A method, device, storage medium and electronic device for simulating water and fertilizer assimilation in drip irrigation

Abstract

The present invention discloses a method, device, storage medium and electronic device for simulating drip irrigation water-fertilizer assimilation. The method improves the simulation efficiency of drip irrigation water-fertilizer assimilation by establishing a first drip irrigation soil moisture and fertilizer kinetic motion model and its alternative model, namely, a second drip irrigation soil moisture and fertilizer kinetic motion model. Meanwhile, the influence of model parameter uncertainty on the model is considered in the process of model establishment. The model parameter set and the training base point parameter set are determined by a random function sampling method, so as to solve the problem of overfitting of model parameters and improve the simulation accuracy of soil moisture and fertilizer concentration.

Description

Technical Field

[0001] The invention relates to the technical field of drip irrigation, and in particular to a method, a device, a storage medium and an electronic device for simulating water-fertilizer assimilation in drip irrigation. Background Art

[0002] Drip irrigation is a widely used water-saving irrigation technology that can deliver water and fertilizer directly to the root zone of crops in a timely and appropriate manner, significantly improving the water and fertilizer utilization efficiency of crops. In order to determine the appropriate irrigation and fertilization system, it is necessary to understand the movement and distribution of water and fertilizer in the soil.

[0003] Most of the existing drip irrigation water and fertilizer simulation methods use deterministic mechanism models, which give little consideration to multi-source uncertainties in the process of simulating water and fertilizer movement. They are prone to overfitting of model parameters, which affects the simulation accuracy of water and fertilizer. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a drip irrigation water-fertilizer assimilation simulation method, device, storage medium and electronic device to solve the technical problem of low simulation accuracy of water and fertilizer obtained by the drip irrigation water-fertilizer simulation method in the prior art.

[0005] The technical solution proposed by the present invention is as follows:

[0006] In a first aspect, an embodiment of the present invention provides a drip irrigation water-fertilizer assimilation simulation method, which includes: obtaining a first drip irrigation soil moisture and fertilizer dynamics motion model and a parameter mean and parameter variance of the drip irrigation soil moisture and fertilizer dynamics motion model; based on the parameter mean and parameter variance, a model parameter set and a training base point parameter set are obtained through random function sampling method processing; based on the training base point parameter set, the first drip irrigation soil moisture and fertilizer dynamics motion model is run to obtain an initial soil moisture simulation value and an initial fertilizer concentration simulation value of the observation point; based on the training base point parameter set, the initial soil moisture simulation value and the initial fertilizer concentration simulation value, a second drip irrigation soil moisture and fertilizer dynamics motion model is established through a Gaussian process method; based on the model parameter set, the second drip irrigation soil moisture and fertilizer dynamics motion model is run to obtain a target soil moisture simulation value and a target fertilizer concentration simulation value of the observation point.

[0007] In combination with the first aspect, in a possible implementation of the first aspect, obtaining a first drip irrigation soil moisture and fertilizer dynamics motion model includes: obtaining a drip irrigation scene parameter set and a drip irrigation soil condition parameter set; and establishing the first drip irrigation soil moisture and fertilizer dynamics motion model based on the drip irrigation scene parameter set and the drip irrigation soil condition parameter set.

[0008] In combination with the first aspect, in another possible implementation of the first aspect, based on the parameter mean and the parameter variance, a model parameter set and a training base point parameter set are obtained through processing by a random function sampling method, including: based on the parameter mean and the parameter variance, a model parameter set is obtained through processing by the random function sampling method; based on the model parameter set, a training base point parameter set is obtained through processing by the random function sampling method.

[0009] In combination with the first aspect, in another possible implementation of the first aspect, before establishing the second drip irrigation soil moisture and fertilizer dynamics motion model based on the training base point parameter set, the initial soil moisture simulation value and the initial first fertilizer concentration simulation value through the Gaussian process method, the method also includes: obtaining a preset mean function and a preset covariance function; and determining the Gaussian process method based on the preset mean function and the preset covariance function.

[0010] In combination with the first aspect, in another possible implementation of the first aspect, the method also includes: determining whether there is observation data at the observation point at the current moment; when the observation data exists, updating the model parameter set using an improved ensemble Kalman filter assimilation algorithm.

[0011] In a second aspect, an embodiment of the present invention provides a drip irrigation water-fertilizer assimilation simulation device, which includes: an acquisition module, used to obtain a first drip irrigation soil moisture and fertilizer dynamics motion model and a parameter mean and parameter variance of the drip irrigation soil moisture and fertilizer dynamics motion model; a processing module, used to obtain a model parameter set and a training base point parameter set based on the parameter mean and parameter variance through a random function sampling method; a first operation module, used to operate the first drip irrigation soil moisture and fertilizer dynamics motion model based on the training base point parameter set to obtain an initial soil moisture simulation value and an initial fertilizer concentration simulation value of the observation point; an establishment module, used to establish a second drip irrigation soil moisture and fertilizer dynamics motion model based on the training base point parameter set, the initial soil moisture simulation value and the initial fertilizer concentration simulation value through a Gaussian process method; a second operation module, used to operate the second drip irrigation soil moisture and fertilizer dynamics motion model based on the model parameter set to obtain a target soil moisture simulation value and a target fertilizer concentration simulation value of the observation point.

[0012] In combination with the second aspect, in a possible implementation of the second aspect, the acquisition module includes: an acquisition submodule, used to acquire a drip irrigation scene parameter set and a drip irrigation soil condition parameter set; and an establishment submodule, used to establish the first drip irrigation soil moisture and fertilizer dynamics motion model based on the drip irrigation scene parameter set and the drip irrigation soil condition parameter set.

[0013] In combination with the second aspect, in another possible implementation of the second aspect, the processing module includes: a first processing sub-module, used to obtain the model parameter set based on the parameter mean and the parameter variance through the random function sampling method; a second processing sub-module, used to obtain the training base point parameter set based on the model parameter set through the random function sampling method.

[0014] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is used to enable the computer to execute the drip irrigation water-fertilizer assimilation simulation method as described in the first aspect and any one of the first aspects of the embodiments of the present invention.

[0015] In a fourth aspect, an embodiment of the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing a computer program, and the processor executing the drip irrigation water-fertilizer assimilation simulation method as described in the first aspect and any one of the first aspects of the embodiment of the present invention by executing the computer program.

[0016] The technical solution provided by the present invention has the following effects:

[0017] The drip irrigation water and fertilizer assimilation simulation method provided by the embodiment of the present invention improves the efficiency of drip irrigation water and fertilizer assimilation simulation by establishing a first drip irrigation soil moisture and fertilizer kinetic motion model and its alternative model (a second drip irrigation soil moisture and fertilizer kinetic motion model); at the same time, the influence of model parameter uncertainty on the model is considered in the model establishment process, and the model parameter set and the training base point parameter set are determined by a random function sampling method, which solves the problem of model parameter overfitting and improves the simulation accuracy of soil moisture and fertilizer concentration. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 is a flow chart of a method for simulating water and fertilizer assimilation in drip irrigation provided according to an embodiment of the present invention;

[0020] Figure 2A is a schematic diagram of comparing the simulated value and the measured value of the soil pressure head provided by an embodiment of the present invention;

[0021] Figure 2BIt is a schematic diagram of comparing the simulated value and the measured value of fertilizer concentration provided by an embodiment of the present invention;

[0022] Figure 3 is another flow chart of a method for simulating water and fertilizer assimilation in drip irrigation provided according to an embodiment of the present invention;

[0023] Figure 4 This is a structural block diagram of a drip irrigation water-fertilizer assimilation simulation device provided according to an embodiment of the present invention;

[0024] Figure 5 is a schematic diagram of the structure of a computer-readable storage medium provided according to an embodiment of the present invention;

[0025] Figure 6 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Numerical model simulation methods can consider the impact of factors such as soil type and climate on the movement of water and fertilizers, and determine the appropriate irrigation system by simulating different irrigation scenarios. At present, a variety of numerical models have been developed to simulate processes such as water movement and solute transport in soil. However, due to insufficient understanding of soil water and solute movement processes, the constructed numerical models are usually affected by uncertainties such as input data and model parameters.

[0029] The embodiment of the present invention provides a method for simulating water and fertilizer assimilation in drip irrigation, such as Figure 1As shown, the method comprises the following steps:

[0030] Step 101: Obtain a first drip irrigation soil moisture and fertilizer dynamics movement model and a parameter mean and parameter variance of the drip irrigation soil moisture and fertilizer dynamics movement model.

[0031] Among them, the parameter mean and parameter variance are preset.

[0032] Take the simulation of the movement of water and fertilizer under drip irrigation under layered soil conditions as an example. Each soil layer is 30 cm thick, and from top to bottom, it is loam, loamy sand, and sandy soil. An observation point is set for each soil layer, and the pressure head and solute concentration of the observation point are recorded every 5 minutes.

[0033] Specifically, it is assumed that the saturated hydraulic conductivity (K S ) obeys the log-normal distribution, and the initial statistical characteristics are log 10 K S ~N(a,0.1), that is, the mean is the initial value of the parameter and the variance is 0.1.

[0034] Longitudinal dispersion (D L ) and lateral dispersivity (D T ) obeys the normal distribution, and the initial statistical characteristics are log 10 D L ~N(a,0.05),log 10 D T ~N(0.5,0.05), that is, the mean is the initial value of the parameter and the variance is 0.05.

[0035] Step 102: Based on the parameter mean and parameter variance, a model parameter set and a training base point parameter set are obtained by processing using a random function sampling method.

[0036] Specifically, according to the parameter mean and parameter variance obtained in step 101, a random function sampling method is used to perform sampling to obtain a model parameter set A and a training base point parameter set B. The model parameter set A includes the training base point parameter set B.

[0037] Step 103: running the first drip irrigation soil moisture and fertilizer dynamics movement model based on the training base point parameter set to obtain an initial soil moisture simulation value and an initial fertilizer concentration simulation value of the observation point.

[0038] Specifically, by running the first drip irrigation soil moisture and fertilizer dynamics motion model obtained in step 101 using the training base point parameter set B, the pressure head (initial soil moisture simulation value) and the initial fertilizer concentration simulation value of each observation point can be obtained.

[0039] Step 104: Based on the training base point parameter set, the initial soil moisture simulation value and the initial fertilizer concentration simulation value, a second drip irrigation soil moisture and fertilizer dynamics movement model is established through a Gaussian process method.

[0040] The second drip irrigation soil moisture and fertilizer dynamics movement model is a substitute model for the first drip irrigation soil moisture and fertilizer dynamics movement model.

[0041] Specifically, the training base point parameter set B is used as input data, the initial soil moisture simulation value and the initial fertilizer concentration simulation value are used as output data, and the Gaussian process method is used to establish the second drip irrigation soil moisture and fertilizer dynamics movement model.

[0042] The Gaussian process method is expressed by the following equation (1):

[0043] G(m)~N(μ(m),(m,m ′ ))(1)

[0044] Where: μ(m) represents the preset mean function; k(m,m ′ ) represents the preset covariance function.

[0045] Step 105: running the second drip irrigation soil moisture and fertilizer dynamics movement model based on the model parameter set to obtain a target soil moisture simulation value and a target fertilizer concentration simulation value of the observation point.

[0046] Specifically, the second drip irrigation soil moisture and fertilizer dynamics movement model obtained in step 104 is run using model parameter set A to obtain a target soil moisture simulation value and a target fertilizer concentration simulation value for each observation point.

[0047] The assimilation simulation of drip irrigation water and fertilizer is performed by using the first drip irrigation soil moisture and fertilizer dynamics movement model and its alternative model (the second drip irrigation soil moisture and fertilizer dynamics movement model), thereby improving the simulation efficiency of drip irrigation water and fertilizer assimilation.

[0048] The drip irrigation water and fertilizer assimilation simulation method provided by the embodiment of the present invention improves the efficiency of drip irrigation water and fertilizer assimilation simulation by establishing a first drip irrigation soil moisture and fertilizer kinetic motion model and its alternative model (a second drip irrigation soil moisture and fertilizer kinetic motion model); at the same time, the influence of model parameter uncertainty on the model is considered in the model establishment process, and the model parameter set and the training base point parameter set are determined by a random function sampling method, which solves the problem of model parameter overfitting and improves the simulation accuracy of soil moisture and fertilizer concentration.

[0049] As an optional implementation manner of an embodiment of the present invention, obtaining a first drip irrigation soil moisture and fertilizer kinetic motion model includes: obtaining a drip irrigation scene parameter set and a drip irrigation soil condition parameter set; and establishing the first drip irrigation soil moisture and fertilizer kinetic motion model based on the drip irrigation scene parameter set and the drip irrigation soil condition parameter set.

[0050] Among them, the drip irrigation scene parameter set reflects the layout parameters of the farmland drip irrigation system; the drip irrigation soil condition parameter set can include parameters such as volumetric moisture content and soil solute concentration.

[0051] Specifically, the first drip irrigation soil moisture and fertilizer dynamics movement model can be trained through the drip irrigation scene parameter set and the drip irrigation soil condition parameter set.

[0052] In the above embodiment of the simulation of the movement process of drip irrigation water and fertilizer under layered soil conditions, due to the axial symmetry of the simulation area below the dripper, the first drip irrigation soil water and fertilizer dynamics movement model constructed is a two-dimensional drip irrigation water flow and fertilizer movement model, as shown in the following equations (2) and (3):

[0053]

[0054]

[0055] Where: θ represents volumetric water content; h represents pressure head; K represents unsaturated hydraulic conductivity; represents the dimensionless anisotropy tensor K A The weight of x i and x j represents the spatial coordinates; S represents the source and sink term; c represents the solute concentration in the soil; q i represents the i-th component of volume flux; D ij represents the diffusion coefficient tensor; c s Represents the concentration of the sink term.

[0056] As an optional implementation of an embodiment of the present invention, step 102 includes: based on the parameter mean and parameter variance, processing by the random function sampling method to obtain the model parameter set; based on the model parameter set, processing by the random function sampling method to obtain the training base point parameter set.

[0057] According to the description of step 102 , the model parameter set A includes the training base point parameter set B.

[0058] Specifically, based on the parameter mean and parameter variance, the random function sampling method is used to sample and obtain the model parameter set A; further, the random function sampling method is used again to sample in the model parameter set A to obtain the training base point parameter set B.

[0059] As an optional implementation of the embodiment of the present invention, before step 104, the method further includes: obtaining a preset mean function and a preset covariance function; and determining the Gaussian process method based on the preset mean function and the preset covariance function.

[0060] The Gaussian process method represents a series of combinations of random variables that obey a normal distribution within an exponential set.

[0061] Specifically, according to the description of step 104, the Gaussian process method is represented by a preset mean function and a preset covariance function.

[0062] In the embodiment of the present invention, the sum of a constant and a linear mean function is selected as the preset mean function μ(m), as shown in the following relational expression (4):

[0063]

[0064] Where: a and b i Represents the hyperparameter of the preset mean function, and the corresponding parameter value can be determined through training; m i represents the model variable vector; n represents the number of variables.

[0065] Select the diagonal square exponential covariance function as the preset covariance function k(m,m ′ ), as shown in the following relation (5):

[0066]

[0067] Where: f and λ represent the hyperparameters of the preset covariance function, and the corresponding parameter values ​​can be determined through training; m represents the model variable vector; m ′ Represents the transpose of the model variable vector.

[0068] As an optional implementation of the embodiment of the present invention, the method further includes: determining whether there is observation data at the observation point at the current moment; when the observation data exists, updating the model parameter set using an improved ensemble Kalman filter assimilation algorithm.

[0069] Specifically, when there are observation data, the model parameter set needs to be updated through the assimilation algorithm.

[0070] In the prior art, for the multidimensional process assimilation problem, the traditional ensemble Kalman filter or particle filter method has low computational efficiency, which limits the application of data assimilation methods in drip irrigation water and fertilizer simulation.

[0071] In the embodiment of the present invention, an improved ensemble Kalman filter assimilation algorithm is used to update the model parameter set, as shown in the following equation (6):

[0072]

[0073] Where: i represents the assimilation time number; j represents the number of sets; X f represents the prediction model parameter vector; X a represents the analysis model parameter vector; ε represents the observation error vector; H represents the observation operator; K i+1 represents the Kalman gain, as shown in the following equation (7):

[0074] K i+1 =P i+1 H T (HP i+1 H T +O i+1 ) -1 (7)

[0075] Where: O represents the observation error variance; P i+1 represents the prediction value error covariance, as shown in the following equation (8):

[0076]

[0077] Where: express The mean of ; J represents the total number of sets.

[0078] In the above-mentioned embodiment of simulating the movement process of drip irrigation water and fertilizer under layered soil conditions, the simulation is performed by the drip irrigation water and fertilizer assimilation simulation method provided by the embodiment of the present invention, and the obtained soil pressure head and fertilizer concentration simulation values ​​are compared with the measured values, such as Figure 2A and 2B shown.

[0079] In one example, a method for simulating water and fertilizer assimilation in drip irrigation is provided, such as Figure 3 As shown, including:

[0080] (1) Construct a dynamic movement model of soil moisture and fertilizer under drip irrigation based on the layout of the drip irrigation system and soil conditions;

[0081] (2) Setting the mean and variance of the water and fertilizer movement model parameters, and using random sampling to obtain the model parameter set;

[0082] (3) randomly sampling from the model parameter set to obtain a training base point parameter set;

[0083] (4) Using the training base point parameter set to run the drip irrigation soil moisture and fertilizer dynamics movement model, obtain the pressure head and fertilizer concentration simulation values ​​at the observation point;

[0084] (5) Using the training base point parameter set as input data and the simulated values ​​of pressure head and fertilizer concentration as output data, an alternative model of the drip irrigation soil moisture and fertilizer dynamics movement model is established through training;

[0085] (6) Using the model parameter set, run the drip irrigation soil moisture and fertilizer movement substitution model to obtain the pressure head and fertilizer concentration at the observation point;

[0086] (7) When there are observation data, the water and fertilizer movement model parameters are updated through the assimilation algorithm, and the drip irrigation soil water and fertilizer dynamic movement model is input to obtain the soil water and fertilizer simulation values.

[0087] By constructing a drip irrigation soil moisture and fertilizer dynamics movement model and its alternative model, and combining the data assimilation method to update the moisture and fertilizer movement model parameters, the efficiency of drip irrigation water and fertilizer assimilation simulation is improved, and it can be applied to the simulation and prediction of drip irrigation water and fertilizer.

[0088] The embodiment of the present invention also provides a drip irrigation water fertilizer assimilation simulation device, such as Figure 4 As shown, the device comprises:

[0089] The acquisition module 401 is used to obtain the first drip irrigation soil moisture and fertilizer dynamics movement model and the parameter mean and parameter variance of the drip irrigation soil moisture and fertilizer dynamics movement model; for details, please refer to the relevant description of step 101 in the above method embodiment.

[0090] The processing module 402 is used to obtain a model parameter set and a training base point parameter set based on the parameter mean and parameter variance by a random function sampling method; for details, see the relevant description of step 102 in the above method embodiment.

[0091] The first operation module 403 is used to operate the first drip irrigation soil moisture and fertilizer dynamics motion model based on the training base point parameter set to obtain the initial soil moisture simulation value and the initial fertilizer concentration simulation value of the observation point; for details, please refer to the relevant description of step 103 in the above method embodiment.

[0092] Establish module 404, which is used to establish a second drip irrigation soil moisture and fertilizer dynamics motion model based on the training base point parameter set, the initial soil moisture simulation value and the initial fertilizer concentration simulation value through the Gaussian process method; for details, see the relevant description of step 104 in the above method embodiment.

[0093] The second operation module 405 is used to run the second drip irrigation soil moisture and fertilizer dynamics movement model based on the model parameter set to obtain the target soil moisture simulation value and the target fertilizer concentration simulation value of the observation point; for details, please refer to the relevant description of step 105 in the above method embodiment.

[0094] The drip irrigation water-fertilizer assimilation simulation device provided by the embodiment of the present invention improves the efficiency of drip irrigation water-fertilizer assimilation simulation by establishing a first drip irrigation soil moisture and fertilizer kinetic motion model and its alternative model (a second drip irrigation soil moisture and fertilizer kinetic motion model); at the same time, the influence of model parameters on the model is considered in the model establishment process, and the model parameter set and the training base point parameter set are determined by a random function sampling method, which solves the problem of overfitting of model parameters and improves the simulation accuracy of soil moisture and fertilizer concentration.

[0095] As an optional implementation manner of an embodiment of the present invention, the acquisition module includes: an acquisition submodule, used to acquire a drip irrigation scene parameter set and a drip irrigation soil condition parameter set; and an establishment submodule, used to establish the first drip irrigation soil moisture and fertilizer dynamics movement model based on the drip irrigation scene parameter set and the drip irrigation soil condition parameter set.

[0096] As an optional implementation of an embodiment of the present invention, the processing module includes: a first processing sub-module, used to obtain the model parameter set based on the parameter mean and parameter variance through processing by the random function sampling method; a second processing sub-module, used to obtain the training base point parameter set based on the model parameter set through processing by the random function sampling method.

[0097] As an optional implementation of the embodiment of the present invention, the device also includes: a first acquisition module, used to obtain a preset mean function and a preset covariance function; a determination module, used to determine the Gaussian process method based on the preset mean function and the preset covariance function.

[0098] As an optional implementation of the embodiment of the present invention, the device also includes: a judgment module, used to judge whether there is observation data at the observation point at the current moment; an update module, used to update the model parameter set using an improved ensemble Kalman filter assimilation algorithm when the observation data exists.

[0099] For a detailed description of the functions of the drip irrigation water-fertilizer assimilation simulation device provided in the embodiment of the present invention, please refer to the description of the drip irrigation water-fertilizer assimilation simulation method in the above embodiment.

[0100] The embodiment of the present invention also provides a storage medium, such as Figure 5As shown, a computer program 501 is stored thereon, and when the program is executed by the processor, the steps of the drip irrigation water fertilizer assimilation simulation method in the above embodiment are implemented. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memory.

[0101] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0102] The embodiment of the present invention further provides an electronic device, such as Figure 6 As shown, the electronic device may include a processor 61 and a memory 62, wherein the processor 61 and the memory 62 may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0103] The processor 61 may be a central processing unit (CPU). The processor 61 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0104] The memory 62 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the corresponding program instructions / modules in the embodiment of the present invention. The processor 61 executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory 62, that is, the drip irrigation water-fertilizer assimilation simulation method in the above method embodiment is realized.

[0105] The memory 62 may include a program storage area and a data storage area, wherein the program storage area may store an application required for operating the device and at least one function; the data storage area may store data created by the processor 61, etc. In addition, the memory 62 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 62 may optionally include a memory remotely arranged relative to the processor 61, and these remote memories may be connected to the processor 61 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0106] The one or more modules are stored in the memory 62, and when executed by the processor 61, the following is performed: Figure 1-3 The drip irrigation water-fertilizer assimilation simulation method in the illustrated embodiment.

[0107] For details of the above electronic equipment, please refer to Figures 1 to 3 The corresponding related descriptions and effects in the illustrated embodiments can be understood and will not be repeated here.

[0108] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for simulating water and fertilizer assimilation in drip irrigation. It is characterized in that The method comprises: Obtaining a first drip irrigation soil moisture and fertilizer kinetic motion model and parameter means and parameter variances of the drip irrigation soil moisture and fertilizer kinetic motion model; Based on the parameter mean and parameter variance, a model parameter set and a training base point parameter set are obtained by processing with a random function sampling method, wherein the model parameter set includes the training base point parameter set; Running the first drip irrigation soil moisture and fertilizer dynamics movement model based on the training base point parameter set to obtain an initial soil moisture simulation value and an initial fertilizer concentration simulation value of the observation point; Based on the training base point parameter set, the initial soil moisture simulation value and the initial fertilizer concentration simulation value, a second drip irrigation soil moisture and fertilizer kinetic motion model is established through a Gaussian process method, wherein the second drip irrigation soil moisture and fertilizer kinetic motion model is an alternative model to the first drip irrigation soil moisture and fertilizer kinetic motion model; Running the second drip irrigation soil moisture and fertilizer dynamics movement model based on the model parameter set to obtain a target soil moisture simulation value and a target fertilizer concentration simulation value of the observation point; Among them, the first drip irrigation soil moisture and fertilizer dynamics movement model is obtained, including: Acquire a drip irrigation scenario parameter set and a drip irrigation soil condition parameter set, wherein the drip irrigation scenario parameter set reflects the layout parameters of the farmland drip irrigation system, and the drip irrigation soil condition parameter set includes volumetric water content and soil solute concentration; Based on the drip irrigation scenario parameter set and the drip irrigation soil condition parameter set, establishing the first drip irrigation soil moisture and fertilizer dynamics movement model; The first drip irrigation soil moisture and fertilizer dynamics movement model is a two-dimensional drip irrigation water flow and fertilizer movement model, which is expressed as the following relationship: Where: Indicates volumetric water content; Indicates the pressure head; represents the unsaturated hydraulic conductivity; represents the dimensionless anisotropy tensor The weight of and Represents spatial coordinates; represents source and sink terms; It represents the solute concentration in the soil; The volume flux Quantity; represents the diffusion coefficient tensor; represents the concentration of the sink term; The method further includes: determining whether there is observation data at the observation point at the current moment; when the observation data exists, updating the model parameter set using an improved ensemble Kalman filter assimilation algorithm; Among them, the improved ensemble Kalman filter assimilation algorithm is expressed as the following relationship: Where: Indicates the assimilation time number; Indicates the number of sets; represents the prediction model parameter vector; represents the analysis model parameter vector; represents the observation error vector; represents the observation operator; represents the Kalman gain.

2. The method according to claim 1, It is characterized in that Based on the parameter mean and parameter variance, a model parameter set and a training base point parameter set are obtained through random function sampling method, including: Based on the parameter mean and parameter variance, the model parameter set is obtained by processing with the random function sampling method; Based on the model parameter set, the training base point parameter set is obtained through processing by the random function sampling method.

3. The method according to claim 1, It is characterized in that Before establishing a second drip irrigation soil moisture and fertilizer dynamics movement model based on the training base point parameter set, the initial soil moisture simulation value and the initial first fertilizer concentration simulation value through a Gaussian process method, the method further includes: Get the preset mean function and the preset covariance function; The Gaussian process method is determined based on the preset mean function and the preset covariance function.

4. A drip irrigation water and fertilizer assimilation simulation device, It is characterized in that The device comprises: An acquisition module, used for acquiring a first drip irrigation soil moisture and fertilizer kinetic motion model and a parameter mean and a parameter variance of the drip irrigation soil moisture and fertilizer kinetic motion model; A processing module, used for obtaining a model parameter set and a training base point parameter set based on the parameter mean and the parameter variance by a random function sampling method, wherein the model parameter set includes the training base point parameter set; A first operation module is used to operate the first drip irrigation soil moisture and fertilizer dynamics movement model based on the training base point parameter set to obtain an initial soil moisture simulation value and an initial fertilizer concentration simulation value of an observation point; An establishment module is used to establish a second drip irrigation soil moisture and fertilizer kinetic motion model based on the training base point parameter set, the initial soil moisture simulation value and the initial fertilizer concentration simulation value through a Gaussian process method, wherein the second drip irrigation soil moisture and fertilizer kinetic motion model is an alternative model to the first drip irrigation soil moisture and fertilizer kinetic motion model; A second operation module is used to operate the second drip irrigation soil moisture and fertilizer dynamics movement model based on the model parameter set to obtain a target soil moisture simulation value and a target fertilizer concentration simulation value of the observation point; Wherein, the acquisition module includes: An acquisition submodule, used to acquire a drip irrigation scene parameter set and a drip irrigation soil condition parameter set, wherein the drip irrigation scene parameter set reflects the layout parameters of the farmland drip irrigation system, and the drip irrigation soil condition parameter set includes a volumetric moisture content and a soil solute concentration; Establishing a submodule, for establishing the first drip irrigation soil moisture and fertilizer dynamics movement model based on the drip irrigation scenario parameter set and the drip irrigation soil condition parameter set; The first drip irrigation soil moisture and fertilizer dynamics movement model is a two-dimensional drip irrigation water flow and fertilizer movement model, which is expressed as the following relationship: Where: Indicates volumetric water content; Indicates the pressure head; represents the unsaturated hydraulic conductivity; represents the dimensionless anisotropy tensor The amount of and Represents spatial coordinates; represents source and sink terms; It represents the solute concentration in the soil; The volume flux Quantity; represents the diffusion coefficient tensor; represents the concentration of the sink term; The device further comprises: a judgment module, used to judge whether there is observation data at the observation point at the current moment; an updating module, used to update the model parameter set using an improved ensemble Kalman filter assimilation algorithm when the observation data exists; Among them, the improved ensemble Kalman filter assimilation algorithm is expressed as the following relationship: Where: Indicates the assimilation time number; Indicates the number of sets; represents the prediction model parameter vector; represents the analysis model parameter vector; represents the observation error vector; represents the observation operator; represents the Kalman gain.

5. The device according to claim 4, It is characterized in that The processing module comprises: A first processing submodule is used to obtain the model parameter set based on the parameter mean and the parameter variance through the random function sampling method; The second processing submodule is used to obtain the training base point parameter set based on the model parameter set through the random function sampling method.

6. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and the computer program is used to enable the computer to execute the drip irrigation water-fertilizer assimilation simulation method according to any one of claims 1 to 3.

7. An electronic device, It is characterized in that include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores a computer program, and the processor executes the drip irrigation water-fertilizer assimilation simulation method according to any one of claims 1 to 3 by executing the computer program.

Images