Intelligent irrigation decision control system for rice seedling based on internet of things

Abstract

The application relates to the technical field of Internet of Things intelligent control, and particularly discloses a rice seedling intelligent irrigation decision control system based on the Internet of Things, which firstly senses the real-time air temperature and light intensity in the field from the late differentiation stage of wild sterile line young panicles to the heading stage, automatically quantizes the low-temperature accumulation effect, and predicts the heading delay degree; when it is predicted that the sterile line and the maintainer line meet in the flowering period and there is a deviation risk, irrigation regulation instructions for water temperature adjustment are generated and executed in time, a complete closed-loop control link from environment sensing, accumulated temperature delay prediction to irrigation decision execution is formed, the process does not require artificial experience judgment, the most critical flowering period meeting management in rice seed production is changed from passive response to active pre-adjustment, the guarantee level of the flowering period synchronization is greatly improved, and the yield loss of the seed production caused by the misalignment of the flowering period is effectively reduced.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) intelligent control technology, specifically to an IoT-based intelligent irrigation decision control system for rice seedling cultivation. Background Technology

[0002] In rice breeding and seed production, the propagation of male-sterile lines is a crucial step in hybrid rice seed production. Wild-aborted male-sterile lines are one of the most widely used types of male-sterile lines in hybrid rice production, possessing advantages such as stable sterility and good outcrossing habits. They are extensively used in the three-line hybrid rice seed production method. The maintenance of their sterility and the efficiency of seed propagation directly affect the yield and quality of hybrid rice seeds. In the propagation process of wild-aborted male-sterile lines, the male-sterile line and the maintainer line need to be interplanted in a certain ratio to achieve outcrossing and seed setting through natural pollination. However, if wild-aborted male-sterile lines encounter sustained low temperatures during the late panicle differentiation stage to the initial heading stage, their heading process will be affected, leading to a deviation in the flowering time of the male-sterile line and the maintainer line, ultimately impacting seed propagation efficiency. Therefore, effectively addressing the interference of low temperatures on the heading process during this critical growth period is an important technical challenge for ensuring the seed propagation efficiency of male-sterile lines.

[0003] Currently, irrigation management during rice seedling and propagation mainly relies on traditional experience-based judgment or timed control methods. Conventional irrigation control systems typically use soil moisture content or field water depth as the main monitoring indicators. By setting lower and upper water thresholds, irrigation is initiated when the monitored value falls below the lower limit and stopped when it rises above the upper limit, thus maintaining soil moisture or water level within a suitable range to meet the basic water requirements for rice growth. Some irrigation systems incorporate weather station data or evapotranspiration models, enabling them to predict rice water demand based on environmental factors and automatically supplement irrigation. Their control logic revolves around maintaining water balance. At different growth stages of rice, these systems adjust the upper and lower limits of soil moisture content to adapt to the approximate differences in water demand at each stage, such as setting different irrigation trigger conditions during the tillering and booting stages. In addition, some irrigation systems use timed control methods, performing fixed irrigation operations according to preset time intervals and irrigation volumes, without relying on real-time sensor monitoring.

[0004] In the application of IoT technology to agriculture, systems combining wireless sensor networks with irrigation control have emerged. These systems deploy multiple sensor nodes in the field to collect environmental parameters such as air temperature and humidity, soil temperature and humidity, and light intensity. The data is then transmitted wirelessly to a control center, which controls the opening and closing of water pumps or valves based on a comparison of the collected data with preset thresholds. These systems achieve remote and automated irrigation control, reducing the need for manual on-site operation. However, their irrigation decisions still rely on the comparison between current environmental parameters and fixed thresholds, with the control objective focused on maintaining water supply in the field.

[0005] In summary, existing irrigation control methods primarily focus on water supply management. Their core lies in controlling irrigation volume to meet the water requirements of rice by monitoring soil moisture or environmental parameters. Field irrigation systems typically use soil moisture or water depth as decision-making criteria, and their control objectives and methods revolve around water balance, without involving the tracking and evaluation of rice growth processes. For the propagation of wild-type sterile lines, ensuring flowering coincidence is not only related to water supply but also closely related to temperature conditions during the heading stage. However, existing irrigation systems do not establish a correlation between temperature conditions and rice growth processes in their control logic. They cannot adjust irrigation strategies based on the impact of temperature changes on rice heading time. Therefore, in the event of low temperatures, it is difficult to mitigate the adverse effects of low temperatures on rice growth processes through proactive regulation, and even more so, it is impossible to proactively intervene in the critical seed production process of flowering coincidence between sterile and maintainer lines. This restricts further improvements in the yield and stability of hybrid rice seed production. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention provides an intelligent irrigation decision control system for rice seedling cultivation based on the Internet of Things, which can effectively solve the problems mentioned in the background technology.

[0007] To achieve the above objectives, the present invention provides the following technical solution: an IoT-based intelligent irrigation decision control system for rice seedlings, comprising a field data acquisition module for real-time acquisition of field environmental data from the late panicle differentiation stage to the heading stage of the wild male sterile line, wherein the field environmental data includes at least air temperature and light intensity; an accumulated temperature prediction delay module for determining the low temperature accumulation effect of the wild male sterile line at the current growth stage based on the field environmental data, and predicting the degree of delay in the heading time of the wild male sterile line based on the low temperature accumulation effect; and an irrigation decision control module for generating an irrigation decision control command for water temperature regulation when the degree of delay indicates a risk of deviation in the flowering period of the wild male sterile line and the maintainer line, and controlling the field irrigation execution device to execute the irrigation decision control command.

[0008] As a further step, the low-temperature accumulation effect of the wild-type sterile line at its current growth stage is determined based on the aforementioned field environmental data. The specific determination process is as follows: Air temperature sequences within a preset time window are extracted from the field environmental data. Each air temperature in the air temperature sequence is compared with the biological lower limit air temperature of the wild male sterile line at the current growth stage to identify periods in the air temperature sequence where the air temperature is continuously lower than the biological lower limit air temperature and mark them as low-temperature events. At the same time, the duration and average temperature deviation amplitude of each low-temperature event are determined. The duration of each low-temperature event within the preset time window is multiplied and accumulated with the corresponding average temperature deviation amplitude to obtain the low-temperature accumulation effect. The low-temperature accumulation effect is used to characterize the degree of inhibition of the rate of photosynthetic product translocation to the panicle during the panicle differentiation process of the wild male sterile line by low-temperature stress.

[0009] As a further approach, the degree of delay in the heading time of wild-type male-sterile lines is predicted based on the aforementioned low-temperature accumulation effect. The specific prediction process is as follows: Obtain the light intensity sequence within the preset time window from the field environmental data. Extract the combined time period where the light intensity is greater than a preset light threshold and the air temperature is greater than the biological lower limit air temperature from the light intensity sequence and the air temperature sequence, and use this combined period as the effective temperature period. Extract several hourly temperatures from the air temperature sequence corresponding to the effective temperature period, and use the difference between each hourly temperature and the biological lower limit air temperature as the contribution of each hourly effective accumulated temperature. Accumulate the hourly effective accumulated temperature contributions within the effective temperature period to obtain the total accumulated effective temperature. Obtain the field abortion... The breeding line completes the target effective accumulated temperature value corresponding to heading during the growth stage, and the difference between the target effective accumulated temperature value and the total accumulated effective temperature is taken as the effective accumulated temperature gap; based on the degree of low temperature stress characterized by the low temperature accumulation effect, the inhibition coefficient of low temperature stress on the daily average effective accumulated temperature accumulation during the effective temperature period is determined; the daily average effective accumulated temperature accumulation during the effective temperature period is corrected with the inhibition coefficient, and based on the corrected daily average effective accumulated temperature accumulation and the effective accumulated temperature gap, the number of delay days required to fill the effective accumulated temperature gap is estimated and used as the degree of delay in the heading time of the wild abortive male sterile line.

[0010] As a further approach, based on the degree of low-temperature stress characterized by the low-temperature accumulation effect, the inhibition coefficient of low-temperature stress on the daily average effective accumulated temperature accumulation during the effective temperature period is determined. The specific process is as follows: Obtain the product value of the low-temperature accumulation effect; match the product value with a pre-constructed correspondence between stress level and inhibition coefficient to determine the inhibition coefficient.

[0011] As a further measure, it is determined whether the degree of delay indicates a risk of discrepancy in the flowering periods of the wild-type sterile line and the maintainer line. The specific determination process is as follows: Obtain the expected heading time window of the maintainer line; add the normal heading time of the wild sterile line to the number of days of delay to obtain the expected heading time of the wild sterile line; compare the degree of overlap between the expected heading time and the expected heading time window with a preset overlap threshold; when the degree of overlap is lower than the overlap threshold, it is determined that the degree of delay indicates that there is a risk of deviation in the flowering period of the wild sterile line and the maintainer line.

[0012] As a further solution, irrigation decision-making and control instructions based on water temperature regulation are generated. The specific generation process is as follows: Based on the number of delay days and the degree of overlap, the intervention intensity level of irrigation decision control is determined; based on the intervention intensity level, the drainage depth of daytime drainage operation and the irrigation depth of nighttime irrigation operation are determined, so as to generate the irrigation decision control instruction containing the drainage depth and the irrigation depth.

[0013] As a further solution, the field irrigation execution device is controlled to execute the irrigation decision control command. The specific control process is as follows: According to the drainage depth in the irrigation decision control command, the drainage valve is controlled to open, and the field water depth is monitored in real time; when the monitored field water depth drops to the drainage depth, the drainage valve is controlled to close; according to the irrigation depth in the irrigation decision control command, the inlet valve is controlled to open, and the field water depth is monitored in real time; when the monitored field water depth rises to the irrigation depth, the inlet valve is controlled to close.

[0014] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: (1) This invention provides an intelligent irrigation decision control system for rice seedlings based on the Internet of Things. First, it senses the field air temperature and light intensity in real time from the late panicle differentiation stage to the heading stage of the wild sterile line. The system automatically quantifies the low temperature accumulation effect and predicts the degree of heading delay. When it is predicted that there is a risk of deviation between the flowering period of the sterile line and the maintainer line, it generates and executes the irrigation control command to regulate the temperature with water in a timely manner, forming a complete closed-loop control link from environmental perception, accumulated temperature delay prediction to irrigation decision execution. This process does not require human experience judgment. It transforms the most critical flowering period matching management in rice seed production from passive response to active pre-adjustment, greatly improves the guarantee level of flowering period synchronization, and effectively reduces the loss of seed production yield caused by flowering period misalignment.

[0015] (2) This invention determines the inhibition coefficient by multiplying the duration of each low temperature event with the average temperature deviation amplitude and matching it with a pre-constructed correspondence between stress degree and inhibition coefficient. This approach accurately captures the dual impact mechanism of low temperature stress, which not only directly reduces accumulated temperature but also subsequently inhibits the accumulation efficiency of daily effective accumulated temperature. As a result, when predicting the degree of heading delay, it not only compensates for the theoretical number of days corresponding to the accumulated temperature gap but also incorporates the continuous physiological inhibition of low temperature on the transport of rice photosynthetic products and the development rate of young panicles into the calculation. This significantly improves the consistency of delay prediction in multiple and intermittent low temperature scenarios and avoids misjudgment of flowering period encounter caused by underestimating the actual growth period delay due to relying solely on the simple effective accumulated temperature gap.

[0016] (3) Based on the degree of overlap between the delay days and the heading time window of the sterile line and the maintainer line, this invention determines the intervention intensity level of irrigation decision-making regulation and generates irrigation instructions containing specific daytime drainage depth and nighttime irrigation depth, realizing dynamic grading and quantification of water-based temperature regulation measures. This transforms field water and heat regulation operations from extensive deep-water irrigation to differentiated interventions that are precisely matched with the degree of risk of flowering deviation. While effectively utilizing the temperature regulation mechanism of water stratification to raise daytime temperature and keep nighttime temperature to accelerate the development of sterile lines, it avoids the ineffective water consumption and field management burden caused by excessive irrigation and drainage, and takes into account both the emergency effect of flowering regulation and the sustainable operation requirements of resource conservation. Attached Figure Description

[0017] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the system module connections of the present invention. Detailed Implementation

[0019] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0020] See Figure 1 The diagram shown is a schematic diagram of the system module connection of the present invention. Preferably, the present invention provides a technical solution: an intelligent irrigation decision control system for rice seedling cultivation based on the Internet of Things, including a field data acquisition module, an accumulated temperature prediction delay module, an irrigation decision control module, and a rice irrigation control database.

[0021] At the system architecture level, the field data acquisition module is connected to the accumulated temperature prediction delay module to transmit the collected real-time field environmental data to the accumulated temperature prediction delay module for subsequent processing; the accumulated temperature prediction delay module is connected to the irrigation decision control module to transmit the predicted delay level to the irrigation decision control module as a decision basis; the field data acquisition module, the accumulated temperature prediction delay module, and the irrigation decision control module are all connected to the rice irrigation control database to read preset parameters, thresholds, and corresponding relationships from the database, and to transmit process data and intermediate results back to the database for storage and recording.

[0022] The rice irrigation control database stores data such as preset time windows, biological lower limit air temperature, preset light threshold, target effective accumulated temperature, normal heading time, predicted heading time window of maintainer lines, preset overlap threshold, and pre-constructed correspondence between stress degree and inhibition coefficient. For example, the biological lower limit air temperature is determined through statistical analysis of the genetic characteristic parameters and historical growth period observation data of wild-sterile lines, enabling the variety to carry out normal physiological activities at the current growth stage. This value is stored in the rice irrigation control database in the form of a data table and can be configured and updated through the database management interface according to the updates of different wild-sterile lines. The other values ​​are similar to the biological lower limit air temperature, and their specific values ​​will vary depending on the type of wild-sterile line, the climate zoning of the planting area, and the variety approval data accessed by the rice irrigation control database. This embodiment does not impose any special limitations. In addition, the rice irrigation control database is a cloud-based agricultural Internet of Things (IoT) data management platform, such as Alibaba Cloud Agricultural IoT Platform or Huawei Cloud IoT Agriculture Platform, which provides standard data storage, query, and update interfaces that can be called by various modules of this system.

[0023] The field data acquisition module is used to collect field environmental data in real time from the late panicle differentiation stage to the beginning of panicle stage of wild sterile lines. The field environmental data includes at least air temperature and light intensity.

[0024] In this embodiment, the late panicle differentiation stage refers to the growth stage from when the panicle length of the wild sterile line reaches more than 80% of its final length until the pollen mother cell meiosis is completed. The initial heading stage refers to the growth stage when the top of the panicle begins to emerge from the flag leaf sheath. The determination of these two stages can be made by identifying the panicle morphology using image sensors deployed in the field and combining it with accumulated temperature data. The air temperature and light intensity data in the field environment are collected in real time by IoT sensor nodes deployed in the wild sterile line planting area. The sensor nodes integrate temperature and light sensors and periodically upload the collected data to the field data acquisition module via ZigBee or LoRa wireless communication protocols to achieve real-time aggregation of data via IoT. To ensure the reliability and spatial representativeness of the data, the sensor nodes are deployed in the field in a grid pattern, with at least one set of sensors deployed in each area. The acquisition frequency can be adaptively adjusted according to weather conditions, and during low temperature warnings, the frequency is increased to once every 10 minutes.

[0025] The accumulated temperature prediction delay module is used to determine the low-temperature accumulation effect of the wild-type male-sterile line at its current growth stage based on the field environmental data, and to predict the degree of delay in the heading time of the wild-type male-sterile line based on the low-temperature accumulation effect. This module is the core decision-making unit of the system, which provides a scientific basis for precise intervention by converting the environmental temperature time series into a quantitative indicator of physiological development delay.

[0026] Specifically, the low-temperature accumulation effect of the wild abortive sterile line at its current growth stage was determined based on the aforementioned field environmental data. The specific determination process is as follows: The air temperature sequence within a preset time window is extracted from the field environmental data. The preset time window refers to a sliding time interval from the end of the panicle differentiation stage to the current moment, and the preset time window is stored in the rice irrigation control database. The air temperature sequence is a set of temperature data formed by arranging the air temperature at each sampling moment within the preset time window in chronological order. This sequence includes both hourly temperature values ​​and corresponding sampling timestamps to facilitate subsequent calculation of the time period length and the amount of accumulated deviation. The current growth stage is from the end of the panicle differentiation stage to the beginning of heading stage.

[0027] Each air temperature in the air temperature sequence is compared with the biological lower limit air temperature of the wild abortive sterile line at the current growth stage to identify periods in the air temperature sequence where the air temperature is continuously lower than the biological lower limit air temperature and mark them as low temperature events. At the same time, the duration and average temperature deviation amplitude of each low temperature event are determined.

[0028] It should be explained that the biological lower limit air temperature refers to the minimum critical air temperature value at which wild sterile lines can maintain normal panicle development and heading process from the end of panicle differentiation to the beginning of heading. This value is usually in the range of 15℃ to 18℃, depending on the variety. This value is stored in the rice irrigation control database. The period during which the air temperature is continuously lower than the biological lower limit air temperature refers to the time interval in the air temperature sequence where the air temperature value at two or more consecutive sampling times is lower than the biological lower limit air temperature. The duration refers to the number of hours that a single low temperature event lasts from start to finish. The average temperature deviation amplitude refers to the arithmetic mean of the absolute values ​​of the differences between the air temperature at each sampling time and the biological lower limit air temperature in a single low temperature event.

[0029] The low-temperature accumulation effect is obtained by multiplying the duration of each low-temperature event within the preset time window with the corresponding average temperature deviation amplitude. This low-temperature accumulation effect characterizes the degree to which low-temperature stress inhibits the rate of photosynthetic product translocation to the panicle during the differentiation process of wild male sterile lines. Preferably, the process of obtaining the low-temperature accumulation effect is as follows: obtaining the product of the duration of each low-temperature event with the average temperature deviation amplitude, accumulating the product results of each low-temperature event to obtain the product value, and using this product value as the low-temperature accumulation effect. The product comprehensively reflects the cumulative stress effect of low temperature in both time duration and intensity deviation dimensions. This low-temperature accumulation effect is not a simple meteorological statistical indicator, but a physiological indicator that is significantly correlated with changes in the development process of wild male sterile lines. For every unit increase in the product value, the corresponding rate of photosynthetic product translocation to the panicle in the young panicle decreases by approximately a proportional gradient. By quantifying this effect, the system can map the abstract low-temperature weather process into a quantifiable and assessable degree of physiological damage.

[0030] Furthermore, based on the aforementioned low-temperature accumulation effect, the degree of delay in the heading time of wild-type male-sterile lines is predicted. The specific prediction process is as follows: The light intensity sequence within the preset time window is obtained from the field environmental data. From the light intensity sequence and the air temperature sequence, a comprehensive period in which the light intensity is greater than a preset light threshold and the air temperature is greater than the biological lower limit air temperature is extracted as the effective temperature period. Here, the light intensity sequence refers to the light data set formed by arranging the light intensities of each sampling moment within the preset time window in chronological order; the preset light threshold refers to the minimum light intensity value that the wild-type male sterile line must reach to perform photosynthesis and generate effective heat accumulation during this growth stage, and this threshold is stored in the rice irrigation control database; the comprehensive period refers to the period in which both light intensity and air temperature meet the above conditions, indicating that the temperature conditions within this period can effectively drive the development process of the wild-type male sterile line, rather than relying solely on the air temperature itself.

[0031] Several hourly temperatures are extracted from the air temperature sequence corresponding to the effective temperature period. These hourly temperatures represent the air temperatures within the air temperature sequence. The difference between each hourly temperature and the biological lower limit air temperature is used as the contribution of each hourly effective accumulated temperature. The hourly effective accumulated temperature contributions within the effective temperature period are accumulated to obtain the total accumulated effective temperature. This accumulation process uses an hourly integration method, which can more accurately capture the impact of diurnal temperature fluctuations on development rates than the commonly used daily average accumulated temperature, especially in spring when the diurnal temperature range is large, resulting in higher computational accuracy.

[0032] The target effective accumulated temperature value corresponding to the completion of heading in the wild male sterile line during the growth stage is obtained. The target effective accumulated temperature value refers to the total effective accumulated temperature required for the wild male sterile line to accumulate from the end of the young panicle differentiation stage to the completion of heading. This value is determined by the genetic characteristics of the variety and is stored in the rice irrigation control database after being calibrated in advance through field trials. The difference between the target effective accumulated temperature value and the total effective accumulated temperature is used as the effective accumulated temperature gap.

[0033] Based on the degree of low-temperature stress characterized by the low-temperature accumulation effect, the inhibition coefficient of low-temperature stress on the daily average effective accumulated temperature during the effective temperature period is determined.

[0034] The average daily effective accumulated temperature accumulation during the effective temperature period is corrected using the inhibition coefficient. Specifically, the correction process involves dividing the average daily effective accumulated temperature accumulation during the effective temperature period by (1 - inhibition coefficient) to obtain the corrected average daily effective accumulated temperature accumulation under normal conditions. Normal conditions refer to a state without low-temperature stress. The average daily effective accumulated temperature accumulation is equal to the total effective accumulated temperature during the effective temperature period divided by the number of days within the effective temperature period. The total effective accumulated temperature is obtained by summing the hourly effective accumulated temperature contributions during the effective temperature period, representing the average daily effective accumulated temperature accumulation that can be provided for the development process during the effective temperature period. Based on the corrected average daily effective accumulated temperature accumulation and the effective accumulated temperature gap, the number of delay days required to fill the effective accumulated temperature gap is estimated and filled. Specifically, the average daily effective accumulated temperature under normal conditions during the effective temperature period is calculated. The difference between the accumulated temperature and the actual daily average accumulated temperature during the effective temperature period is used to obtain the daily average accumulated temperature difference. The total accumulated temperature loss during the effective temperature period is obtained by multiplying the number of days included in the effective temperature period by the daily average accumulated temperature difference. The total accumulated temperature loss is then divided by the daily average accumulated temperature under normal conditions to obtain the number of days the heading time of the wild male sterile line is delayed, which is used as the degree of delay in the heading time of the wild male sterile line. The inhibition coefficient is negatively correlated with the panicle differentiation sensitive period of the wild male sterile line. The panicle differentiation sensitive period refers to the specific developmental stage during the development of rice panicles that is most strongly responsive to changes in environmental factors such as temperature and moisture, and has the greatest impact on the final yield or fertility after stress. The longer the panicle differentiation sensitive period, the smaller the inhibition coefficient corresponding to the same low temperature accumulation effect, so as to differentiate the differences in the tolerance of different wild male sterile line varieties to low temperature.

[0035] Specifically, based on the degree of low-temperature stress characterized by the low-temperature accumulation effect, the inhibition coefficient of low-temperature stress on the daily average effective accumulated temperature accumulation during the effective temperature period is determined. The specific process is as follows: Obtain the product value of the low-temperature accumulation effect, which is also the degree of low-temperature stress.

[0036] The product value is matched against a pre-constructed correspondence between stress level and inhibition coefficient to determine the inhibition coefficient. This pre-constructed correspondence refers to a mapping table or function relationship pre-calibrated through field trials, with the product value as the independent variable and the inhibition coefficient of daily effective accumulated temperature as the dependent variable. This correspondence is stored in a rice irrigation control database. During actual calibration, different low-temperature treatment gradients are set in artificial climate chambers or open-field heating facilities. The daily effective accumulated temperature accumulation rate of the wild-type sterile line under each treatment is measured and compared with the accumulation rate of the control treatment (no low-temperature stress). The inhibition coefficient under each stress gradient is calculated, and a correspondence between the product value and the inhibition coefficient is established. This correspondence can be constructed using piecewise linear interpolation or nonlinear fitting. The inhibition coefficient is a dimensionless value between 0 and 1; a larger value indicates stronger inhibition of daily effective accumulated temperature accumulation by low-temperature stress.

[0037] It should be noted that the accumulated value is mapped to the inhibition coefficient through the correspondence between the stress degree and the inhibition coefficient, and then participates in the subsequent calculation of the delay days. This mapping relationship is calibrated based on field historical data of multiple varieties and years, which can effectively distinguish the different response patterns of different varieties to intermittent low temperature and continuous low temperature. Compared with the conventional prediction method that uses the effective accumulated temperature gap alone, this embodiment reduces the delay prediction error by a relative proportion in the complex scenario of multiple alternating low temperatures, and significantly improves the reliability of the flowering period coincidence determination.

[0038] The irrigation decision control module is used to generate an irrigation decision control command for water temperature regulation when the delay level indicates a risk of deviation in the flowering period of the wild sterile line and the maintainer line, and to control the field irrigation execution device to execute the irrigation decision control command.

[0039] Specifically, the determination of whether the degree of delay indicates a risk of discrepancy in the flowering periods of the wild-type sterile line and the maintainer line is as follows: Obtain the expected heading time window of the maintainer line. The expected heading time window refers to the time interval from the earliest possible heading date to the latest possible heading date of the maintainer line, which is predicted based on the characteristics of the maintainer line variety and historical growth period data. This window is predetermined by field cultivation management records combined with the accumulated temperature characteristics of the variety and stored in the rice irrigation control database.

[0040] The expected heading time of the wild male sterile line is obtained by adding the normal heading time to the number of days of delay. The normal heading time refers to the historical average heading date of the wild male sterile line under ideal accumulated temperature conditions without low temperature stress. This date is determined by the varietal characteristics and local climate zoning and is stored in the rice irrigation control database.

[0041] The overlap between the expected heading time and the expected heading time window is compared with a preset overlap threshold. The overlap degree refers to the ratio of the number of days the expected heading time falls within the expected heading time window to the total number of days in the expected heading time window. The preset overlap threshold is the minimum overlap threshold required to ensure sufficient overlap between the flowering periods of the male-sterile line and the maintainer line. This overlap threshold is dynamically adjusted based on the pollination compatibility coefficients of the wild-aborted male-sterile line and the maintainer line. The pollination compatibility coefficients corresponding to each pair are pre-stored in the rice irrigation control database. These coefficients represent the potential for cross-pollination between the male-sterile line and a specific maintainer line under overlapping flowering conditions. The values ​​are calibrated through field testcross experiments, specifically using the average spikelet fertility of the testcross F1 as a quantitative indicator. The overlap threshold is dynamically adjusted based on the affinity coefficient. Specifically, the adjustment method involves multiplying the preset basic overlap threshold in the rice irrigation control database by an adjustment factor positively correlated with the pollination affinity coefficient. This adjustment factor is less than 1 when the affinity coefficient is higher than the benchmark value and greater than 1 when it is lower than the benchmark value. This means that the higher the affinity, the more lenient the requirement for flowering period overlap. In other words, the higher the affinity coefficient, the lower the overlap threshold, allowing for a greater tolerance for flowering period deviation in combinations with high pollination affinity. This overlap threshold is stored in the rice irrigation control database. When the degree of overlap is lower than the overlap threshold, it is determined that the degree of delay indicates a risk of deviation in the flowering period of the wild-type sterile line and the maintainer line. This risk of deviation will lead to insufficient pollen supply to the maintainer line during the pollination period of the sterile line, resulting in a decrease in cross-pollination seed setting rate and ultimately affecting seed production yield.

[0042] Furthermore, irrigation decision-making and control instructions based on water temperature regulation are generated. The specific generation process is as follows: Based on the number of delay days and the degree of overlap, the intervention intensity level for irrigation decision-making is determined. The determination process involves comparing the number of delay days and the degree of overlap with preset grading thresholds in the rice irrigation control database. A higher intervention intensity level indicates a larger delay day and a smaller degree of overlap. The intervention intensity level represents the implementation strength and urgency of water temperature control measures and is divided into three levels: low, medium, and high. For example, the preset grading logic could be: when the delay day is ≤2 days and the overlap is ≥60%, the intervention intensity level is low; when the delay day is between 3 and 5 days and the overlap is between 40% and 60%, the intervention intensity level is medium; and when the delay day is ≥6 days or the overlap is ≤40%, the intervention intensity level is high.

[0043] Based on the intervention intensity level, the drainage depth for daytime drainage operations and the irrigation depth for nighttime irrigation operations are determined to generate the irrigation decision control command that includes the drainage depth and the irrigation depth. Here, drainage depth refers to the target value of the water layer thickness retained in the field after daytime drainage, and irrigation depth refers to the target value of the water layer thickness reached in the field after nighttime irrigation. The basic principle of water-based temperature regulation is as follows: during the day, by reducing the water layer thickness, the heat capacity of the water body is reduced, allowing the soil and near-surface air to warm up more quickly under solar radiation, thereby increasing the accumulation rate of effective daytime accumulated temperature; at night, by increasing the water layer thickness, the high specific heat capacity of water is utilized to slow down heat loss in the field, reducing the nighttime temperature drop and thus reducing the inhibition of young spikelet development by low nighttime temperatures.

[0044] It should be explained that the determination of drainage depth and irrigation depth based on the intervention intensity level is achieved by querying a pre-calibrated table of the correspondence between intervention intensity level and water depth parameters in the rice irrigation control database. The low intensity level corresponds to a shallower drainage depth and irrigation depth, which utilizes the heat storage of water to regulate temperature through moderate daytime water reduction and nighttime irrigation. The high intensity level corresponds to a deeper drainage depth and irrigation depth, which significantly reduces the water layer during the daytime to enhance the soil's absorption of solar radiation and increase temperature, and significantly deepens the water layer at night to enhance the heat preservation effect. This control instruction, by quantifying the water depth parameter, transforms the flowering period promotion requirement into an executable dynamic water layer adjustment operation, realizing a closed-loop control that uses water to regulate temperature and promote the accelerated development of sterile lines.

[0045] Specifically, the field irrigation execution device is controlled to execute the irrigation decision control command, and the specific control process is as follows: First, the field irrigation execution device includes an electric inlet valve, an electric outlet valve, and a water depth sensor installed in the field. This device is connected to the irrigation decision-making and control module via a wireless communication module to receive and execute the irrigation decision-making and control commands. The electric inlet valve is connected to the irrigation water source (such as a canal or reservoir), the electric outlet valve is connected to the field drainage ditch, and the water depth sensor is installed at a representative location in the field. Its measurement data is collected and fed back to the control system via a field controller (such as a PLC or microcontroller).

[0046] According to the drainage depth in the irrigation decision control command, the drainage valve is controlled to open, and the field water layer depth is monitored in real time. The field water layer depth refers to the vertical height of the irrigation water layer above the field surface, which is measured by a water layer depth sensor through ultrasonic or pressure sensing.

[0047] When the monitored field water depth drops to the drainage depth, the drainage valve is closed to stop the drainage process and prevent root water stress caused by excessively shallow water.

[0048] Based on the irrigation depth specified in the irrigation decision control instructions, the water inlet valve is opened, and the water depth in the field is monitored in real time.

[0049] When the monitored field water depth rises to the irrigation depth, the inlet valve is closed to stop the irrigation process and prevent the field water temperature from being too low or the roots from being hypoxic due to excessive water depth.

[0050] The drainage and irrigation operations are executed in shifts according to irrigation decision-making and control instructions. Drainage is performed during the day to lower the water level and promote soil heat absorption and warming, while irrigation is performed at night to deepen the water level and utilize the high specific heat capacity of water to slow heat loss from the field, thus achieving heat preservation. Through this dynamic regulation of the water level during the day and night, the effective accumulated temperature accumulation rate of the wild-type sterile line is accelerated, thereby shortening the heading delay and promoting the synchronization of flowering with the maintainer line. It should be noted that daytime drainage lowering the water level increases soil temperature by a temperature gradient compared to conditions with deeper water, while nighttime irrigation deepening the water level slows the rate of temperature decrease in the field compared to conditions without water protection by a temperature gradient. Through this diurnal temperature difference regulation, under the premise of constant daily average temperature, the daily accumulation of effective accumulated temperature can be increased proportionally under low-temperature suppression conditions. All of the above effect parameters were obtained in advance through field comparison experiments and stored in the rice irrigation control database, providing quantitative regulatory effect data for the water-based temperature intervention of this system.

[0051] The above description is merely an example and illustration of the structure of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. An IoT-based intelligent irrigation decision control system for rice seedling cultivation, characterized in that: include: The field data acquisition module is used to collect field environmental data in real time from the late panicle differentiation stage to the beginning of panicle stage of wild sterile lines. The field environmental data includes at least air temperature and light intensity. The accumulated temperature prediction delay module is used to determine the low temperature accumulation effect of the wild male sterile line at the current growth stage based on the field environmental data, and to predict the degree of delay in the heading time of the wild male sterile line based on the low temperature accumulation effect. The irrigation decision control module is used to generate an irrigation decision control command for water temperature regulation when the delay level indicates a risk of deviation in the flowering period of the wild sterile line and the maintainer line, and to control the field irrigation execution device to execute the irrigation decision control command.

2. The IoT-based intelligent irrigation decision control system for rice seedling cultivation according to claim 1, characterized in that: The low-temperature accumulation effect of the wild abortive sterile line at its current growth stage was determined based on the field environmental data. The specific determination process is as follows: Extract the air temperature sequence within a preset time window from the field environment data; Each air temperature in the air temperature sequence is compared with the biological lower limit air temperature of the wild abortive sterile line at the current growth stage to identify periods in the air temperature sequence where the air temperature is continuously lower than the biological lower limit air temperature and mark them as low temperature events. At the same time, the duration and average temperature deviation amplitude of each low temperature event are determined. The duration of each low-temperature event within the preset time window is multiplied and accumulated with the corresponding average temperature deviation amplitude to obtain the low-temperature accumulation effect. The low-temperature accumulation effect is used to characterize the degree of inhibition of the rate of photosynthetic product translocation to the panicle during the young panicle differentiation process of wild abortive male sterile lines by low-temperature stress.

3. The IoT-based intelligent irrigation decision control system for rice seedling cultivation according to claim 2, characterized in that: The degree of delay in heading time of wild abortive male lines is predicted based on the aforementioned low-temperature accumulation effect. The specific prediction process is as follows: Obtain the light intensity sequence within the preset time window from the field environment data, and extract the combined time period from the light intensity sequence and the air temperature sequence where the light intensity is greater than the preset light threshold and the air temperature is greater than the biological lower limit air temperature, as the effective temperature time period; Several hourly temperatures are extracted from the air temperature sequence corresponding to the effective temperature period. The difference between each hourly temperature and the biological lower limit air temperature is used as the contribution of each hourly effective accumulated temperature. The contribution of each hourly effective accumulated temperature within the effective temperature period is accumulated to obtain the total accumulated effective temperature. Obtain the target effective accumulated temperature value corresponding to the completion of heading in the growth stage of the wild abortive male sterile line, and use the difference between the target effective accumulated temperature value and the total accumulated effective temperature as the effective accumulated temperature gap; Based on the degree of low temperature stress characterized by the low temperature accumulation effect, determine the inhibition coefficient of low temperature stress on the daily average effective accumulated temperature during the effective temperature period; The average daily effective accumulated temperature during the effective temperature period is corrected using the inhibition coefficient. Based on the corrected average daily effective accumulated temperature and the effective accumulated temperature gap, the number of delayed days required to fill the effective accumulated temperature gap is estimated and used as the degree of delay in the heading time of the wild sterile line.

4. The IoT-based intelligent irrigation decision control system for rice seedling cultivation according to claim 3, characterized in that: Based on the degree of low-temperature stress characterized by the aforementioned low-temperature accumulation effect, the inhibition coefficient of low-temperature stress on the daily average effective accumulated temperature accumulation during the effective temperature period is determined. The specific process is as follows: Obtain the product value of the low-temperature accumulation effect; The product value is matched against a pre-built correspondence between stress level and inhibition coefficient to determine the inhibition coefficient.

5. The IoT-based intelligent irrigation decision control system for rice seedling cultivation according to claim 4, characterized in that: The specific determination process for whether the degree of delay indicates a risk of discrepancy in the flowering periods of the wild-type sterile line and the maintainer line is as follows: Obtain the expected heading time window for the maintenance line; The normal heading time of the wild abortive male sterile line is added to the number of days of delay to obtain the expected heading time of the wild abortive male sterile line; The degree of overlap between the expected heading time and the expected heading time window is compared with a preset overlap threshold. When the degree of overlap is lower than the overlap threshold, it is determined that the degree of delay indicates a risk of deviation in the flowering period of the wild sterile line and the maintainer line.

6. The IoT-based intelligent irrigation decision control system for rice seedling cultivation according to claim 5, characterized in that: The process of generating irrigation decision-making and control instructions based on water temperature regulation is as follows: The intervention intensity level for irrigation decision-making and regulation is determined based on the number of delay days and the degree of overlap. Based on the intervention intensity level, the drainage depth for daytime drainage operations and the irrigation depth for nighttime irrigation operations are determined to generate the irrigation decision control instruction that includes the drainage depth and the irrigation depth.

7. The IoT-based intelligent irrigation decision control system for rice seedling cultivation according to claim 6, characterized in that: The field irrigation execution device is controlled to execute the irrigation decision and control command. The specific control process is as follows: According to the drainage depth in the irrigation decision control instruction, control the opening of the drainage valve and monitor the water depth in the field in real time. When the monitored field water depth drops to the drainage depth, the drainage valve is closed. According to the irrigation depth in the irrigation decision control instruction, control the opening of the water inlet valve and monitor the water depth in the field in real time; When the monitored field water depth rises to the irrigation depth, the inlet valve is closed.

Images