Corn stress resistance prediction system and method based on multi-source data

Abstract

The invention relates to the technical field of agricultural prediction analysis, in particular to a corn stress resistance prediction system and method based on multi-source data, and the method comprises the following steps: obtaining genotype marker data, real-time environmental stress data and farmland historical operation records of a target corn plant; inputting the obtained data into a dynamic decision engine, and outputting a stress resistance decision vector comprising a stress type identifier and a regulation and control time window; and activating corresponding farming equipment according to the regulation and control time window, and implementing regulation and control operation associated with the stress type identifier in the specified time window. According to the agricultural control system, the problems of response delay, untimely processing of equipment faults and the like in a traditional agricultural Internet of Things system are avoided, and the continuity and the safety of agricultural control operation under the high-risk stress condition are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural prediction and analysis, and in particular to a maize stress resistance prediction system and method based on multi-source data. Background Art

[0002] Abiotic stress such as drought and salinity is one of the key factors restricting the high and stable yield of maize. Traditional maize stress resistance management relies on long-term breeding screening and static agronomic rules, lacking the ability of dynamic regulation for the real-time state of individual plants, and it is difficult to meet the development needs of precision agriculture.

[0003] The existing maize stress resistance regulation methods have the following deficiencies: Poor timeliness of data acquisition: Currently, the judgment of plant stress resistance traits is mostly based on laboratory molecular detection and long-term field observation. The detection cycle is long (usually several days), which cannot meet the demand for rapid response to environmental changes; Insufficient accuracy of stress recognition: Mainstream environmental monitoring parameters (such as soil conductivity, air humidity) are not sensitive to the early response of stress, resulting in a lag in adversity response and affecting the regulation effect; The decision-making mechanism lacks the support of a quantitative time window: Existing systems mostly only output "stress exists" or "risk level", lacking a mechanism to map stress intensity into an executable time control, and it is difficult to provide an interpretable scheduling signal for agricultural equipment; Poor stability of operation execution: Currently, most agricultural automation systems use general-purpose processors to send control instructions, which are easily affected by communication delays and software blockages, and lack a mandatory verification mechanism for job completion status. The operation failure rate is high, affecting the reliability of field application. Summary of the Invention

[0004] The present invention provides a maize stress resistance prediction system and method based on multi-source data, which integrates a full-process stress resistance prediction and execution system of rapid gene detection, precise environmental monitoring, stress intensity calculation and control strategy linkage, and realizes individualized, real-time and closed-loop regulation of maize adversity response.

[0005] A maize stress resistance prediction method based on multi-source data includes the following steps: S1, synchronously collect data: Obtain genotype marker data, real-time environmental stress data and farmland historical operation records of the target maize plant; S2, generate a stress resistance decision vector: Input the data of S1 into a dynamic decision engine, and output a stress resistance decision vector including a stress type identifier and a regulation time window; S3. Execute the regulation instruction: Activate the corresponding agricultural equipment according to the regulation time window, and implement the regulation operation associated with the stress type identifier within the specified time window.

[0006] Optionally, the S1 specifically includes: S11. Obtain the genotype marker data of the target corn plant. Collect the leaf tissue fluid through a field portable genotyping device, and based on the CRISPR-Cas12a nucleic acid rapid detection technology, output the genotype marker codes including the drought-resistant gene ZmNAC111 and the salt-tolerant gene ZmHKT1. S12. Obtain the real-time environmental stress data, including: Continuously monitor the change rate of rhizosphere ion flux through an embedded root sensor; Collect the fluctuation value of transpiration rate through a leaf clip-type micro meteorological station; S13. Obtain the historical operation records of the farmland. Extract the encrypted operation logs from the blockchain agricultural affairs deposit system, and generate a structured operation sequence including the irrigation water volume, fertilizer type, and the application times of biopesticides after timestamp parsing.

[0007] Optionally, the change rate of rhizosphere ion flux is expressed as: ; where represents the ion flux absorbed or excreted by the root system, represents the unit time interval, is the "differential" symbol, representing a small change amount, represents the small change amount of the ion flux absorbed or excreted by the root system per unit time; The fluctuation value of transpiration rate is expressed as: ; represents the transpiration rate per unit area of the leaf at the th sampling, represents the average value of the transpiration rate, represents the standard deviation of the transpiration rate, which is used to measure the activity of stomatal opening and closing changes.

[0008] Optionally, the specific steps of S2 include: S21. Construct a multi-source decision matrix: Align the genotype marker codes, the change rate of rhizosphere ion flux, the fluctuation value of transpiration rate, and the structured operation sequence obtained in S1 along the time axis as the decision matrix; S22. Calculate the stress response intensity: When it is detected that the fluctuation value of transpiration rate exceeds the baseline by 30% and lasts for a predetermined time duration, activate the drought response channel, output the drought stress intensity index, and then determine it as the dominant stress channel; When the Na + / K + ratio in the change rate of rhizosphere ion flux is greater than the predetermined limit threshold, activate the saline-alkali response channel, output the salt ion toxicity concentration gradient, and then determine it as the dominant stress channel; When the fluctuation value of the transpiration rate and the change rate of the rhizosphere ion flux exceed the limit simultaneously, the change rate of the rhizosphere ion flux is given the first priority, that is, the change rate of the rhizosphere ion flux is the dominant stress channel; S23. Generate a stress resistance decision vector: Based on the genotype marker coding, call the preset golden window period parameter table, and map the stress response intensity to a countdown-type regulation time window.

[0009] Optionally, in S23, the corresponding stress type identifier is selected according to the dominant stress channel, where the drought identifier is "DT" and the saline-alkali identifier is "SJ".

[0010] Optionally, the drought stress intensity index is defined as: ; where represents the drought sensitivity coefficient, represents the duration exceeding the threshold, is the drought stress intensity index, that is, the normalized intensity level, which can correspond to the window period mapping table, represents the historical benchmark value of the maize transpiration rate fluctuation value.

[0011] Optionally, the salt ion toxicity concentration gradient is defined as: ; where is the ion gradient response gain coefficient, is the salt toxicity concentration gradient, and the larger the value, the stronger the stress; if a minimum lower limit value needs to be set to prevent division-by-zero errors.

[0012] Optionally, S3 specifically includes: S31. Analyze the decision vector: Extract the stress type identifier and the regulation time window in the stress resistance decision vector, and convert the regulation time window into a countdown trigger instruction executable by the device; S32. Match the regulation strategy library: When the stress type identifier is "DT", call the drought regulation strategy to generate an operation instruction set including gradient boost irrigation parameters and the injection ratio of the anti-drought agent; When the stress type identifier is "SJ", call the saline-alkali regulation strategy to generate an operation instruction set including the concentration of the calcium ion chelator and the application rate of the osmotic regulator.

[0013] Optionally, S3 further includes performing a time window binding operation: Write the operation instruction set into the FPGA controller of the corresponding agricultural equipment; Start the countdown trigger instruction, and forcefully verify the operation completion degree 5 minutes before the regulation time window closes; If the operation is not completed at the end of the countdown, the backup device is started to perform the compensation operation.

[0014] A corn stress resistance prediction system based on multi-source data is used to implement the above corn stress resistance prediction method, including the following modules: Data acquisition module, used to synchronously obtain genotype marker data of target corn plants, real-time environmental stress data and historical operation records of farmland; The decision engine module is used to construct a multi-source decision matrix, calculate the stress response intensity, and output the stress resistance decision vector in combination with genotype parameters; The control execution module is used to parse the stress type identifier and the control time window according to the stress resistance decision vector, match the corresponding agronomic operation strategy and write the instruction into the controller, and control the agricultural equipment to execute the control operation according to the countdown trigger mechanism.

[0015] Beneficial effects of the present invention: The present invention introduces the field portable CRISPR-Cas12a nucleic acid detection technology into the genotype data collection process, significantly shortens the traditional laboratory detection cycle, and realizes the synchronous integration with the second-level environmental stress monitoring data, effectively solving the problems of delayed stress resistance information and missed regulation opportunities in the prior art. + / K + The linkage analysis mechanism of flux ratio can dynamically generate time-effective stress resistance decision vectors, thereby achieving variety-specific differentiated and precise responses.

[0016] The present invention constructs a mapping relationship between the stress intensity index and the genotype golden window period parameter table, and for the first time converts the abstract stress response into a quantifiable countdown regulation window, solving the problem that the traditional system only outputs the stress probability but cannot guide the operation execution time. The mechanism supports risk level identification and response priority sorting for multiple adverse stresses (drought / salinity / double), ensuring that the regulatory measures are executed within the optimal physiological time window.

[0017] The present invention introduces the FPGA controller to directly write the decision vector instruction, combines the TRIGGER countdown trigger mechanism and the mandatory verification logic, performs the operation completion detection before the control time window is about to close, and automatically switches to the backup device and performs the compensation operation if the operation fails, effectively improving the execution robustness in the complex field environment. This design avoids the problems of response delay and equipment failure not handled in time in the traditional agricultural Internet of Things system, and ensures the continuity and safety of agronomic control operations under high-risk stress situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] To more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only those of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0019] Figure 1 Schematic diagram of the method flow of the embodiment of the present invention; Figure 2 Schematic diagram of the system function module of the embodiment of the present invention. Detailed implementation manners

[0020] The following will describe the present invention in detail with reference to the accompanying drawings and specific embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; moreover, the accompanying drawings are only for more specific description of the embodiments and are not intended to specifically limit the present invention.

[0021] As Figure 1 shown, a maize stress resistance prediction method based on multi-source data includes the following steps: S1, Synchronously collect data: Obtain genotype marker data, real-time environmental stress data, and farmland historical operation records of the target maize plants; S2, Generate a stress resistance decision vector: Input the data of S1 into the dynamic decision engine, and output a stress resistance decision vector including a stress type identifier and a regulation time window; S3. Execute the regulation instruction: Activate the corresponding agricultural equipment according to the regulation time window, and implement the regulation operation associated with the stress type identifier within the specified time window.

[0022] S1 specifically includes: S11, Genotype marker data collection: Collect the leaf tissue fluid of the target maize plants through a portable field genotyping device, and use the CRISPR-Cas12a nucleic acid rapid detection technology to output genotype marker codes including the drought-resistant gene ZmNAC111 and the salt-tolerant gene ZmHKT1 within 15 minutes.

[0023] S12, Real-time environmental stress data collection: Include the following two key sensor measurement indicators: Rhizosphere ion flux change rate: ; Collected by an embedded root ion flux sensor at a frequency of 1 time per second, where represents the ion flux absorbed or excreted by the roots, represents the unit time interval, is the "differential" symbol, indicating a small change amount, Represents the small change in the ion flux absorbed or excreted by the root system per unit time; Transpiration rate fluctuation value: ; The transpiration rate is collected by the clamping type leaf meteorological sensor at a frequency of 1 time / minute Samples, and calculate the standard deviation Characterize the dynamic changes of stomata, where Represents the ions in the rhizosphere region (such as Flow rate, Represents the Transpiration rate per unit area of the leaf at the th sampling, Represents the mean value of the transpiration rate, Represents the standard deviation of the transpiration rate, which is used to measure the activity of stomatal opening and closing changes,

[0024] S13, Obtaining farmland historical operation records: Extract encrypted operation logs from the blockchain agricultural event deposit system, and generate the following structured operation sequence by parsing the timestamp: ; Among them, Represents the th timestamp of the agricultural operation, Represents the irrigation water volume, Represents the fertilization type code (such as organic = 01, chemical fertilizer = 10), Represents the number of times of biological agent application, Represents the total number of agricultural operation record entries parsed from the blockchain agricultural event deposit system. Through the non - modifiable mechanism on the blockchain, the authenticity and credibility of the records are guaranteed, and it can provide time - series compensation support for subsequent regulation strategies.

[0025] The blockchain agricultural event deposit system refers to a reliable record and traceability platform for agricultural operation data based on blockchain technology. Its core role is to provide true, non - modifiable, and time - series traceable reliable records for historical agricultural operation behaviors, such as irrigation, fertilization, and pesticide application, facilitating the system to obtain verifiable farmland management background data during the prediction and decision - making process.

[0026] The agricultural event deposit system is a reliable storage platform for agricultural data that integrates blockchain ledger, encrypted identification, and timestamp mechanism, used to record and verify the occurrence time, behavior type, parameter configuration, and responsible entity of agricultural management operation behaviors, and support subsequent data analysis and intelligent decision - making applications.

[0027] This system mainly serves the following purposes: True record: Record the occurrence time, type, parameters, etc. of each agricultural operation, such as irrigation water volume, fertilization type, number of times of biological agent use, etc.; Tamper-proof guarantee: Utilize the distributed consensus mechanism of blockchain to ensure that data cannot be forged or modified retrospectively; Time alignment support: Achieve multi-source data alignment by synchronizing the operation timestamp with the sampling time of environmental sensors; Regulation compensation support: Support modeling the impact of historical operation behaviors on the current stress response analysis, such as the analysis of the weakening trend of stress resistance in fields with "frequent fertilization"; The specific structure includes: Data on-chain module: Agricultural machinery equipment, mobile terminals or central control systems upload agricultural events (with timestamps + parameter values) in real-time; Encryption identification module: Generate a unique hash value for each agricultural record and encrypt and identify the recorder and device information; Block packaging module: Package several operation logs into a new block, broadcast it to the blockchain node network and write it through consensus; Traceability query module: Support the system to query historical operations by time, location or crop code and extract structured operation sequences.

[0028] The specific process of generating a structured operation sequence is as follows The system calls the blockchain query interface and locates all relevant blocks of the farmland unit to which the current target corn plant belongs in the ledger according to the spatial coordinates and gene encoding of the corn plant; Decode the encrypted fields of each log and extract: Operation timestamp, operation type (irrigation, fertilization, pesticide application), operation parameters (irrigation volume, fertilization type encoding, number of biological pesticide applications).

[0029] S2 specifically includes: S21, construct a multi-source decision matrix to align various types of data obtained in S1 along a unified time axis to form a multi-source decision matrix: ; Among them, represents the genotype marker encoding at time t, represents the change rate of rhizosphere ion flux, represents the fluctuation value of transpiration rate, represents the historical agricultural operation record corresponding to the timestamp.

[0030] S22, calculate the stress response intensity: S221, drought response determination condition: If within 5 consecutive minutes, the fluctuation value of transpiration rate satisfies: ; then activate the drought response channel and output the drought stress intensity index , the drought stress intensity index is defined as: ; among which, represents the drought sensitivity coefficient (adjusted according to varieties and field trials, with a recommended initial value ), represents the duration above the threshold, with a maximum of 5 minutes, is the normalized intensity level, which can correspond to the window period mapping table, represents the historical baseline value of the fluctuation of the transpiration rate of maize.

[0031] Drought sensitivity coefficient is set based on field trial participation and genotype difference normalization analysis. It is a proportional factor that regulates the influence degree of transpiration rate fluctuation on the intensity of drought response, and is used to map the sensor observation value to a standardized response level; through the comparison of the field trial results of multiple maize varieties (such as with or without the drought-resistant gene ZmNAC111) under drought stress, it is found that: For maize with the ZmNAC111+ genotype, the sensitivity of its transpiration rate to water stress is higher than that of non-drought-resistant varieties; the normalized change range of transpiration fluctuation is approximately in the range of 1.1 - 1.6 times When in this range, the plant will have different degrees of stomatal closure, growth inhibition or root extension behavior. The setting purpose is to achieve the normalization of hierarchical response, and is set as the median value of the standard drought-resistant response factor level, so that the value calculated can be stably mapped to the subsequent window mapping table to realize the scheduling of control instructions.

[0032] Duration above the threshold is set as follows: 1. The physiological reaction lag is matched with the regulatory response delay. When maize is under moderate drought stress, the significant fluctuation of its transpiration rate usually changes significantly (stomatal closure, conductance decline) within 2 - 6 minutes; considering the sensor sampling period (once per minute) and the need for at least 3 fluctuation samples for response calculation, it is set that continuous duration > 3 minutes can trigger drought determination, and 5 minutes is the tolerable limit window.

[0033] 2. The balance between false trigger control and regulatory reaction coordination. If the duration is set too short (1 - 2 minutes), it is easily interfered by accidental weather fluctuations (such as instantaneous high temperature, wind speed change), resulting in the triggering of "false drought". If the duration is too long (such as > 10 minutes), the actual regulatory response time lags, missing the "golden window" of drought resistance intervention, especially during the high-temperature noon period when drought intensifies rapidly.

[0034] S222, saline-alkali response determination condition: If at any moment, the rhizosphere ion flux satisfies the following ratio: ; Then activate the saline-alkali response channel and output the salt ion toxicity concentration gradient , the salt ion toxicity concentration gradient is defined as: ; where is the ion gradient response gain coefficient (initially set , trainable), is the salt toxicity concentration gradient, and the larger the value, the stronger the stress; if a very small lower limit value needs to be set to prevent division-by-zero errors , , represents , the instantaneous flux of , represents the corresponding response intensity index and serves as the input for window period mapping.

[0035] is the response gain coefficient of the salt ion toxicity concentration gradient , and its function is to map the logarithmic level of the change in the Na + / K + ratio to a standardized response level that can be recognized by the device execution system; actually, it plays the role of a "sensitivity factor" for quantifying the risk intensity and is used to determine whether the saline-alkali stress reaches the regulation threshold. The setting basis is as follows: Logarithmic compression characteristics of the ratio feature: The change in the rhizosphere ion concentration ratio usually ranges from 1.0 to 10.0 and has a non-linear sudden increase characteristic. After compressing its dynamic range using a logarithmic function, even if Na + suddenly increases by ten times, the maximum value of this logarithmic term is approximately , and its numerical range is small. To enhance the discrimination of the model for different intensities of toxicity, an appropriate gain factor needs to be introduced to expand the original physiological response index level to the linear control range. In field trials, through retrospective analysis of data from typical saline-alkali stress sample areas, it is found that: When , and sharply drops to within 1.5 - 2.0 mmol / m²·s, the plant shows obvious toxicity symptoms such as leaf tip burning and growth stagnation; under the above conditions, the term is approximately 0.8 - 1.2. If multiplied by , the output gradient is the significant stress level interval. Therefore, is set to 50, which can make the output fall within the 0 - 100 interval, facilitating unified normalization comparison with other indicators and device threshold configuration.

[0036] The output results of the two response channels are finally unified as: Response intensity index Look up the table or model mapping , thus supporting the subsequent derivation of the countdown window and identifier generation.

[0037] If the transpiration fluctuates violently ( high) but the Na + / K + ratio is normal → the dominant channel is "DT" (drought) If the rhizosphere Na + surges and the K + absorption is limited → the dominant channel is "SJ" (saline-alkali); If both exceed the threshold, (saline-alkali > drought).

[0038] S23, generate the stress resistance decision vector. According to the dominant stress channel and genotype marker encoding, output the stress resistance decision vector containing the regulation time window and type identifier: ; represents the type identifier, where: Mapping rules (extracted from the golden window period parameter table): If the genotype is ZmNAC111+ and the dominant channel is drought: Identifier = "DT", Twindow ∈ [6h, 8h]; If the genotype is ZmHKT1+ and the dominant channel is saline-alkali: Identifier = "SJ", Twindow ∈ [4h, 6h]; Identifier represents the short code identifier, "DT" represents drought, "SJ" represents saline-alkali, which is compatible with the agricultural equipment instruction format. Twindow represents the window period time segment, which is used to accurately regulate the operation time. The decision vector can be directly embedded into the Internet of Things device control logic.

[0039] Table 1 Golden window period parameter table

[0040] The regulation time window Twindow means that the device needs to complete the agronomic intervention within this time period from the activation of the response channel, such as starting irrigation and applying chelating agents; For the case of "double gene positive", it is necessary to preferentially select the corresponding channel according to the principle of saline-alkali > drought and execute its window time; All time windows are in hours (which can be converted to the HH:MM:SS format and written into the hardware controller).

[0041] S3 specifically includes: S31, parse the decision vector: Extract the stress resistance decision vector: ; Among them, represents the stress type identifier, represents the regulation time window; Convert the time window into a countdown trigger instruction executable by the device: ; And encode it into an execution format: ; Among them, represents reserving a 5-minute verification buffer. The TRIGGER instruction is in the format acceptable to the device and directly drives the FPGA controller to start the countdown.

[0042] S32. Match the regulation strategy library: Perform the following strategy matching according to the identifier: S321. When Identifier = "DT" (drought), match the drought regulation strategy and generate an operation instruction set: Gradient boosting irrigation parameters (pressure changes with stages): ; Proportion of anti-drought agent injection: ; represents the proportion of anti-drought agent injection, represents the application volume of polyglutamic acid (PGA) anti-drought agent, represents the application volume of irrigation water; Among them, represents the irrigation pressure, applied in three stages, represents the window time period division point, represents the ratio of polyglutamic acid (PGA) anti-drought agent to irrigation water.

[0043] S322. When Identifier = "SJ" (saline-alkali), match the saline-alkali regulation strategy and generate an operation instruction set: Calcium ion chelating agent concentration setting: ; Application rate of osmotic regulator: ; Among them, represents the concentration of EDTA-Ca solution, represents the application rate, controlled within the safety threshold to prevent phytotoxicity.

[0044] I. Injection ratio of the anti-drought agent (the ratio of polyglutamic acid PGA to irrigation water is 1:2000), considering the plant protection safety threshold: As a water-soluble biological anti-drought agent, the recommended safe concentration of polyglutamic acid (PGA) in dryland crops such as corn is generally in the range of 0.03% - 0.05% (w / v), that is, a mass ratio of 1:2000 to 1:3000 can ensure effective water retention without causing rhizosphere blockage or nutrient adsorption inhibition.

[0045] Field drought tolerance test results of corn in multiple places show that injecting PGA at a concentration of 1:2000 into the drip irrigation system can promote the vertical growth of roots and soil water retention, and will not inhibit the activity of rhizosphere microorganisms. Currently, the dose control modules of most agricultural irrigation equipment use liquid dilution tanks or backpressure proportional injection devices, and their lowest stable injection ratio is generally set at 0.05% (i.e., 1:2000) to ensure mixing uniformity and system stability.

[0046] II. Setting of the concentration of calcium ion chelating agent (EDTA-Ca = 0.5 mmol / L) based on the standard dose range for alleviating soil sodium toxicity: In international plant nutrition research, it is generally recommended to use 0.3 - 0.8 mmol / L of EDTA-Ca as the upper limit of the concentration of the slow-release chelating agent under alkaline or saline-alkali stress soil conditions to chelate and exchange free Na in the rhizosphere + , reduce the toxicity of sodium ions. Applying EDTA-Ca at a concentration of 0.5 mmol / L can effectively prevent Na + from accumulating in the root cortex, avoid electrolyte imbalance, and at the same time do not trigger osmotic bursting of the cell wall or cause ion overload poisoning.

[0047] III. Setting of the application rate of the osmotic regulator (5 L / min) based on the effective rate and root zone osmotic balance considerations: The osmotic regulator (such as glycerol, polyols) needs to be evenly applied to the root zone at a certain rate. 5 L / min is a safe rate that can quickly cover the target root layer without causing seepage erosion or sudden changes in water potential, and is suitable for drip irrigation and rotary sprinkler irrigation systems. Simulation experiments show that in medium-loamy fields, a pesticide application rate of 5 L / min can stabilize the osmotic regulator concentration at a root layer depth of 20 cm within 10 minutes, which is beneficial for the roots to adjust the osmotic pressure to relieve saline-alkali stress.

[0048] S33, perform the operation of binding the execution time window: 1. Directly write the operation instruction set into the FPGA controller of the corresponding agricultural equipment; 2. Start the countdown trigger TRIGGERHH:MM:SS; 3. Perform forced verification at time: Drought response verification index (example): Soil moisture content ; Salinity-alkalinity response verification index (example): Soil conductivity 。

[0049] Indicates the forced verification lead time, that is, the verification time period reserved before the end of the time window Indicates the target soil moisture content threshold, which is used to judge whether the drought regulation is effective Indicates the conductivity safety threshold, which represents the upper limit of the salt concentration in the soil after regulation and is set according to the salt tolerance of the crop

[0050] Such as Figure 2 As shown, a maize stress resistance prediction system based on multi-source data is used to implement the above method, including the following modules Data acquisition module, which is used to synchronously obtain the genotype marker data, real-time environmental stress data and farmland historical operation records of the target maize plants Decision engine module, which is used to construct a multi-source decision matrix, calculate the stress response intensity, and output a stress resistance decision vector in combination with genotype parameters Regulation execution module, which is used to analyze the stress type identifier and regulation time window according to the stress resistance decision vector, match the corresponding agronomic operation strategy, write the instruction into the controller, and control the agricultural equipment to execute the regulation operation according to the countdown trigger mechanism

[0051] The present invention covers any alternatives, modifications, equivalent methods and solutions made on the essence and scope of the present invention. In order to enable the public to have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, and those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion to the essence of the present invention, well-known methods, processes, flows, components and circuits are not described in detail

[0052] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention

Claims

1. A corn stress resistance prediction method based on multi-source data, characterized in that, It includes the following steps: S1. Synchronously collect data: Obtain the genotype marker data of the target corn plant, real-time environmental stress data, and farmland historical operation records; S2. Generate a stress resistance decision vector: Input the data of S1 into the dynamic decision engine, and output a stress resistance decision vector including a stress type identifier and a regulation time window; S3. Execute the regulation instruction: Activate the corresponding agricultural equipment according to the regulation time window, and implement the regulation operation associated with the stress type identifier within the specified time window.

2. The maize stress resistance prediction method based on multi-source data according to claim 1, wherein The specific content of S1 includes: S11. Obtain the genotype marker data of the target corn plant. Collect the leaf tissue fluid through a portable field genotyping device, and based on the CRISPR-Cas12a nucleic acid rapid detection technology, output the genotype marker codes including the drought-resistant gene ZmNAC111 and the salt-tolerant gene ZmHKT1; S12. Obtain the real-time environmental stress data, including: Continuously monitor the change rate of rhizosphere ion flux through an embedded root sensor; Collect the fluctuation value of transpiration rate through a leaf clip-type micro meteorological station; S13. Obtain the farmland historical operation records. Extract the encrypted operation logs from the blockchain agricultural evidence storage system, and generate a structured operation sequence including irrigation water volume, fertilizer type, and the application times of biological agents after timestamp parsing.

3. The maize stress resistance prediction method based on multi-source data according to claim 2, wherein, The change rate of rhizosphere ion flux is expressed as: ; where represents the ion flux absorbed or excreted by the root system, represents the unit time interval, is the "differential" symbol, indicating a small change amount, represents the small change amount of the ion flux absorbed or excreted by the root system per unit time; The transpiration rate fluctuation value is expressed as: ; represents the transpiration rate per unit area of the leaf at the -th sampling, represents the mean value of the transpiration rate, represents the standard deviation of the transpiration rate, which is used to measure the activity of the stomatal opening and closing changes.

4. A method for predicting maize stress resistance based on multi-source data according to claim 2, characterized in that, The specific content of S2 includes: S21. Construct a multi-source decision matrix: Align the genotype marker codes, rhizosphere ion flux change rate, transpiration rate fluctuation value, and structured operation sequence obtained in S1 along the time axis as a decision matrix; S22. Calculate the stress response intensity: When it is detected that the transpiration rate fluctuation value exceeds the baseline by 30% and lasts for a predetermined time, activate the drought response channel, output the drought stress intensity index, and then determine it as the dominant stress channel; When the Na + / K + ratio in the rhizosphere ion flux change rate is greater than a predetermined limit threshold, activate the saline-alkali response channel, output the salt ion toxicity concentration gradient, and then determine it as the dominant stress channel; When both the transpiration rate fluctuation value and the rhizosphere ion flux change rate exceed the limit, take the rhizosphere ion flux change rate as the first priority, that is, the rhizosphere ion flux change rate is the dominant stress channel; S23. Generate a stress resistance decision vector: Based on the genotype marker codes, call the preset golden window period parameter table, and map the stress response intensity to a countdown-type regulation time window.

5. A method for predicting maize stress resistance based on multi-source data according to claim 4, characterized in that, In S23, select the corresponding stress type identifier according to the dominant stress channel, where the drought identifier is "DT" and the saline-alkali identifier is "SJ".

6. The maize stress resistance prediction method based on multi-source data according to claim 4, wherein, The definition of the drought stress intensity index is: ; wherein, represents the drought sensitivity coefficient, represents the duration of exceeding the threshold, is the drought stress intensity index, that is, the normalized intensity level, which can be corresponded to the window period mapping table, represents the historical benchmark value of the fluctuation value of the transpiration rate of maize.

7. A method for predicting maize stress resistance based on multi-source data according to claim 4, characterized in that, The definition of the salt ion toxicity concentration gradient is: ; wherein, is the ion gradient response gain coefficient, is the salt toxicity concentration gradient, and the larger the value, the stronger the stress; if a minimum lower limit value needs to be set to prevent division-by-zero errors.

8. A method for predicting maize stress resistance based on multi-source data according to claim 1, characterized in that, The specific content of S3 includes: S31. Analyze the decision vector: Extract the stress type identifier and the regulation time window in the stress resistance decision vector, and convert the regulation time window into a countdown trigger instruction executable by the device; S32. Match the regulation strategy library: When the stress type identifier is "DT", call the drought regulation strategy to generate an operation instruction set including gradient boost irrigation parameters and the injection ratio of drought-resistant agents; When the stress type identifier is "SJ", call the saline-alkali regulation strategy to generate an operation instruction set including the concentration of calcium ion chelating agent and the application rate of osmotic regulator.

9. The maize stress resistance prediction method based on multi-source data according to claim 8, characterized in that, S3 also includes performing a time window binding operation: Write the operation instruction set into the FPGA controller of the corresponding agricultural equipment; Start the countdown trigger instruction to forcibly verify the operation completion 5 minutes before the regulation time window closes; If the operation is not completed at the end of the countdown, start the standby device to perform the compensation operation.

10. A maize stress resistance prediction system based on multi-source data, which is used to implement a maize stress resistance prediction method based on multi-source data according to any one of claims 1-9, characterized in that, It includes the following modules: The data acquisition module is used to synchronously obtain the genotype marker data of the target corn plants, the real-time environmental stress data, and the farmland historical operation records; The decision engine module is used to construct a multi-source decision matrix, calculate the stress response intensity, and output the stress resistance decision vector in combination with the genotype parameters; The regulation execution module is used to parse the stress type identifier and the regulation time window according to the stress resistance decision vector, match the corresponding agronomic operation strategy and write the instruction into the controller, and control the agricultural equipment to perform the regulation operation according to the countdown trigger mechanism.

Images