A dynamic optimization method and system for rice field irrigation and drainage strategies

Abstract

The present invention discloses a method and system for dynamically optimizing a rice field irrigation and drainage strategy, comprising: collecting environmental parameters of a target rice field in a current decision cycle; determining an objective to be optimized for the target rice field, and constructing a multi-objective optimization model in combination with the environmental parameters; using an intelligent algorithm to dynamically program and solve the multi-objective optimization model to obtain a real-time optimized irrigation and drainage strategy for the current decision cycle; implementing the real-time optimized irrigation and drainage strategy for the current decision cycle; monitoring whether the end of the rice growth period is reached at the end of the current decision cycle: otherwise, collecting actual environmental parameters at the end of the decision cycle to correct a state vector at this time, and updating an initial state vector of the target rice field in the next decision cycle through a transfer function, and repeating the process of solving and implementing the real-time optimized irrigation and drainage strategy; if so, the cycle ends, and the optimal irrigation and drainage strategy for the entire 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 in particular to a method and system for dynamically optimizing rice field irrigation and drainage strategies. Background Art

[0002] Traditional irrigation methods usually rely on farmers' experience to make decisions and cannot be effectively adjusted dynamically according to real-time meteorological changes. This experience-based irrigation model is difficult to cope with the impact of weather changes on crop demand and easily leads to waste of water resources. In addition, traditional irrigation optimization methods are mostly single-objective optimization, usually focusing on only one aspect of the effect, such as water saving or increasing production, but it is difficult to take into account water conservation, crop yield improvement and operational efficiency optimization at the same time, which makes it difficult to maximize the overall benefits. Moreover, most irrigation systems use static models. These models cannot flexibly respond to real-time changes in the field environment, such as field water layer depth, soil moisture, crop growth stage and fluctuations in meteorological factors, making it difficult for the system to achieve accurate and efficient irrigation and drainage management. Summary of the Invention

[0003] To overcome the shortcomings of existing irrigation optimization methods, which struggle to simultaneously address multiple optimization objectives and suffer from poor timeliness, the present invention provides a dynamic optimization method for rice field irrigation and drainage strategies. By introducing a multi-objective optimization model and real-time optimization mechanism, this method effectively addresses the technical challenges of delayed response and single optimization objectives in traditional irrigation and drainage systems. Compared to traditional irrigation and drainage methods, this method can adjust irrigation and drainage strategies in real time based on daily weather forecasts, significantly improving irrigation and drainage accuracy, reducing water waste, and avoiding droughts and flooding, thereby achieving more efficient water resource management and agricultural irrigation.

[0004] According to one aspect of the present invention, a method for dynamically optimizing a rice field irrigation and drainage strategy is provided, comprising:

[0005] Collect environmental parameters of the target rice fields in the current decision cycle;

[0006] Determine the target to be optimized for the target rice field and build a multi-objective optimization model based on environmental parameters;

[0007] Intelligent algorithms are used to dynamically solve the multi-objective optimization model to obtain the real-time optimized irrigation and drainage strategy for the current decision cycle;

[0008] Implement real-time optimized irrigation and drainage strategies for the current decision cycle;

[0009] Monitor whether the rice growing period has reached its end at the end of the current decision cycle:

[0010] Otherwise, the actual environmental parameters at the end of the decision cycle are collected to correct the state vector at this time, and the initial state vector of the target rice field in the next decision cycle 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 cycle ends and the optimal irrigation and drainage strategy for the target rice field during the entire growth period is obtained.

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

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

[0013] The sub-objective function is defined with rainfall utilization rate, irrigation and drainage times, and yield index as the optimization targets. The formula is as follows:

[0014]

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

[0016] Determine constraints based on the environmental parameters of the target rice field, including water balance constraints, boundary constraints, and flooding / drought duration constraints;

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

[0018]

[0019] Where, 、 and are the weights of rainfall utilization rate, irrigation and drainage times, and yield index, respectively. =1.

[0020] As a further implementation scheme, the steps of dynamically solving the irrigation and drainage strategy for the current decision cycle in real time are as follows:

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

[0022] Each decision cycle of the target rice field with irrigation and drainage decisions within the decision cycle is regarded as a single subsystem. The T-stage model of the subsystem's rice field irrigation and drainage strategy optimization is constructed based on the multi-objective optimization model and the weather forecast data of a certain forecast period of the subsystem. The decision set in the candidate decision set that makes the stage objective function obtain the maximum function value is solved as the optimal decision set. The decision corresponding to this decision cycle in the optimal decision set is selected as the real-time optimized irrigation and drainage strategy, and the decision cycle sequence is deduced from the front to the back until the real-time optimized irrigation and drainage strategy of the entire decision cycle is obtained.

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

[0024]

[0025] in, represents the state vector of the kth decision cycle; is the decision vector of the kth decision cycle; is the initial state vector; is the forecast input vector of the kth decision cycle; T1 is the number of forecast periods in the first decision cycle; Represents the function value of the multi-objective optimization model in the kth decision cycle.

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

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

[0028] As a further implementation plan, it also includes: when the rice enters the field drying period, waiting until the field drying period ends to enter the next decision-making process.

[0029] According to another aspect of the present specification, a rice field irrigation and drainage strategy dynamic optimization system is provided, comprising:

[0030] Data collection module, which collects environmental parameters of the target rice field during the current decision cycle;

[0031] Multi-objective optimization module, building a multi-objective optimization model for rice field indicators to be optimized;

[0032] Dynamic decision-making module, dynamically solves the multi-objective optimization model and obtains the real-time optimized irrigation and drainage strategy for the current decision cycle;

[0033] Decision implementation module, which implements the real-time optimized irrigation and drainage strategy of the current decision cycle;

[0034] The cycle determination module determines whether to enter the decision process in the next decision cycle and provides the state parameter update function;

[0035] The result output module outputs the optimal irrigation and drainage strategy for the target rice field during its entire growth period.

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

[0037] As a further implementation scheme, the cyclic determination module monitors when the rice enters the field drying period and waits until the field drying period ends before entering the next decision process.

[0038] Compared with existing technologies, the present invention offers significant advantages: It innovatively introduces a multi-objective optimization model and real-time optimization mechanism, effectively addressing the technical challenges of delayed response and single optimization objectives in traditional irrigation and drainage systems. Compared with traditional irrigation and drainage methods, the present invention can adjust irrigation and drainage strategies in real time based on daily weather forecasts, significantly improving irrigation and drainage accuracy, reducing water waste, and avoiding droughts and flooding, thereby achieving more efficient water resource management and agricultural irrigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief introduction will be given below to the drawings used in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 A schematic diagram of a flow chart of a method for dynamic optimization of paddy field irrigation and drainage strategies provided by an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of a dynamic optimization system for rice field irrigation and drainage strategies provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] It should be noted that:

[0043] The terms "including" and "having" and any variations thereof in the description and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions, for example, a process, method, system, product or apparatus that includes a series of steps or units is not necessarily limited to the steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

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

[0045] In order to make the purpose, 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, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, the technical features in the various embodiments or single embodiments provided by the present invention are arbitrarily combined with each other to form a new technical solution. This combination is not restricted by the sequence of steps and / or structural composition mode, but must be based on the ability of ordinary technicians in this field to implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that this combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

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

[0047] Collect environmental parameters of the target rice fields in the current decision cycle;

[0048] Determine the target to be optimized for the target rice field and build a multi-objective optimization model based on environmental parameters;

[0049] Intelligent algorithms are used to dynamically solve the multi-objective optimization model to obtain the real-time optimized irrigation and drainage strategy for the current decision cycle;

[0050] Implement real-time optimized irrigation and drainage strategies for the current decision cycle;

[0051] Monitor whether the rice growing period has reached its end at the end of the current decision cycle:

[0052] Otherwise, the actual environmental parameters at the end of the decision cycle are collected to correct the state vector at this time, and the initial state vector of the target rice field in the next decision cycle 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 cycle ends and the optimal irrigation and drainage strategy for the target rice field during the entire growth period is obtained.

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

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

[0055]

[0056]

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

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

[0059] The sub-objective function is defined with rainfall utilization rate, irrigation and drainage times, and yield index as the optimization targets. The formula is as follows:

[0060]

[0061] Among them, R represents 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] Constraints are determined based on the environmental parameters of the target rice field, including water balance constraints, boundary constraints, and flooding / drought duration constraints.

[0063] Specifically, the water balance constraint is:

[0064]

[0065] and are the field water level depths at time points i and i-1, respectively; is the rainfall at time point i; is the evaporation and transpiration at time point i, is the deep seepage at time point i, I is the irrigation water volume, and D is the drainage volume;

[0066] The boundary constraints are:

[0067]

[0068] Where, is the wilting coefficient of a specific crop under specific conditions. The height of the ridge.

[0069] The duration of flooding / drought is constrained as follows:

[0070]

[0071] Where, is the duration of time when the soil moisture content is lower than the minimum moisture content; The duration that the field water level is higher than the maximum allowable flooding depth; 、 The longest drought and flooding durations respectively;

[0072] Determine the weight of each sub-objective function and obtain the final multi-objective optimization model, which is mathematically expressed as follows:

[0073]

[0074] Where, 、 and are the weights of rainfall utilization rate, irrigation and drainage times, and yield index, respectively. =1.

[0075] Specifically, the weight value can be selected according to the actual situation. Generally, =1 / 3. If the target rice fields focus on improving rainfall utilization efficiency, the weight of rainfall utilization efficiency can be increased, and the =2 / 3, = =1 / 6; focusing on reducing the number of irrigation and drainage times can increase the weight of irrigation and drainage times, taking =2 / 3, = =1 / 6.

[0076] Furthermore, the steps of dynamic programming to obtain the real-time optimized irrigation and drainage strategy for the current decision cycle are as follows:

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

[0078] The decision cycle of the target rice field is regarded as a single subsystem. The stage objective function of the subsystem is constructed according to the multi-objective optimization model and the weather forecast data of a certain forecast period of the subsystem. The decision set in the candidate decision set that makes the stage objective function obtain the maximum function value is solved as the optimal decision set. The decision corresponding to this decision cycle in the optimal decision set is selected as the real-time optimized irrigation and drainage strategy for this decision cycle.

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

[0080]

[0081] in, represents the state vector of the kth decision cycle; is the decision vector of the kth decision cycle; is the initial state vector; is the forecast input vector of the kth decision cycle; T1 is the number of forecast periods in the first decision cycle; Represents the function value of the multi-objective optimization model in the kth decision cycle.

[0082] Solve the problem and get the optimal strategy {x1, x2, …, x T1}. Take x1 from the optimal decision and make a real-time decision.

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

[0084] Furthermore, in the process of solving the repeated real-time optimized irrigation and drainage strategy, the stage objective functions of the subsequent subsystems are calculated from the front to the back in the order of 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 actual environmental parameters collected, and the initial state vector of the target rice field in the next decision cycle is updated based on the transfer function.

[0085] Specifically, after the action in state s is completed in the tth 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. The correction formula for soil moisture content or water layer depth is:

[0086]

[0087] In the formula is the actual soil moisture content or water layer depth on day t+1 of the irrigation and drainage cycle, mm; , and are the actual rainfall, actual crop evapotranspiration, and deep field seepage during the irrigation and drainage cycle (t days), respectively, in mm. When there is a water layer in the field, the default deep field seepage is 2 mm / d. When there is no water layer in the field, the default deep field seepage is 0.

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

[0089] After the state parameters are updated, the second round of forecasting is carried out. The forecast period is set to T2 decision cycles. The system inputs the second round of forecast sequence P2. After the decision of the first decision cycle is implemented, the system state vector s is updated. k The decision model for the second round is:

[0090]

[0091] The optimal strategy under this forecast data is solved again. Then the third round of decision-making is carried out, and this cycle continues until the decision-making cycle reaches the end of the reproductive period.

[0092] After the tth decision cycle ends, the system waits or immediately enters the next decision process based on the updated state until the end of the growing season. During the rice drying period, the paddy field is left to dry naturally, eliminating the need for irrigation or drainage. The system waits until the drying period ends. For the remaining growing stages, the system proceeds directly to the next decision process without waiting.

[0093] A method for dynamically optimizing rice field irrigation and drainage strategies comprises the following steps:

[0094] Step 1: Collect environmental parameters for the target rice field during the current decision cycle. These parameters include weather forecast data for a preset future time period, actual soil moisture content or water depth, rice growth and development period, crop coefficient, rice variety, plant height, deep seepage, soil type, and other parameters. Weather forecast data for these environmental parameters is public weather forecast or numerical weather forecast data, including but not limited to temperature, wind speed, rainfall, sunshine, and weather type.

[0095] Based on the obtained environmental parameters and the target to be optimized of the target rice field, a multi-objective optimization model is constructed. For example, the objective function of the model can be expressed as:

[0096]

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

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

[0099]

[0100] Where, is the rainfall utilization rate in the kth decision cycle, %; is the number of irrigation and drainage times in the kth decision cycle; is the production reduction rate in the k-th decision cycle; is the rainfall in the kth decision cycle, mm; is the water discharge at the kth growth stage, mm; is the rice yield reduction rate after flooding in the kth decision cycle; is the rice yield reduction rate after drought in the kth decision cycle; m represents the irrigation drainage volume.

[0101] On day i within the target rice field forecast period, the water balance factors in the field can be derived using the water balance equation:

[0102]

[0103] Where, is the soil moisture content or water layer depth in the field before irrigation or drainage on day i, mm; is the soil moisture content or water layer depth in the field at the end of day i-1, mm; is the rainfall on day i, mm; is the amount of irrigation on day i, mm; is the evaporation and transpiration on day i; is the leakage of rice fields; is the water displacement on day i, mm.

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

[0105]

[0106] Where, is the rice yield reduction rate after flooding, %; h is the percentage of flooding depth to plant height, h = 100%·H / H R; T is the duration of flooding, days; H C is the critical water depth of rice flooding, m. According to relevant literature, 20% of the rice plant height is taken as the critical water depth of rice flooding; H R is the rice plant height, m; a, b, c are model parameters that need to be determined according to Table 1 according to the rice growth and development period.

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

[0108]

[0109] When considering weather forecasts when formulating irrigation and drainage strategies, it's possible to wait for rain without irrigation, leading to water stress and yield reduction. Therefore, to assess the impact of water stress on yield, a crop water production function was used to establish a functional relationship between water deficit and yield at specific crop growth stages. Using the Jensen model to quantify this, the formula for calculating drought losses can be expressed as:

[0110]

[0111] Where, is the rice yield reduction rate after drought; is the actual evapotranspiration; is the reference crop evapotranspiration; is the crop growth stage number, i is the crop growth stage ordinal number, i=1,2,…,n; For the The water deficit sensitivity index is determined according to the rice crop growth and development period and variety. The values ​​are determined according to the rice growth and development period and variety, as shown in Table 2.

[0112] Table 2 Water deficit sensitivity index at different growth stages of early, middle and late rice

[0113]

[0114] Crop evapotranspiration is determined by the following formula:

[0115]

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

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

[0118]

[0119] Where, is the amount of water consumed in the root zone (i.e., water deficit relative to field capacity), mm; is the total available water in the root zone, mm; It is the effective amount of water that crops can easily absorb from the root layer, mm.

[0120] and It is given by:

[0121]

[0122]

[0123] Where, is the field water capacity, m 3 / m 3 ; is the wilting coefficient, m 3 / m 3 ; is the varying root zone depth, m; It is the ratio of the amount of water that can be consumed in the root zone before water stress occurs to the total available water in the soil, which is taken as 0.2.

[0124] Step 3: Calculate the predicted crop evapotranspiration of the target rice field based on the weather forecast data for the target rice field within a preset time period in the future 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 forecast reference crop evapotranspiration, mm / d; the forecast reference crop evapotranspiration is calculated by the locally calibrated HS model, which can be expressed as follows:

[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 The predicted maximum and minimum temperatures are °C, respectively.

[0129] Each decision cycle requiring irrigation and drainage management during the growing period is decomposed into a single subsystem. Based on the acquired environmental parameters, an intelligent algorithm is used in combination with a multi-objective optimization model within the current decision cycle forecast period to obtain the T-stage model for optimizing the irrigation and drainage strategy of rice fields as the stage objective model of the subsystem.

[0130] For example, the forecast period is divided into T stages according to the weather forecast period, and the time difference Δt between adjacent stages is 1 day. t Forecast rainfall, h t Soil moisture content or water layer depth, ET in the current irrigation and drainage decision cycle t ct The predicted crop evapotranspiration in the current irrigation and drainage decision cycle t; s is the state vector, which is discretized and the state difference between two adjacent states is Δs. In real-time control, the initial state s i is the state of stage i at the current moment; starting from the initial state, according to the initial condition f(s0)=0 and the recursive equation of stage T, it is calculated from front to back.

[0131] Assuming the number of time periods in the first round of forecast period is T1, then the first round decision problem is:

[0132]

[0133] Solve the problem and get the optimal strategy {x1, x2, …, x T1}. Take x1 from the optimal decision and make a real-time decision.

[0134] After the decision x1 is implemented, the second round of forecasting is carried out. The forecast period is set to T2 decision cycles. The system inputs the second round of forecast sequence P2. After the decision of the first decision cycle is implemented, the system state vector s is updated. k The decision model for the second round is:

[0135]

[0136] The optimal strategy under this forecast data is solved again. Then the third round of decision making is carried out, and the cycle continues.

[0137] Optionally, the objective function value in step 2 is maximized, and the optimization is performed with a step size of 1 mm. The daily irrigation and drainage water volume varies within a range of -200 to 50 mm. During the optimization process, a positive value indicates irrigation, a negative value indicates drainage, and 0 indicates neither irrigation nor drainage, that is:

[0138]

[0139] in, =-200mm, =50mm, step size Δm=1mm. Calculate the water balance elements daily and generate the candidate decision set {X t}, select the optimal decision x according to the objective function t *, obtain real-time optimal irrigation and drainage strategies.

[0140] For example, it is implemented by using the Python genetic algorithm tool library Geatpy2. The specific process is as follows: 1) Define the decision variables {m1, m2, ..., m T1}; 2) Define the sub-objective function , , 3) Define constraints; 4) Initialize the parent population P with a population size of N = 150 and calculate the fitness of the parent population P; 5) Generate a child population Q of size N through selection, crossover, and mutation operators and calculate the fitness of the child population Q; 6) Merge the parent population P and child population Q to form a recombinant population R of size 2N; 7) Perform fast non-dominated sorting and individual crowding calculation on the recombinant population R to generate a new parent population; 8) Perform selection, crossover, and mutation on the newly generated parent population to form a new child population and calculate its fitness; 9) Determine whether the termination condition (number of iterations ≥ 120) is met. If so, the optimization ends and the result is output; otherwise, return to step 5. The final irrigation strategy is obtained based on the obtained non-inferior solution set and the stage objective function.

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

[0142] For example, the state of the next irrigation and drainage decision cycle t+1 is updated by the transfer function Q. State expression ;in is the predicted rainfall sequence for a period of time in the next irrigation and drainage decision cycle t+1; The predicted crop evapotranspiration in the next irrigation and drainage decision cycle t+1; is the soil moisture content or water layer depth in the next irrigation and drainage decision cycle t+1. After the action is executed 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 soil moisture content or water layer depth is:

[0143]

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

[0145] Step 6: Determine whether this is the last irrigation and drainage decision cycle. If so, proceed to step 7; if not, return to step 3. When the rice enters the drying period, the paddy field is allowed to dry naturally, eliminating the need for irrigation and drainage. Wait until the drying period ends. For the remaining growth stages, the next decision process proceeds directly without waiting. The number of irrigation and drainage decision cycles can be set based on experience.

[0146] Step seven: At the end of the growing period, determine the optimal irrigation and drainage strategy for the target rice field throughout its growing period.

[0147] The dynamic optimization method for rice field irrigation and drainage strategies provided by the embodiment of the present invention takes into account future weather forecast data, with the goal of maximizing rainfall utilization, minimizing irrigation and drainage times, and ensuring no reduction in crop yields. This improves the accuracy and scientific nature of irrigation and drainage decision-making, achieves real-time optimization of irrigation and drainage strategies, and has low labor intensity and low cost.

[0148] The implementation of each embodiment of the present invention is based on programmed processing by a system with processor functionality. Therefore, in practical engineering, the technical solutions and functions of each embodiment of the present invention are encapsulated into various modules. Based on this reality, and in addition to the aforementioned embodiments, an embodiment of the present invention provides a system for dynamically optimizing rice field irrigation and drainage strategies. This system is used to implement a method for dynamically optimizing rice field irrigation and drainage strategies described in the aforementioned method embodiments.

[0149] See also Figure 2 , the system comprises:

[0150] Data collection module, which collects environmental parameters of the target rice field during the current decision cycle;

[0151] Multi-objective optimization module, building a multi-objective optimization model for rice field indicators to be optimized;

[0152] Dynamic decision-making module, dynamically solves the multi-objective optimization model and obtains the real-time optimized irrigation and drainage strategy for the current decision cycle;

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

[0154] The cycle determination module determines whether to enter the decision process in the next decision cycle and provides the state parameter update function;

[0155] The result output module outputs the optimal irrigation and drainage strategy for the target rice field during its entire growth period.

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

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

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

[0159] The cyclic determination module monitors when the rice enters the field drying period and waits until the field drying period ends before entering the next decision process.

[0160] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, located in one place or distributed across multiple network units. Depending on practical needs, some or all of these modules may be selected to achieve the objectives of this embodiment. Persons of ordinary skill in the art will understand and implement these embodiments without inventive effort.

[0161] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0162] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes 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 a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0163] These computer program instructions may 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, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0164] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0165] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A method for dynamic optimization of rice field irrigation and drainage strategy, characterized in that: include: Collect environmental parameters of the target rice fields in the current decision cycle; Determine the target to be optimized for the target rice field and build a multi-objective optimization model based on environmental parameters; Intelligent algorithms are used to dynamically solve the multi-objective optimization model to obtain the real-time optimized irrigation and drainage strategy for the current decision cycle; Set the step size and daily irrigation and drainage increase and decrease range, and generate candidate decision sets accordingly; The decision cycle of the target rice field is regarded as a single subsystem. The subsystem's stage objective function is constructed based on the multi-objective optimization model and the weather forecast data of the subsystem for a certain forecast period. The decision set in the candidate decision set that maximizes the stage objective function is solved as the optimal decision set. The decision corresponding to the current decision cycle in the optimal decision set is selected as the real-time optimized irrigation and drainage strategy for this decision cycle. The objective function of the first decision cycle is expressed as: ； in, represents the state vector of the kth decision cycle; is the decision vector of the kth decision cycle; is the initial state vector; is the forecast input vector of the kth decision cycle; T1 is the number of forecast periods in the first decision cycle; represents the function value of the multi-objective optimization model in the k-th decision cycle; Solve the optimal strategy {x1, x2, …, x T1 }, take x1 in the optimal strategy to make real-time decisions; Implement real-time optimized irrigation and drainage strategies for the current decision cycle; Monitor whether the rice growing period has reached its end at the end of the current decision cycle: Otherwise, the actual environmental parameters at the end of the decision cycle are collected to correct the state vector at this time, and the initial state vector of the target rice field in the next decision cycle 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 cycle ends and the optimal irrigation and drainage strategy for the target rice field during the entire growth period is obtained.

2. A method for dynamic optimization of 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, crop coefficient, paddy field moisture conditions, measured meteorological data and weather forecast data for a preset number of days in the future.

3. The method for dynamic optimization of paddy field irrigation and drainage strategy according to claim 1, characterized in that: The steps for constructing the multi-objective optimization model are specifically as follows: The sub-objective function is defined with rainfall utilization rate, irrigation and drainage times, and yield index as the optimization targets. The formula is as follows: ； Among them, R represents rainfall utilization rate; N is the number of irrigation and drainage times; Y is the yield index; represents the decision vector; , and They are all sub-objective functions; Determine constraints based on the environmental parameters of the target rice field, including water balance constraints, boundary constraints, and flooding / drought duration constraints; Determine the weight of each sub-objective function and obtain the final multi-objective optimization model, which is mathematically expressed as follows: ； Where, 、 and are the weights of rainfall utilization rate, irrigation and drainage times, and yield index, respectively. =1.

4. A method for dynamic optimization of paddy field irrigation and drainage strategy according to claim 1, characterized in that: The state vector includes: soil moisture content or water layer depth, predicted crop evapotranspiration and predicted rainfall sequence.

5. A method for dynamic optimization of paddy field irrigation and drainage strategy according to claim 4, characterized in that: In the process of solving the repeated real-time optimized irrigation and drainage strategy, the stage objective functions of the subsequent subsystems are calculated sequentially from the front to the back in the order of the decision cycles. The calculation logic is as follows: the state vector at the end of the previous decision cycle is corrected by the actual environmental parameters collected, and the initial state vector of the target rice field in the next decision cycle is updated based on the transfer function.

6. A method for dynamic optimization of paddy field irrigation and drainage strategy according to claim 1, characterized in that: Also includes: When it is detected that the decision cycle enters the rice drying period, there is no need to obtain the irrigation and drainage strategy, and the next decision process can be entered after the rice drying period ends.

7. A dynamic optimization system for rice field irrigation and drainage strategy, characterized in that: A method for dynamically optimizing a rice field irrigation and drainage strategy according to any one of claims 1 to 6, comprising: Data collection module, which collects environmental parameters of the target rice field during the current decision cycle; Multi-objective optimization module, building a multi-objective optimization model for rice field indicators to be optimized; The dynamic decision-making module dynamically solves the multi-objective optimization model to obtain the real-time optimized irrigation and drainage strategy for the current decision cycle; sets the step size and daily irrigation and drainage volume increase and decrease range, and generates a candidate decision set based on this; The decision cycle of the target rice field is regarded as a single subsystem. The subsystem's stage objective function is constructed based on the multi-objective optimization model and the weather forecast data of the subsystem for a certain forecast period. The decision set in the candidate decision set that maximizes the stage objective function is solved as the optimal decision set. The decision corresponding to the current decision cycle in the optimal decision set is selected as the real-time optimized irrigation and drainage strategy for this decision cycle. The objective function of the first decision cycle is expressed as: ； in, represents the state vector of the kth decision cycle; is the decision vector of the kth decision cycle; is the initial state vector; is the forecast input vector of the kth decision cycle; T1 is the number of forecast periods in the first decision cycle; represents the function value of the multi-objective optimization model in the k-th decision cycle; Solve the optimal strategy {x1, x2, …, x T1 }, take x1 in the optimal strategy to make real-time decisions; Decision implementation module, which implements the real-time optimized irrigation and drainage strategy of the current decision cycle; The cycle determination module determines whether to enter the decision process in the next decision cycle and provides the state parameter update function; The result output module outputs the optimal irrigation and drainage strategy for the target rice field during its entire growth period.

8. A rice field irrigation and drainage strategy dynamic optimization system according to claim 7, characterized in that: The cycle determination module determines whether the cycle is finished by monitoring the growth period of rice. When the decision cycle reaches the end of the growth period, the cycle is finished.

9. A rice field irrigation and drainage strategy dynamic optimization system according to claim 8, characterized in that: When the cyclic determination module monitors that the rice has entered the field drying period, it waits until the field drying period ends before entering the next decision-making process.

Images