Irrigation multi-objective decision method and device based on water conversion process

Abstract

The application provides an irrigation multi-objective decision-making method and device based on a water conversion process, which comprises the following steps: acquiring meteorological data, groundwater data, soil water data and water quality pollution data of an irrigation unit in a crop growth period, and acquiring a crop planting structure of the irrigation unit; inputting the meteorological data, the groundwater data, the soil water data, the water quality pollution data and the crop planting structure into a multi-objective simulation optimization coupling model to obtain target irrigation information of the irrigation unit output by the multi-objective simulation optimization coupling model; wherein the target irrigation information comprises a target irrigation area, a target irrigation time and a target irrigation water quantity, and the multi-objective simulation optimization coupling model is constructed based on a water conversion process of irrigation water, soil water and groundwater of the irrigation unit. The method improves the temporal and spatial optimization water distribution precision of irrigation water by using the multi-objective simulation optimization coupling model established based on the water conversion process, and promotes the efficient use of agricultural water resources and the ecological and sustainable development.

Description

Technical Field

[0001] This invention relates to the field of agricultural water conservancy engineering technology, and in particular to a multi-objective decision-making method and apparatus for irrigation based on water conversion processes. Background Technology

[0002] Against the backdrop of a global food crisis, water scarcity crisis, pressure from continuous population growth, and an increasingly prominent contradiction between water supply and demand, the optimized allocation of agricultural irrigation water is a key approach to the efficient utilization of agricultural water resources. In the arid and semi-arid regions of Northwest China, due to low rainfall and uncertainty, water resources have become a major factor limiting crop yields in traditional surface water irrigation areas. Optimizing water resource allocation is of paramount importance for increasing crop yields in arid regions and controlling ecological degradation.

[0003] Currently, most irrigation water allocation studies in agricultural production systems focus on single-objective optimization of water resources, crop yield, or land resources. Such studies often overlook other aspects, leading to an excessive pursuit of economic benefits. Multi-objective studies merely simplify agricultural hydrological processes, neglecting the integrity, coordination, and complexity of agricultural production systems, and thus failing to obtain irrigation water allocation schemes that meet the scientific allocation of water resources. Summary of the Invention

[0004] This invention provides a multi-objective decision-making method and apparatus for irrigation based on water conversion processes, which addresses the shortcomings of existing technologies in achieving scientific allocation of irrigation water.

[0005] This invention provides a multi-objective decision-making method for irrigation based on water transformation processes, comprising:

[0006] Acquire meteorological data, groundwater data, soil water data, and water pollution data of the irrigation unit during the crop growth period, and acquire the crop planting structure of the irrigation unit;

[0007] The meteorological data, groundwater data, soil water data, water pollution data, and crop planting structure are input into a multi-objective simulation optimization coupling model to obtain the target irrigation information of the irrigation unit output by the target simulation optimization coupling model.

[0008] The target irrigation information includes the target irrigation area, target irrigation time, and target irrigation water volume. The multi-objective simulation optimization coupling model is constructed based on the water transformation process of irrigation water, soil water, and groundwater in the irrigation unit.

[0009] According to the present invention, a multi-objective decision-making method for irrigation based on water transformation processes is provided, wherein the multi-objective simulation optimization coupled model is established through the following steps:

[0010] Couple the first simulation model and the second optimization model to establish a multi-objective function based on the crop economic benefits, crop irrigation yield and water pollution level of the irrigation unit. The multi-objective simulation optimization coupled model is established with constraints on the crop growth water consumption, soil water balance, groundwater balance, crop yield and water pollution index of the irrigation unit.

[0011] The first simulation model is constructed based on crop data, water data, and environmental data of the irrigation unit, the second optimization model is constructed based on irrigation district water allocation data of the irrigation unit, and the source and sink terms of the multi-objective simulation optimization coupling model are determined based on rainfall data, irrigation data, channel seepage data, and groundwater evaporation data.

[0012] According to the present invention, a multi-objective decision-making method for irrigation based on water transformation processes is provided, wherein establishing a multi-objective function based on the crop economic benefits, crop irrigation yield, and water pollution level of the irrigation unit includes:

[0013] With the goal of maximizing the economic benefits of crops in the entire irrigation district, a first objective function is constructed, wherein the entire irrigation district includes multiple irrigation units;

[0014] A second objective function is constructed with the goal of maximizing crop irrigation yield in the entire irrigation district.

[0015] A third objective function is constructed with the goal of minimizing the water pollution level of the entire irrigation area.

[0016] According to the present invention, a multi-objective decision-making method for irrigation based on water transformation processes includes inputting meteorological data, groundwater data, soil water data, water pollution data, and crop planting structure into a multi-objective simulation optimization coupling model to obtain the target irrigation information of the irrigation unit output by the target simulation optimization coupling model, comprising:

[0017] The meteorological data, groundwater data, soil water data, water pollution data, and crop planting structure are input into the multi-objective simulation optimization coupling model;

[0018] By introducing NSGA-II with an elite strategy and a multi-objective fuzzy optimization method, the solution of the multi-objective simulation optimization coupled model is transformed into solving the Pareto front of the solution space and obtaining the multi-objective scheme after optimization decision, thereby determining the target irrigation information.

[0019] According to the present invention, an irrigation multi-objective decision-making method based on water transformation process is provided. This method introduces NSGA-II with elitist strategy and a multi-objective fuzzy optimization method, transforming the solution of the multi-objective simulation optimization coupled model into solving the Pareto front of the solution space and obtaining the multi-objective scheme after optimization decision-making, thereby determining the target irrigation information, including:

[0020] Based on the NSGA-II with elite strategy and the multi-objective fuzzy optimization method, the optimal irrigation set is obtained. The optimal irrigation set includes the optimal Pareto front corresponding to the maximum crop economic benefit, the maximum crop irrigation yield, and the minimum water pollution. The multi-objective scheme optimization decision is then performed. The NSGA-II has adaptive crossover probability and mutation probability.

[0021] Based on the preferred irrigation set, the target irrigation information is determined.

[0022] According to the present invention, an irrigation multi-objective decision-making method based on water conversion process is provided, wherein the irrigation unit is determined based on canal system distribution information, which includes the distribution information of irrigation main canals, branch canals and tributary canals.

[0023] The present invention also provides an irrigation multi-objective decision-making device based on water conversion processes, comprising:

[0024] The acquisition module is used to acquire meteorological data, groundwater data, soil water data and water pollution data of the irrigation unit during the crop growth period, and to acquire the crop planting structure of the irrigation unit.

[0025] The processing module is used to input the meteorological data, the groundwater data, the soil water data, the water pollution data, and the crop planting structure into a multi-objective simulation optimization coupling model to obtain the target irrigation information of the irrigation unit output by the target simulation optimization coupling model;

[0026] The target irrigation information includes the target irrigation area, target irrigation time, and target irrigation water volume. The multi-objective simulation optimization coupling model is constructed based on the water transformation process of irrigation water, soil water, and groundwater in the irrigation unit.

[0027] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the irrigation multi-objective decision-making method based on the water conversion process as described above.

[0028] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the irrigation multi-objective decision-making method based on the water conversion process as described above.

[0029] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the irrigation multi-objective decision-making method based on the water conversion process as described above.

[0030] The present invention provides a multi-objective decision-making method and apparatus for irrigation based on water transformation processes. By establishing a multi-objective simulation optimization coupling model based on water transformation processes, it improves the spatiotemporal optimization accuracy of irrigation water allocation, promotes efficient utilization of agricultural water resources and ecological sustainable development, and can make optimization decisions for multiple objectives such as irrigation water conservation, efficient utilization and control of non-point source pollution. It avoids problems such as waste of agricultural water and aggravation of agricultural non-point source pollution caused by pursuing economic benefits alone, alleviates water shortage pressure and improves the agricultural hydrological environment. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0032] Figure 1 This is one of the flowcharts of the multi-objective decision-making method for irrigation based on water conversion process provided by the present invention;

[0033] Figure 2 This is the second flowchart of the multi-objective decision-making method for irrigation based on water conversion process provided by the present invention;

[0034] Figure 3 This is a schematic diagram of the process for constructing the multi-objective simulation optimization coupling model provided by the present invention;

[0035] Figure 4 This is a schematic diagram of the NSGA-II algorithm solution provided by the present invention;

[0036] Figure 5 This is a schematic diagram of the structure of the irrigation multi-objective decision-making device based on the water conversion process provided by the present invention;

[0037] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0039] In the description of the embodiments of the present invention, it should be noted that the terms "first", "second" and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0040] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0041] The irrigation-drainage-soil water movement and crop growth processes within the agricultural production system make the transformation and allocation of irrigation water more complex. Among these processes, crop growth directly depends on agricultural irrigation, and the amount of irrigation water is one of the determining factors in the mutual transformation process of irrigation water, soil water, and groundwater within the agricultural production system.

[0042] How to select appropriate crop irrigation patterns, optimize irrigation water volume during the crop growing season, and quantify water conversion during the crop growth period under the constraints of water resources and land carrying capacity, so as to ensure sustainable land use and food production, is an important issue.

[0043] In fact, taking the agricultural water resources optimization allocation system as the research object, how to quantify the key factors affecting the allocation of agricultural water resources in different irrigation units and the spatial differences and multiple complexities of agricultural hydrological processes in different irrigation units caused by water transformation processes, and then obtain reasonable agricultural water resources optimization allocation schemes for each irrigation unit, each crop, and each stage, is a difficult and complex task.

[0044] Traditional research rarely considers that arid agricultural areas are complex agricultural production systems with multiple links of water supply, water consumption, and drainage, as well as water transformation, formed by the feedback of multiple relatively independent subsystems. All these issues have become major bottlenecks that seriously restrict our understanding of water transformation processes and the optimal allocation of irrigation water.

[0045] Currently, most irrigation water allocation studies in agricultural production systems focus on single-objective optimization of water resources, crop yield, or land resources. Such studies often overlook other aspects, leading to an excessive pursuit of economic benefits while neglecting the overall, coordinated, and complex nature of the agricultural production system. Consequently, they fail to arrive at irrigation water allocation schemes that meet the scientific requirements of water resource allocation.

[0046] The following is combined Figures 1 to 4 This invention describes a multi-objective decision-making method for irrigation based on water transformation processes, which effectively balances economic benefits, social benefits, and ecological environment, characterizes the spatial variability and multi-dimensional complexity of agricultural hydrological water transformation processes, and achieves multi-dimensional rational regulation of economic, social, ecological, environmental, and water transformation processes.

[0047] like Figure 1 As shown, the irrigation multi-objective decision-making method based on water conversion process in this embodiment of the invention includes steps 110 and 120.

[0048] Step 110: Obtain meteorological data, groundwater data, soil water data, and water pollution data of the irrigation unit during the crop growth period, and obtain the crop planting structure of the irrigation unit.

[0049] Among them, the crop growth period refers to the time from sowing to seed maturity, usually expressed in the number of days required. For some crops, such as hemp, potatoes, sugarcane, and green manure, it refers to the time from sowing to harvest of the main product.

[0050] In this step, meteorological data of the irrigation unit during the crop growth period can be obtained through meteorological station observations. Groundwater and soil water data are obtained from long-term field measurement data, and water pollution data can be obtained by consulting literature and relevant materials.

[0051] Water pollution data can include water nitrogen content, ammonia nitrogen content, and other water pollution data related to agricultural production.

[0052] The normal ammonia nitrogen content in water bodies is usually <0.2 mg / L. Ammonia nitrogen is a compound nitrogen that exists in the form of ammonia or ammonium ions, that is, in water as free ammonia (NH3) and ammonium ions (NH4). + Nitrogen, existing in the form of nitrogen, pollutes the environment.

[0053] In this embodiment, the crop planting structure of the irrigation unit can be obtained through remote sensing imagery. The crop planting structure refers to the planting ratio of different types of crops.

[0054] It should be noted that in this step, the irrigation unit is a unit in the agricultural production system. The agricultural production system can be divided into multiple irrigation units. Meteorological data, groundwater data, soil water data, water pollution data, and corresponding crop planting structures of multiple irrigation units during the crop growth period can be obtained and analyzed.

[0055] Step 120: Input meteorological data, groundwater data, soil water data, water pollution data and crop planting structure into the multi-objective simulation optimization coupling model to obtain the target irrigation information of the irrigation unit output by the target simulation optimization coupling model.

[0056] In this embodiment, the multi-objective simulation optimization coupling model is constructed based on the water transformation process of irrigation water, soil water and groundwater in the irrigation unit. It can fully characterize the physical transformation process among multiple water cycle elements such as irrigation water, soil water and groundwater in the process of water resource utilization in agricultural production system, thereby solving the contradictions and conflicts between multiple objectives in the multi-objective simulation optimization coupling model.

[0057] Among them, the multi-objective simulation optimization coupling model can be a multi-objective model for regulating the economic benefits, yield, and agricultural pollution of crops in agricultural production systems.

[0058] It should be noted that in agricultural production, irrigation water, soil water, and groundwater transform into each other and are inextricably linked to crop yield. The water transformation process in irrigation units has a clear chain relationship with the formation of water productivity. By using a multi-objective simulation optimization coupled model based on the water transformation process to allocate irrigation water, the agricultural production process can be optimized.

[0059] In this embodiment, the multi-objective simulation optimization coupling model solves for meteorological data, groundwater data, soil water data, water pollution data, and crop planting structure to obtain target irrigation information that can be used to guide irrigation units in their irrigation work.

[0060] The target irrigation information includes the target irrigation area, target irrigation time, and target irrigation water volume. The target irrigation area can guide the irrigation space; the target irrigation time can guide the irrigation time, for example, irrigation on a certain day or irrigation during a certain period of time; and the target irrigation water volume can guide the amount of water used for irrigation.

[0061] In this embodiment, the target irrigation information is the spatiotemporal irrigation water volume that guides irrigation work. It can accurately guide the irrigation area, irrigation time and irrigation water volume of the irrigation unit. By analyzing multiple irrigation units in the agricultural production system, the spatiotemporal irrigation water volume of different irrigation units and different crop planting structures in different months can be obtained.

[0062] The irrigation multi-objective decision-making method based on water transformation process provided by the present invention improves the spatiotemporal optimization accuracy of irrigation water allocation by establishing a multi-objective simulation optimization coupling model based on water transformation process, promotes efficient utilization of agricultural water resources and ecological sustainable development, and can make optimization decisions for multiple objectives such as irrigation water saving, efficient utilization and control of non-point source pollution, avoiding problems such as waste of agricultural water and aggravation of agricultural non-point source pollution caused by pursuing economic benefits alone, alleviating water shortage pressure and improving the agricultural hydrological environment.

[0063] In some embodiments, a multi-objective simulation optimization coupled model is established through the following steps:

[0064] By coupling the first simulation model and the second optimization model, a multi-objective function based on the crop economic benefits, crop irrigation yield and water pollution level of the irrigation unit is established. The multi-objective simulation optimization coupled model is established with constraints on the crop growth water consumption, soil water balance, groundwater balance, crop yield and water pollution index of the irrigation unit.

[0065] The first simulation model is constructed based on crop data, water data, and environmental data of the irrigation unit. In other words, the first simulation model is an agricultural-water-environment simulation model concerning the three elements of agriculture, water, and environment.

[0066] like Figure 3 As shown, the first simulation model describes the simulation of water transport and distribution and seepage loss in irrigation unit canal system, soil water transformation process and crop response, groundwater and non-point source pollution, drainage of ditches and reduction of groundwater level, as well as the water environment and agricultural productivity of irrigation unit.

[0067] The second optimization model is constructed based on the irrigation district water distribution data of the irrigation unit, also known as the irrigation district water distribution optimization model. It should be noted that the irrigation water is transported and distributed through channels, and the irrigation unit is a unit area divided according to the distribution of channels. The leakage that occurs during the transportation and distribution process is related to the area division.

[0068] like Figure 3 As shown, the second optimization model can be used to analyze multiple irrigation units, including unit 1, unit i to unit N, for a total of N irrigation units. Each irrigation unit is planted with crop 1, crop i to crop N, and the irrigation water allocation data for each crop in each irrigation unit from month 1 to month N is optimized.

[0069] This includes optimizing water allocation for irrigation units, optimizing water allocation for crops during their growth period, and then optimizing crop irrigation systems.

[0070] It is understandable that in the second optimization model, N represents a positive integer not less than 1 in the number of N irrigation units, the N types of crops planted in each irrigation unit, and the irrigation time for N months, and the specific values ​​represented by the three N are different.

[0071] In this embodiment, a multi-objective simulation-optimization coupled model is established by coupling the first simulation model and the second optimization model, and the source and sink terms of the water transformation process in the multi-objective simulation-optimization coupled model are determined by rainfall data, irrigation data, channel seepage data and groundwater evaporation data.

[0072] In this embodiment, the first simulation model and the second optimization model are combined to construct a multi-objective simulation optimization coupling model that integrates irrigation and drainage coordination, canal system water distribution, and regulation of agricultural hydrological processes. This model enables the analysis of the game relationship between multiple objectives, including crop economic benefits, crop irrigation yield, and water pollution levels. The model uses crop growth water consumption, soil water balance, groundwater balance, crop yield, and water pollution indicators as constraints to provide the multi-objective simulation optimization coupling model with target irrigation information for making reasonable spatiotemporal optimization decisions on irrigation water resources.

[0073] In some embodiments, a multi-objective function is established based on the crop economic benefits, crop irrigation yield, and water pollution level of the irrigation unit, including: constructing a first objective function with the goal of maximizing the crop economic benefits of the entire irrigation area; constructing a second objective function with the goal of maximizing the crop irrigation yield of the entire irrigation area; and constructing a third objective function with the goal of minimizing the water pollution level of the entire irrigation area.

[0074] In this embodiment, three objective functions are established to consider the multi-objective optimization decision-making of irrigation water conservation, efficient utilization and control of non-point source pollution in the water conversion process. This effectively solves the problems of agricultural water waste and aggravated agricultural non-point source pollution caused by excessive pursuit of economic benefits, alleviates water shortage pressure and improves the agricultural hydrological environment.

[0075] It should be noted that the entire irrigation district refers to the entire agricultural production system that requires irrigation, and the entire irrigation district includes multiple irrigation units.

[0076] The following example uses an agricultural production system comprising multiple irrigation units, each planted with spring wheat, corn, and sunflowers, to illustrate specific implementations of the first, second, and third objective functions.

[0077] Firstly, with the goal of maximizing crop economic benefits, the first objective function is constructed as follows:

[0078]

[0079] In the formula, F1 represents the economic benefit (in yuan); NB iA is the price of crop i after deducting planting costs (yuan / kg); i Y is the planting area (ha) of the i-th crop; mi t represents the maximum yield (kg / ha) of the i-th crop under conditions of fertilizer and water supply; n represents different irrigation sub-units; i represents different crops, i = 1, 2, 3 representing spring wheat, corn, and sunflower respectively; t represents the crop growing season, t = 1, 2, 3, ..., 7 representing March to September respectively; ET ait and ET mit K represents the actual and maximum cumulative transpiration (mm) of the i-th crop at time t; yi is the sensitivity index of the i-th crop to water shortage, reflecting the degree of impact of stage-specific water shortage on yield; WP is the irrigation cost (yuan / m³). 3 ); IW it η is the irrigation water volume (mm) for the i-th crop at time t; s The comprehensive irrigation water utilization coefficient.

[0080] Secondly, with the goal of maximizing crop irrigation yield, a second objective function is constructed as follows:

[0081]

[0082] In the formula, F2 is the irrigation water productivity, which is the output value per unit of irrigation water consumed (kg / m³). 3 ); β i This is the yield ratio coefficient between the specified crop and the benchmark crop (spring wheat). Other parameters have the same practical meaning as above.

[0083] In this embodiment, the crop irrigation yield is maximized, which means that the irrigation unit of the agricultural production system has the highest irrigation water productivity.

[0084] Thirdly, with the goal of minimizing water pollution, a third objective function is constructed as follows:

[0085]

[0086] In the formula, F3 represents the degree of water pollution, and α represents the ratio of the grey water footprint of agricultural production to the total available surface water resources; N is the nitrogen loss rate; C is the net amount of nitrogen fertilizer applied (kg); and F3 is the nitrogen loss rate. max,i Maximum permissible pollutant concentration (kg / m³) for the i-th crop in the environment 3 );C nat,i The original nitrogen concentration (kg / m³) in the groundwater for the i-th crop in the irrigation subsystem 3 ); P t The effective rainfall (mm) at time t.

[0087] Among the three objective functions, ET aitThis is the actual cumulative transpiration (mm) during the crop's growing season, calculated using the following formula:

[0088] ET a,nit =K c,nit ·K sw,nit ·ET 0t

[0089] Among them, K c,it K is the crop coefficient for the i-th crop at time t; sw,it ET is the crop evapotranspiration reduction coefficient for the i-th crop at time t, determined by the soil moisture content in the crop root zone; 0,t The reference crop evapotranspiration rate (mm) at time t.

[0090]

[0091]

[0092] Where, θ it θ is the soil moisture content of crop i at time t; fc,it θ is the soil moisture content at time t when the field water holding capacity is met for crop i; wp,it WGH is the soil moisture content at time t when crop i is at its wilting point under water stress; t GH is the weighted groundwater depth (m) for each crop at time t; max is the ultimate groundwater depth, which is considered to be the point at which no more groundwater evaporation occurs when the actual groundwater depth exceeds this limit (m); q represents soil characteristic parameters.

[0093]

[0094]

[0095]

[0096]

[0097] Among them, D i P t For the i-th crop, the deep permeability at time t is (mm / month); W it It is the soil moisture content (mm) at a root zone depth of z = 1m; DR it γ represents the field drainage volume (mm / month) for the i-th crop at time t; d H is the drainage coefficient, which quantifies the drainage volume between the groundwater depth and the bottom surface difference of the drainage ditch; d,n GH represents the depth of the drainage ditch bottom (m). it It is the groundwater depth (m) of the i-th crop.

[0098] The following section provides a detailed description of the constraints on crop water consumption, soil water balance, groundwater balance, crop yield, and water pollution indicators for irrigation units in a multi-objective simulation optimization coupled model.

[0099] For example, in an agricultural production system comprising multiple irrigation units, each planted with spring wheat, corn, and sunflowers, the objective functions of the multi-objective simulation optimization coupled model are the first, second, and third objective functions mentioned above.

[0100] Firstly, the water consumption constraint for crop growth is as follows:

[0101] ET a,nit ≤ET m,nit

[0102] TET a,ni ≤TET m,ni

[0103]

[0104]

[0105] Among them, K c For crop coefficients, TET a,ni TET represents the total evaporation (mm) of crop i during the growing season in the nth irrigation unit. m,ni This represents the total maximum evaporation (mm) of crop i during its growing season in the nth irrigation unit.

[0106] Secondly, the available irrigation water volume is constrained as follows:

[0107]

[0108]

[0109]

[0110]

[0111] Among them, Q s Total available water volume (m³) 3 The constraint reflects the water competition relationship between the various irrigation sub-units; taking corn as an example, t = 3, 4, 5, 6 means that during the growing season from March to September, irrigation is only carried out in May, June, July, and August.

[0112] Thirdly, the soil water balance constraint is as follows:

[0113]

[0114]

[0115] Soil water balance refers to the water content balance of soil at a depth of 1m in the crop root zone.

[0116] Fourth, the groundwater balance constraint is as follows:

[0117]

[0118]

[0119]

[0120]

[0121]

[0122] Where dp is the specific yield of groundwater, which refers to the volume of water released per unit depth of groundwater level in an aquifer; λ is the weight assigned based on the proportion of each crop's planting area; Q loss,t Let t be the channel leakage loss (m) 3 L is the channel length (km); σ is the water loss coefficient per kilometer of channel; η z η is the water utilization coefficient of the canal. d η is the water utilization coefficient of the canal. f The water utilization coefficient of agricultural irrigation canals refers to the water balance constraint of shallow groundwater.

[0123] Fifth, the crop yield constraint is as follows:

[0124]

[0125] Crop yield, or grain yield, needs to guarantee the basic living standards of the local people. min,i The production safety level (kg) for crop i.

[0126] Sixth, the constraints of water pollution indicators are as follows:

[0127]

[0128] Among them, the water pollution indicator is the grey water footprint. The grey water footprint generated by any crop in the irrigation unit should not exceed the current available irrigation water volume, so as to avoid the optimization results from aggravating the adverse environmental impact.

[0129] Seventh, the nonnegativity constraint is as follows:

[0130]

[0131]

[0132] Understandably, it is necessary to constrain the relevant data that need to be limited to non-negative values ​​in the multi-objective simulation optimization coupled model.

[0133] It should be noted that, in this embodiment, the symbol interpretations in the constraint formulas correspond to the symbol interpretations of the objective function.

[0134] In some embodiments, step 120 includes: inputting meteorological data, groundwater data, soil water data, water pollution data, and crop planting structure into a multi-objective simulation optimization coupled model;

[0135] By introducing NSGA-II with an elite strategy and a multi-objective fuzzy optimization method, the solution of the multi-objective simulation optimization coupled model is transformed into solving the Pareto front of the solution space and obtaining the multi-objective scheme after optimization decision, thus determining the target irrigation information.

[0136] Among them, NSGA-II is a multi-objective genetic algorithm. NSGA-II reduces the complexity of non-dominated sorting genetic algorithms and has the advantages of fast running speed and good convergence of solution set. Introducing an elite strategy into NSGA-II can ensure that some superior individuals in the population will not be discarded during the evolution process, thereby improving the accuracy of optimization results.

[0137] In practice, the computation process of NSGA-II with elitist strategy includes fast non-dominated sorting and improved crowding distance calculation, crossover operator based on simulated normal distribution random numbers and non-uniform mutation operator.

[0138] In this case study, the multi-objective simulation optimization coupled model is solved using NSGA-II with elitist strategy and multi-objective fuzzy optimization method. It solves the Pareto front in the solution space and the optimal decision of multi-objective schemes, improves the accuracy of spatiotemporal optimization of irrigation water allocation, realizes the analysis of game relationship between multiple dimensions of objectives, and provides reasonable spatiotemporal optimization decision of irrigation water resources.

[0139] In some embodiments, based on NSGA-II with an elite strategy and a multi-objective fuzzy optimization method, an optimal irrigation set is obtained. The optimal irrigation set includes the optimal Pareto front corresponding to the maximum crop economic benefit, the maximum crop irrigation yield, and the minimum water pollution level, and a multi-objective scheme optimization decision is made. Based on the optimal irrigation set, target irrigation information is determined.

[0140] When solving the optimal irrigation set based on NSGA-II with elitist strategy and multi-objective fuzzy optimization method, adaptively adjusted crossover and mutation probabilities are designed to avoid insufficient search capability when solving multi-objective problems, which may lead to getting trapped in local optima.

[0141] In this embodiment, the optimal Pareto fronts corresponding to maximizing crop economic benefits, maximizing crop irrigation yield, and minimizing water pollution in each irrigation unit are analyzed, as well as the schemes where all three objectives are relatively preferred, to obtain the preferred irrigation set. Then, a multi-objective scheme optimization decision is made to determine the target irrigation information.

[0142] Optimal irrigation systems can provide guidance for balancing the comprehensive benefits of irrigated agriculture in arid regions by integrating crop types and irrigation water allocation, as well as weighing economic, social, and ecological objectives.

[0143] In practice, the process of simultaneously solving multiple irrigation units of an agricultural production system using a multi-objective simulation optimization coupled model can also be combined with multi-threaded model tools. For example, the data obtained in step 110 can be imported into Python 3.8 for multi-threaded model solving to simultaneously solve the objective function for multiple irrigation units.

[0144] The solution process of the NSGA-II algorithm will be described in detail below.

[0145] like Figure 4 As shown, initialization is performed, setting the initial population of NSGA-II, generating the first generation subpopulation Gen=1, and using R... t Non-dominated sorting forms non-dominated sets Z, R t It is a new population, the parent population P. t More than twice as much.

[0146] Z is introduced into the new parent population P through an elite strategy. t+1 Determine P t+1 Check if the number of elements is equal to N, and sort by crowding degree using Zi = Zi+1 = Zi+3 = ...

[0147] Determine P t+1 When the number of elements is equal to N, perform crossover and mutation operations to obtain a new offspring population Q. t+1 By setting the new Gen = Gen + 1, we determine if Gen is less than the maximum generation. If Gen is not less than the maximum generation, we merge the offspring and parent populations to form a population R of size 2N. t .

[0148] It should be noted that the solution process of the NSGA-II algorithm with elite strategy in the embodiments of the present invention is the same as that of the conventional NSGA-II algorithm.

[0149] In some embodiments, the irrigation unit is determined based on canal system distribution information, which includes the distribution information of main irrigation canals, branch canals, and tributary canals.

[0150] In practice, the agricultural production system can be divided into multiple irrigation units. Each irrigation unit is divided according to the distribution of the main irrigation canal, branch canals, and major tributary canals. Each irrigation unit is assumed to be homogeneous, and the meteorological, soil, and groundwater factors within each irrigation unit are uniform.

[0151] This invention fully utilizes spatial data to divide the agricultural production system into several irrigation units. On the one hand, it makes up for the shortcomings of traditional methods that generalize model parameters for different regions, soil types, and meteorological conditions. On the other hand, it quantifies the dynamic changes in agricultural water use during water transformation through the rational and efficient allocation of irrigation water resources, proposes a water-saving, high-yield, and pollution-controlled irrigation regulation model for irrigation districts, and greatly reveals the agricultural hydrological processes in shallow groundwater arid areas, which is helpful for developing water-saving and optimized regulation of irrigation districts.

[0152] In this embodiment, the agricultural production system is divided into multiple irrigation units. Each irrigation unit takes maximizing crop economic benefits, maximizing crop irrigation yield, and minimizing water pollution as its objective functions. Based on field experiments and field survey data, the first simulation model is combined with the second optimization model to construct a multi-objective simulation optimization coupling model that integrates irrigation and drainage coordination, canal system water distribution, and regulation of agricultural hydrological processes. This model enables the analysis of the game relationship between multiple dimensions of objectives and allows for reasonable spatiotemporal optimization decisions for irrigation water resources.

[0153] The following is a specific example.

[0154] like Figure 2 As shown, in step 210, based on remote sensing images, irrigation units are divided, and data on crops, soil, groundwater, etc. of irrigation units are collected and preprocessed.

[0155] Step 220: Based on the irrigation water-driven agricultural production system, couple the first simulation model with the second optimization model.

[0156] Step 230: Construct a multi-objective simulation optimization coupled model based on the water conversion process.

[0157] Step 240: The multi-objective decision-making simulation optimization coupled model solves the data to obtain the optimal irrigation allocation scheme.

[0158] like Figure 3 As shown, the first simulation model and the second optimization model are coupled to obtain a multi-objective simulation-optimization coupled model. The model is then optimized and solved using NSGA-II with an elite strategy and multi-objective fuzzy optimization. The multi-objective simulation-optimization coupled model yields multi-objective optimization decisions that can improve economic benefits, enhance agricultural water use efficiency, and control agricultural non-point source pollution. This effectively addresses the problems of agricultural water waste and aggravated agricultural non-point source pollution caused by excessive pursuit of economic benefits, alleviates water shortage pressure, and improves the agricultural hydrological environment.

[0159] The following describes the irrigation multi-objective decision-making device based on the water conversion process provided in the embodiments of the present invention. The irrigation multi-objective decision-making device based on the water conversion process described below can be referred to in correspondence with the irrigation multi-objective decision-making method based on the water conversion process described above.

[0160] like Figure 5 As shown, the irrigation multi-objective decision-making device based on water conversion process provided in this embodiment of the invention includes:

[0161] The acquisition module 510 is used to acquire meteorological data, groundwater data, soil water data and water pollution data of the irrigation unit during the crop growth period, and to acquire the crop planting structure of the irrigation unit.

[0162] The processing module 520 is used to input meteorological data, groundwater data, soil water data, water pollution data and crop planting structure into the multi-objective simulation optimization coupling model to obtain the target irrigation information of the irrigation unit output by the target simulation optimization coupling model.

[0163] The target irrigation information includes the target irrigation area, target irrigation time, and target irrigation water volume. The multi-objective simulation optimization coupling model is constructed based on the water transformation process of irrigation water, soil water, and groundwater in the irrigation unit.

[0164] The irrigation multi-objective decision-making device based on the water conversion process provided in the embodiments of the present invention improves the spatiotemporal optimization water allocation accuracy of irrigation water through a multi-objective simulation optimization coupling model established based on the water conversion process, promotes the efficient use of agricultural water resources and ecological sustainable development, and can make optimization decisions for multiple objectives such as irrigation water saving, efficient utilization and control of non-point source pollution, avoiding problems such as agricultural water waste and aggravation of agricultural non-point source pollution caused by pursuing economic benefits alone, alleviating water shortage pressure and improving the agricultural hydrological environment.

[0165] In some embodiments, a multi-objective simulation optimization coupled model is established through the following steps:

[0166] Couple the first simulation model and the second optimization model to establish a multi-objective function based on the crop economic benefits, crop irrigation yield and water pollution level of the irrigation unit. With the crop growth water consumption, soil water balance, groundwater balance, crop yield and water pollution index of the irrigation unit as constraints, a multi-objective simulation optimization coupled model is established.

[0167] The first simulation model is constructed based on crop data, water data, and environmental data of the irrigation unit, the second optimization model is constructed based on irrigation district water allocation data of the irrigation unit, and the source and sink terms of the multi-objective simulation optimization coupling model are determined based on rainfall data, irrigation data, channel leakage data, and groundwater evaporation data.

[0168] In some embodiments, a multi-objective function is established based on the crop economic benefits, crop irrigation yield, and water pollution level of the irrigation unit, including:

[0169] With the goal of maximizing the economic benefits of crops throughout the entire irrigation district, a first objective function is constructed.

[0170] A second objective function is constructed with the goal of maximizing crop irrigation yield across the entire irrigation district.

[0171] A third objective function is constructed with the goal of minimizing the degree of water pollution in the entire irrigation area.

[0172] In some embodiments, the processing module 520 is used to input meteorological data, groundwater data, soil water data, water pollution data, and crop planting structure into a multi-objective simulation optimization coupled model;

[0173] By introducing NSGA-II with an elite strategy and a multi-objective fuzzy optimization method, the solution of the multi-objective simulation optimization coupled model is transformed into solving the Pareto front of the solution space and obtaining the multi-objective scheme after optimization decision, thus determining the target irrigation information.

[0174] In some embodiments, the processing module 520 is used to solve for an optimal irrigation set based on NSGA-II with an elite strategy and a multi-objective fuzzy optimization method. The optimal irrigation set includes the optimal Pareto front corresponding to the maximum crop economic benefit, the maximum crop irrigation yield, and the minimum water pollution level. The module then makes the multi-objective scheme optimization decision. NSGA-II has adaptive crossover probability and mutation probability.

[0175] Based on the optimized irrigation set, the target irrigation information is determined.

[0176] In some embodiments, the irrigation unit is determined based on canal system distribution information, which includes the distribution information of main irrigation canals, branch canals, and tributary canals.

[0177] Figure 6 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 6As shown, the electronic device may include a processor 610, a communication interface 620, a memory 630, and a communication bus 640. The processor 610, communication interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions in the memory 630 to execute a multi-objective decision-making method for irrigation based on the water conversion process. This method includes: acquiring meteorological data, groundwater data, soil water data, and water pollution data of the irrigation unit during the crop growth period, and acquiring the crop planting structure of the irrigation unit; inputting the meteorological data, groundwater data, soil water data, water pollution data, and crop planting structure into a multi-objective simulation optimization coupling model to obtain the target irrigation information of the irrigation unit output by the target simulation optimization coupling model.

[0178] The target irrigation information includes the target irrigation area, target irrigation time, and target irrigation water volume. The multi-objective simulation optimization coupling model is constructed based on the water transformation process of irrigation water, soil water, and groundwater in the irrigation unit.

[0179] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0180] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the irrigation multi-objective decision-making method based on the water transformation process provided by the above methods. The method includes: acquiring meteorological data, groundwater data, soil water data, and water pollution data of the irrigation unit during the crop growth period, and acquiring the crop planting structure of the irrigation unit; inputting the meteorological data, groundwater data, soil water data, water pollution data, and crop planting structure into a multi-objective simulation optimization coupling model to obtain the target irrigation information of the irrigation unit output by the target simulation optimization coupling model;

[0181] The target irrigation information includes the target irrigation area, target irrigation time, and target irrigation water volume. The multi-objective simulation optimization coupling model is constructed based on the water transformation process of irrigation water, soil water, and groundwater in the irrigation unit.

[0182] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the multi-objective decision-making method for irrigation based on the water transformation process provided by the above methods. The method includes: acquiring meteorological data, groundwater data, soil water data, and water pollution data of an irrigation unit during the crop growth period, and acquiring the crop planting structure of the irrigation unit; inputting the meteorological data, groundwater data, soil water data, water pollution data, and crop planting structure into a multi-objective simulation optimization coupling model to obtain the target irrigation information of the irrigation unit output by the target simulation optimization coupling model.

[0183] The target irrigation information includes the target irrigation area, target irrigation time, and target irrigation water volume. The multi-objective simulation optimization coupling model is constructed based on the water transformation process of irrigation water, soil water, and groundwater in the irrigation unit.

[0184] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0185] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0186] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-objective decision-making method for irrigation based on water transformation processes, characterized in that, include: Acquire meteorological data, groundwater data, soil water data, and water pollution data of the irrigation unit during the crop growth period, and acquire the crop planting structure of the irrigation unit; The meteorological data, groundwater data, soil water data, water pollution data, and crop planting structure are input into a multi-objective simulation optimization coupling model to obtain the target irrigation information of the irrigation unit output by the multi-objective simulation optimization coupling model. The target irrigation information includes the target irrigation area, target irrigation time, and target irrigation water volume. The multi-objective simulation optimization coupling model is constructed based on the water transformation process of irrigation water, soil water, and groundwater in the irrigation unit. The multi-objective simulation optimization coupled model is established through the following steps: Couple the first simulation model and the second optimization model to establish a multi-objective function based on the crop economic benefits, crop irrigation yield and water pollution level of the irrigation unit. The multi-objective simulation optimization coupled model is established with constraints such as crop growth water consumption, available irrigation water, soil water balance, groundwater balance, crop yield, water pollution index and non-negative constraints of the irrigation unit. The first simulation model is constructed based on crop data, water data, and environmental data of the irrigation unit; the second optimization model is constructed based on irrigation district water allocation data of the irrigation unit; and the source and sink terms of the multi-objective simulation-optimization coupling model are determined based on rainfall data, irrigation data, channel seepage data, and groundwater evaporation data. The establishment of a multi-objective function based on the irrigation unit, considering crop economic benefits, crop irrigation yield, and water pollution levels, includes: With the goal of maximizing the economic benefits of crops in the entire irrigation district, a first objective function is constructed, wherein the entire irrigation district includes multiple irrigation units; A second objective function is constructed with the goal of maximizing crop irrigation yield in the entire irrigation district. A third objective function is constructed with the goal of minimizing the water pollution level of the entire irrigation area.

2. The irrigation multi-objective decision-making method based on water conversion process according to claim 1, characterized in that, The step of inputting the meteorological data, groundwater data, soil water data, water pollution data, and crop planting structure into a multi-objective simulation optimization coupling model to obtain the target irrigation information of the irrigation unit output by the multi-objective simulation optimization coupling model includes: The meteorological data, groundwater data, soil water data, water pollution data, and crop planting structure are input into the multi-objective simulation optimization coupling model; By introducing NSGA-II with an elite strategy and a multi-objective fuzzy optimization method, the solution of the multi-objective simulation optimization coupled model is transformed into solving the Pareto front of the solution space and obtaining the multi-objective scheme after optimization decision, thereby determining the target irrigation information.

3. The irrigation multi-objective decision-making method based on water conversion process according to claim 2, characterized in that, The introduction of NSGA-II with an elitist strategy and a multi-objective fuzzy optimization method transforms the solution of the multi-objective simulation optimization coupled model into solving the Pareto front of the solution space and obtaining the multi-objective scheme after optimization decision-making, determining the target irrigation information, including: Based on the NSGA-II with elite strategy and the multi-objective fuzzy optimization method, the optimal irrigation set is obtained. The optimal irrigation set includes the optimal Pareto front corresponding to the maximum crop economic benefit, the maximum crop irrigation yield, and the minimum water pollution. The multi-objective scheme optimization decision is then performed. The NSGA-II has adaptive crossover probability and mutation probability. Based on the preferred irrigation set, the target irrigation information is determined.

4. The irrigation multi-objective decision-making method based on water transformation process according to any one of claims 1-3, characterized in that, The irrigation unit is determined based on the canal system distribution information, which includes the distribution information of the main irrigation canals, branch canals, and tributary canals.

5. A multi-objective decision-making device for irrigation based on water transformation processes, characterized in that, include: The acquisition module is used to acquire meteorological data, groundwater data, soil water data and water pollution data of the irrigation unit during the crop growth period, and to acquire the crop planting structure of the irrigation unit. The processing module is used to input the meteorological data, the groundwater data, the soil water data, the water pollution data, and the crop planting structure into a multi-objective simulation optimization coupling model to obtain the target irrigation information of the irrigation unit output by the multi-objective simulation optimization coupling model. The target irrigation information includes the target irrigation area, target irrigation time, and target irrigation water volume. The multi-objective simulation optimization coupling model is constructed based on the water transformation process of irrigation water, soil water, and groundwater in the irrigation unit. The multi-objective simulation optimization coupled model is established through the following steps: Couple the first simulation model and the second optimization model to establish a multi-objective function based on the crop economic benefits, crop irrigation yield and water pollution level of the irrigation unit. The multi-objective simulation optimization coupled model is established with constraints such as crop growth water consumption, available irrigation water, soil water balance, groundwater balance, crop yield, water pollution index and non-negative constraints of the irrigation unit. The first simulation model is constructed based on crop data, water data, and environmental data of the irrigation unit; the second optimization model is constructed based on irrigation district water allocation data of the irrigation unit; and the source and sink terms of the multi-objective simulation-optimization coupling model are determined based on rainfall data, irrigation data, channel seepage data, and groundwater evaporation data. The establishment of a multi-objective function based on the irrigation unit, considering crop economic benefits, crop irrigation yield, and water pollution levels, includes: With the goal of maximizing the economic benefits of crops in the entire irrigation district, a first objective function is constructed, wherein the entire irrigation district includes multiple irrigation units; A second objective function is constructed with the goal of maximizing crop irrigation yield in the entire irrigation district. A third objective function is constructed with the goal of minimizing the water pollution level of the entire irrigation area.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the irrigation multi-objective decision-making method based on the water conversion process as described in any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the irrigation multi-objective decision-making method based on the water conversion process as described in any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the irrigation multi-objective decision-making method based on the water conversion process as described in any one of claims 1 to 4.

Images