Intelligent control method and system for broccoli root zone alternate irrigation device

Abstract

The application discloses an intelligent control method of a broccoli root area alternate irrigation device, relates to the alternate irrigation field, and comprises the following steps: obtaining broccoli related information; outputting an initial growth period through an initial period prediction model; collecting broccoli remote sensing information through a remote sensing unmanned aerial vehicle; combining the broccoli remote sensing information and the broccoli related information to assimilate the initial period prediction model, obtaining a standard period prediction model, and determining a standard growth period based on the standard period prediction model; generating an alternate irrigation strategy based on the standard growth period, and intelligently regulating and controlling the alternate irrigation device according to the alternate irrigation strategy. The application can effectively reduce water resource waste.

Description

TECHNICAL FIELD

[0001] The embodiment of the present application relates to the field of alternate irrigation, in particular to an intelligent control method and system of broccoli root zone alternate irrigation device. BACKGROUND

[0002] Alternate irrigation is a water-saving irrigation technique that optimizes plant water uptake by scientifically regulating the water distribution in the crop root zone, thereby improving water resource utilization efficiency. The core lies in alternating the wetting of different root zones of crops, and using the physiological response mechanism of plants to maintain yield while reducing irrigation water volume.

[0003] Existing alternate irrigation devices usually rely on past experience to design fixed irrigation plans. When unexpected drought or precipitation occurs, which is difficult to predict by relying on past experience, it is difficult to adjust the irrigation plan in time for the next growth cycle of vegetables, which may lead to insufficient or excessive irrigation of vegetables, affecting crop growth and causing waste of water resources. SUMMARY

[0004] The embodiment of the present application provides an intelligent control method of a broccoli root zone alternate irrigation device, which is used to solve the problem of water resource waste in the application process of traditional alternate irrigation devices.

[0005] To achieve the above-mentioned purpose, the embodiments of the present application adopt the following technical solutions:

[0006] In a first aspect, an intelligent control method of a broccoli root zone alternate irrigation device is provided, which comprises:

[0007] Obtaining broccoli associated information of a target vegetable field;

[0008] Inputting the broccoli associated information into a pre-constructed initial period prediction model, and outputting all initial growth periods of target broccoli in the target vegetable field through the initial period prediction model;

[0009] When the initial growth period is reached for the first time, collecting broccoli remote sensing information of the target vegetable field through a remote sensing unmanned aerial vehicle;

[0010] Combining the broccoli remote sensing information and the broccoli associated information to assimilate the initial period prediction model, obtaining a standard period prediction model, and correcting the initial growth period based on the standard period prediction model to obtain a standard growth period;

[0011] When reaching any standard growth period, generating an alternate irrigation strategy for the target vegetable field based on the standard growth period, and intelligently controlling the alternate irrigation device preset in the target vegetable field according to the alternate irrigation strategy.

[0012] Optionally, the broccoli-related information includes first weather information of a location of the target vegetable field and broccoli information in the target vegetable field, and soil information of the target vegetable field, the soil information including pre-acquired soil water absorption rate, soil water holding rate, and soil type, and soil water content collected in real time by a soil sensor preset in the target vegetable field.

[0013] Optionally, the initial growth cycle is corrected based on the standard cycle prediction model to obtain a standard growth cycle, including the following steps:

[0014] The broccoli remote sensing information is preprocessed.

[0015] The preprocessed broccoli remote sensing information is processed by an inversion algorithm, and target vegetable field remote sensing parameters including broccoli index and vegetable field water content are extracted according to an inversion result.

[0016] The spatial fusion of the vegetable field water content and the soil water content is completed by using a data fusion algorithm to obtain the fusion water content of the target vegetable field.

[0017] The initial cycle prediction model is assimilated with the broccoli index and the fusion water content to obtain a standard cycle prediction model.

[0018] The first weather information, the broccoli information, and the soil information in the initial growth cycle are input into the standard cycle prediction model, and the standard growth cycle of the target broccoli is output by the standard cycle prediction model.

[0019] Optionally, the spatial fusion of the vegetable field water content and the soil water content is completed by using a data fusion algorithm to obtain the fusion water content of the target vegetable field, including the following steps:

[0020] The soil water content collected in the initial growth cycle is taken as the target water content.

[0021] The vegetable field water content and the target water content are standardized.

[0022] The data correlation between the standardized vegetable field water content and the target water content is calculated by using a correlation coefficient formula.

[0023] The spatial aggregation of the standardized vegetable field water content and the target water content is analyzed by using a preset variation function.

[0024] The spatial aggregation and the data correlation are combined, and the vegetable field water content and the target water content are interpolated and fused by using a Kriging interpolation method to obtain the fusion water content of the target vegetable field in the initial growth cycle.

[0025] Optionally, the standard period prediction model is obtained by combining the broccoli index and the fusion water content assimilation initial period prediction model, and includes the following steps:

[0026] Aligning the spatio-temporal scale between the broccoli index and the fusion water content;

[0027] Normalizing the broccoli index and the fusion water content after the spatio-temporal scale alignment to obtain a standard index and a standard water content, respectively;

[0028] Defining an error covariance matrix by combining the standard index and the standard water content;

[0029] Generating an initial state set of the initial period prediction model according to the broccoli-related information;

[0030] Running the initial period prediction model according to the initial state set and according to the ensemble Kalman filter algorithm to obtain a prediction state set;

[0031] Calculating a Kalman gain by combining the prediction state set and the error covariance matrix;

[0032] Adjusting the model parameters of the initial period prediction model by combining the Kalman gain, the standard index and the standard water content to obtain the standard period prediction model.

[0033] Optionally, the alternate irrigation strategy for the target vegetable field is generated based on the standard growth period, and includes the following steps:

[0034] Generating an alternate irrigation period for the target vegetable field according to the period type and the period time in the standard growth period;

[0035] Re-acquiring second meteorological information of the target vegetable field location within the standard growth period, the second meteorological information including meteorological parameters and total precipitation;

[0036] Calculating a reference evapotranspiration of the target broccoli according to the meteorological parameters;

[0037] Determining a crop coefficient of the target broccoli according to the period type;

[0038] Calculating a broccoli theoretical water requirement of the target broccoli by combining the reference evapotranspiration and the crop coefficient;

[0039] Taking the soil water content collected within the standard growth period as a standard water content;

[0040] Correcting the broccoli theoretical water requirement by using the soil water absorption rate, the soil water holding rate and the standard water content to obtain a broccoli actual water requirement;

[0041] Calculating a daily average irrigation amount of the target broccoli by combining the total precipitation and the broccoli actual water requirement;

[0042] The alternating irrigation cycle and the daily average irrigation amount are integrated to obtain the alternating irrigation strategy of the target vegetable field.

[0043] Optionally, the method further comprises:

[0044] After completing the intelligent irrigation task in any standard growth cycle, the irrigation qualification degree formula is used to calculate the irrigation qualification degree in the standard growth cycle;

[0045] If the irrigation qualification degree is located in the preset qualification threshold interval, it is determined that the intelligent irrigation task is qualified;

[0046] If the irrigation qualification degree is not located in the qualification threshold interval, it is determined that the intelligent irrigation task is unqualified;

[0047] If the intelligent irrigation task is qualified, the intelligent irrigation task in the next standard growth cycle is continued to be completed;

[0048] If the intelligent irrigation task is unqualified, the strategy correction factor is output according to the irrigation qualification degree, and the alternating irrigation strategy of the next standard growth cycle is corrected by using the strategy correction factor.

[0049] Optionally, the irrigation qualification degree formula comprises:

[0050]

[0051] Wherein, S x is the actual irrigation amount of the target broccoli, S y is the daily average irrigation amount of the target broccoli, γ is an irrigation correction factor, W l and W r are the daily average soil water content on the left and right sides of the target broccoli respectively, is a preset water content difference threshold, N is the number of soil sensors, δ is a preset fixed integer parameter, K is a pre-acquired soil water conductivity coefficient, T is the daily average irrigation duration, and F is a preset air temperature attenuation factor.

[0052] In a second aspect, the present application provides a machine readable storage medium, characterized in that the machine readable storage medium stores instructions for causing a machine to execute the method for intelligent control of the broccoli root zone alternating irrigation device according to any one of the first aspect.

[0053] In a third aspect, the present application provides an intelligent control system for a broccoli root zone alternating irrigation device, characterized in that it comprises:

[0054] a memory configured to store instructions; and

[0055] a processor configured to call the instructions from the memory and capable of implementing the method for intelligent control of the broccoli root zone alternating irrigation device according to any one of the first aspect when executing the instructions.

[0056] Through the above technical solution, the initial growth cycle of the target broccoli is predicted through the broccoli related information and the pre-constructed initial cycle prediction model. When the initial growth cycle is reached for the first time, the remote sensing information of the target broccoli in the vegetable field is collected, and the initial cycle prediction model is combined with the remote sensing information of the broccoli and the real-time acquired soil water content to synthesize the initial cycle prediction model. The standard cycle prediction model obtained after the synthesis is more accurate, that is, the standard growth cycle is more in line with the actual growth condition of the target broccoli, so that the alternating irrigation cycle of the irrigation device can be dynamically adjusted according to the different initial growth cycles of the target broccoli, thereby promoting the root development and physiological regulation of the target broccoli. In addition, according to the different initial growth cycles of the target broccoli and the different weather conditions in different growth cycles, the daily irrigation amount of the target broccoli is determined, so that the target broccoli can not be over-irrigated or under-irrigated due to sudden drought or precipitation during growth. In summary, compared with the existing alternating irrigation technology, the present application dynamically regulates the alternating irrigation device, which not only promotes the growth and development of the target broccoli and improves its yield, but also effectively reduces water resource waste and improves irrigation accuracy, thereby providing strong technical support for modern agricultural production.

[0057] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0058] Figure 1 A flowchart of intelligent control of a broccoli root zone alternating irrigation device provided by the embodiments of the present application is shown;

[0059] Figure 2 A flowchart of generating an alternating irrigation strategy provided by the embodiments of the present application is shown. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme of the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific embodiments described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present application.

[0061] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative positional relationship, movement condition, etc. between the components in a certain posture (as shown in the drawings), and if the certain posture changes, the directional indications also change accordingly.

[0062] In addition, if the description of "first", "second" and the like is involved in the embodiments of the present application, the description of "first", "second" and the like is only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features limited by "first", "second" can explicitly or implicitly include at least one of the features. In addition, the technical solutions of various embodiments can be combined with each other, but it must be based on the realization of ordinary skilled in the art, when the combination of technical solutions appears contradictory or cannot be realized, it should be considered that the combination of technical solutions does not exist, nor in the protection scope required by the present application.

[0063] Figure 1 The flowchart of the method for intelligently controlling the broccoli root zone alternate irrigation device according to the embodiments of the present application is schematically shown. As shown in Figure 1 The embodiments of the present application provide a method for intelligently controlling the broccoli root zone alternate irrigation device, which can include the following steps:

[0064] S101, obtaining the broccoli related information of the target vegetable field;

[0065] In the embodiments, the broccoli related information refers to the information that will affect the initial growth cycle, and the broccoli related information includes the first meteorological information of the location of the target vegetable field, such as precipitation, temperature, wind speed, humidity, etc., the broccoli information in the target vegetable field, such as broccoli varieties (early-maturing varieties, late-maturing varieties, etc.), etc., the soil information of the target vegetable field, the soil information includes soil water absorption rate, soil water holding capacity, soil type and soil water content, etc.

[0066] S102, inputting the broccoli related information into the pre-constructed initial cycle prediction model, and outputting all the initial growth cycles of the target broccoli in the target vegetable field through the initial cycle prediction model;

[0067] In the embodiment, the initial cycle prediction model can be constructed based on a neural network model, or can be constructed based on an existing WOFOST model or DSSAT model. Taking the neural network model as an example, historical broccoli planting information of the target vegetable field is obtained, the historical broccoli planting information includes historical growth cycles of the target broccoli planted in the target vegetable field in a historical time period and historical soil information (including historical average soil moisture, historical soil type, etc.), and historical meteorological information of the location of the target vegetable field in the historical time period, the historical growth cycle, the historical meteorological information and the historical soil information are randomly divided into a model training set and a model validation set of the initial cycle prediction model after data cleaning and information labeling. The initial cycle prediction model includes an input layer for receiving information, a hidden layer for nonlinear transformation and feature extraction of the input information, and an output layer for generating a final prediction result, the initial node numbers of the input layer, the hidden layer and the output layer are set according to the feature dimensions of the historical broccoli planting information, a suitable loss function and an optimizer are selected, for example, mean square error (MSE) can be selected as the loss function, and the optimizer can select SGD (stochastic gradient descent). The loss function is used to measure the difference between the prediction result of the model and the true label, and to measure the performance of the model. The core function of the optimizer is to update the parameters of the model according to the gradient of the loss function, which can be used to select a suitable learning rate, or dynamically adjust the learning rate during the training process, thereby accelerating the convergence speed and improving the model training speed. After multiple iterations of training the broccoli cycle prediction using the model training set, the model parameters are continuously optimized, and the model learning rate, batch size and other parameters are adjusted until the maximum number of iterations is reached. Then the model performance of the trained initial cycle prediction model is evaluated using the validation set, the parameters used for evaluation include accuracy, recall rate, etc., when each parameter reaches the preset parameter threshold, the initial cycle prediction model training is completed. The first meteorological information, broccoli information, soil type and soil moisture in the broccoli correlation information are input into the initial cycle prediction model, and the initial growth cycle of the target broccoli in the target vegetable field is output by the initial cycle prediction model, for example, the seedling period of the target broccoli is 35 days, the growth period is 71 days, and the mature period is 17 days.

[0068] In addition, an existing WOFOST model or a DSSAT model developed by relevant researchers can be directly selected as the initial growth cycle prediction model. The WOFOST model is developed by the Wageningen Agricultural University in the Netherlands and the World Food Research Center, and is used to simulate the growth process of annual crops under specific soil and climate conditions, including crop growth simulation under potential growth conditions, water limitation conditions and nutrient limitation conditions. The WOFOST model can simulate the growth cycle of broccoli, including sowing, growth, harvesting and other stages, because it adopts a modular structure and can be parameterized and adapted to different crops and environmental conditions. Specifically, after converting the data such as temperature, light, soil moisture, precipitation, soil moisture, soil type into a fixed format, the data are input into the WOFOST model, and a simulation scenario such as alternate irrigation is set, so that the WOFOST model can be used to simulate and analyze the growth cycle of the target broccoli, that is, the prediction date of the growth stages such as the seedling stage, the flowering stage and the mature stage of the target broccoli is obtained, that is, the initial growth cycle of the target broccoli is obtained. Therefore, if the above model construction steps are omitted and the WOFOST model or the DSSAT model is directly used as the initial growth cycle prediction model, the time for model construction and prediction can be effectively saved.

[0069] S103, when the initial growth cycle is first reached, the broccoli remote sensing information of the target vegetable field is collected by a remote sensing unmanned aerial vehicle;

[0070] In this embodiment, the initial growth cycle refers to the cycle type and cycle time of each growth cycle of broccoli in the process from the broccoli seed breaking through the soil to the emergence of seedlings to maturity. For example, the seedling stage of the target broccoli is 35 days, the growth period is 71 days, and the mature period is 17 days, and the seedling stage, the flowering stage and the mature stage are the cycle types. Therefore, the initial growth cycle first reached is generally the seedling stage. Because the target vegetable field is large, the remote sensing information of the target vegetable field can be collected by a remote sensing unmanned aerial vehicle loaded with a remote sensing device. Common remote sensing devices include hyperspectral imagers, thermal infrared sensors, optical cameras and infrared cameras, etc. At the predicted harvesting time node, the remote sensing unmanned aerial vehicle is controlled to shoot the target vegetable field in all directions and in different regions according to the pre-set monitoring method and monitoring path. After shooting, the remote sensing images obtained by shooting are spliced according to the actual scene of the target vegetable field according to the real-time positioning information of the remote sensing unmanned aerial vehicle, and the complete broccoli remote sensing information of the target vegetable field is obtained. The broccoli remote sensing information refers to an optical remote sensing image, which is collected by devices such as a multispectral camera and a hyperspectral imager arranged in the remote sensing unmanned aerial vehicle.

[0071] For most vegetables, before the seedling stage, due to the root system has not been formed, only a main root, no lateral root branch, cannot induce root zonation growth by alternate irrigation, at this time the vegetable seeds need stable humid environment, alternate irrigation leads to local drought, may cause uneven emergence of vegetables. Therefore, before the first arrival of the initial growth cycle, no need to carry out alternate irrigation, also no need to design alternate irrigation scheme, directly according to the past experience to start all the alternate irrigation equipment to carry out overall irrigation on the target vegetable field. Based on the above reasons, when the first arrival of the initial growth cycle, only then begin to assimilate the initial cycle prediction model, generate the alternate irrigation strategy, because the generated alternate irrigation strategy at this time has significance and effect.

[0072] S104, assimilate the initial cycle prediction model combined with broccoli remote sensing information and broccoli associated information, obtain a standard cycle prediction model, and correct the initial growth cycle based on the standard cycle prediction model to obtain a standard growth cycle;

[0073] In this embodiment, the broccoli remote sensing information is preprocessed first, the preprocessing steps include geometric correction, image denoising and radiation calibration. Then the broccoli index and field water content of the target broccoli are inversed by using the response algorithm. The broccoli index refers to the leaf area index of the target broccoli, which can be calculated according to the normalized vegetation index. The field water content is calculated by the echo intensity of the microwave signal in the broccoli remote sensing information. Then the kriging interpolation method can be used to fuse the field water content and the target water content to obtain the fused water content of the target vegetable field in the initial growth cycle. Kriging interpolation is a best linear unbiased estimation method based on variogram, which considers the spatial correlation of data and can provide optimal estimation value and estimation error for unsampled points. By using the kriging interpolation method, the field water content and the target water content can be fully fused to provide data support for the subsequent assimilation step.

[0074] Assimilation is a method of combining observation data with data considering spatial and temporal distribution, observation field and background field error to optimize model prediction results. Ensemble Kalman filter (EnKF) can be used to assimilate the initial cycle prediction model. Ensemble Kalman filter (EnKF) is a data assimilation technique that effectively fuses model prediction and observation data by using a set of prediction samples (ensemble) to represent the state and uncertainty of the system. The core idea of EnKF is to use these ensemble members to approximate the error covariance of the system, and then update the estimate of the system state. The basic process of EnKF includes initialization, observation step, analysis step and prediction step. The standard cycle prediction model obtained after assimilation is more accurate than the initial cycle prediction model without assimilation.

[0075] Finally, the first weather information, broccoli information and soil information in the initial growth cycle are converted into a fixed format and input into the standard cycle prediction model. Then, the standard cycle prediction model is used to simulate the following process day by day with a step of one day: according to the broccoli information, the physiological parameters (such as photosynthetic rate, respiratory efficiency) corresponding to different broccoli varieties are determined; according to the first weather information and the physiological parameters, the efficiency of converting light energy into biomass during the day is calculated; and according to the physiological parameters, the respiratory consumption of the target broccoli is calculated, combined with the first weather information to simulate the influence of temperature and water stress on growth. After the simulation process is completed, the standard growth cycle of the target broccoli is output by the standard cycle prediction model. At this time, the standard growth cycle obtained is more accurate than the initial growth cycle.

[0076] S105, when reaching any standard growth cycle, an alternate irrigation strategy of the target vegetable field is generated based on the standard growth cycle, and the alternate irrigation device preset in the target vegetable field is intelligently controlled according to the alternate irrigation strategy.

[0077] In this embodiment, when reaching any standard growth cycle, the alternate irrigation cycle of the target vegetable field is generated according to the cycle type and cycle time in the standard growth cycle. The cycle type includes the growth stages of the target broccoli such as the seedling stage, the flowering stage and the fruiting stage. The cycle time is the duration of different growth stages of the target broccoli. For example, the flowering stage of the target broccoli is 14 days. The approximate range of the alternate irrigation cycle of the target broccoli in different standard growth cycles is obtained according to historical experience, and then the final alternate irrigation cycle is generated with the constraint condition of achieving irrigation balance on the left and right sides of the target broccoli. At the same time, the second weather information of the target vegetable field in this standard growth cycle is immediately obtained through a weather website. The second weather information includes weather parameters and total precipitation. The weather parameters include temperature, net radiation, soil heat flux, dry and wet table constant, wind speed, saturated water vapor pressure, actual water vapor pressure and other parameters. Then, the weather parameters are input into the FAO Penman-Monteith formula, and the reference evapotranspiration of the target broccoli is calculated by using the FAO Penman-Monteith formula. Then, the broccoli theoretical water requirement of the target broccoli is calculated by combining the reference evapotranspiration and the crop coefficient of the target broccoli, and the broccoli theoretical water requirement is obtained by correcting the broccoli theoretical water requirement according to the soil water content, soil water absorption rate and soil water holding rate at this time. The daily average irrigation amount of the target broccoli is calculated by combining the broccoli theoretical water requirement and the total precipitation in this standard growth cycle. By this method, the precipitation can be effectively used to complete the intelligent irrigation task, thereby saving water resources. Finally, the alternate irrigation cycle and the daily average irrigation amount in the same standard growth cycle are integrated to obtain the alternate irrigation strategy of the target vegetable field, and the irrigation instruction is generated according to the alternate irrigation strategy. The alternate irrigation device preset in the target vegetable field is intelligently controlled according to the irrigation instruction. In this way, the target broccoli can be ensured to have sufficient irrigation amount, and unnecessary waste of water resources can be reduced as much as possible.

[0078] In one embodiment, the broccoli-related information includes first weather information of a target vegetable field location and broccoli information in the target vegetable field, and soil information of the target vegetable field, the soil information including pre-acquired soil water absorption rate, soil water holding capacity and soil type, and soil water content collected in real time by soil sensors preset in the target vegetable field.

[0079] In this embodiment, the first weather information refers to weather forecast acquired before the target vegetable field is planted with broccoli, including but not limited to precipitation, temperature, wind speed, humidity and the like. The broccoli information refers to information such as the variety of broccoli (early-maturing variety, late-maturing variety, etc.) planted in the target vegetable field. The soil information includes soil water absorption rate, soil water holding capacity and soil type, wherein the soil water absorption rate is determined by collecting soil samples of the target vegetable field, and then using capillary method or pressure plate method under different water conditions, which is used to reflect the ability of soil to absorb water, i.e. the speed of water infiltration into the soil per unit time, which can affect the daily irrigation amount of the target broccoli. If the soil has poor water absorption capacity, it may lead to water loss during alternate irrigation, resulting in insufficient irrigation of the target broccoli. Therefore, the soil water absorption rate of the target vegetable field needs to be considered when calculating the daily irrigation amount of the target broccoli. The soil water holding capacity refers to the water content retained by the soil after gravity drainage, which is the upper limit of the available water for the target broccoli, and is one of the important factors affecting the daily irrigation amount. If the daily irrigation amount is too high and exceeds the upper limit of the available water for the target broccoli, it will lead to waste of water resources. The soil type includes types such as sandy soil and clay, and the soil type will affect the growth cycle of the target broccoli, so it needs to be acquired in advance. The soil water content can reflect the soil humidity, which can be acquired by capacitive or time-domain reflectance sensors preset in the target vegetable field. The sensors cover the entire target vegetable field and are evenly distributed in a grid shape, with one sensor installed at each grid point to collect and upload the soil water content of the target vegetable field in real time, providing key basic data for subsequent precision irrigation decision-making, and also for monitoring whether the soil water content is abnormal.

[0080] In one embodiment, the initial growth cycle is corrected based on the standard cycle prediction model obtained by assimilating the broccoli remote sensing information and the broccoli-related information into the initial cycle prediction model to obtain a standard cycle prediction model, and the standard growth cycle includes the following steps:

[0081] Preprocessing the broccoli remote sensing information;

[0082] Inverting the preprocessed broccoli remote sensing information using an inversion algorithm, and extracting the vegetable field remote sensing parameters in the target vegetable field according to the inversion result, the vegetable field remote sensing parameters including broccoli index and vegetable field water content;

[0083] The data fusion algorithm is used to complete spatial fusion of the vegetable field water content and the soil water content, so as to obtain the fused water content of the target vegetable field.

[0084] The initial growth cycle prediction model is combined with the broccoli index and the fused water content to obtain a standard growth cycle prediction model.

[0085] The first meteorological information, the broccoli information and the soil information in the initial growth cycle are input into the standard growth cycle prediction model, and the standard growth cycle prediction model is used to output the standard growth cycle of the target broccoli.

[0086] In the embodiment, the broccoli remote sensing information is preprocessed, and the preprocessing steps include geometric correction, image denoising and radiation calibration. The geometric correction refers to the process of eliminating or correcting the geometric error of the broccoli remote sensing information. The main purpose of the image denoising is to remove the noise in the broccoli remote sensing information and improve the accuracy of the broccoli remote sensing information. The radiation calibration is the process of converting the brightness gray value of the broccoli remote sensing information into an absolute radiation brightness value. Through the above steps, the image quality of the broccoli remote sensing information is improved, and the image distortion is reduced.

[0087] The inversion algorithm includes the leaf area index inversion and the soil water content inversion. The leaf area index inversion refers to the use of the broccoli remote sensing information to invert the broccoli index of the target broccoli, and the broccoli index refers to the leaf area index of the target broccoli. Specifically, the appropriate wave band is selected for analysis using the broccoli remote sensing information, and the red light band (NIR) and the near-infrared light band (RED) are usually used. The normalized difference vegetation index (NDVI) of the target broccoli is calculated according to the red light band and the near-infrared light band, and the calculation formula is NDVI=(NIR-RED) / (NIR+RED). Then, the broccoli index of the target broccoli is calculated according to the linear regression equation between the normalized difference vegetation index and the leaf area index which is constructed in advance. The soil water content inversion is to analyze the echo intensity of the microwave signal through the broccoli remote sensing information, extract the dielectric constant of the soil, and calculate the vegetable field water content of the target vegetable field.

[0088] The vegetable field water content refers to the overall water content of the target vegetable field as a whole, and the soil water content monitored by the sensor refers to the local water content of multiple sampling points of the target vegetable field. Therefore, the Kriging interpolation method can be used to fuse the vegetable field water content and the target water content to obtain the fused water content of the target vegetable field in the initial growth period. Specifically, the soil water content collected at the initial growth period is first retrieved and used as the target water content for assimilating the initial period prediction model. Then, the vegetable field water content and the target water content are standardized to eliminate the dimensional differences between different data sources and variables, so that the data are comparable. Then, the spatial aggregation of the standardized vegetable field water content and the target water content is analyzed using a pre-set variogram function, which can also be referred to as spatial correlation. The variogram function is an important tool for describing the spatial correlation of data, which reflects the influence of spatial distance on data similarity. Common variogram function models include spherical model, exponential model and Gaussian model, etc. Finally, according to the data correlation and spatial aggregation analyzed above, the Kriging interpolation method is used to perform spatial interpolation on the standardized vegetable field water content and the target water content to obtain the fused water content of the target vegetable field in the initial growth period. Kriging interpolation is a best linear unbiased estimation method based on variogram function, which considers the spatial correlation of data and can provide optimal estimation value and estimation error for unsampled points. Using the Kriging interpolation method, the vegetable field water content and the target water content can be fully fused to provide data support for subsequent assimilation steps.

[0089] Assimilation is a method of combining observation data with data considering spatial and temporal distribution, observation field and background field error to optimize model prediction results. Ensemble Kalman filter (EnKF) is a data assimilation technology which effectively fuses model prediction and observation data by using a set of prediction samples (ensemble) to represent the state and uncertainty of the system. The core idea of EnKF is to use these ensemble members to approximate the error covariance of the system, and then update the estimate of the system state. The basic process of EnKF includes initialization, observation step, analysis step and prediction step.

[0090] Specifically, first, the time and space scales between the broccoli index and the fusion water content are aligned to determine the sampling time of the broccoli index and the fusion water content, and then the time stamps of the two are aligned. Next, it is necessary to ensure that the spatial resolution of the broccoli index and the fusion water content is consistent. After that, the broccoli index and the fusion water content that have completed the time and space scale alignment are normalized to eliminate the dimensional differences between different data sources and variables. Then, according to the sampling accuracy of the sensor and the remote sensing unmanned aerial vehicle, the observation error covariance matrix of the broccoli index and the fusion water content is constructed, and at the same time, the model error covariance matrix of the initial period prediction model is constructed according to the error of the historical period prediction result. The model error covariance matrix and the observation error covariance matrix are integrated as the error covariance matrix. Next, a plurality of state samples are randomly generated according to the broccoli correlation information, and are integrated into an initial state set. The initial state set is used as the input of the initial period prediction model to drive the initial period prediction model to predict the predicted growth period of the current target broccoli, the predicted broccoli index, and the predicted water content of the target vegetable field. Finally, all the prediction results are integrated to obtain a prediction state set. The mean and covariance of all prediction states in the prediction state set are calculated, and the prediction covariance matrix is constructed according to the mean and the covariance. The prediction state set and the observation state set constructed by the standard index and the standard water content are one-to-one corresponding to obtain the observation operator, and then the Kalman gain is calculated by combining the prediction covariance matrix, the observation operator and the error covariance matrix and using the Kalman gain formula. The standard period prediction model is obtained by using the Kalman gain, the standard index and the standard water content to correct the model parameters of the initial period prediction model. The model parameters refer to the state variables such as the predicted leaf area index and the root zone soil water content of the initial period prediction model. Since the state variables can affect the prediction results of the initial period prediction model, correcting the state variables through the observation state set can indirectly improve the prediction accuracy of the initial period prediction model for the target initial growth period, and a standard period prediction model with higher prediction accuracy is obtained.

[0091] After the first weather information, broccoli information and soil information in the initial growth period are converted into a fixed format and input into the standard period prediction model, the following process is simulated day by day using the standard period prediction model with a step of one day: according to the broccoli information, the physiological parameters (such as photosynthetic rate and respiration efficiency) corresponding to different broccoli varieties are determined, the efficiency of converting light energy into biomass during the day is calculated according to the first weather information and the physiological parameters, and the respiration consumption of the target broccoli is calculated according to the physiological parameters. Combined with the first weather information, the influence of temperature and water stress on growth is simulated, and after the simulation process is completed, the standard growth period of the target broccoli is output by the standard period prediction model. At this time, the standard growth period obtained is more accurate than the initial growth period.

[0092] In one embodiment, the spatial fusion of the vegetable field water content and the soil water content is completed by using a data fusion algorithm to obtain the fused water content of the target vegetable field, including the following steps:

[0093] The soil water content collected in the initial growth period is taken as the target water content;

[0094] The vegetable field water content and the target water content are normalized;

[0095] The data correlation between the normalized vegetable field water content and the target water content is calculated by using a correlation coefficient formula;

[0096] The spatial aggregation of the normalized vegetable field water content and the target water content is analyzed by using a preset variation function;

[0097] The vegetable field water content and the target water content are fused by using the Kriging interpolation method combined with the spatial aggregation and the data correlation to obtain the fused water content of the target vegetable field in the initial growth period.

[0098] In this embodiment, the soil water content collected at the initial growth period is first retrieved and taken as the target water content for assimilating the initial period prediction model. Then, the vegetable field water content and the target water content are normalized to eliminate the dimensional differences between different data sources and variables, so that the data is comparable. The z-score normalization method is usually used for normalization, that is, the original data is subtracted by the mean value and then divided by the standard deviation. The specific calculation formula is: Z=(X-μ) / σ, where X is the original data, μ is the data mean value, and σ is the data standard deviation. The normalized data will have a distribution characteristic of mean value 0 and standard deviation 1, which is beneficial to subsequent data fusion and analysis. Then, the data correlation between the vegetable field water content and the target water content is calculated by using a correlation coefficient formula. Common correlation coefficient formulas include Pearson correlation coefficient, Spearman correlation coefficient, etc. Taking the Pearson correlation coefficient as an example, its mathematical expression is as follows:

[0099]

[0100] Wherein, X i and Y i are the i-th vegetable field water content and target water content, respectively; and are the sample mean values of the vegetable field water content and the target water content, respectively, and n is the sample size.

[0101] Then the spatial aggregation of the normalized vegetable field water content and the target water content is analyzed by using a preset variation function. The spatial aggregation can also be referred to as spatial correlation. The variation function is an important tool for describing the spatial correlation of data, which reflects the influence of spatial distance on data similarity. Commonly used variation function models include a spherical model, an exponential model and a Gaussian model, etc. Taking the spherical model as an example, the mathematical expression is: γ(h) = C0+C*(1.5h / a-0.5(h / a)3), when h < a; γ(h) = C0+C, when h ≥ a. Wherein, h is the spatial distance, C0 is the nugget value (indicating the variation at the minimum scale), C is the base value (indicating the overall variation), and a is the range (indicating the effective distance of spatial correlation). In specific implementation, firstly, the experimental variation function values at different distances are calculated, and then the theoretical variation function model is fitted by using the least square method. For example, assuming that the experimental variation function values calculated at different distances are [(100, 0.2), (200, 0.4), (300, 0.6), (400, 0.7), (500, 0.75)], the spherical model parameters C0=0.1, C=0.7 and a=450 can be obtained by fitting.

[0102] Finally, according to the data correlation and spatial aggregation analyzed in the foregoing, the spatial interpolation processing is performed on the normalized vegetable field water content and the target water content by using the Kriging interpolation method, so as to obtain the fused water content of the target vegetable field in the initial growth period. The Kriging interpolation is a best linear unbiased estimation method based on the variation function, which considers the spatial correlation of data and can provide the optimal estimation value and estimation error for the un-sampled points. The interpolation formula of Kriging is: Z*(x0) = Σ(λi*Z(xi)), wherein Z*(x0) is the predicted value of the to-be-estimated point, Z(xi) is the observation value of the known sampling point, and λi is the weight coefficient. The determination of the weight coefficient is the core of the Kriging interpolation, and a linear equation group needs to be solved: Σ(λj*γ(xi,xj))+μ=γ(xi,x0), wherein γ(xi,xj) is the variation function value between two points, and μ is the Lagrange multiplier. In specific implementation, firstly, the Kriging equation group is constructed, then the weight coefficient is solved, and finally the interpolation calculation is performed. For example, assuming that the observation values of three points are [7, 10, 5] respectively, the distances between the to-be-observed point and the three points are [85, 100, 110] respectively, the variation function values are calculated according to the variation function model obtained in the foregoing, the weight coefficient is [0.5405, 0.4595, 0], and the predicted value of the to-be-estimated point is 0.5405*7+0.4595*10+0*5≈8.38. By using the Kriging interpolation method, the vegetable field water content and the target water content can be fused comprehensively, thereby providing data support for the subsequent assimilation step.

[0103] In one embodiment, the standard cycle prediction model is obtained by combining the initial cycle prediction model with the broccoli index and the fusion water content, including the following steps:

[0104] aligning the temporal and spatial scales between the broccoli index and the fusion water content;

[0105] normalizing the broccoli index and the fusion water content after the temporal and spatial scale alignment to obtain a standard index and a standard water content, respectively;

[0106] defining an error covariance matrix by combining the standard index and the standard water content;

[0107] generating an initial state set of the initial cycle prediction model according to the correlation information of the broccoli;

[0108] running the initial cycle prediction model according to the initial state set and according to the ensemble Kalman filter algorithm to obtain a prediction state set;

[0109] calculating a Kalman gain by combining the prediction state set and the error covariance matrix;

[0110] adjusting the model parameters of the initial cycle prediction model by combining the Kalman gain, the standard index and the standard water content to obtain the standard cycle prediction model.

[0111] In this embodiment, assimilation is a method of combining observation data with data considering the temporal and spatial distribution, observation field and background field error to optimize the prediction results of the model. Ensemble Kalman filter (EnKF) is a data assimilation technique that effectively fuses model prediction and observation data by using a set of prediction samples (ensemble) to represent the state and uncertainty of the system. The core idea of EnKF is to use these ensemble members to approximate the error covariance of the system, and then update the estimate of the system state. The basic process of EnKF includes initialization, observation step, analysis step and prediction step. In the initialization stage, the state variables of the system, the initial error covariance matrix and the initial state prediction set are set. In the observation step, the observation set and the observation error covariance matrix are calculated. The analysis step involves calculating the Kalman gain matrix, the analysis set, the analysis set mean and the analysis error covariance matrix. Finally, in the prediction step, the prediction set, the prediction set mean and the prediction error covariance matrix are calculated.

[0112] Specifically, first, the spatiotemporal scales of the broccoli index and the fusion water content are aligned to determine the sampling time of the broccoli index and the fusion water content, and then the time stamps of the two are aligned. Next, it is necessary to ensure that the spatial resolution of the broccoli index and the fusion water content is consistent. After that, the broccoli index and the fusion water content that have completed the spatiotemporal scale alignment are normalized to eliminate the dimensional differences between different data sources and variables, so that the data are comparable. Normalization usually uses the z-score normalization method, that is, the original data is subtracted by the mean and divided by the standard deviation. Since both the soil water content collected by the sensor and the broccoli index and the vegetable field water content inverted from the broccoli remote sensing information may have certain errors, it is necessary to construct an observation error covariance matrix. The elements in the error covariance matrix are determined by the sampling accuracy of the sensor and the remote sensing unmanned aerial vehicle, for example, the sensor error is ±0.02 m 3 / m 3, the corresponding element is set to 0.0004, and the model error covariance matrix of the initial period prediction model is constructed according to the error of the historical period prediction result. If the historical initial growth period prediction error is ±3 days, the corresponding variance is set to 9, that is, the corresponding element in the model error covariance matrix is 9. The model error covariance matrix and the observation error covariance matrix are integrated into the error covariance matrix. Then the broccoli associated information is standardized. The first meteorological information, broccoli information and soil information in the broccoli associated information are standardized to 0-1, and the broccoli associated information after standardization is integrated into the state set. Then a plurality of state samples are randomly generated according to the state set, and are integrated into the initial state set. The initial state set needs to cover the uncertainty range of each data in the state set to avoid excessive concentration or divergence, that is, each data in the initial state set cannot be greater than the maximum value of each data in the initial state set, and cannot be less than the minimum value. The maximum value and the minimum value are determined according to the historical broccoli planting information and the historical meteorological information. The initial state set is taken as the input of the initial period prediction model to drive the initial period prediction model to predict the predicted growth period of the current target broccoli, the predicted broccoli index, and the predicted water content of the target vegetable field. Taking the initial period prediction model based on the WOFOST model as an example, the model can calculate the vegetation canopy leaf area index day by day through the simulation of crop photosynthesis, dry matter accumulation and other physiological processes combined with temperature, light and other meteorological conditions. The built-in crop growth stage division module of the model can accurately match the LAI variation characteristics corresponding to each growth period of broccoli (such as the seedling stage, the flowering stage and the mature stage). Therefore, the WOFOST model can predict the predicted broccoli index (LAI) while predicting the growth period. In addition, the WOFOST model can calculate the root layer soil water content through the water balance module. The module integrates parameters such as precipitation, irrigation, evapotranspiration and soil infiltration, and can output daily soil water content data. Therefore, the WOFOST model can also predict the corresponding predicted water content while predicting the growth period. Finally, all the prediction results are integrated to obtain a prediction state set. The mean and covariance of all prediction states in the prediction state set are calculated, and a prediction covariance matrix is constructed according to the mean and the covariance. The prediction state set is one-to-one corresponding to the observation state set constructed by the standard index and the standard water content, for example, the predicted broccoli index output by the model directly corresponds to the standard broccoli index, to obtain an observation operator. The observation operator is a unit matrix containing the corresponding parameters of the observation state set in the prediction state set. Then, the Kalman gain is calculated by combining the prediction covariance matrix P xy , the observation operator H and the error covariance matrix R, and using the Kalman gain formula: K=P xy ·(H·P xy +R) -1The Kalman gain is a weighting coefficient used to weight the prediction value and the measurement value, and ultimately attributed to the mean square error matrix of the prediction and measurement. Its role is to adjust the weight of the prediction value and the measurement value, so that the final estimated value is as close to the true value as possible, thereby reducing the estimation error. The model parameters of the initial periodic prediction model are corrected by using the Kalman gain, the standard index and the standard water content to obtain a standard periodic prediction model, and the correction formula is: F(x) = F(y) + K(Y-HF(y)), wherein F(y) is the model parameter before correction, K is the Kalman gain, and Y is the observation state set obtained by integrating the standard index and the standard water content. The model parameters refer to the state variables such as the predicted leaf area index and the root zone soil water content of the initial periodic prediction model. Since the state variables can affect the prediction results of the initial periodic prediction model, the prediction accuracy of the initial periodic prediction model for the target initial growth period can be indirectly improved by correcting the state variables through the observation state set.

[0113] Using the assimilated standard periodic prediction model, each growth stage of the target broccoli and the corresponding time of each growth stage can be more accurately predicted, for example, the seedling stage of the tomato is 15 days, the flowering stage is 14 days, and the fruiting stage is 45 days. The alternating irrigation strategy generated according to the accurate periodic prediction result is also more suitable for the irrigation needs of the target broccoli. The specific reasons are as follows: the target broccoli is in different standard growth periods, and the appropriate alternating period in the process of alternating irrigation is also different, for example, the irrigation direction needs to be adjusted every 2-3 days in the seedling stage of the tomato, and every 4-5 days in the flowering stage of the tomato. When reaching different growth stages, the alternating irrigation period needs to be changed in time to ensure the normal growth of the target broccoli. In addition, when designing the alternating irrigation period, it is also necessary to try to maintain the irrigation balance of the left and right sides of the target broccoli to prevent the total irrigation amount of one side from being less than the other side in a certain period, for example, the seedling stage of the tomato is 15 days, and alternating irrigation is generally needed every 2-3 days. In order to maintain the irrigation balance of both sides in the seedling stage, alternating irrigation can be set every 2.5 days. In addition, the target broccoli is in different standard growth periods, and the irrigation amount required is also different, and the precipitation in different standard growth periods is also different, so the daily irrigation amount required needs to be dynamically adjusted according to the different growth stages of the target broccoli to ensure that the target broccoli does not appear to be insufficiently irrigated or excessively irrigated. Based on this, the growth stages of the target broccoli and the corresponding time of each growth stage need to be accurately predicted, so that the alternating period and the daily irrigation amount can be dynamically adjusted according to the different stages of the target broccoli, so that the normal growth of the target broccoli can be ensured while the water resources are accurately regulated, thereby achieving the purpose of saving water resources.

[0114] In one embodiment, refer to Figure 2, the alternate irrigation strategy of the target vegetable field based on the standard growth cycle comprises the following steps:

[0115] generating an alternate irrigation cycle of the target vegetable field according to a cycle type and a cycle time in the standard growth cycle;

[0116] retrieving second meteorological information of a location of the target vegetable field in the standard growth cycle, the second meteorological information comprising meteorological parameters and total precipitation;

[0117] calculating a reference evapotranspiration of the target broccoli according to the meteorological parameters;

[0118] determining a crop coefficient of the target broccoli according to the cycle type;

[0119] calculating a theoretical water requirement of the target broccoli according to the reference evapotranspiration and the crop coefficient;

[0120] taking the soil water content collected in the standard growth cycle as a standard water content;

[0121] correcting the theoretical water requirement of the target broccoli by using the soil water absorption rate, the soil water holding rate and the standard water content to obtain an actual water requirement of the target broccoli;

[0122] calculating a daily average irrigation amount of the target broccoli according to the total precipitation and the actual water requirement of the target broccoli;

[0123] integrating the alternate irrigation cycle and the daily average irrigation amount to obtain the alternate irrigation strategy of the target vegetable field.

[0124] In the embodiment, an alternate irrigation cycle of the target vegetable field is generated according to a cycle type and a cycle time in the standard growth cycle, the cycle type comprising growth stages of the target broccoli such as a seedling stage, a flowering stage and a fruiting stage, and the cycle time being a time length of different growth stages of the target broccoli, for example, the flowering stage of the target broccoli is 14 days. The approximate range of the alternate irrigation cycle of the target broccoli in different standard growth cycles is obtained according to historical experience, and then the final alternate irrigation cycle is generated with the constraint condition of achieving irrigation balance on the left and right sides of the target broccoli. For example, the seedling stage of the tomato is 15 days, the flowering stage is 14 days, and the fruiting stage is 45 days. According to historical experience, the irrigation direction of the tomato is adjusted every 2-3 days in the seedling stage, every 4-5 days in the flowering stage, and every 5-7 days in the fruiting stage. The generated alternate irrigation cycle is: the irrigation direction is adjusted every 2.5 days in the first 15 days, the irrigation direction is adjusted every 4 days in the 16th-29th day, and the irrigation direction is adjusted every 5.5 days in the 30th-74th day.

[0125] When reaching any standard growth cycle, immediately obtain second meteorological information of the target vegetable field location in the standard growth cycle through a meteorological website, the second meteorological information including meteorological parameters and total precipitation, the meteorological parameters including temperature, net radiation, soil heat flux, dry-wet table constant, wind speed, saturated water vapor pressure, actual water vapor pressure and the like. Then input the meteorological parameters into a FAO Penman-Monteith formula, and calculate the reference evapotranspiration of the target broccoli by using the FAO Penman-Monteith formula. The FAO Penman-Monteith formula is as follows:

[0126]

[0127] Wherein, Δ is a saturated water vapor pressure slope, R n is a net radiation, G is a soil heat flux (usually can be ignored, short-term calculation is set to 0), γ is a dry-wet table constant, T is a daily average temperature, u2 is a wind speed at a height of 2 meters, e s is a saturated water vapor pressure, e a is an actual water vapor pressure.

[0128] The saturated water vapor pressure slope refers to a change amount of the saturated water vapor pressure when the temperature changes by 1 degree, which can be calculated according to the temperature and the saturated water vapor pressure. The daily average temperature can be calculated according to the temperature and the cycle time of the standard growth cycle.

[0129] Then, the crop coefficient of the target broccoli is determined according to the cycle type, which can reflect the difference in water demand of broccoli at different growth stages. The crop coefficient can be directly accessed from the FAO (Food and Agriculture Organization of the United Nations) database or the official website of the relevant agricultural department, and the corresponding crop coefficient is queried according to the cycle type of the target broccoli. For example, the crop coefficient of tomato seedling stage is 0.4. The reference evapotranspiration is multiplied by the crop coefficient to obtain the theoretical water requirement of the target broccoli. Then, the soil moisture content collected by the sensor in the standard growth cycle is extracted as the standard moisture content. The theoretical water requirement of the broccoli is corrected according to the standard moisture content, the soil water absorption rate and the soil water holding rate. If any one of the standard moisture content, the soil water absorption rate and the soil water holding rate is less than the corresponding preset threshold (for example, the soil water absorption rate is less than the preset water absorption rate threshold), the theoretical water requirement of the broccoli can be appropriately increased to obtain the actual water requirement of the broccoli after the increase, and the increase amplitude cannot exceed a fixed proportion of the theoretical water requirement of the broccoli (for example, it cannot exceed 10% of the theoretical water requirement of the broccoli), to prevent excessive irrigation. If the standard moisture content, the soil water absorption rate and the soil water holding rate are all greater than or equal to the corresponding preset threshold, the theoretical water requirement of the broccoli does not need to be adjusted, and the theoretical water requirement of the broccoli can be directly used as the actual water requirement of the broccoli. Then, the daily average irrigation amount of the target broccoli is calculated by combining the total amount of precipitation and the actual water requirement of the broccoli. The actual water requirement of the broccoli is subtracted from the total amount of precipitation and then divided by the cycle time to obtain the daily average irrigation amount of the target broccoli. By this method, the precipitation can be effectively utilized to complete the intelligent irrigation task, thereby saving water resources. Finally, the alternate irrigation cycle and the daily average irrigation amount in the same standard growth cycle are integrated to obtain the alternate irrigation strategy of the target vegetable field, and the irrigation instruction is generated according to the alternate irrigation strategy. The alternate irrigation device executes the intelligent irrigation task according to the irrigation instruction.

[0130] In one embodiment, the method further comprises:

[0131] After completing the intelligent irrigation task in any standard growth cycle, the irrigation qualification degree formula is used to calculate the irrigation qualification degree in the standard growth cycle;

[0132] If the irrigation qualification degree is located in the preset qualification threshold interval, it is determined that the intelligent irrigation task is qualified;

[0133] If the irrigation qualification degree is not located in the qualification threshold interval, it is determined that the intelligent irrigation task is unqualified;

[0134] If the intelligent irrigation task is qualified, the intelligent irrigation task in the next standard growth cycle is continued to be completed;

[0135] If the intelligent irrigation task is unqualified, the irrigation qualification output strategy correction factor is output according to the irrigation qualification degree, and the alternate irrigation strategy of the next standard growth cycle is corrected by using the strategy correction factor. The irrigation qualification degree formula includes:

[0136]

[0137] wherein S x is the actual irrigation amount of the target broccoli, S y is the daily average irrigation amount of the target broccoli, γ is an irrigation correction factor, W l and W r are the daily average soil water content of the left and right sides of the target broccoli, respectively, is a preset water content difference threshold, N is the number of soil sensors, δ is a preset fixed integer parameter, K is a pre-acquired soil water conductivity coefficient, T is the daily average irrigation duration, and F is a preset air temperature attenuation factor.

[0138] In this embodiment, the irrigation eligibility degree of the standard growth cycle is calculated immediately after the completion of the intelligent irrigation task in each standard growth cycle. The actual irrigation amount in the irrigation eligibility degree formula is the daily average actual irrigation amount calculated from the daily irrigation amount and the cycle time. The daily irrigation amount can be detected by sensors (such as flow meters and pressure sensors) preset in the alternate irrigation device. The irrigation correction factor is set based on the actual total precipitation, which is the precipitation obtained at the end of the standard growth cycle. Compared with the pre-obtained total precipitation, the actual total precipitation obtained at this time is more accurate because unexpected precipitation (such as artificial rainfall) may occur in the standard growth cycle. Because unexpected precipitation or unexpected drought is not considered in the actual irrigation process, the irrigation correction factor needs to be introduced when calculating the irrigation eligibility degree. The size of the irrigation correction factor depends on the difference between the actual total precipitation and the total precipitation. For example, if the calculated difference is within the difference interval (such as [0.3, -0.3]), the irrigation correction factor can be 1. If the calculated difference is not within the difference interval, greater than the first difference threshold (such as 0.3), the irrigation correction factor is 1.2. If the difference is not within the difference interval, less than the second difference threshold (such as -0.3), the irrigation correction factor is 0.8. The first difference threshold is greater than the second difference threshold. The daily average soil moisture content is collected in real time by soil sensors preset in the target vegetable field. The number of soil sensors and the fixed integer parameter are used to introduce the correction factor of sensor density. The closer the number of soil sensors and the fixed integer parameter, the more reliable the monitored data, and the closer the correction factor of sensor density to 1, the smaller the impact on the irrigation eligibility degree. The moisture difference threshold is generally set according to the soil type, for example, 10% of the actual irrigation amount for sandy soil and 6% of the actual irrigation amount for clay soil. The soil water conductivity depends on the permeability and water content of the soil layer, which can be queried on the website of the relevant agricultural department according to the soil type, for example, 20 mm / h for sandy soil and 8 mm / h for clay soil. The air temperature attenuation factor is set according to the daily average air temperature in the standard growth cycle, for example, when the daily average air temperature is less than or equal to 30 degrees Celsius, the air temperature attenuation factor is 1, when the daily average air temperature u is greater than 30 degrees Celsius, the air temperature attenuation factor is 1-0.05(u-30), for example, when u = 35 degrees Celsius, the air temperature attenuation factor is 0.925.

[0139] The irrigation eligibility degree in the standard growth cycle is calculated. If the irrigation eligibility degree is within a preset eligibility threshold interval, for example, [1.2, 0.8], it indicates that the intelligent irrigation task is qualified, and the next standard growth cycle irrigation task can be directly executed. If the irrigation eligibility degree is not within the eligibility threshold interval, it is determined that the intelligent irrigation task is unqualified. If the irrigation eligibility degree is greater than a preset first eligibility threshold (for example, 1.2), it indicates that there is over-irrigation in the standard growth cycle. If the irrigation eligibility degree is less than a preset second eligibility threshold (for example, 0.8), it indicates that there is insufficient irrigation in the standard growth cycle. When over-irrigation or insufficient irrigation occurs in the last standard growth cycle, the actual water requirement of the broccoli in the next standard growth cycle needs to be adjusted. When over-irrigation occurs, the actual water requirement of the broccoli needs to be reduced. When insufficient irrigation occurs, the actual water requirement of the broccoli needs to be increased, so as to ensure that the target broccoli grows normally while reducing water resource waste.

[0140] The above method further includes the following steps:

[0141] But when the number of unqualified intelligent irrigation tasks is greater than a preset number threshold, the irrigation water flow is collected by the irrigation sensor preset in the alternate irrigation device;

[0142] The irrigation sensor whose irrigation water flow is greater than a preset first flow threshold or less than a preset second flow threshold is marked as an abnormal irrigation sensor;

[0143] The irrigation position information of the abnormal irrigation sensor is obtained;

[0144] All adjacent soil sensors of the abnormal irrigation sensor are screened out according to the irrigation position information;

[0145] For any adjacent soil sensor, the soil moisture content collected by the adjacent soil sensor is retrieved as adjacent soil moisture content;

[0146] The adjacent soil sensor whose adjacent soil moisture content is higher than a preset first soil moisture threshold or lower than a preset second soil moisture threshold is marked as an abnormal soil sensor;

[0147] The soil position information of the abnormal soil sensor is obtained;

[0148] The abnormal position information of the alternate irrigation device is located by combining the irrigation position information and the soil position information.

[0149] There is also a case when the intelligent irrigation task is unqualified in the continuous multiple (may be two) standard growth cycles, and is over-irrigation or is insufficient irrigation, the irrigation sensor in the preset irrigation device collects the irrigation water flow, and the irrigation sensor can be a flow meter. When the irrigation water flow is greater than the preset first flow threshold or less than the preset second flow threshold, the first flow threshold is greater than the second flow threshold, the corresponding irrigation sensor is immediately marked as an abnormal irrigation sensor, and the sensor number of the abnormal irrigation sensor is immediately uploaded. According to the sensor number, the irrigation location information of the abnormal irrigation sensor with the corresponding number can be directly queried from the pre-constructed database, the soil moisture content collected by all adjacent soil sensors within the preset range around the irrigation sensor is retrieved according to the irrigation location information, the abnormal analysis is performed on all soil moisture contents, the soil sensor with the abnormality is marked as an abnormal soil sensor according to the abnormal analysis result, the position information of the abnormal soil sensor, that is, the soil position information, is obtained, and the abnormal position information of the alternate irrigation device can be located according to the irrigation position information and the soil position information, that is, the position of the alternate irrigation device where the abnormality occurs is located between the abnormal soil sensor and the abnormal irrigation sensor. Finally, the abnormal position information is uploaded to the alternate irrigation management system to remind the relevant staff to troubleshoot the fault in time. In addition, the abnormal analysis in the above is that whether there is data with soil moisture content higher than the preset first soil moisture content threshold or lower than the preset second soil moisture content threshold in all soil moisture contents collected by the soil sensor in any preset range, that is, adjacent soil moisture content, if there is, the adjacent soil sensor is marked as an abnormal soil sensor. This is because when the irrigation device is broken, the actual irrigation amount is higher than the daily average irrigation amount, so the soil moisture content will be higher than the first soil moisture content threshold, and when the irrigation device is blocked, the actual irrigation amount is lower than the daily average irrigation amount, so the soil moisture content will be lower than the second soil moisture content threshold. Through this method, the corresponding abnormal position information of the alternate irrigation device when the blockage or breakage occurs can be quickly and conveniently located, and the relevant staff is reminded to troubleshoot the abnormality in time, so as to prevent water resource waste and prevent the yield of target broccoli from decreasing due to insufficient irrigation.

[0150] The application also discloses a machine readable storage medium, characterized in that the machine readable storage medium has instructions stored thereon, the instructions being used to cause a machine to execute the method for intelligent control of the broccoli root area alternate irrigation device according to any one of the above.

[0151] The application also discloses an intelligent control system of a broccoli root area alternate irrigation device, characterized in that the system comprises:

[0152] a memory configured to store instructions; and

[0153] A processor configured to call instructions from the memory and implement the method of intelligent control of the broccoli root zone alternate irrigation device according to any of the above when executing the instructions.

[0154] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), programmable logic devices (PLD), discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The present application is not limited in this respect.

[0155] The memory can be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device, or an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SMC), a secure digital card (SD), a flash card (FC), etc. The memory can also be a combination of the internal storage unit and the external storage device of the computer device. The memory is used to store computer programs and other programs and data required by the computer device. The memory can also be used to temporarily store data that has been output or will be output. The present application is not limited in this respect.

[0156] The present application also provides a machine-readable storage medium having instructions stored thereon for causing a machine to perform the method of intelligent control of the broccoli root zone alternate irrigation device.

[0157] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can be in the form of a completely hardware embodiment, a completely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0158] The present application is described with reference to the flowcharts and / or block diagrams of the method, device (system), computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The flow or multiple flows and / or blocksFigure 1 means for performing the function specified by the block or blocks.

[0159] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flow Figure 1 flow or flows and / or blocks Figure 1 means for performing the function specified by the block or blocks.

[0160] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 flow or flows and / or blocks Figure 1 means for performing the function specified by the block or blocks.

[0161] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0162] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory. The memory can also include non-volatile memory, such as read-only memory (ROM), electrically programmable read-only memory (EPROM), electrically erasable read-only memory (EEPROM), programmable read-only memory (PROM), flash memory, or any other non-volatile memory. Memory is an example of computer-readable media.

[0163] Computer-readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile discs (DVDs) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

[0164] It should also be noted that the terms "comprising", "comprises" or other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0165] The above embodiments are only used to illustrate the present application, but not to limit it. Instead of the above, various modifications and changes can be made to the application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall fall into the scope of the claims of the application.

Claims

1. A method for intelligent control of broccoli root zone alternate irrigation device, characterized in that, The method comprises the following steps: Obtain the broccoli associated information of the target vegetable field; Input the broccoli associated information into the pre-constructed initial cycle prediction model, and output the initial growth cycle of the target broccoli in the target vegetable field through the initial cycle prediction model; When the initial growth cycle is reached for the first time, collect the broccoli remote sensing information of the target vegetable field through the remote sensing unmanned aerial vehicle; Combine the broccoli remote sensing information and the broccoli associated information to assimilate the initial cycle prediction model, obtain the standard cycle prediction model, and correct the initial growth cycle based on the standard cycle prediction model to obtain the standard growth cycle; When reaching any standard growth cycle, generate the alternate irrigation cycle of the target vegetable field according to the cycle type and cycle time in the standard growth cycle; Re-obtain the second meteorological information of the target vegetable field in the standard growth cycle, and the second meteorological information comprises meteorological parameters and total precipitation; Calculate the reference evapotranspiration of the target broccoli according to the meteorological parameters; Determine the crop coefficient of the target broccoli according to the cycle type; Calculate the broccoli theoretical water requirement of the target broccoli according to the reference evapotranspiration and the crop coefficient; Take the soil water content collected in the standard growth cycle as the standard water content; Correct the broccoli theoretical water requirement by using the soil water absorption rate, the soil water holding rate and the standard water content to obtain the broccoli actual water requirement; Calculate the daily average irrigation amount of the target broccoli according to the total precipitation and the broccoli actual water requirement; Integrate the alternate irrigation cycle and the daily average irrigation amount to obtain the alternate irrigation strategy of the target vegetable field, and intelligently control the alternate irrigation device preset in the target vegetable field according to the alternate irrigation strategy.

2. The method of claim 1, wherein, The broccoli associated information comprises the first meteorological information of the location of the target vegetable field, the broccoli information in the target vegetable field, and the soil information of the target vegetable field, and the soil information comprises the pre-obtained soil water absorption rate, soil water holding rate and soil type, and the real-time collected soil water content through the soil sensor preset in the target vegetable field.

3. The method of claim 2, wherein, The combination of the broccoli remote sensing information and the broccoli associated information to assimilate the initial cycle prediction model, obtain the standard cycle prediction model, and correct the initial growth cycle based on the standard cycle prediction model to obtain the standard growth cycle comprises the following steps: Preprocess the broccoli remote sensing information; Invert the preprocessed broccoli remote sensing information by using an inversion algorithm, and extract the vegetable field remote sensing parameters in the target vegetable field according to the inversion result, wherein the vegetable field remote sensing parameters comprise a broccoli index and a vegetable field water content; Complete the spatial fusion of the vegetable field water content and the soil water content by using a data fusion algorithm to obtain the fusion water content of the target vegetable field; Combine the broccoli index and the fusion water content to assimilate the initial cycle prediction model to obtain the standard cycle prediction model; Input the first meteorological information, the broccoli information and the soil information in the initial growth cycle into the standard cycle prediction model, and output the standard growth cycle of the target broccoli through the standard cycle prediction model.

4. The method of claim 3, wherein, The spatial fusion of the vegetable field water content and the soil water content by using a data fusion algorithm to obtain the fusion water content of the target vegetable field comprises the following steps: Take the soil water content collected in the initial growth cycle as the target water content; Standardize the vegetable field water content and the target water content; The data correlation between the soil moisture content after the standardization processing and the target water content is calculated by using the correlation coefficient formula; The spatial aggregation of the soil moisture content after the standardization processing and the target water content is analyzed by using the preset variation function; The fusion water content of the target vegetable field in the initial growth period is obtained by combining the spatial aggregation and the data correlation and using the Kriging interpolation method to interpolate and fuse the soil moisture content and the target water content.

5. The method of claim 3, wherein, The method for obtaining the standard period prediction model by assimilating the initial period prediction model with the broccoli index and the fusion water content comprises the following steps: Aligning the spatio-temporal scale between the broccoli index and the fusion water content; Normalizing the broccoli index and the fusion water content after the spatio-temporal scale alignment to obtain the standard index and the standard water content, respectively; Defining the error covariance matrix by combining the standard index and the standard water content; Generating an initial state set of the initial period prediction model according to the correlation information of the broccoli; Running the initial period prediction model according to the initial state set and according to the ensemble Kalman filtering algorithm to obtain a prediction state set; Calculating the Kalman gain by combining the prediction state set and the error covariance matrix; Adjusting the model parameters of the initial period prediction model by combining the Kalman gain, the standard index and the standard water content to obtain the standard period prediction model.

6. The method of claim 1, wherein, The method further comprises: After completing the intelligent irrigation task in any standard growth period, calculating the irrigation qualification degree in the standard growth period by using the irrigation qualification degree formula; If the irrigation qualification degree is located in the preset qualification threshold interval, it is determined that the intelligent irrigation task is qualified; If the irrigation qualification degree is not located in the qualification threshold interval, it is determined that the intelligent irrigation task is unqualified; If the intelligent irrigation task is qualified, the intelligent irrigation task in the next standard growth period is continued to be completed; If the intelligent irrigation task is unqualified, a strategy correction factor is output according to the irrigation qualification degree, and the alternate irrigation strategy of the next standard growth period is corrected by using the strategy correction factor.

7. The method of claim 6, wherein, The irrigation qualification degree formula comprises: ， wherein, is the actual irrigation amount for the target broccoli, is the daily average irrigation amount for the target broccoli, is the irrigation correction factor, and are the daily average soil water content of the left and right sides of the target broccoli, respectively, is a preset water content difference threshold, is the number of soil sensors, is a preset fixed integer parameter, is a pre-acquired soil water conductivity, is the daily average irrigation duration, is a preset air temperature attenuation factor.

8. A machine-readable storage medium, characterized in that, The machine readable storage medium has instructions stored thereon, which are used to enable the machine to execute the method for intelligent control of the broccoli root zone alternate irrigation device according to any one of claims 1 to 7.

9. An intelligent control system for broccoli root zone alternate irrigation device, characterized in that, Comprise: a memory configured to store instructions; and a processor configured to call the instructions from the memory and capable of implementing the method for intelligent control of the broccoli root zone alternate irrigation device according to any one of claims 1 to 7 when executing the instructions.

Images