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

Abstract

The present application relates to the technical field of agricultural prediction analysis, and particularly relates to a corn stress resistance prediction system and method based on multi-source data, comprising the following steps: obtaining genotype marker data, real-time environmental stress data and farmland historical operation records of target corn plants; inputting the obtained data into a dynamic decision engine to output a stress resistance decision vector comprising a stress type identifier and a regulation time window; and activating corresponding farm equipment according to the regulation time window to implement the regulation operation associated with the stress type identifier within the specified time window. The present application avoids the problems of response delay and device failure not being handled in time in the traditional agricultural Internet of Things system, and guarantees the continuity and safety of agronomic regulation operations under high-risk stress conditions.

Description

TECHNICAL FIELD

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

[0002] Drought, salinity and other abiotic stress is one of the key factors restricting the high yield and stable yield of corn. Traditional corn stress resistance management relies on long-term breeding selection and static agronomic rules, and lacks dynamic regulation ability for real-time state of individual plants, which is difficult to meet the development needs of precision agriculture.

[0003] The existing corn stress resistance regulation method has the following disadvantages:

[0004] Poor timeliness of data acquisition: current plant resistance trait judgment is mostly based on laboratory molecular detection and long-term field observation, with long detection period (usually several days), which cannot meet the needs of rapid response to environmental changes;

[0005] Insufficient stress recognition accuracy: the mainstream environmental monitoring parameters (such as soil conductivity and air humidity) are not sensitive to the early response of stress, resulting in delayed stress response and affecting the regulation effect;

[0006] Lack of quantitative time window support for decision mechanism: existing systems mostly output "stress exists" or "risk level", lack of mechanism to map stress intensity to executable time control, and are difficult to provide interpretable scheduling signals for agronomic equipment;

[0007] Poor operation execution stability: current agricultural automation systems mostly use general-purpose processors to send control instructions, which are easily affected by communication delay and software blocking, and lack a forced verification mechanism for operation completion status, with high operation failure rate, affecting the reliability of field application. SUMMARY

[0008] The present application provides a corn stress resistance prediction system and method based on multi-source data, which integrates rapid gene detection, accurate environmental monitoring, stress intensity calculation and control strategy linkage of the whole process of stress resistance prediction and execution system, realizes individual, real-time and closed-loop regulation of corn stress response.

[0009] A corn stress resistance prediction method based on multi-source data, comprising the following steps:

[0010] S1, synchronously collecting data: acquiring genotype marker data, real-time environmental stress data and farmland historical operation records of target corn plants;

[0011] S2, generating stress resistance decision vector: inputting the data of S1 into a dynamic decision engine to output a stress resistance decision vector including stress type identifier and regulation time window;

[0012] 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.

[0013] Optionally, the S1 specifically comprises:

[0014] S11, obtain the genotype marker data of the target corn plant, collect leaf tissue fluid through a field portable typing device, and output genotype marker codes including drought-resistant gene ZmNAC111 and salt-tolerant gene ZmHKT1 based on CRISPR-Cas12a nucleic acid rapid detection technology;

[0015] S12, obtain real-time environmental stress data, including:

[0016] monitor the rhizosphere ion flux change rate continuously through a buried root system sensor;

[0017] collect transpiration rate fluctuation values through a leaf clamp type micro weather station;

[0018] S13, obtain the historical operation record of the farmland, extract encrypted operation logs from a blockchain agricultural record system, and generate a structured operation sequence including irrigation water volume, fertilizer type, and biological pesticide application times after time stamp analysis.

[0019] Optionally, the rhizosphere ion flux change rate is represented as: wherein, represents the ion flux absorbed or discharged by the root system, represents a unit time interval, is a "differential" symbol, representing a small change amount, represents a small change amount of ion flux absorbed or discharged by the root system per unit time;

[0020] The transpiration rate fluctuation value is represented 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 degree of change in stomatal opening and closing.

[0021] Optionally, the S2 specifically comprises:

[0022] 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 into a decision matrix according to the time axis;

[0023] S22, calculate the stress response intensity:

[0024] ​When the transpiration rate fluctuation value exceeds the baseline by 30% and lasts for a predetermined duration, the drought response channel is activated, and the drought stress intensity index is output, and the dominant stress channel is determined;

[0025] When the Na + / K + ratio exceeds the predetermined limit threshold, the salt-alkali response channel is activated, and the salt ion toxicity concentration gradient is output, and the dominant stress channel is determined;

[0026] When the transpiration rate fluctuation value and the rhizosphere ion flux change rate are both out of limits, the rhizosphere ion flux change rate is the first priority, i.e., the rhizosphere ion flux change rate is the dominant stress channel;

[0027] S23, generating an anti-stress decision vector: based on the genotype marker code, a preset golden window period parameter table is called to map the stress response intensity to a countdown type regulation time window.

[0028] Optionally, in S23, a corresponding stress type identifier is selected according to the dominant stress channel, wherein the drought identifier is "DT" and the salt-alkali identifier is "SJ".

[0029] Optionally, the drought stress intensity index is defined as:

[0030] ; wherein, is the drought sensitivity coefficient, is the threshold value duration, is the drought stress intensity index, i.e., the normalized intensity level, which can be mapped to the window period table, is the historical baseline value of the corn transpiration rate fluctuation value.

[0031] Optionally, the salt ion toxicity concentration gradient is defined as:

[0032] ; 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 zero error.

[0033] Optionally, S3 specifically includes:

[0034] S31, analyzing the decision vector: extracting the stress type identifier and the regulation time window from the anti-stress decision vector, and converting the regulation time window into a countdown trigger instruction executable by the device;

[0035] S32, matching the regulation strategy library:

[0036] When the stress type identifier is "DT", a drought regulation strategy is called to generate an operation instruction set including gradient pressure irrigation parameters and drought resistance agent injection ratio;

[0037] When the stress type identifier is "SJ", a saline-alkali regulation strategy is called to generate an operation instruction set including calcium ion chelating agent concentration and osmotic regulator application rate.

[0038] Optionally, the S3 further comprises a time window binding operation:

[0039] The operation instruction set is written to the FPGA controller of the corresponding agricultural equipment;

[0040] The countdown trigger instruction is started, and the completion degree of the operation is forced to be checked 5 minutes before the regulation time window is closed;

[0041] If the operation is not completed when the countdown ends, a backup device is started to perform a compensation operation.

[0042] A corn stress resistance prediction system based on multi-source data is used to implement the corn stress resistance prediction method, and comprises the following modules:

[0043] A data acquisition module is used to synchronously acquire genotype marker data, real-time environmental stress data and farmland historical operation records of target corn plants;

[0044] A decision engine module is used to construct a multi-source decision matrix, calculate stress response intensity, and output a stress resistance decision vector in combination with genotype parameters;

[0045] A regulation execution module is used to parse a stress type identifier and a regulation time window according to the stress resistance decision vector, match a corresponding agricultural operation strategy, write instructions to a controller, and control agricultural equipment to perform regulation operations in a countdown trigger mechanism.

[0046] The present application has the following advantages:

[0047] The present application introduces a field portable CRISPR-Cas12a nucleic acid detection technology into the genotype data acquisition process, significantly shortens the traditional laboratory detection period, and realizes synchronous fusion with second-level environmental stress monitoring data, effectively solving the problems of stress resistance information lag and missed regulation opportunity in the prior art. By means of a linkage analysis mechanism of genotype markers and stress parameters (such as transpiration rate fluctuation value, Na + / K + flux ratio), a stress resistance decision vector with timeliness can be dynamically generated, so that a variety-specific differentiated precise response is realized.

[0048] The application constructs a mapping relationship based on stress intensity index and genotype golden window period parameter table, first converts the abstract stress response into a quantifiable countdown control window, solves the problem that only stress probability is output in the traditional system and operation execution time cannot be guided, and the mechanism supports risk level identification and response priority sorting of multiple adversity stresses (drought / saline-alkali / dual), and ensures that the control measures are executed within the optimal physiological time window.

[0049] The application introduces a FPGA controller to directly write a decision vector instruction, combines a TRIGGER countdown trigger mechanism and forced verification logic, performs job completion degree detection before the control time window is about to close, automatically switches to a backup device and performs compensation operation if the operation fails, and effectively improves the execution robustness in the complex field environment. The design avoids the problems of response delay and device failure not being processed in time in the traditional agricultural Internet of Things system, and guarantees the continuity and safety of agronomic control operation under high-risk stress conditions. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only illustrate the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0051] Figure 1 The method flowchart of the embodiment of the application is shown in the figure.

[0052] Figure 2 The system function module schematic diagram of the embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0053] The application will be described in detail below with reference to the drawings and specific embodiments. For some known technologies, other alternative ways can also be used by those skilled in the art to implement them; and the drawings are only used to more specifically describe the embodiments, and are not intended to specifically limit the application.

[0054] As shown in the figure, a corn resistance prediction method based on multi-source data includes the following steps: Figure 1

[0055] S1, synchronously collecting data: acquiring genotype marker data, real-time environmental stress data and farmland historical operation records of target corn plants;

[0056] S2, generating resistance decision vector: inputting the data of S1 into a dynamic decision engine to output a resistance decision vector including a stress type identifier and a control time window;

[0057] ​S3. Execute control instruction: activate corresponding agricultural equipment according to control time window, and implement control operation associated with stress type identifier within specified time window.

[0058] S1 specifically includes:

[0059] S11, genotype marker data collection: collect target corn plant leaf tissue fluid through field portable typing device, and use CRISPR-Cas12a nucleic acid rapid detection technology to output genotype marker code containing drought resistance gene ZmNAC111 and salt tolerance gene ZmHKT1 within 15 minutes.

[0060] S12, real-time environmental stress data collection: including the following two key sensor measurement indicators:

[0061] Root zone ion flux change rate: ; collected by buried root ion flux sensor at a frequency of 1 time / s, wherein, represents the ion flux absorbed or discharged by the root system, represents the unit time interval, is the "derivative" symbol, indicating a small change, represents the small change in ion flux absorbed or discharged by the root system per unit time;

[0062] Transpiration rate fluctuation value: ; collected by clamping type leaf meteorological sensor at a frequency of 1 time / min sample transpiration rate characterizes the dynamic change of stomata, wherein, represents the ion (such as flow rate in the rhizosphere region, represents the transpiration rate per unit area of the leaf at the sampling time, 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 opening and closing of stomata, represents the number of transpiration rate samples.

[0063] S13, historical operation record acquisition of farmland: extract encrypted operation log from blockchain agricultural record system, and generate the following structured operation sequence by analyzing the timestamp:

[0064] ; wherein, represents the timestamp of the th agricultural operation, represents the irrigation water volume, represents the fertilizer type code (such as organic = 01, chemical fertilizer = 10), indicates the number of times of biological agent administration, indicates the total number of agricultural operation record entries parsed from the blockchain agricultural record system. The authenticity of the record is ensured by the blockchain on-chain non-algorithmic modification mechanism, and the time sequence compensation support can be provided for subsequent regulation strategies.

[0065] The blockchain agricultural record system refers to an agricultural operation data credible record and traceability platform constructed based on blockchain technology. The core role is to provide real, non-tamperable, and time-series traceable credible records for historical agricultural operation behaviors such as irrigation, fertilization, and pesticide application, so as to facilitate the system to obtain verifiable farmland management background data in the process of prediction and decision-making.

[0066] The agricultural record system is an agricultural data credible storage platform that integrates blockchain ledger, encryption identification, and timestamp mechanism, and is used to record and verify the occurrence time, behavior type, parameter configuration, and responsible subject of agricultural management operation behaviors, and support subsequent data analysis and intelligent decision-making applications.

[0067] The system mainly serves the following purposes:

[0068] Real record: record the occurrence time, type, and parameters of each agricultural operation, such as irrigation water volume, fertilizer type, and number of biological agent applications;

[0069] Anti-tampering protection: use the distributed consensus mechanism of blockchain to ensure that data cannot be falsified or modified afterwards;

[0070] Time alignment support: synchronize operation timestamps with environmental sensor sampling times to achieve multi-source data alignment;

[0071] Regulation compensation support: support modeling of the influence of historical operation behaviors on current stress response analysis, such as analysis of the weakening trend of the resistance of fields that have been frequently fertilized;

[0072] The specific structure includes:

[0073] Data chaining module: agricultural machinery equipment, mobile terminal, or central control system uploads agricultural events (with timestamp + parameter value) in real time;

[0074] Encryption identification module: generates a unique hash value for each agricultural record and encrypts the identifier and device information;

[0075] Block packaging module: package a number of operation logs to form a new block, broadcast to the blockchain node network and consensus write;

[0076] Traceability query module: supports system query of historical operations by time, location, or crop code, and extraction of structured operation sequences.

[0077] The specific process of generating structured operation sequences is as follows

[0078] The system calls the blockchain query interface to locate all relevant blocks of the farmland unit to which the current target corn plant belongs in the ledger, based on the spatial coordinates and gene code of the target corn plant.

[0079] Decode the encrypted fields of each log entry and extract:

[0080] Operation timestamp, operation type (irrigation, fertilization, pesticide application), operation parameters (irrigation volume, fertilizer type code, number of biological agents).

[0081] S2 specifically includes:

[0082] S21, Construct a multi-source decision matrix by aligning the various types of data obtained in S1 along a unified time axis to form a multi-source decision matrix:

[0083] ;

[0084] in, This represents the genotype marker encoding at time t. This represents the rate of change in rhizosphere ion flux. This represents the fluctuation value of the transpiration rate. This indicates the historical agricultural operation record corresponding to the timestamp.

[0085] S22, Calculate the stress response intensity:

[0086] S221, Drought Response Judgment Criteria: If the transpiration rate fluctuation value meets the following criteria within 5 consecutive minutes:

[0087] This activates the drought response channel and outputs the drought stress intensity index. Drought stress intensity index Defined as:

[0088] ;in, This represents the drought sensitivity coefficient (adjusted based on variety and field trials; recommended initial value). ), This indicates the duration of the threshold being exceeded, with a maximum of 5 minutes. It is a normalized intensity level, which can be mapped to a window period mapping table. This represents the historical baseline value for the fluctuation of corn transpiration rate.

[0089] drought sensitivity coefficient The settings were based on field trial data and genotype difference normalization analysis. is a proportional factor to adjust the influence degree of transpiration rate fluctuation on drought response intensity, which is used to map the sensor observation value to the standardized response level; By comparing the field test results of multiple corn varieties (such as containing or not containing drought-resistant gene ZmNAC111) under drought stress, it is found that:

[0090] The sensitivity of corn containing ZmNAC111+ genotype to water stress is higher than that of non-drought-resistant varieties; When the normalized change range of transpiration fluctuation is about 1.1-1.6 times , the plant will produce different degrees of stomatal closure, growth inhibition or root extension behavior. The purpose is to realize the normalization of level response, and is set as the median value of the standard drought-resistant response factor level, so that the calculated value can be stably mapped to the subsequent window mapping table, realizing the scheduling of control instructions.

[0091] The setting basis of the duration of the threshold value is as follows:

[0092] 1. The physiological response lag and the regulation response delay are matched. When corn is subjected to moderate drought stress, the significant fluctuation of transpiration rate usually changes obviously (stomatal closure, conductance decrease) within 2-6 minutes. Considering the sensor sampling period (1 time / 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.

[0093] 2. Balance of false trigger control and regulation response. If the duration is set too short (1-2 minutes), it is easy to be disturbed by accidental weather fluctuations (such as instantaneous high temperature and wind speed change), leading to "false drought" trigger. If the duration is too long (such as >10 minutes), the actual regulation response time is lagged, and the "golden window" of drought resistance intervention is missed, especially during the high-temperature noon period, when drought intensifies rapidly.

[0094] S222, salt and alkali response determination condition: if at any time, the rhizosphere ion flux satisfies the following ratio:

[0095] , then activate the salt and alkali response channel, output the salt ion toxicity concentration gradient , the salt ion toxicity concentration gradient is defined as:

[0096] ; wherein, is the ion gradient response gain coefficient (initially set , which can be trained), is the salt toxicity concentration gradient, the larger the value, the stronger the stress; if , a minimum lower limit value needs to be set to prevent zero error​ , , represents , instantaneous flux of , represents the corresponding response intensity index as the input of the window period mapping.

[0097] is the response gain factor of the salt ion toxicity concentration gradient , which serves to map the logarithmic level of the Na + / K + ratio change to the standardized response level that can be recognized by the device execution system; in fact, it acts as a risk intensity quantification "sensitivity factor" for determining whether the saline-alkali stress reaches the control threshold, and the setting basis is as follows:

[0098] Logarithmic compression characteristics of the ratio feature: rhizosphere ion concentration ratio changes are usually between 1.0-10.0, with a nonlinear surge characteristic, and after compressing its dynamic range using a logarithmic function, even if the Na + surges tenfold, the logarithmic term is at most , which itself has a small numerical range, and in order to enhance the model's discrimination degree for different intensities of toxicity, a moderate gain factor is introduced to expand the original physiological response index level to the linear control range. In field tests, through retrospective analysis of data from typical saline-alkali stress sample areas, it is found that:

[0099] When , and drops sharply to within 1.5-2.0 mmol / m²·s, the plant shows obvious leaf tip burn, growth stagnation, and other toxicity symptoms; under the above conditions, is about 0.8-1.2, and if multiplied by , the output gradient is the significant stress level interval, so is set to 50, which can make the output of fall within the 0-100 interval, facilitating unified normalization comparison with other indicators and device threshold configuration.

[0100] The output results of the two response channels are finally unified as:

[0101] response intensity index look-up table or model mapping , thereby supporting subsequent countdown window derivation and identifier generation.

[0102] If the transpiration fluctuation is severe ( high) but the Na + / K+ Ratio Normal → Dominant Channel is "DT" (Drought)

[0103] If Rhizosphere Na + Surges and K + Absorption is Limited → Dominant Channel is "SJ" (Salinity)

[0104] If both exceed threshold, (Salinity > Drought).

[0105] S23, generate stress resistance decision vector according to dominant stress channel and genotype marker, output stress resistance decision vector containing regulation time window and type identifier: ; Identifier represents type identifier, wherein:

[0106] Mapping rules (extracted from Golden Window Period Parameter Table):

[0107] If genotype is ZmNAC111+ and dominant channel is drought: Identifier="DT", Twindow∈[6h,8h];

[0108] If genotype is ZmHKT1+ and dominant channel is salinity: Identifier="SJ", Twindow∈[4h,6h];

[0109] Identifier represents short code identifier, "DT" represents drought, "SJ" represents salinity, compatible with agricultural equipment instruction format, Twindow represents window period time period, used for precise regulation operation time, decision vector can be directly embedded into Internet of Things device control logic.

[0110] Table 1 Golden Window Period Parameter Table

[0111]

[0112] Regulation time window Twindow represents that the device needs to complete agronomic intervention within this time period from activating the response channel, such as starting irrigation, applying chelating agent;

[0113] For the case of "double gene positive", the corresponding channel needs to be selected according to the principle of salinity > drought and its window time is executed;

[0114] All time windows are in units of hours (which can be converted into HH:MM:SS format and written into hardware controllers).

[0115] S3 specifically includes:

[0116] S31, parse decision vector:

[0117] Extract stress resistance decision vector: ;

[0118] wherein, Identifier represents the stress type identifier, Window represents the regulation time window;

[0119] Convert the time window into device executable countdown trigger instruction: ;

[0120] and encode into execution format: ;

[0121] wherein, TRIGGER instruction is device acceptance format, directly driving FPGA controller countdown start.

[0122] S32, match regulation strategy library: according to the identifier, execute the following strategy matching:

[0123] S321, when Identifier = “DT” (drought), match drought regulation strategy, generate operation instruction set:

[0124] Gradient pressure irrigation parameters (pressure changes with stage):

[0125] ;

[0126] Drought-resistant agent injection ratio: ; Identifier represents the drought-resistant agent injection ratio, Identifier represents the application volume of polyglutamic acid (PGA) drought-resistant agent, Identifier represents the application volume of irrigation water;

[0127] wherein, Identifier represents the irrigation pressure, applied in three stages, Identifier represents the window time period division point, Identifier represents the ratio of polyglutamic acid (PGA) drought-resistant agent to irrigation water.

[0128] S322, when Identifier = “SJ” (saline-alkali), match saline-alkali regulation strategy, generate operation instruction set:

[0129] Calcium ion chelating agent concentration setting: ;

[0130] Osmotic regulator application rate: ;

[0131] wherein, Identifier represents the EDTA-Ca solution concentration, Identifier represents the drug application rate, controlled within the safety threshold to prevent pesticide damage.

[0132] I. Anti-drought agent injection ratio (polyglutamic acid PGA to irrigation water ratio 1:2000) Based on the safety threshold of plant protection: Polyglutamic acid (PGA) as a water-soluble biological anti-drought agent, the recommended safe concentration on drought-resistant crops such as corn is generally in the range of 0.03%~0.05% (w / v), that is, mass ratio 1:2000 to 1:3000 can ensure effective water retention without causing rhizosphere blockage or nutrient adsorption inhibition.

[0133] Multi-site corn drought-tolerant field test results show that: in the drip irrigation system, injecting PGA at a concentration of 1:2000 can improve root longitudinal growth and soil water holding capacity, and will not inhibit rhizosphere microbial activity. The dose control module of most agricultural irrigation equipment currently uses a liquid dilution tank or a back pressure proportional injection device, and the minimum stable injection ratio is generally set to 0.05% (i.e. 1:2000) to ensure uniformity and system stability.

[0134] II. Calcium ion chelator concentration setting (EDTA-Ca = 0.5 mmol / L) is based on the standard dose interval for sodium toxicity relief:

[0135] International plant nutrition research generally recommends using 0.3~0.8 mmol / L EDTA-Ca as the upper limit of the concentration of slow-release chelating agent in alkaline or saline-alkali stress soil conditions to chelate and exchange rhizosphere free Na + , reduce sodium ion toxicity, and application of EDTA-Ca at a concentration of 0.5 mmol / L can effectively prevent Na + from accumulating in the root cortex, avoiding electrolyte imbalance, while not triggering cell wall osmotic swelling and rupture or causing ion overload poisoning.

[0136] III. Permeability regulator application rate (5L / min) is based on effective rate and root zone osmotic balance considerations: Permeability regulators (such as glycerol, polyols) need to be uniformly applied to the root zone at a certain rate. 5L / min is a safe rate that can quickly cover the target root layer without causing seepage flushing or water potential mutation, suitable for drip irrigation and rotating sprinkler irrigation systems. Simulation experiments show that in medium loamy fields, a 5L / min application rate can stabilize the osmotic agent concentration to a depth of 20cm in the root layer within 10 minutes, which is beneficial to the regulation of osmotic pressure by the roots to alleviate saline-alkali stress.

[0137] S33, perform time window binding operation:

[0138] 1. Write the operation instruction set directly to the FPGA controller of the corresponding agricultural equipment;

[0139] 2. Start the countdown trigger TRIGGERHH:MM:SS;

[0140] 3. Perform forced verification at time:

[0141] Drought response check indicator (example): soil water content ;

[0142] Salinity response check indicator (example): soil electrical conductivity .

[0143] represents the mandatory check advance, that is, the check time period reserved in advance before the end of the time window, represents the target soil water content threshold value for judging whether the drought regulation is effective, represents the electrical conductivity safety threshold value, which represents the upper limit value of the salt concentration in the soil after regulation, and is set according to the salt tolerance of crops.

[0144] As shown in Figure 2 , a corn stress resistance prediction system based on multi-source data is used to implement the above method, comprising the following modules:

[0145] A data acquisition module is used to synchronously acquire genotype marker data, real-time environmental stress data and farmland historical operation records of the target corn plant.

[0146] A decision engine module is used to build a multi-source decision matrix, calculate the stress response intensity, and output a stress resistance decision vector in combination with the genotype parameter.

[0147] A 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, write the instruction into the controller, and control the agricultural equipment to perform the regulation operation according to the countdown trigger mechanism.

[0148] The present application covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present application. In order to make the public have a thorough understanding of the present application, specific details are described in the following preferred embodiments of the present application, and the present application can also be fully understood without the description of these details to those skilled in the art. In addition, in order to avoid unnecessary confusion to the essence of the present application, well-known methods, processes, procedures, elements and circuits are not described in detail.

[0149] The above is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled in the art, without departing from the principle of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be regarded as the protection scope of the present application.

Claims

1. A method for corn stress resistance prediction based on multi-source data, characterized in that, The method comprises the following steps: S1, synchronously collecting data: acquiring genotype marker data, real-time environmental stress data and historical operation records of the target corn plant; S2, generating stress resistance decision vector: inputting the data of S1 into a dynamic decision engine to output a stress resistance decision vector including a stress type identifier and a regulation time window; S3, executing regulation instructions: activating corresponding agricultural equipment according to the regulation time window and implementing the regulation operation associated with the stress type identifier within the specified time window; The S1 specifically comprises: S11, acquiring genotype marker data of the target corn plant, collecting leaf tissue fluid through a field portable typing device, and outputting genotype marker codes including drought-resistant gene ZmNAC111 and salt-tolerant gene ZmHKT1 based on CRISPR-Cas12a nucleic acid rapid detection technology; S12, acquiring real-time environmental stress data, including: continuously monitoring the rhizosphere ion flux change rate through a buried root sensor; collecting transpiration rate fluctuation values through a leaf clamp type micro weather station; S13, acquiring historical operation records of the farmland, extracting encrypted operation logs from a blockchain agricultural record system, and generating a structured operation sequence including irrigation water volume, fertilizer type and biological pesticide application frequency after timestamp analysis. 2.The corn stress resistance prediction method based on multi-source data according to claim 1, wherein, The rate of change of the rhizosphere ion flux is expressed as: ; wherein, represents the ion flux absorbed or discharged by the root system, represents a unit time interval, is a "differential" symbol, representing a small change amount, represents a small change amount of the ion flux absorbed or discharged by the root system per unit time; The transpiration rate fluctuation value is expressed as: ; Indicates the first Transpiration rate per unit area of ​​leaf at the time of sampling This represents the mean transpiration rate. The standard deviation of transpiration rate is used to measure the activity of stomatal opening and closing. 3.The corn stress resistance prediction method based on multi-source data according to claim 1, wherein, The S2 specifically comprises: S21, constructing a multi-source decision matrix: aligning the genotype marker codes, rhizosphere ion flux change rate, transpiration rate fluctuation values and structured operation sequence obtained in S1 into a decision matrix according to the time axis; S22, calculating stress response intensity: when the transpiration rate fluctuation value exceeds the baseline by 30% and lasts for a predetermined length of time, activate the drought response channel, output the drought stress intensity index, and then determine 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 the dominant stress channel; when the transpiration rate fluctuation value and the rhizosphere ion flux change rate are both out of limits, the rhizosphere ion flux change rate is the first priority, i.e. the rhizosphere ion flux change rate is the dominant stress channel; S23, generating stress resistance decision vector: mapping the stress response intensity to a countdown type regulation time window based on the genotype marker code calling a preset golden window period parameter table.

4. The corn stress resistance prediction method based on multi-source data according to claim 3, characterized in that, In S23, the corresponding stress type identifier is selected according to the dominant stress channel, wherein the drought identifier is "DT" and the saline-alkali identifier is "SJ".

5. The corn stress resistance prediction method based on multi-source data according to claim 3, characterized in that, The drought stress intensity index is defined as: ; wherein, represents a transpiration rate fluctuation value, represents a drought sensitivity coefficient, represents a threshold value exceeding duration, is a drought stress intensity index, i.e., a normalized intensity level, which can correspond to a window period mapping table, represents a historical reference value of the corn transpiration rate fluctuation value.

6. The corn stress resistance prediction method based on multi-source data according to claim 3, characterized in that, The salt ion toxicity concentration gradient is defined as: ; wherein, is the ion gradient response gain coefficient, is the salt toxicity concentration gradient, the greater the value represents the stronger stress; if a minimum lower limit value is required to be set to prevent zero error, , represents , the instantaneous flux of 7. The corn stress resistance prediction method based on multi-source data according to claim 1, characterized in that, The S3 specifically comprises: S31, analyzing the decision vector: extracting the stress type identifier and the regulation time window from the stress resistance decision vector, and converting the regulation time window into a device executable countdown trigger instruction; S32, matching the regulation strategy library: when the stress type identifier is "DT", call the drought regulation strategy to generate an operation instruction set including gradient pressurized irrigation parameters and drought-resistant agent injection ratio; when the stress type identifier is "SJ", call the saline-alkali regulation strategy to generate an operation instruction set including calcium ion chelating agent concentration and osmotic regulator application rate.

8. The corn stress resistance prediction method based on multi-source data according to claim 7, characterized in that, The S3 further comprises performing a time window binding operation: write the operation instruction set to the FPGA controller of the corresponding agricultural equipment; start the countdown trigger instruction to force the verification of operation completion degree 5 minutes before the regulation time window is closed; if the operation is not completed when the countdown is over, start the backup equipment to perform compensation operation.

9. A multi-source data based corn stress resistance prediction system for implementing the multi-source data based corn stress resistance prediction method according to any one of claims 1-8. comprise the following modules: a data acquisition module for synchronously acquiring genotype marker data, real-time environmental stress data, and farmland historical operation records of the target corn plant; a decision engine module for constructing a multi-source decision matrix, calculating stress response intensity, and outputting an anti-stress decision vector in combination with genotype parameters; a regulation execution module for analyzing stress type identifiers and regulation time windows according to the anti-stress decision vector, matching corresponding agricultural operation strategies, writing instructions to the controller, and controlling agricultural equipment to perform regulation operation according to the countdown trigger mechanism.

Images