[0148] A list of personalized prevention and control strategies constitutes the core content of field early warning reports.

[0149] Specifically, for the comprehensive risk level, firstly, the corresponding risk range, namely the boundary of the corn planting area that the pathogen may spread and cover, is defined, and then the judgment criteria for risk intensity and urgency are preset. The preset risk intensity judgment criteria are achieved by conducting experiments on the correlation between pathogen concentration and corn disease incidence. In the experiments, the probability of corn disease and the severity of disease under different pathogen concentrations are monitored, and the correspondence between concentration and disease severity is established as the basis for risk intensity judgment.

[0150] Furthermore, the pre-set criteria for determining urgency can be achieved by conducting experiments on the effects of temporal changes in environmental factors. In the experiments, the changing trends of environmental adaptability potential levels are simulated, and the changes in the spread rate of pathogens under different trends are monitored to determine the criteria for determining the strength of urgency. Then, the risk intensity, i.e. the probability of pathogens infecting corn in different regions, is determined based on these two pre-set criteria. At the same time, the urgency is analyzed in conjunction with the temporal changing trends of environmental adaptability potential levels. If the environmental adaptability potential level continues to rise, the urgency is determined to be strong, and vice versa.

[0151] Furthermore, based on these analysis results, corresponding basic response measures are matched. For example, if the risk range is large, it is included in the overall patrol measures; if the risk intensity is high, it is included in the enhanced drug control measures; and if the urgency is high, it is included in the immediate response measures. These matched measures are then integrated to form a preliminary set of response measures.

[0152] Furthermore, experiments were conducted on the effectiveness of different response measures. For scenarios with different risk intensities and urgency, the implementation effects, timeliness, and costs of measures such as full-area patrols, drug control, and immediate response were tested. The ranking characteristics of the measures with the best effect in high-risk and high-urgency scenarios were extracted as the priority ranking criteria.

[0153] It should be noted that, in order to determine the basis and specific duration for advancing the implementation time of prevention and control measures, a field pathogen diffusion rate gradient experiment can be conducted. Plots with soil and climate conditions consistent with the current corn planting area should be selected, and experimental zones with different environmental adaptability potential levels should be set up. Initial infection points of pathogens should be set up at the same location in each zone. The boundary range of pathogen diffusion from the initial infection point should be monitored regularly. The time required for pathogens to diffuse to the same distance boundary within zones of different environmental adaptability potential levels should be recorded. Multiple batches of experimental data should be analyzed to extract patterns, clarifying that the higher the environmental adaptability potential level, the faster the pathogen diffusion rate. Simultaneously, the diffusion time difference between zones of different environmental adaptability potential levels and the benchmark area of ​​medium adaptability potential level should be statistically analyzed to form a rule for determining the environmental adaptability potential level and diffusion time difference.

[0154] Furthermore, information on risk intensity, diffusion time sequence changes, and risk differences in different micro-regions is extracted from the multidimensional risk feature vector. Based on preset standards, the risk intensity and urgency are used as the priority ranking criteria, with the response measures that have higher risk intensity and greater urgency ranking higher.

[0155] Simultaneously, the spatial range and temporal change trends reflected by multidimensional risk feature vectors are combined to optimize spatiotemporal adaptability. For areas with priority diffusion directions, their environmental adaptability potential level is extracted. By comparing with the preset environmental adaptability potential level-diffusion time difference judgment rule, the corresponding time difference is matched as the duration for advancing the implementation time of prevention and control measures. The implementation frequency and scope of measures are adjusted for micro-areas with different risk intensities. After sorting and optimization, the measures are organized into a personalized prevention and control strategy list according to implementation priority, time node and specific area.

[0156] Finally, the personalized prevention and control strategy list details the specific operational content and implementation time of each prevention and control measure, the applicable corn planting areas, and the key precautions during implementation. This list serves as the core content, supplemented by the specific criteria for determining the current transmission risk level and key characteristic information on pathogen spread, together forming a field early warning report to provide precise action guidance for field prevention and control work.

[0157] Overall, this embodiment first analyzes the scope, intensity, and urgency corresponding to the transmission risk level to accurately match basic response measures, avoiding blind implementation of prevention and control measures and ensuring that measures are precisely aligned with risk characteristics. Prioritization is achieved by combining multi-dimensional risk feature vectors, using risk intensity and urgency as the core ranking criteria, allowing high-priority measures to be implemented first, improving the efficiency of prevention and control response. Simultaneously, through spatiotemporal adaptability optimization, measures are deployed in advance for priority spread areas, and the frequency and scope of measures are adjusted according to micro-regional risk differences, achieving personalized prevention and control.

[0158] Overall, the final field early warning report, with a personalized list of prevention and control strategies at its core, clarifies the operational details, timelines, and applicable areas of the measures, thus reducing farmers' decision-making costs.

[0159] Example 4, as Figure 4 The diagram shown is a functional block diagram of a maize pathogen early warning system based on big data provided in an embodiment of the present invention.

[0160] This invention relates to a big data-based early warning system for maize pathogens that can be installed in an electronic device. Depending on the functions implemented, the big data-based early warning system for maize pathogens may include a data mapping and database construction module 101, a real-time sequence feature extraction module 102, an environment-pathogen coupling analysis module 103, an environment-pathogen coupling analysis module 104, and an early warning report generation module 105. The modules of this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, and are stored in the memory of the electronic device.

[0161] In this embodiment, the functions of each module / unit are as follows:

[0162] The data mapping library module 101 is used to compare the sequences in historical small RNA deep sequencing data with the validated viral pathogen monitoring data, establish the mapping relationship between the two, and obtain the pathogen-small RNA reference correspondence library.

[0163] The real-time sequence feature extraction module 102 is used to match the small RNA deep sequencing data of the current monitoring period with the pathogen-small RNA reference correspondence library, extract sequence fragments that are consistent with the mapping relationship in the library, and obtain the characteristic sequence of the target viral pathogen.

[0164] The environment-pathogen coupling analysis module 103 is used to couple the characteristic sequence of the target viral pathogen with the current environmental factor data, and evaluate the degree of influence of environmental conditions on the survival and activity of the pathogen based on the coupled data, and obtain the environment-pathogen suitability criterion.

[0165] The dynamic simulation module 104 for transmission risk is used to integrate spatiotemporal information from environmental-pathogen adaptability criteria and historical disease transmission records to analyze the potential diffusion trend of the target pathogen and obtain the transmission risk level.

[0166] The early warning report generation module 105 is used to determine the field early warning report by matching the preset early warning response strategy according to the transmission risk level.

[0167] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and there may be other division methods in actual implementation.

[0168] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0169] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0170] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0171] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0172] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A corn pathogen early warning method based on big data, characterized in that, The method includes: S1. Compare the sequences in historical small RNA deep sequencing data with the validated viral pathogen monitoring data, establish the mapping relationship between the two, and obtain the pathogen-small RNA reference correspondence library; S2. Match the small RNA deep sequencing data of the current monitoring period with the pathogen-small RNA reference correspondence library, extract the sequence fragments that are consistent with the mapping relationship in the library, and obtain the characteristic sequence of the target viral pathogen; S3. Couple the characteristic sequence of the target viral pathogen with the current environmental factor data, and evaluate the degree of influence of environmental conditions on the survival and activity of the pathogen based on the data obtained by coupling, so as to obtain the environment-pathogen adaptability criterion. S4. By integrating environmental-pathogen adaptability criteria with spatiotemporal information from historical disease transmission records, potential diffusion trend analysis of target pathogens is conducted to obtain the transmission risk level. S5. Based on the transmission risk level, match the preset early warning response strategy and determine the field early warning report.

2. The method for early warning of maize pathogens based on big data as described in claim 1, characterized in that, The sequence is compared with historical small RNA deep sequencing data and validated viral pathogen monitoring data to establish a mapping relationship between the two, resulting in a pathogen-small RNA reference correspondence library, including: Based on historical small RNA deep sequencing data, small RNA sequence fragments that appear stably in virus-infected samples were screened to obtain candidate small RNA sequence fragments. Co-occurrence association analysis was performed on candidate small RNA sequence fragments and validated viral pathogen monitoring data to obtain stable associations between small RNAs and pathogens; Based on stable association relationships, a pathogen-small RNA reference correspondence library was constructed.

3. The method for early warning of maize pathogens based on big data as described in claim 1, characterized in that, The small RNA deep sequencing data of the current monitoring period is matched with the pathogen-small RNA reference correspondence library. Sequence fragments that match the mapping relationship in the library are extracted to obtain the characteristic sequences of the target viral pathogen, including: Based on the small RNA deep sequencing data of the current monitoring period and the pathogen-small RNA reference correspondence database, sequence similarity comparison was performed to obtain a preliminary set of matching sequences; The preliminary matching sequence set is clustered according to the homology of the candidate small RNA sequence fragments from which it originates, resulting in a classified sequence set; Based on the relative abundance of the classification sequence set in the sample, the characteristic sequences of the target viral pathogen are identified.

4. The method for early warning of maize pathogens based on big data as described in claim 1, characterized in that, The coupling of the target viral pathogen's characteristic sequence with current environmental factor data includes: The characteristic sequences of target viral pathogens are analyzed to determine their species and infection characteristics, thereby obtaining a description of the pathogen's biological characteristics. Based on the description of the biological characteristics of pathogens, key environmental factors are extracted from the current environmental factor data to obtain a subset of key environmental factors. By horizontally and synchronously associating and integrating real-time status data of a subset of key environmental factors with the characteristic sequences of target viral pathogens, a dynamic environmental-pathogen association dataset is obtained.

5. The method for early warning of maize pathogens based on big data as described in claim 4, characterized in that, The assessment of the impact of environmental conditions on pathogen survival and activity based on coupled data includes: Based on the dynamic correlation dataset between environment and pathogen, a consistency analysis was conducted on the status of key environmental factors and the biological requirements of pathogens to obtain the results of the consistency degree judgment. Based on the consistency assessment results, the comprehensive promotion potential of the environment on pathogen activity is quantified to obtain the environmental adaptation potential level. The environmental adaptability potential level constitutes the environmental-pathogen adaptability criterion.

6. The method for early warning of maize pathogens based on big data as described in claim 1, characterized in that, The fusion of environmental pathogen adaptability criteria and spatiotemporal information from historical disease transmission records includes: From historical disease transmission records, spatiotemporal path information of historical events that are homologous to the current pathogen is extracted to obtain a set of historical transmission paths; We conducted a weighted historical transmission path analysis based on environmental background similarity between the historical transmission path set and the environment-pathogen adaptability criterion to obtain the weighted historical transmission path. Based on weighted historical propagation paths, a potential diffusion corridor prediction map driven by current environmental conditions is generated.

7. The method for early warning of maize pathogens based on big data as described in claim 6, characterized in that, The potential spread trend analysis of the target pathogen includes: Identify the main diffusion directions in the potential diffusion corridor prediction map to obtain the preferred diffusion directions; By combining the spatial layout of farmland, the pathogen diffusion process was simulated along the preferred diffusion direction, and preliminary diffusion simulation results were obtained. Based on the differences in environmental adaptability potential levels of different micro-regions in the preliminary diffusion simulation results, the propagation speed and range are corrected to obtain a dynamic spatial risk distribution map.

8. The method for early warning of maize pathogens based on big data as described in claim 7, characterized in that, The obtained transmission risk level includes: Multidimensional information is aggregated to obtain a multidimensional risk feature vector by analyzing the temporal trends of spatial range, risk intensity, and environmental adaptability potential level in the dynamic spatial risk distribution map. A comprehensive risk assessment of agronomic risk is conducted on the multidimensional risk feature vector to obtain the comprehensive risk level.

9. The method for early warning of maize pathogens based on big data as described in claim 8, characterized in that, The process of determining field early warning reports based on a pre-set early warning response strategy matched with the transmission risk level includes: For the comprehensive risk level, analyze the risk scope, intensity and urgency information, and generate a preliminary set of response measures based on the analysis results; By combining multidimensional risk feature vectors, the initial set of response measures is prioritized and optimized for spatiotemporal adaptability to obtain a personalized list of prevention and control strategies. A list of personalized prevention and control strategies constitutes the core content of field early warning reports.

10. A big data-based early warning system for maize pathogens, used to implement the big data-based early warning method for maize pathogens as described in any one of claims 1-9, characterized in that, The system includes: The data mapping and library building module is used to compare the sequences in historical small RNA deep sequencing data with the validated viral pathogen monitoring data, establish the mapping relationship between the two, and obtain a pathogen-small RNA reference correspondence library. The real-time sequence feature extraction module is used to match the small RNA deep sequencing data of the current monitoring period with the pathogen-small RNA reference correspondence library, extract sequence fragments that are consistent with the mapping relationship in the library, and obtain the characteristic sequence of the target viral pathogen. The environment-pathogen coupling analysis module is used to couple the characteristic sequence of the target viral pathogen with the current environmental factor data, and evaluate the degree of influence of environmental conditions on the survival and activity of the pathogen based on the coupled data, so as to obtain the environment-pathogen suitability criterion. The dynamic simulation module for transmission risk is used to integrate spatiotemporal information from environmental-pathogen adaptability criteria and historical disease transmission records to analyze the potential spread trend of target pathogens and obtain the transmission risk level. The early warning report generation module is used to match the preset early warning response strategy with the transmission risk level and determine the field early warning report.

Images