Method and system for dynamically optimizing irrigation and drainage strategy of rice field

Abstract

The invention discloses a rice field irrigation drainage strategy dynamic optimization method and system. The method comprises the steps of collecting environmental parameters of a target rice field in a current decision period; determining a to-be-optimized target of the target rice field, and constructing a multi-target optimization model in combination with the environmental parameters; performing dynamic planning solution on the multi-objective optimization model by adopting an intelligent algorithm to obtain a real-time optimized irrigation drainage strategy of the current decision period; implementing a real-time optimized irrigation drainage strategy of the current decision period; monitoring whether the final period of the rice growth period is reached when the current decision-making period is ended or not: otherwise, acquiring actual environment parameters when the decision-making period is ended, correcting the state vector at the moment, updating the initial state vector of the next decision-making period of the target rice field through the transfer function, and repeating the solving and implementation process of the irrigation and drainage strategy optimized in real time; if yes, the circulation is ended, and the optimal irrigation drainage strategy in the whole growth period of the target rice field is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of water-saving irrigation, and particularly relates to a method and system for dynamically optimizing the irrigation and drainage strategy of paddy fields. Background Art

[0002] Traditional irrigation methods usually rely on farmers' experience for decision-making and cannot effectively make dynamic adjustments according to real-time meteorological changes. This experience-dependent irrigation mode is difficult to cope with the impact of weather changes on crop water requirements and is prone to waste of water resources. In addition, most traditional irrigation optimization methods are single-objective optimizations, usually only focusing on one aspect of the effect, such as water conservation or yield increase, but it is difficult to simultaneously take into account water resource conservation, crop yield improvement, and operation efficiency optimization, making it difficult to maximize the comprehensive benefits. Moreover, most irrigation systems use static models, which cannot flexibly respond to real-time changes in the field environment, such as fluctuations in the depth of the water layer in the field, soil moisture, crop growth stage, and meteorological factors, resulting in the system being difficult to achieve precise and efficient irrigation and drainage management. Summary of the Invention

[0003] To overcome the deficiencies of the existing irrigation optimization methods that are difficult to simultaneously take into account multi-objective optimization and have poor timeliness in the optimization process, the present invention provides a method for dynamically optimizing the irrigation and drainage strategy of paddy fields. By introducing a multi-objective optimization model and a real-time optimization mechanism, the technical problems of the traditional irrigation and drainage system with lagging response and single optimization objective are effectively solved. Compared with traditional irrigation and drainage methods, the present invention can adjust the irrigation and drainage strategy in real time according to the daily updated weather forecast, significantly improve the accuracy of irrigation and drainage, reduce water resource waste, avoid drought and flooding problems, and thus achieve more efficient water resource management and agricultural irrigation.

[0004] According to one aspect of the specification of the present invention, there is provided a method for dynamically optimizing the irrigation and drainage strategy of paddy fields, including:

[0005] Collecting the environmental parameters of the target paddy field in the current decision-making cycle;

[0006] Determining the optimization objectives to be optimized for the target paddy field and constructing a multi-objective optimization model in combination with the environmental parameters;

[0007] Using an intelligent algorithm to perform dynamic programming on the multi-objective optimization model to obtain the real-time optimized irrigation and drainage strategy for the current decision-making cycle;

[0008] Implementing the real-time optimized irrigation and drainage strategy for the current decision-making cycle;

[0009] Monitoring whether the end of the rice growth period is reached at the end of the current decision-making cycle:

[0010] Otherwise, the actual environmental parameters at the end of the acquisition decision cycle are used to correct the current state vector, and the state vector at the beginning of the next decision cycle of the target paddy field is updated through the transfer function, and the solution and implementation process of the real-time optimized irrigation and drainage strategy are repeated; if so, the loop ends, and the optimal irrigation and drainage strategy for the entire growth period of the target paddy field is obtained.

[0011] As a further implementation plan, the environmental parameters include the current growth and development stage of the crop, the crop coefficient, the water status of the paddy field, the measured meteorological data, and the weather forecast data for the preset number of days in the future.

[0012] As a further implementation plan, the construction steps of the multi-objective optimization model are specifically as follows:

[0013] Define sub-objective functions with the rainfall utilization rate, the number of irrigation and drainage times, and the yield index as the objectives to be optimized. The formula is expressed as follows:

[0014]

[0015] Among them, R represents the rainfall utilization rate; N is the number of irrigation and drainage times; Y is the yield index; represents the decision vector; , and are both sub-objective functions;

[0016] Determine the constraint conditions based on the environmental parameters of the target paddy field, including: water balance constraint, boundary constraint, and flooding / drought duration constraint;

[0017] Determine the weights of each sub-objective function to obtain the final multi-objective optimization model, which is mathematically expressed as follows:

[0018]

[0019] In the formula, , and are the weight values of the rainfall utilization rate, the number of irrigation and drainage times, and the yield index respectively, = 1.

[0020] As a further implementation plan, the steps for solving the real-time optimized irrigation and drainage strategy for the current decision cycle by dynamic programming are as follows:

[0021] Set the step size and the range of daily irrigation and drainage volume increase and decrease, and generate a candidate decision set accordingly;

[0022] Take each decision cycle with irrigation and drainage decisions in the target paddy field during the decision cycle as a single subsystem. Based on the multi-objective optimization model and the weather forecast data for a certain prediction period of the subsystem, construct the T-stage model for optimizing the paddy field irrigation and drainage strategy of the subsystem. Solve the decision set in the candidate decision set that maximizes the stage objective function value as the optimal decision set. Select the decision corresponding to this decision cycle in the optimal decision set as the real-time optimized irrigation and drainage strategy, and calculate sequentially from the front to the back according to the decision cycle order until the real-time optimized irrigation and drainage strategy for the entire decision cycle is obtained.

[0023] Among them, the stage objective function corresponding to the first decision cycle of the subsystem is expressed as:

[0024]

[0025] Among them, represents the state vector of the k-th decision cycle; is the decision vector of the k-th decision cycle; is the initial state vector; is the forecast input vector of the k-th decision cycle; T1 is the number of time periods in the forecast period of the first decision cycle; represents the function value of the multi-objective optimization model of the k-th decision cycle.

[0026] As a further implementation plan, the state vector includes: soil moisture content or water layer depth, forecast crop evapotranspiration, and forecast rainfall sequence.

[0027] As a further implementation plan, during the process of solving the real-time optimized irrigation and drainage strategy, the stage objective function of the subsequent subsystems is calculated sequentially from the front to the back according to the time period order of the decision cycle. The calculation logic is: the state vector at the end of the previous decision cycle is corrected by the collected actual environmental parameters, and the initial state vector of the next decision cycle of the target paddy field is updated based on the transfer function.

[0028] As a further implementation plan, it also includes: when the rice enters the field drying period, wait until the end of the field drying period and then enter the next decision process.

[0029] According to another aspect of this specification, a dynamic optimization system for paddy field irrigation and drainage strategy is also provided, including:

[0030] A data acquisition module that acquires the environmental parameters of the target paddy field in the current decision cycle;

[0031] A multi-objective optimization module that constructs a multi-objective optimization model for the paddy field indicators to be optimized;

[0032] A dynamic decision module that dynamically solves the multi-objective optimization model to obtain the real-time optimized irrigation and drainage strategy for the current decision cycle;

[0033] A decision implementation module that implements real-time optimized irrigation and drainage strategies for the current decision cycle;

[0034] A loop determination module that determines whether to enter the decision-making process in the next decision cycle and provides a status parameter update function;

[0035] A result output module that outputs the optimal irrigation and drainage strategies for the entire growth period of the target paddy field.

[0036] As a further implementation, the loop determination module determines whether the loop ends by monitoring the growth period of the rice. When the decision cycle reaches the end of the growth period, the loop ends.

[0037] As a further implementation, when the loop determination module monitors that the rice enters the field drying period, it waits until the end of the field drying period and then enters the next decision-making process.

[0038] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention innovatively introduces a multi-objective optimization model and a real-time optimization mechanism, effectively solving the technical problems of the traditional irrigation and drainage system with lagging response and single optimization objective. Compared with the traditional irrigation and drainage methods, the present invention can adjust the irrigation and drainage strategies in real time according to the daily updated weather forecast, significantly improving the accuracy of irrigation and drainage, reducing water resource waste, avoiding drought and flooding problems, and thus achieving more efficient water resource management and agricultural irrigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings used in the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0040] Figure 1 It is a flowchart of a method for dynamically optimizing the irrigation and drainage strategies of a paddy field provided by an embodiment of the present invention;

[0041] Figure 2 It is a schematic diagram of a system for dynamically optimizing the irrigation and drainage strategies of a paddy field provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] It should be noted that:

[0043] In the description, claims and above-mentioned drawings of the present invention, the terms "comprising", "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0044] The block diagrams shown in the drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices. The flowcharts shown in the drawings are only illustrative and do not necessarily include all content and operations / steps, nor do they have to be executed in the described order. For example, some operations / steps can be decomposed, while some operations / steps can be combined or partially combined, so the actual execution order may change according to the actual situation.

[0045] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions 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, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention. In addition, the technical features in each embodiment or a single embodiment provided by the present invention can be combined arbitrarily with each other to form a new technical solution. This combination is not restricted by the order of steps and / or the mode of structural composition, but must be based on the fact that those of ordinary skill in the art can implement it. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope required by the present invention.

[0046] The present invention provides a method for dynamically optimizing paddy field irrigation and drainage strategies, including:

[0047] Collecting the environmental parameters of the target paddy field in the current decision-making cycle;

[0048] Determining the optimization objectives of the target paddy field and constructing a multi-objective optimization model in combination with the environmental parameters;

[0049] Using an intelligent algorithm to perform dynamic programming on the multi-objective optimization model to obtain the real-time optimized irrigation and drainage strategy for the current decision-making cycle;

[0050] Implementing the real-time optimized irrigation and drainage strategy for the current decision-making cycle;

[0051] Monitor whether the end of the current decision cycle reaches the end of the rice growth period:

[0052] Otherwise, collect the actual environmental parameters at the end of the decision cycle to correct the state vector at this time, update the initial state vector of the target paddy field for the next decision cycle through the transfer function, and repeat the solution and implementation process of the real-time optimized irrigation and drainage strategy; if yes, the loop ends, and the optimal irrigation and drainage strategy for the entire growth period of the target paddy field is obtained.

[0053] Furthermore, the environmental parameters include the current growth and development stage of the crop, the crop coefficient, the water status of the paddy field, the measured meteorological data, and the weather forecast data for the preset number of days in the future.

[0054] Furthermore, the objective function can be expressed as:

[0055]

[0056]

[0057] Among them, the decision vector x = (x1, x2, x3,..., x m ) The space Ω where it is located is called the decision space, and there are P inequality constraint conditions g i (x) ≤ 0, and these constraint conditions limit the value range of the decision variable x; the space where the vector F(x) is located is the objective space.

[0058] The specific steps for constructing the multi-objective optimization model are as follows:

[0059] Define sub-objective functions with the rainfall utilization rate, the number of irrigation and drainage times, and the yield index as the objectives to be optimized. The formula is expressed as follows:

[0060]

[0061] Among them, R represents the rainfall utilization rate; N is the number of irrigation and drainage times; Y is the yield index; Represents the decision vector; , And Are all sub-objective functions.

[0062] Determine the constraint conditions based on the environmental parameters of the target paddy field, including: water balance constraint, boundary constraint, and flooding / drought duration constraint.

[0063] Specifically, the water balance constraint is:

[0064]

[0065] And Are the field water level depths at time points i and i - 1 in mm respectively; Rainfall at time point i; Evapotranspiration at time point i, Deep percolation at time point i, I is irrigation water volume, D is drainage volume;

[0066] The boundary constraints are:

[0067]

[0068] In the formula, Wilting coefficient of a certain specific crop under specific environment, Is the ridge height.

[0069] The duration constraints of being flooded / drought-stricken are:

[0070]

[0071] In the formula, Is the duration when soil moisture content is lower than the minimum water content; Is the duration when the field water level is higher than the allowable maximum flooding depth; , Are the longest drought-stricken and flooded durations respectively;

[0072] Determine the weights of each sub-objective function to obtain the final multi-objective optimization model, and the mathematical expression is as follows:

[0073]

[0074] In the formula, , And Are the weight values of rainfall utilization rate, irrigation and drainage times, and yield index respectively, = 1.

[0075] Specifically, the weight values can be selected according to the actual situation. Generally, = 1 / 3. If the target paddy field focuses on improving the rainfall utilization rate, the weight of the rainfall utilization rate can be increased, and take = 2 / 3, = = 1 / 6; if it focuses on reducing the irrigation and drainage times, the weight of the irrigation and drainage times can be increased, and take = 2 / 3, = = 1 / 6.

[0076] Furthermore, the steps to obtain the real-time optimized irrigation and drainage strategy for the current decision-making period by dynamic programming solution are:

[0077] Set the step size and the range of daily increase and decrease of irrigation and drainage volume, and generate a candidate decision set accordingly;

[0078] Take the decision-making cycle of the target paddy field as a single subsystem. Based on the multi-objective optimization model and the weather forecast data with a certain prediction period of the subsystem, construct the stage objective function of the subsystem. Solve the decision set in the candidate decision set that maximizes the function value of the stage objective function as the optimal decision set, and select the decision corresponding to this decision cycle in the optimal decision set as the real-time optimized irrigation and drainage strategy for this decision cycle.

[0079] The stage objective function of the first decision cycle is expressed as:

[0080]

[0081] Among them, represents the state vector of the k-th decision cycle; is the decision vector of the k-th decision cycle; is the initial state vector; is the forecast input vector of the k-th decision cycle; T1 is the number of time periods of the forecast period of the first decision cycle; represents the function value of the multi-objective optimization model of the k-th decision cycle.

[0082] Solve the problem to obtain the optimal strategy {x1, x2, …, x T1} under the first-round forecast data. Take x1 in the optimal decision for real-time decision-making.

[0083] Furthermore, the state vector includes: soil moisture content or water layer depth, forecasted crop evapotranspiration, and forecasted rainfall sequence.

[0084] Furthermore, during the process of repeating the solution of the real-time optimized irrigation and drainage strategy, the stage objective function of the subsequent subsystems is calculated sequentially from front to back according to the time periods of the decision cycle. The calculation logic is: the state vector at the end of the previous decision cycle is corrected by the collected actual environmental parameters, and the initial state vector of the next decision cycle of the target paddy field is updated based on the transfer function.

[0085] Specifically, after the action is executed in the state s of the t-th decision cycle, the actual environmental parameters at this time need to be collected to correct the state vector at the end of the decision cycle. Among them, the correction formula for the soil moisture content or water layer depth is:

[0086]

[0087] In the formula is the actual soil moisture content or water layer depth on the (t + 1)-th day of the irrigation and drainage cycle, mm; , and They are the actual rainfall, actual crop evapotranspiration, and deep percolation in the field within the irrigation and drainage cycle of t days, in mm. When there is a water layer in the field, the deep percolation is defaulted to 2 mm / d. When there is no water layer in the field, the deep percolation in the field is assumed to be 0.

[0088] Update the state of the next irrigation and drainage decision cycle t + 1 through the transfer function Q. The state expression is: ; where is the predicted rainfall sequence for a future period within the next irrigation and drainage decision cycle t + 1; is the predicted crop evapotranspiration within the next irrigation and drainage decision cycle t + 1; is the soil moisture content or water layer depth within the next irrigation and drainage decision cycle t + 1.

[0089] After updating the state parameters, a second-round prediction is carried out. Let the prediction period be T2 decision cycles. The system inputs the second-round prediction sequence P2. After the decision in the first decision cycle is implemented, the system state vector s is updated k . The decision model for the second round is:

[0090]

[0091] Solve the optimal strategy for this prediction data again. Then, a third-round decision is made, and so on in a loop until the decision cycle reaches the end of the growth period.

[0092] Furthermore, at the end of the t decision cycle process, wait based on the updated state or immediately enter the next decision process until the end of the growth period. Among them, when the rice enters the field drying period, the paddy field needs to dry naturally without performing irrigation and drainage actions and wait until the end of the field drying period. In other growth stages, there is no need to wait and directly enter the next decision process.

[0093] A dynamic optimization method for paddy field irrigation and drainage strategies includes the following steps:

[0094] Step 1: Collect the environmental parameters of the target paddy field in the current decision cycle. Among them, the environmental parameters include weather forecast data, actual soil moisture content or water layer depth, rice growth and development period, crop coefficient, rice variety, plant height, deep percolation, soil type and other parameters within a preset future time period. The weather forecast data in the environmental parameters is public weather forecast or numerical weather forecast data, including but not limited to temperature, wind force, rainfall, sunshine, weather type, etc.

[0095] Based on the obtained environmental parameters and the optimization objectives of the target paddy field, construct a multi-objective optimization model; Exemplarily, the objective function of the model can be expressed as:

[0096]

[0097] , , are the weight values of rainfall utilization rate, irrigation and drainage frequency, and yield reduction rate, respectively.

[0098] The stage objective function and sub-objective function can be expressed as:

[0099]

[0100] In the formula, is the rainfall utilization rate in the k-th decision period, %; is the irrigation and drainage frequency in the k-th decision period; is the yield reduction rate in the k-th decision period; is the rainfall amount in the k-th decision period, mm; is the drainage amount in the k-th growth stage, mm; is the yield reduction rate of rice after being flooded in the k-th decision period; is the yield reduction rate of rice after being drought-stricken in the k-th decision period; m represents the irrigation and drainage amount.

[0101] On the i-th day during the forecast period of the target paddy field, each water balance element in the field can be calculated using the water balance equation:

[0102]

[0103] In the formula, is the soil moisture content or water layer depth in the field before irrigation or drainage on the i-th day, mm; is the soil moisture content or water layer depth at the end of the (i - 1)-th day, mm; is the rainfall amount on the i-th day, mm; is the irrigation amount on the i-th day, mm; is the evapotranspiration amount on the i-th day; is the paddy field seepage amount; is the drainage amount on the i-th day, mm.

[0104] Exemplarily, the rice yield loss ( ) is divided into waterlogging loss and drought loss. When the water layer depth is higher than the critical waterlogging depth of rice, the waterlogging loss is calculated. When the soil moisture content is lower than the field water holding capacity, the drought loss is calculated. Otherwise, yk = 0. Among them, the calculation formula for waterlogging loss is taken as:

[0105]

[0106] In the formula, is the yield reduction rate of rice after being flooded, %; h is the percentage of waterlogging depth to plant height, h = 100% H / HR ; T is the duration of flooding, in days; H C is the critical water depth for flooding rice, in m. According to relevant literature, 20% of the rice plant height is taken as the critical flooding depth for rice; H R is the rice plant height, in m; where a, b, and c are model parameters that need to be determined by referring to Table 1 according to the rice growth and development stages.

[0107] Table 1 Recommended parameters for the rice flooding yield reduction model

[0108]

[0109] When formulating irrigation and drainage strategies considering weather forecasts, the phenomenon of waiting for rain without rain may occur, resulting in water stress and yield reduction. Therefore, in order to evaluate the impact of water stress on yield, a crop water production function is used to establish the functional relationship between water deficit at specific crop growth stages and yield. The Jensen model is used for quantification, and the drought loss calculation formula can be expressed as:

[0110]

[0111] In the formula, is the yield reduction rate after drought stress for rice; is the actual evapotranspiration; is the reference crop evapotranspiration; is the number of crop growth stages, i is the ordinal number of the crop growth stage, i = 1, 2,..., n; is for the period water deficit sensitivity index, which is determined according to the rice crop growth and development stages and varieties. The values of each rice type are determined according to the rice growth and development stages and varieties, as shown in Table 2.

[0112] Table 2 Water deficit sensitivity indices for each growth stage of early, middle, and late rice

[0113]

[0114] The crop evapotranspiration is determined by the following formula:

[0115]

[0116] In the formula, is the single crop coefficient; is the water stress coefficient, which is determined by the field capacity and the wilting coefficient of rice; is the forecast reference crop evapotranspiration, which is determined by weather forecast data.

[0117] When soil water stress occurs, , when there is no soil water stress ; When soil water stress occurs, the soil water stress coefficient is given by the following formula:

[0118]

[0119] Where, is the consumed water volume in the root zone (i.e., the water deficit relative to the field capacity), mm; is the total available water volume in the root zone, mm; is the available water volume that can be easily absorbed by the crop from the root zone, mm.

[0120] and are given by the following formula:

[0121]

[0122]

[0123] Where, is the field capacity, m 3 / m 3 ; is the wilting coefficient, m 3 / m 3 ; is the variable root zone depth, m; is the ratio of the water volume that can be consumed in the root zone before water stress occurs to the total available water volume of the soil, taking 0.2.

[0124] Step 3: Calculate the predicted crop evapotranspiration of the target paddy field according to the weather forecast data in the future preset time period and the growth and development stage of the crop; the formula for crop evapotranspiration is as follows:

[0125]

[0126] Where, K c is the crop coefficient; K s is the water stress coefficient, ET0 is the predicted reference crop evapotranspiration, mm / d; the predicted reference crop evapotranspiration is calculated by the locally calibrated HS model, and the HS model can be written in the following form:

[0127]

[0128] Where ET 0,HS is the ET0 value calculated by the HS method; the two parameters C and E are obtained through calibration; Ra is the extraterrestrial radiation, MJ / m 2 / d; and are the predicted maximum temperature and minimum temperature respectively, °C.

[0129] Decompose each decision-making cycle that requires irrigation and drainage management during the growth period into a single subsystem. Based on the obtained environmental parameters, an intelligent algorithm is used to combine the multi-objective optimization model during the prediction period of the current decision-making cycle to obtain the optimized T-stage model of the irrigation and drainage strategy for the paddy field as the stage target model of the subsystem.

[0130] Exemplarily, divide the prediction period into T stages according to the weather forecast foresight period, and the time difference Δt between adjacent stages is 1 day. Select to include P t predicted rainfall, h t soil moisture content or water layer depth within the current irrigation and drainage decision-making cycle t, ET ct predicted crop evapotranspiration within the current irrigation and drainage decision-making cycle t; s is the state vector, which is discretized, and the state difference between adjacent two states is Δs. During real-time control, the initial state s i is the state at the current moment i stage; starting from the initial state, according to the initial condition f(s0)=0 and the recurrence equation of the Tth stage, calculate backward from the front.

[0131] Let the number of periods in the first-round prediction period be T1, then the first-round decision problem is:

[0132]

[0133] Solve the problem to obtain the optimal strategy {x1, x2, …, x T1} under the first-round prediction data. Take x1 in the optimal decision for real-time decision-making.

[0134] After implementing the decision x1, conduct the second-round prediction. Let the prediction period be T2 decision-making cycles, input the second-round prediction sequence P2 into the system, and update the system state vector s k after the decision of the first decision-making cycle is implemented. The decision model for the second round is:

[0135]

[0136] Solve the optimal strategy under this prediction data again. Then conduct the third-round decision, and so on in a cycle.

[0137] Optionally, with the goal of maximizing the objective function value in step 2, optimize with a step size of 1 mm, vary the daily irrigation and drainage water volume within the range of -200~50 mm. During the optimization process, a positive value means irrigation, a negative value means drainage, and 0 means no irrigation and no drainage, that is:

[0138]

[0139] Among them, =-200mm, = 50 mm, step size Δm = 1 mm. Calculate each element of the water balance day by day, and generate a candidate decision set {X t} through the NSGA-II algorithm. Screen the optimal decision x t * according to the objective function to obtain the real-time optimal irrigation and drainage strategy.

[0140] Exemplarily, it is implemented through the PYTHON genetic algorithm library Geatpy2. The specific process is as follows: 1) Define decision variables {m1, m2,..., m T1}; 2) Define sub-objective functions , , ; 3) Define constraint conditions; 4) Initialize the parent population P, population size N = 150, and calculate the fitness of the parent population P; 5) Generate a child population Q with size N through selection, crossover, and mutation operators, and calculate the fitness of the child population Q; 6) Combine the parent population P and the child population Q to form a recombinant population R with population size 2N; 7) Perform fast non-dominated sorting and individual crowding degree calculation on the recombinant population R to generate a new parent population; 8) Perform selection, crossover, and mutation operations on the newly generated parent population to form a new child population and calculate the fitness; 9) Determine whether the termination condition (number of iterations ≥ 120) is satisfied. If it meets the condition, the optimization ends and the result is output. Otherwise, return to 5). Obtain the final irrigation strategy according to the obtained non-dominated solution set and the stage objective function.

[0141] After the decision of the current decision cycle ends, update the state of the next irrigation and drainage decision cycle through the transfer function according to the selected strategy and the current state.

[0142] Exemplarily, update the state of the next irrigation and drainage decision cycle t + 1 through the transfer function Q. The state expression ; where is the predicted rainfall sequence in a future period within the next irrigation and drainage decision cycle t + 1; is the predicted crop evapotranspiration within the next irrigation and drainage decision cycle t + 1; is the soil moisture content or water layer depth within the next irrigation and drainage decision cycle t + 1. After performing an action in state s, the environmental state parameters need to be corrected according to the actual meteorological conditions and irrigation and drainage decisions. The correction formula for the soil moisture content or water layer depth is:

[0143]

[0144] In the formula is the actual soil moisture content or water layer depth on the (t + 1)-th day of the irrigation and drainage cycle, mm; , and They are the actual rainfall, actual crop evapotranspiration, and deep percolation in the field during the irrigation and drainage cycle of t days, in mm. When there is a water layer in the field, the deep percolation is defaulted to 2 mm / d. When there is no water layer in the field, the deep percolation in the field is assumed to be 0.

[0145] Step six, determine whether it is the last irrigation and drainage decision cycle. If so, execute operation step 7; if not, return to operation step three. When the rice enters the field drying period, the paddy field needs to dry naturally without performing irrigation and drainage actions, and wait until the end of the field drying period. In other growth stages, there is no need to wait and directly enter the next decision-making process. The number of irrigation and drainage decision cycles can be set according to empirical values.

[0146] Step seven, at the end of the growth period, determine the optimal irrigation and drainage strategy for the target paddy field throughout the growth period.

[0147] The dynamic optimization method for paddy field irrigation and drainage strategy provided by the embodiment of the present invention improves the accuracy and scientificity of irrigation and drainage decision-making by considering future weather forecast data, with the goals of the highest rainfall utilization rate, the fewest irrigation and drainage times, and no reduction in crop yield, realizes the real-time optimization of irrigation and drainage strategies, has low labor intensity and low cost.

[0148] The implementation basis of each embodiment of the present invention is realized through programmed processing by a system with a processor function. Therefore, in engineering practice, the technical solutions and functions of each embodiment of the present invention are encapsulated into various modules. Based on this actual situation, on the basis of the above embodiments, the embodiment of the present invention provides a dynamic optimization system for paddy field irrigation and drainage strategy, and this system is used to execute a dynamic optimization method for paddy field irrigation and drainage strategy in the above method embodiment.

[0149] See Figure 2 , this system includes:

[0150] A data acquisition module, which acquires the environmental parameters of the target paddy field in the current decision cycle;

[0151] A multi-objective optimization module, which constructs a multi-objective optimization model for the indexes to be optimized in the paddy field;

[0152] A dynamic decision-making module, which dynamically solves the multi-objective optimization model to obtain the real-time optimized irrigation and drainage strategy in the current decision cycle;

[0153] A decision implementation module, which implements the real-time optimized irrigation and drainage strategy in the current decision cycle;

[0154] A loop determination module, which determines whether to enter the decision-making process in the next decision cycle and provides a status parameter update function;

[0155] A result output module, which outputs the optimal irrigation and drainage strategy for the target paddy field throughout the growth period.

[0156] It should be noted that the system embodiments provided by the present invention are used not only to implement the methods in the above method embodiments, but also to implement the methods in other method embodiments provided by the present invention. The difference lies only in setting corresponding functional modules. The principle is basically the same as that of the above system embodiments provided by the present invention. As long as those skilled in the art, on the basis of the above system embodiments, refer to the specific technical solutions in other method embodiments, obtain corresponding technical means by combining technical features, and the technical solutions constituted by these technical means, and on the premise of ensuring the practicability of the technical solutions, improve the system in the above system embodiments to obtain corresponding system-like embodiments for implementing the methods in other method-like embodiments.

[0157] Based on the content of the above system embodiments, as a preferred embodiment, a dynamic optimization of paddy field irrigation and drainage strategies provided in the embodiments of the present invention further includes:

[0158] The loop determination module determines whether the loop ends by monitoring the growth stage of rice. When the decision period reaches the end of the growth stage, the loop ends.

[0159] When the loop determination module monitors that the rice enters the field drying stage, it waits until the end of the field drying stage and then enters the next decision-making process.

[0160] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, located in one place, or distributed to multiple network units. Select some or all of the modules according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0161] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0162] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0163] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0164] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operating steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the functions specified in one block or multiple blocks.

[0165] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A dynamic optimization method for paddy field irrigation and drainage strategies, characterized in that Including: Collecting the environmental parameters of the target paddy field in the current decision-making cycle; Determining the optimization targets of the target paddy field, and constructing a multi-objective optimization model in combination with the environmental parameters; Using an intelligent algorithm to perform dynamic programming on the multi-objective optimization model based on the environmental parameters to obtain the real-time optimized irrigation and drainage strategy for the current decision-making cycle, and the strategy includes the type of irrigation and drainage and the change amount of the water surface height of the paddy field; Implementing the real-time optimized irrigation and drainage strategy for the current decision-making cycle; Monitoring whether the end of the current decision-making cycle reaches the end of the rice growth period: Otherwise, collect the actual environmental parameters at the end of the decision-making cycle to correct the state vector at this time, and update the initial state vector of the target paddy field for the next decision-making cycle through the transfer function, and repeat the solution and implementation process of the real-time optimized irrigation and drainage strategy; if so, the loop ends, and the optimal irrigation and drainage strategy for the entire growth period of the target paddy field is obtained.

2. The dynamic optimization method for a paddy field irrigation and drainage strategy according to claim 1, characterized in that The environmental parameters include the current growth and development stage of the crop, the crop coefficient, the water status of the paddy field, the measured meteorological data, and the weather forecast data for the preset number of days in the future.

3. The dynamic optimization method for paddy field irrigation and drainage strategy according to claim 1, characterized in that The specific steps for constructing the multi-objective optimization model are as follows: Defining sub-objective functions with the rainfall utilization rate, the number of irrigation and drainage times, and the yield index as the optimization targets, and the formula is expressed as follows: ； Among them, R represents the rainfall utilization rate; N is the number of irrigation and drainage times; Y is the yield index; represents the decision vector; , and are both sub-objective functions; Determining the constraint conditions based on the environmental parameters of the target paddy field, including: water balance constraint, boundary constraint, and flooding / drought duration constraint; Determining the weights of each sub-objective function to obtain the final multi-objective optimization model, and the mathematical expression is as follows: ； In the formula, , and are the weight values of rainfall utilization rate, irrigation and drainage frequency, and yield index respectively, = 1.

4. The dynamic optimization method for a paddy field irrigation and drainage strategy according to claim 1, characterized in that The steps for obtaining the real-time optimized irrigation and drainage strategy for the current decision-making cycle by dynamic programming are: Setting the step size and the range of daily irrigation and drainage volume increase and decrease, and generating a candidate decision set accordingly; Regarding the decision-making cycle of the target paddy field as a single subsystem, constructing the stage objective function of the subsystem according to the multi-objective optimization model and the weather forecast data of the subsystem for a certain prediction period, and solving the decision set in the candidate decision set that makes the stage objective function obtain the maximum function value as the optimal decision set, and selecting the decision corresponding to the current decision-making cycle in the optimal decision set as the real-time optimized irrigation and drainage strategy for this decision-making cycle; ； Among them, represents the state vector of the k-th decision cycle; is the decision vector of the k-th decision cycle; is the initial state vector; is the predicted input vector of the k-th decision cycle; T1 is the number of time periods of the prediction period of the first decision cycle; represents the function value of the multi-objective optimization model of the k-th decision cycle.

5. The dynamic optimization method for a paddy field irrigation and drainage strategy according to claim 4, wherein, The state vector includes: soil moisture content or water layer depth, predicted crop evapotranspiration, and predicted rainfall sequence.

6. The dynamic optimization method for a paddy field irrigation and drainage strategy according to claim 5, wherein, During the repeated solution process of the real-time optimized irrigation and drainage strategy, the stage objective function of the subsequent subsystem is calculated sequentially from front to back according to the time period of the decision-making cycle, and the calculation logic is: the state vector at the end of the previous decision-making cycle is corrected by the collected actual environmental parameters, and the initial state vector of the target paddy field for the next decision-making cycle is updated based on the transfer function.

7. The dynamic optimization method for a paddy field irrigation and drainage strategy according to claim 1, characterized in that Also including: When it is monitored that the decision-making cycle enters the rice field drying period, there is no need to obtain the irrigation and drainage strategy, and wait until the end of the drying period and then enter the next decision-making process.

8. A dynamic optimization system for paddy field irrigation and drainage strategies, characterized in that, Used to implement the dynamic optimization method of a paddy field irrigation and drainage strategy described in any one of claims 1-8, including: A data collection module that collects the environmental parameters of the target paddy field in the current decision-making cycle; A multi-objective optimization module that constructs a multi-objective optimization model for the optimization indicators of the paddy field; A dynamic decision-making module that dynamically solves the multi-objective optimization model to obtain the real-time optimized irrigation and drainage strategy for the current decision-making cycle; Decision implementation module, which implements the real-time optimized irrigation and drainage strategy for the current decision cycle; Circulation determination module, which determines whether to enter the decision-making process in the next decision cycle and provides the function of updating status parameters; Result output module, which outputs the optimal irrigation and drainage strategy for the entire growth period of the target paddy field.

9. The dynamic optimization system for paddy field irrigation and drainage strategies according to claim 8, wherein, The circulation determination module determines whether the circulation ends by monitoring the growth period of rice. When the decision cycle reaches the end of the growth period, the circulation ends.

10. A dynamic optimization system for paddy field irrigation and drainage strategies according to claim 9, characterized in that, When the circulation determination module monitors that the rice enters the field drying period, it waits until the end of the field drying period and then enters the next decision-making process.

Images