Rolling correction intelligent irrigation decision-making method for regional wheat-corn rotation system

Abstract

The invention discloses a rolling correction intelligent irrigation decision-making method for a regional wheat-corn rotation system, belongs to the technical field of agricultural irrigation, and aims to construct a regional high-water-efficiency intelligent irrigation decision-making model. In the model, irrigation data in an area does not only depend on annual average weather and soil data, but meticulous weather elements and soil moisture content information are read and processed in real time, so that an irrigation strategy is dynamically optimized according to daily changes. By optimizing the irrigation volume of the regional grids day by day, the spatial heterogeneity of a crop growth environment in a large-scale region can be reflected more finely, so that the accuracy and reliability of a crop model in large-scale application are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of agricultural irrigation, and particularly relates to a rolling correction intelligent irrigation decision-making method for a regional wheat-maize rotation system. Background Art

[0002] At present, most of the optimization methods for wheat and maize irrigation systems at the regional scale are based on the division of hydrological years, and the seasonal changes in water demand in the wheat-maize rotation system are not fully considered. The water demands of winter wheat and summer maize vary greatly during the growing season and have a certain degree of water complementarity. Reasonable allocation of water resources is the key to efficient agricultural water use.

[0003] In the water management of the wheat-maize rotation system, there is a lack of research on the soil water allocation mechanism between the two crop growing seasons, the dynamic regulation of the upper and lower limits of soil water is insufficient, the improvement effect of straw returning on water infiltration and irrigation demand is not fully quantified, and the irrigation system has deficiencies in terms of adaptability to regional real-time water supply conditions and meteorological changes, and cannot well meet the growth needs of wheat and maize.

[0004] The precise and intelligent irrigation decision-making for the wheat-maize rotation system requires refined management and intelligent decision-making according to the actual needs of wheat and maize growth, including sowing date, irrigation amount, irrigation date, and irrigation frequency. With the development of information technology and intelligent optimization algorithms, it has become possible to make intelligent decisions using data such as remote sensing, meteorology, and hydrology. However, there is currently no dynamic optimization strategy based on real-time meteorological data and soil moisture changes to achieve a new balance between agricultural irrigation water use and wheat and maize yields, thereby maximizing economic benefits. Summary of the Invention

[0005] In order to solve the technical problems existing in the background art, the present invention aims to provide a rolling correction intelligent irrigation decision-making method for a regional wheat-maize rotation system.

[0006] To solve the technical problems, the technical solution of the present invention is as follows:

[0007] A rolling correction intelligent irrigation decision-making method for a regional wheat-maize rotation system, the method comprising:

[0008] S1: Input the obtained driving data into the crop growth model, perform sensitivity analysis on the parameters of the crop growth model using the Sobol method, screen out the non-sensitive parameters in the crop growth model, set them as default values, and calibrate the sensitive parameters; input the calibrated sensitive parameters into the growth localization model, couple with the multi-objective optimization model, and jointly calibrate the model parameters of the particle swarm optimization algorithm PSO and the crop growth model. With the goal of minimizing the error between the measured value and the simulated value of the crop growth index, automatically calibrate the sensitive parameters in the crop growth model to obtain the crop parameters and soil parameters of the localized crop growth model of the wheat-maize rotation system, and establish a localized growth model of the wheat-maize rotation system;

[0009] S2: Input the crop model driving data of the planned year into the local winter wheat - summer maize rotation system growth model, construct the distributed growth local model of the regional winter wheat - summer maize rotation system in the planned year, couple with the multi - objective optimization model to determine the impacts of water allocation and straw returning to the field on soil moisture and irrigation demand; based on the objectives of maximizing regional yield, minimizing irrigation water volume, and maximizing economic benefits, obtain the Pareto optimal solution of the high - resolution irrigation regime, and use the TOPSIS method to assign weights to the long - term irrigation regimes of different regions to obtain the long - term irrigation regime of the winter wheat - summer maize rotation system for different regional spatial grids, that is, obtain the regional spatial long - term irrigation decision - making optimization model;

[0010] S3: Taking the long - term irrigation regime as a reference, collect and input the real - time read crop data, soil data, hydrological data, meteorological data, field management data, and water supply data into the regional spatial long - term irrigation decision - making optimization model in real time to determine the impact of climate change on the phenological period and optimize the field management strategy. When the irrigation regime is adjusted in real time with the period biomass, water demand, and available water volume as constraints, judge whether to modify the reference irrigation regime; by coupling with the multi - objective optimization model, construct a dynamic irrigation correction method, aiming at maximizing biomass, minimizing water demand decision error, and maximizing economic benefits, and adjust the irrigation plan in real time.

[0011] Further, before the step S1, the method further includes:

[0012] Driving data collection, using remote sensing, field soil detectors, and meteorological stations to collect crop data, meteorological data, field management data, and soil data of winter wheat - summer maize; regional division, according to the crop distribution map, soil type, and water supply conditions, divide the decision - making area into multiple sub - regions and perform rasterization processing.

[0013] Further, the specific process of the Sobol method in the step S1 and the parameter calibration of the combined PSO algorithm and the crop growth model include:

[0014] S101: Determine the model input parameters and target variables: Determine the input parameters and parameter ranges of the winter wheat - summer maize growth model. The input parameters include: crop parameters, soil parameters, and meteorological parameters; determine the target variables of the winter wheat - summer maize growth model. The target variables are the wheat / maize leaf area index and above - ground dry matter accumulation amount output in time series and the wheat / maize yield output in non - time series.

[0015] S102: Sampling of input variables: Use the Latin hypercube sampling method to ensure that each variable is evenly distributed within its range, and generate a set of sample points for each input variable for model calculation.

[0016] S103: Model evaluation: Output the sample data generated by the Latin hypercube sampling method, run the model to calculate its output results, repeat this process, and conduct sensitivity analysis to ensure the sample size and analysis accuracy;

[0017] S104: Calculate variance decomposition: The Sobol method evaluates the influence of input variables through variance decomposition; the output variance is expressed as the sum of the variance contributions of each input variable:

[0018]

[0019] Among them, V i represents the contribution of a single input variable to the output variance, V ij represents the contribution of the interaction effect of two input variables to the output variance, k is the number of input parameters, and Var(Y) is the total output variance of the model;

[0020] S105: Calculate the Sobol sensitivity index: The Sobol index is a quantitative index used to measure the contribution degree of each input parameter to the model output; calculate the first-order sensitivity index, second-order sensitivity index, and total-order sensitivity index through programming software:

[0021] First-order sensitivity index (S i ): It represents the contribution degree of a single input variable to the output variance, which is the influence degree of this input variable on the output result without considering other interaction effects. The calculation formula is as follows:

[0022]

[0023] S i is the first-order sensitivity index, V i represents the contribution of a single input variable to the output variance, and Var(Y) is the total output variance of the model;

[0024] Second-order sensitivity index (S ij ): It represents the contribution degree of the interaction effect of two input variables to the output variance. The calculation formula is as follows:

[0025]

[0026] S ij is the second-order sensitivity index, V ij represents the contribution of the interaction effect of two input variables to the output variance;

[0027] Global sensitivity index (ST i ): It represents the total contribution degree of a certain input variable to the output, including the first-order effect of this variable and the interaction effect with other input variables. The calculation formula is as follows:

[0028]

[0029] ST i is the global sensitivity index, and V -i represents the variance of all parameters except the i-th parameter;

[0030] S106: Result analysis and interpretation: According to the calculated sensitivity indices, analyze the sensitivity of each parameter to wheat / maize yield, leaf area index, and aboveground dry matter accumulation, and calibrate the input parameters with larger sensitivity indices;

[0031] S107: Parameter calibration of the wheat-maize rotation system growth model: Through the Sobol analysis method, screen out the sensitive parameters of the model, and jointly calibrate the parameters by combining PSO and the wheat-maize rotation system growth model.

[0032] Furthermore, the specific steps of PSO in the step S107 are as follows:

[0033] S1071: Initialization: Set the initial particle swarm size, define the maximum number of algorithm iterations, set the initial values of the particle position and velocity. Each particle represents a set of model parameter combinations, the position is the model parameter combination, and the velocity is the step size when the particle is updated;

[0034] S1072: Evaluate the fitness of each particle according to the objective function, that is, minimize the error between the measured value and the simulated value of the crop growth index. The fitness value is used to measure the quality of the particle solution;

[0035] S1073: Update velocity and position: According to the historical best position of the particle and the global best position in the population, adjust the velocity and position of the particle using the update formula of particle swarm optimization;

[0036] S1074: Local optimal and global optimal update: After each particle updates its velocity and position, recalculate its fitness value and compare it with its personal historical best position. If the current fitness is better, update the personal optimal position. Through the fitness evaluation of the entire population, select the particle with the best fitness as the global optimal;

[0037] S1075: Evaluation: Evaluate the fitness of the updated particles according to the objective function, and calculate their performance in the optimization objective. The fitness evaluation is used to determine whether to update the personal optimal position and the global optimal position of the particles;

[0038] S1076: Iterative update: Repeat steps S2073 to S2075 until the maximum number of iterations is reached or the fitness value converges;

[0039] S1077: Termination condition: When the maximum number of iterations is reached or the fitness converges, terminate the algorithm operation;

[0040] S1078: Output result: Output the optimal solution set, that is, a set of optimal combinations of model parameters that minimize the error between the simulated value and the measured value.

[0041] Furthermore, for the establishment of the growth model of the local wheat - maize rotation system, the objective function is as follows:

[0042]

[0043] In the formula, and are respectively the measured value and the simulated value of the wheat / maize leaf area index; and are respectively the measured value and the simulated value of the above - ground dry matter accumulation of wheat / maize; and are respectively the measured value and the simulated value of the wheat / maize yield; n is the sampling times of the wheat / maize leaf area index and the above - ground dry matter accumulation in the measured sampling or experiment, and m is the sampling times of the wheat / maize yield.

[0044] Furthermore, the step S2 includes:

[0045] S201: Data input: Input the data required for the distributed growth local model of the wheat - maize rotation system in the planned year into the crop model, including meteorological data, soil data, field management data, and local model parameters, and create a distributed growth local model of the wheat - maize rotation system adapted to the planned year; Determine the objective function: Determine the optimization objectives, that is, maximizing crop yield, minimizing irrigation water volume, and maximizing economic effects;

[0046] S202: Set constraint conditions: Constrained by the upper and lower limits of the soil volume water content and the regional water supply conditions, considering the soil allocation characteristics and water complementarity in the wheat - maize rotation system: At the end of the winter wheat growth season, the soil water should be stored sufficiently to meet the water demand during the maize growth season to ensure the limitation of available resources in actual production and the normal growth of wheat and maize;

[0047] The relationship formula between the soil water content of wheat and maize:

[0048] SM cron (t 0 ) = SM wheat (t 1 ) + SM(t 2 , t 3 )

[0049] In the formula: SM cron (t0) is the soil water content at the beginning of the maize growth period; SM wheat(t1) is the soil water content at the time of winter wheat harvest; ΔSM(t2,t3) is the change in soil moisture between the end of winter wheat growth and the start of maize growth, including the effects of precipitation, evaporation, and irrigation;

[0050] S203: Water resource allocation and complementarity between crops: Combining the seasonal characteristics of wheat - maize rotation, the water resource requirements of winter wheat and summer maize are configured according to the soil moisture conditions during the growth periods of different crops in the optimized model;

[0051] S204: Influence of straw returning to the field on soil water infiltration and irrigation requirements: In the distributed growth local model of the wheat - maize rotation system, the improvement effect of straw returning to the field on soil porosity and infiltration rate after the maize growth season is considered;

[0052] Relationship formula for the soil volume water content at the initial stage of winter wheat with summer maize straw returning to the field:

[0053] SM t = SM 0 + SM s - SM e

[0054] SM s = ΔSOM × S water

[0055] In the formula, SM t is the soil volume water content at the initial stage of winter wheat; SM 0 is the initial soil volume water content of winter wheat; SM s is the change in soil volume water content caused by straw returning to the field; SM e is the soil water evaporation; ΔSOM is the amount of straw returning to the field; S water is the ability coefficient of soil organic matter to retain water;

[0056] S205: Model coupling: Coupling the distributed growth local model of the wheat - maize rotation system with the multi - objective optimization model, transferring the decision variable crop input data of the optimization model to the distributed growth local model of the wheat - maize rotation system, and feeding back the yield, irrigation water volume, and economic benefits after the operation of the distributed growth local model of the wheat - maize rotation system to the optimization model;

[0057] S206: Model solution: Using the NSGA - Ⅱ algorithm to solve the optimization model and output the Pareto optimal solution set of irrigation regimes under high - resolution grids in the region;

[0058] S207: Selecting the best by TOPSIS comprehensive evaluation method: Selecting the best from the Pareto solution set and further selecting the best from the Pareto solution set using the TOPSIS comprehensive evaluation method.

[0059] Furthermore, the step S207 includes:

[0060] S2071: Determine evaluation indicators: clarify the decision-making objectives, select relevant evaluation indicators, that is, the larger the crop yield value, the better, the smaller the irrigation water volume value, the better, and the larger the economic benefit value, the better;

[0061] S2072: Construct a normalized decision matrix: organize and normalize the original data, and organize the crop yield, irrigation water volume, and economic benefit data in the Pareto solution set into a decision matrix Di×j, where i represents the number of Pareto solution sets and j represents the number of decision-making objectives. Each row of this matrix is an alternative solution. Use the linear normalization method to convert the data into a unified scale; Determine the weights of evaluation indicators: Different weight combinations are carried out for each evaluation indicator from the perspective of decision-maker preferences, which can be divided into long-term irrigation system plans for wheat-maize rotation systems in high water use efficiency and economic benefit regions, long-term irrigation system plans for wheat-maize rotation systems in high yield and economic benefit regions, and long-term irrigation system plans for wheat-maize rotation systems in water-saving and economic benefit regions;

[0062] S2073: Calculate the positive and negative ideal solutions: calculate the distances from each alternative solution to the positive and negative ideal solutions;

[0063] S2074: Conduct sorting: calculate the relative closeness based on the distances from each alternative solution to the positive and negative ideal solutions, and sort the alternative solutions according to the relative closeness. The one with the largest value is the best long-term irrigation decision plan for the regional wheat-maize rotation system under this preference angle.

[0064] Furthermore, the objective function of the regional space long-term irrigation decision optimization model is as follows:

[0065] Obj 1 = max TWSO

[0066] Obj 2 = min I

[0067] Obj 3 = max NEB

[0068] In the formula, TWSO is the wheat / maize yield per unit area; I is the irrigation water volume per unit area; NEB is the wheat / maize economic benefit per unit area;

[0069] The constraint conditions of the regional wheat-maize rotation system distributed growth localization model are as follows:

[0070] Soil water content constraint:

[0071] SM min ≤ SM ≤ SM max

[0072] In the formula, SM represents the soil water content in the root zone, SM min and SMmax represent the lower and upper limits of the soil water content in the root zone, respectively;

[0073] Irrigation water volume constraint:

[0074] I < R

[0075] where I is the irrigation water volume per unit area; R is the available water volume per unit area;

[0076] Yield constraint:

[0077] ΣTWSO·A = TWSO REG

[0078] where TWSO REG is the grain demand in the area where the irrigation district is located.

[0079] Furthermore, the step S3 includes:

[0080] S301: Apply the long-term irrigation regime of the region as the reference long-term irrigation regime to the research area, and set the corresponding aboveground biomass under the reference long-term irrigation regime as the reference aboveground biomass;

[0081] S302: Obtain the remote sensing images of the irrigation decision-making area through a satellite platform or an unmanned aerial vehicle, and inversely obtain crop data such as aboveground biomass and leaf area index in combination with a regression model; obtain real-time soil data by arranging soil moisture monitors in the irrigation decision-making area; obtain hydrological data through long-term runoff monitoring data of a hydrological station; obtain real-time meteorological data by setting up a small meteorological station in the irrigation decision-making area; obtain field management data by the real-time input of agricultural management measures by field managers, and the agricultural management measures include: single irrigation volume, irrigation date, fertilization amount, fertilization date;

[0082] S303: At the end of winter wheat harvest or summer maize harvest, explore the influence of changes in real-time meteorological conditions on the phenology of wheat and maize by reading the driving data in real time, and input the future meteorological data into the distributed growth local model of the regional wheat-maize rotation system, and explore the optimal sowing dates of summer maize or winter wheat with the goal of maximizing yield;

[0083] S304: Input the real-time driving data into the distributed growth local model of the regional wheat-maize rotation system, and judge whether to correct the reference irrigation regime through constraint conditions. Grid points that do not meet any of the three constraint conditions need to re-decide the irrigation regime, and grid points that meet the constraint conditions follow the reference irrigation regime; the specific constraint conditions are as follows:

[0084] Period biomass constraint:

[0085] K·Bio ≥ Bio R

[0086] Where K is the correction coefficient; Bio is the biomass in a period; Bio R is the biomass in a period under the reference irrigation regime;

[0087] Water supply constraint:

[0088] Q S ≥Q D

[0089] Where Q S is the water supply; Q D is the water demand;

[0090] Water demand decision error constraint:

[0091]

[0092] Where I R is the total irrigation amount in the current period, P is the rainfall in the current period; ET is the water demand in the current period;

[0093] S305: Re-decide the irrigation regime for the next 15 days for the grids that need to update the irrigation regime. To ensure the operation efficiency of the model, the particle swarm optimization algorithm is used to solve the model, and an adaptive correction decision model is constructed with the goal of maximizing the biomass in a period and minimizing the water demand decision error.

[0094] Compared with the prior art, the advantages of the present invention are as follows:

[0095] The present invention constructs a regional high-water-efficiency intelligent irrigation decision model. In this model, the irrigation data in the region no longer simply depends on the annual average meteorological and soil data, but reads and processes detailed meteorological elements and soil moisture information in real time, so as to dynamically optimize the irrigation strategy according to the daily changes. By optimizing the irrigation amount of the regional grids day by day, it can more precisely reflect the spatial heterogeneity of the crop growth environment in the large-scale region, thereby improving the accuracy and reliability of the crop model in large-scale applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] Figure 1 FIG. is the technical flow chart of a regional wheat-maize rotation system rolling correction intelligent irrigation decision method of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0097] The following describes the specific embodiments of the present invention in conjunction with the embodiments:

[0098] It should be noted that the structures, ratios, sizes, etc. shown in this specification are only used to cooperate with the content disclosed in the specification for those familiar with this technology to understand and read, and are not used to limit the implementation conditions of the present invention. Any modification of the structure, change of the proportional relationship or adjustment of the size, without affecting the effects that the present invention can produce and the purposes that can be achieved, should still fall within the scope covered by the technical content disclosed in the present invention.

[0099] At the same time, the terms such as "upper", "lower", "left", "right", "middle" and "one" cited in this specification are only for the convenience of clear narration, and are not used to limit the scope of implementation of the present invention. The change or adjustment of their relative relationship, without substantial change in the technical content, should also be regarded as the scope of implementation of the present invention.

[0100] Example 1:

[0101] As Figure 1 shown, the present invention provides a rolling correction intelligent irrigation decision-making method for a regional winter wheat-summer maize rotation system, including the following steps:

[0102] S1: Basic data collection and irrigation decision-making area division

[0103] Using remote sensing technology, field soil detectors and meteorological stations to collect crop data, meteorological data, field management data and soil data of winter wheat-summer maize in the region; dividing the decision-making area into 4 sub-regions according to the winter wheat-summer maize planting distribution map, soil type and regional water supply conditions in the region; rasterizing each sub-region;

[0104] S2: Sensitivity analysis and crop model localization

[0105] Input the model-driven data into the crop growth model, use the Sobol method to conduct sensitivity analysis on the parameters of the crop growth model, screen out the non-sensitive parameters in the crop growth model, set them as default values, and calibrate the sensitive parameters.

[0106] The process of the Sobol method is as follows:

[0107] 1. Determine the model input parameters and target variables:

[0108] Determine the input parameters and parameter ranges of the wheat-maize growth model. The input parameters include: crop parameters, soil parameters and meteorological parameters; determine the target variables of the wheat-maize growth model. The target variables are the wheat / maize leaf area index and above-ground dry matter accumulation amount output in time series and the wheat / maize yield output in non-time series;

[0109] 2. Sampling of input variables:

[0110] Using the Latin hypercube sampling method to ensure that each variable is evenly distributed within its range. A set of sample points needs to be generated for each input variable, and these sample points will be used for the calculation of the model;

[0111] 3. Model evaluation:

[0112] Output the sample data generated by the Latin hypercube sampling method, run the model to calculate its output results, and repeat this process until enough sample output sample points are obtained for sensitivity analysis to ensure that the sample size is large enough (thousands of samples) to guarantee the accuracy of the analysis;

[0113] 4. Calculate variance decomposition:

[0114] The Sobol method evaluates the impact of input variables through variance decomposition. Specifically, the output variance can be expressed as the sum of the variance contributions of each input variable:

[0115]

[0116] where V i represents the contribution of a single input variable to the output variance, V ij represents the contribution of the interaction effect of two input variables to the output variance, k is the number of input parameters, and Var(Y) is the total output variance of the model;

[0117] 5. Calculate Sobol sensitivity indices:

[0118] The Sobol index is a quantitative indicator used to measure the contribution degree of each input parameter to the model output; calculate the first-order sensitivity index, second-order sensitivity index, and total-order sensitivity index through programming software:

[0119] First-order sensitivity index (S i ): Represents the contribution degree of a single input variable to the output variance. It can be understood as the influence degree of this input variable on the output result without considering other interaction effects. The calculation formula is as follows:

[0120]

[0121] S i is the first-order sensitivity index, V i represents the contribution of a single input variable to the output variance, and Var(Y) is the total output variance of the model;

[0122] Second-order sensitivity index (S ij ): Represents the contribution degree of the interaction effect of two input variables to the output variance. The calculation formula is as follows:

[0123]

[0124] S ij is the second - order sensitivity index, and V ij represents the contribution of the interaction effect of two input variables to the output variance;

[0125] Global sensitivity index (ST i ): It represents the total contribution of a certain input variable to the output, including the first - order effect of this variable and the interaction effects with other input variables. The calculation formula is as follows:

[0126]

[0127] ST i is the global sensitivity index, and V -i represents the variance of all parameters except the i - th parameter;

[0128] 6. Result analysis and interpretation:

[0129] According to the calculated sensitivity indices, analyze the sensitivity of each parameter to wheat / maize yield, leaf area index, and above - ground dry matter accumulation, and calibrate the input parameters with larger sensitivity indices;

[0130] Determine the sensitivity scores to be calibrated for each sub - region, and jointly use the particle swarm optimization algorithm (PSO) and the crop growth model for model parameter calibration. With the goal of minimizing the error between the measured and simulated values of crop growth indicators, realize the automatic calibration of sensitivity parameters in the crop growth model, obtain the crop parameters and soil parameters localized for the crop growth model, and establish a localized growth model for the wheat - maize rotation system.

[0131] The specific steps of PSO are as follows:

[0132] 1. Initialization: Set the initial particle swarm size, define the maximum number of algorithm iterations, and set the initial values of the positions and velocities of the particles. Each particle represents a set of model parameter combinations, the position is the model parameter combination, and the velocity is the step size for updating this particle;

[0133] 2. According to the objective function, evaluate the fitness of each particle, that is, minimize the error between the measured and simulated values of crop growth indicators. The fitness value is used to measure the quality of the solution of this particle;

[0134] 3. Update velocity and position: According to the historical best position (personal best) of the particle and the global best position in the population, use the update formula of particle swarm optimization to adjust the velocity and position of the particle;

[0135] 4. Local Optimal and Global Optimal Updates: After each particle updates its velocity and position, it recalculates its fitness value and compares it with its personal historical best position. If the current fitness is better, the personal optimal position is updated. Through the fitness evaluation of the entire population, the particle with the best fitness is selected as the global optimal;

[0136] 5. Evaluation: According to the objective function, the fitness of the updated particles is evaluated to calculate their performance in the optimization objective. Fitness evaluation is used to determine whether to update the personal optimal position and the global optimal position of the particles;

[0137] 6. Iterative Update: Repeat steps 3 to 5 until the maximum number of iterations is reached or the fitness value converges.

[0138] 7. Termination Condition: When the maximum number of iterations is reached or the fitness converges, the algorithm runs is terminated.

[0139] 8. Output Result: Output the optimal solution set, that is, the optimal combination of a set of model parameters that minimizes the error between the simulated value and the measured value.

[0140] According to the embodiment, the objective function of the local optimization model of the wheat - maize rotation system growth model in step S27 is as follows:

[0141]

[0142] In the formula, and are the measured value and the simulated value of the wheat / maize leaf area index respectively; and are the measured value and the simulated value of the above - ground dry matter accumulation of wheat / maize respectively; and are the measured value and the simulated value of the wheat / maize yield respectively; n is the number of samplings of the wheat / maize leaf area index and the above - ground dry matter accumulation in the measured sampling or experiment, and m is the number of samplings of the wheat / maize yield.

[0143] S3: Regional Long - term Reference Irrigation System Decision - making Scheme

[0144] Input the crop model driving data (crop data, field management data, meteorological data, and soil data) under the planned year into the localized wheat - maize rotation system growth model to construct a distributed growth localized model for the regional wheat - maize rotation system in the planned year; couple the distributed growth localized model of the wheat - maize rotation system with the multi - objective optimization model to clarify the soil water allocation and complementary relationship in the wheat - maize rotation system, clarify the regulatory effect of straw returning in the wheat - maize rotation system on soil water infiltration and irrigation demand, construct a regional grid - refined and dynamic irrigation decision - making technology, and with the maximization of regional wheat / maize yield, minimization of irrigation water volume, and maximization of wheat / maize economic benefits as the goals, and the upper and lower limits of soil volumetric water content and water supply conditions as the constraint conditions, obtain the Pareto optimal solution of the irrigation regime for the wheat - maize rotation system at a high - resolution regional level, and assign weights to multiple objectives through the TOPSIS comprehensive evaluation method to obtain the long - term irrigation regime for the wheat - maize rotation system in different regional spatial grids;

[0145] To formulate a long - term irrigation decision - making plan for the regional space, it is necessary to couple the distributed growth localized model of the wheat - maize rotation system with the multi - objective optimization model. The specific steps are as follows:

[0146] 1. Data input: Input the data required for the distributed growth localized model of the wheat - maize rotation system under the planned year into the crop model, including meteorological data, soil data, field management data, and localized model parameters, and create a distributed growth localized model of the wheat - maize rotation system adapted to the planned year; Determine the objective function: Determine the optimization objectives, namely, maximization of crop yield, minimization of irrigation water volume, and maximization of economic effects;

[0147] 2. Set constraint conditions: With the upper and lower limits of soil volumetric water content and regional water supply conditions as constraints, consider the soil allocation characteristics and water complementarity in the wheat - maize rotation system: At the end of the winter wheat growing season, the soil water should be adequately reserved to meet the water demand during the maize growing season. To ensure the limitation of available resources in actual production and the normal growth of wheat and maize;

[0148] The relationship formula between the soil water content of wheat and maize:

[0149] SM cron (t 0 )=SM wheat (t 1 )+SM(t 2 ,t 3 )

[0150] In the formula: SM cron (t0) is the soil water content at the beginning of the maize growth period; SMwheat(t1) is the soil water content at the time of winter wheat harvest; ΔSM(t2,t3) is the change in soil water (including the influence of precipitation, evaporation, and irrigation) between the end of winter wheat growth and the start of maize growth.

[0151] 3. Water resource allocation and complementarity among crops: Combining the seasonal characteristics of wheat - maize rotation, the water resource demands of winter wheat and summer maize are configured according to the soil moisture conditions during the growth periods of different crops in the optimization model.

[0152] 4. Influence of straw returning on soil water infiltration and irrigation demand: In the distributed growth local model of the wheat - maize rotation system, the improvement effect of straw returning on soil porosity and infiltration rate after the end of the maize growth season is considered.

[0153] Formula for the relationship between the soil volume water content at the initial stage of winter wheat and the straw returning of summer maize:

[0154] SM t =SM 0 +SM s -SM e

[0155] SM s =ΔSOM×S water

[0156] In the formula, SM t is the soil volume water content at the initial stage of winter wheat; SM 0 is the initial soil volume water content of winter wheat; SM s is the change in soil volume water content caused by straw returning; SM e is the soil water evaporation; ΔSOM is the amount of straw returning; S water is the ability coefficient of soil organic matter to retain water;

[0157] 5. Model coupling: Coupling the distributed growth local model of the wheat - maize rotation system with the multi - objective optimization model, the decision variables and crop input data of the optimization model are transferred to the distributed growth local model of the wheat - maize rotation system, and the yield, irrigation water volume and economic benefits after the operation of the distributed growth local model of the wheat - maize rotation system are fed back to the optimization model;

[0158] 6. Model solution: The NSGA - Ⅱ algorithm is used to solve the optimization model, and the Pareto optimal solution set of irrigation regimes under high - resolution grids in the region is output;

[0159] Furthermore, the specific steps of NSGA - Ⅱ are as follows:

[0160] Initialization: Set the initial population size, define the maximum number of algorithm iterations, set the crossover probability and mutation probability, randomly generate the initial population, and each individual is a set of irrigation regime combinations for each grid;

[0161] Evaluation: According to the objective function, evaluate the fitness of each individual, that is, maximizing the regional crop yield, minimizing the irrigation water volume and maximizing the economic benefits;

[0162] Selection: Individuals are ranked through non - dominated sorting and the crowding distance is calculated to maintain diversity. Preferentially select individuals with a lower non - dominated rank and a larger crowding distance;

[0163] Crossover: Perform crossover operations on the selected parent individuals to generate new individuals; The crossover operation determines whether to perform crossover through the crossover probability. By combining the gene information of two parent individuals, new individuals are generated;

[0164] Mutation: Perform mutation operations on the individuals after crossover to increase population diversity and avoid falling into local optima; The mutation operation determines whether to perform mutation through the mutation probability. By randomly changing the gene information of individuals, new individuals are generated;

[0165] Evaluation: Evaluate the fitness of the newly generated individuals according to the objective function, calculate their performance in the optimization objective, and use it for sorting and screening;

[0166] Replacement: Select the parents and offspring through non - dominated sorting and crowding distance, optimize and retain high - quality individuals, and generate the next generation of the population;

[0167] Termination condition: Terminate the algorithm when the maximum number of iterations is reached or the fitness converges;

[0168] Output result: Output the optimal solution set, that is, a set of optimal combinations of grid irrigation systems that maximize regional crop yield, minimize irrigation water volume, and maximize economic benefits;

[0169] Select the best by TOPSIS comprehensive evaluation method: Select the best from the Pareto solution set, and further select the best from the Pareto solution set using the TOPSIS comprehensive evaluation method;

[0170] The specific steps of the TOPSIS comprehensive evaluation method are as follows:

[0171] 1. Determine evaluation indicators: Clearly define the decision - making objective and select relevant evaluation indicators, that is, the larger the crop yield value, the better, the smaller the irrigation water volume value, the better, and the larger the economic benefit value, the better;

[0172] 2. Construct the normalized decision matrix: Organize and normalize the original data, and organize the crop yield, irrigation water volume, and economic benefit data in the Pareto solution set into a decision matrix \(D_{i×j}\), where \(i\) represents the number of Pareto solution sets and \(j\) represents the number of decision-making objectives. Each row of this matrix is an alternative solution. Use the linear normalization method to convert the data into a unified scale; Determine the evaluation index weights: For different weight combinations of each evaluation index from the perspective of decision-maker preferences, it can be divided into long-term irrigation system plans for wheat-maize rotation systems in high water use efficiency and economic benefit regions, long-term irrigation system plans for wheat-maize rotation systems in high yield and economic benefit regions, and long-term irrigation system plans for wheat-maize rotation systems in water-saving and economic benefit regions;

[0173] 3. Calculate the positive and negative ideal solutions: Calculate the distances from each alternative solution to the positive and negative ideal solutions;

[0174] 4. Conduct ranking: Calculate the relative closeness based on the distances from each alternative solution to the positive and negative ideal solutions, and rank the alternative solutions according to the relative closeness. The one with the largest value is the best long-term irrigation decision plan for the regional wheat-maize rotation system under this preference angle.

[0175] According to some embodiments, the objective function of the regional space long-term irrigation decision optimization model is as follows:

[0176] Obj 1 = max TWSO

[0177] Obj 2 = min I

[0178] Obj 3 = max NEB

[0179] In the formula, TWSO is the wheat / maize yield per unit area; I is the irrigation water volume per unit area; NEB is the wheat / maize economic benefit per unit area;

[0180] The constraint conditions of the distributed growth localization model of the regional wheat-maize rotation system are as follows:

[0181] Soil moisture content constraint:

[0182] SM min ≤ SM ≤ SM max

[0183] In the formula, SM represents the soil moisture content in the root zone, and SM min and SM max represent the lower and upper limits of the soil moisture content in the root zone respectively;

[0184] Irrigation water volume constraint:

[0185] I < R

[0186] Wherein, I is the irrigation water volume per unit area; R is the available water volume per unit area;

[0187] Yield constraint:

[0188] ΣTWSO·A = TWSO REG

[0189] Wherein, TWSO REG is the grain demand in the area where the irrigation district is located;

[0190] S4: Real-time dynamic correction scheme for regional irrigation regime

[0191] Take the long-term irrigation regime of the regional spatial grid wheat-maize rotation system as the reference irrigation regime and apply it to the decision-making area. Input the crop data, soil data, hydrological data, meteorological data, field management data, and water supply data read in real time into the distributed growth local model of the regional wheat-maize rotation system to explore the impact of climate change on the phenological period of the wheat-maize rotation system and optimize the field management strategy. When the irrigation regime is adjusted in real time with the biomass, water demand, and available water volume in each period as constraints, judge whether to correct the reference irrigation regime; couple the distributed growth local model of the wheat-maize rotation system with the multi-objective optimization model to construct a refined and dynamic irrigation correction technology for the regional grid, with the maximization of biomass in each period, the minimization of water demand decision error, and the maximization of economic benefits as the goals, and the soil volumetric water content and water supply conditions as constraints, and correct the reference irrigation regime in real time.

[0192] The real-time dynamic correction scheme for regional irrigation regime is as follows:

[0193] 1. Take the regional long-term irrigation regime as the reference long-term irrigation regime and apply it to the research area, and set the above-ground biomass corresponding to the reference long-term irrigation regime as the reference above-ground biomass.

[0194] 2. Obtain the remote sensing images of the irrigation decision-making area through the satellite platform or unmanned aerial vehicle, and inversely obtain the crop data such as above-ground biomass and leaf area index in combination with the regression model; obtain the real-time soil data by arranging soil moisture monitors in the irrigation decision-making area; obtain the hydrological data through the long-term runoff monitoring data of the hydrological station; obtain the real-time meteorological data by setting up small meteorological stations in the irrigation decision-making area; obtain the field management data by the real-time input of agricultural management measures by the field manager, and the agricultural management measures include but are not limited to: single irrigation volume, irrigation date, fertilization amount, fertilization date;

[0195] 3. At the end of winter wheat harvest or summer maize harvest, explore the impact of real-time meteorological condition changes on the phenological period of wheat and maize by real-time reading of driving data, input the future meteorological data into the distributed growth local model of the regional wheat-maize rotation system, and explore the best sowing dates of summer maize or winter wheat with the maximization of yield as the goal.

[0196] 4. Input the real-time driving data into the distributed growth localization model of the regional wheat-maize rotation system, and judge whether to correct the reference irrigation regime through constraint conditions. For grid points that do not meet any of the three constraint conditions, the irrigation regime needs to be re-decided, while grid points that meet the constraint conditions follow the reference irrigation regime. The specific constraint conditions are as follows:

[0197] Biomass constraint for a time period:

[0198] K·Bio≥Bio R

[0199] In the formula, K is the correction coefficient; Bio is the biomass for a time period; Bio R is the biomass for a time period under the reference irrigation regime;

[0200] Water supply constraint:

[0201] Q S ≥Q D

[0202] In the formula, Q S is the water supply; Q D is the water demand;

[0203] Water demand decision error constraint:

[0204]

[0205] In the formula, I R is the total irrigation amount for the current time period, P is the rainfall for the current time period; ET is the water demand for the current time period

[0206] 5. Re-decide the irrigation regime for the next 15 days for the grid points that need to update the irrigation regime. To ensure the operation efficiency of the model, the particle swarm algorithm is used to solve the model, and an adaptive correction decision model is constructed with the maximization of biomass for a time period and the minimization of water demand decision error as the objectives.

[0207] The preferred embodiments of the present invention are described in detail above, but the present invention is not limited to the above embodiments. Within the knowledge scope of those of ordinary skill in the art, various changes can be made without departing from the gist of the present invention.

[0208] Many other changes and modifications can be made without departing from the concept and scope of the present invention. It should be understood that the present invention is not limited to the specific embodiments, and the scope of the present invention is defined by the appended claims.

Claims

1. A rolling correction intelligent irrigation decision method for a regional wheat-corn rotation system, characterized in that: The method comprises: S1: Input the acquired driving data into the crop growth model, use the Sobol method to perform sensitivity analysis on the crop growth model parameters, screen out the non-sensitive parameters in the crop growth model, set them as default values, calibrate the sensitive parameters, and calibrate the model parameters by combining the particle swarm optimization algorithm PSO with the crop growth model. With the goal of minimizing the error between the measured value and the simulated value of the crop growth index, automatically calibrate the sensitive parameters in the crop growth model, obtain the localized crop parameters and soil parameters of the crop growth model, and establish a localized wheat-corn rotation system growth model. S2: Input the crop model driving data of the planning year into the localized wheat-corn rotation system growth model, construct the distributed growth localized model of the regional wheat-corn rotation system in the planning year, and couple it with the multi-objective optimization model to determine the impact of water allocation and straw return on soil moisture and irrigation demand, that is, to obtain the regional spatial long-term irrigation decision-making optimization model; based on the goals of maximizing regional yield, minimizing irrigation volume and maximizing economic benefits, obtain the high-resolution Pareto optimal solution of the irrigation system, and use the TOPSIS method to assign weights to the long-term irrigation systems of different regions, and obtain different regional spatial grid wheat-corn rotation system long-term irrigation systems; S3: Taking the long-term irrigation system as a reference, real-time crop data, soil data, hydrological data, meteorological data, field management data and water supply data are collected and input into the regional spatial long-term irrigation decision-making optimization model to determine the impact of climate change on phenological periods and optimize field management strategies. The irrigation system is adjusted in real time with the biomass, water demand and water supply as constraints to determine whether to correct the reference irrigation system. By coupling the multi-objective optimization model, a dynamic irrigation correction method is constructed to adjust the irrigation plan in real time with the goal of maximizing biomass, minimizing water demand decision errors and economic benefits.

2. The rolling correction intelligent irrigation decision method for regional wheat-corn rotation system according to claim 1 is characterized in that: Before step S1, the method further includes: Drive data collection, use remote sensing, field soil testers and meteorological stations to collect crop data, meteorological data, field management data and soil data of winter wheat and summer corn; regional division, divide the decision area into multiple sub-areas according to crop distribution maps, soil types and water supply conditions, and perform raster processing.

3. The rolling correction intelligent irrigation decision method for regional wheat-corn rotation system according to claim 1 is characterized in that: The specific process of the Sobol method in step S1 and the parameter calibration of the combined PSO algorithm and the crop growth model include: S101: Determine model input parameters and target variables: Determine input parameters and parameter ranges of the wheat / maize growth model, the input parameters include: crop parameters, soil parameters and meteorological parameters; determine target variables of the wheat / maize growth model, the target variables are the wheat / maize leaf area index and aboveground dry matter accumulation output in time series and the wheat / maize yield output in non-time series; S102: Sampling of input variables: Use Latin hypercube sampling to ensure that each variable is evenly distributed within its range, and generate a set of sample points for each input variable for model calculation; S103: Model evaluation: Output the sample data generated by the Latin hypercube sampling method, run the model to calculate its output results, repeat this process, and perform sensitivity analysis to ensure the sample size and analysis accuracy; S104: Calculate variance decomposition: The Sobol method evaluates the impact of input variables by variance decomposition; the output variance is expressed as the sum of the variance contributions of each input variable: Among them, V i Represents the contribution of a single input variable to the output variance, V ij It represents the contribution of the interaction effect of two input variables to the output variance, k is the number of input parameters, and Var(Y) is the total output variance of the model; S105: Calculate Sobol sensitivity index: The Sobol index is a quantitative index used to measure the contribution of each input parameter to the model output; the first-order sensitivity index, the second-order sensitivity index and the full-order sensitivity index are calculated by programming software: The first-order sensitivity index (S i ): The contribution of a single input variable to the output variance is the degree of influence of the input variable on the output result without considering other interactions. The calculation formula is as follows: S i is the first-order sensitivity index, V i It represents the contribution of a single input variable to the output variance, and Var(Y) is the total output variance of the model; The second-order sensitivity index (S ij ): It represents the contribution of the interaction between two input variables to the output variance. The calculation formula is as follows: S ij is the second-order sensitivity index, V ij It represents the contribution of the interaction effect of two input variables to the output variance; Global sensitivity index (ST i ): It represents the total contribution of an input variable to the output, including the first-order effect of the variable and the interaction effect with other input variables. The calculation formula is as follows: ST i is the global sensitivity index, V -i represents the variance of all parameters except the i-th parameter; S106: Result analysis and interpretation: Based on the calculated sensitivity indexes, analyze the sensitivity of each parameter to wheat / corn yield, leaf area index and aboveground dry matter accumulation, and calibrate the input parameters with greater sensitivity indexes; S107: Parameter calibration of wheat-corn rotation system growth model: The sensitive parameters of the model were screened out through the Sobol analysis method, and the parameters were calibrated by combining PSO with the wheat-corn rotation system growth model.

4. The rolling correction intelligent irrigation decision method for regional wheat-corn rotation system according to claim 3 is characterized in that: The specific steps of PSO in step S107 are as follows: S1071: Initialization: Set the initial particle swarm size, define the maximum number of iterations of the algorithm, and set the initial values ​​of the particle position and velocity. Each particle represents a set of model parameter combinations. The position is the model parameter combination, and the velocity is the step size when the particle is updated. S1072: Evaluate the fitness of each particle according to the objective function, that is, minimize the error between the measured value and the simulated value of the crop growth index, and the fitness value is used to measure the quality of the particle solution; S1073: Update speed and position: According to the historical optimal position of the particle and the global optimal position in the population, the particle speed and position are adjusted using the particle swarm optimization update formula; S1074: Local optimum and global optimum update: After updating the speed and position, each particle recalculates its fitness value and compares it with its personal best historical position. If the current fitness is better, the personal best position is updated. Through the fitness evaluation of the entire population, the particle with the best fitness is selected as the global optimum. S1075: Evaluation: Perform fitness evaluation on the updated particles according to the objective function and calculate their performance in the optimization objective. The fitness evaluation is used to decide whether to update the individual optimal position and global optimal position of the particles; S1076: Iterative update: repeat steps S2073 to S2075 until the maximum number of iterations is met or the fitness value converges; S1077: Termination condition: When the maximum number of iterations is reached or the fitness converges, the algorithm is terminated; S1078: Output result: Output the optimal solution set, that is, the optimal combination of model parameters that minimizes the error between the simulated value and the measured value.

5. The rolling correction intelligent irrigation decision method for regional wheat-corn rotation system according to claim 1 is characterized in that: The objective function of the localized wheat-corn rotation system growth model is as follows: Where LAI i m and LAI i s are the measured and simulated values ​​of wheat / corn leaf area index; TAGP i m and TAGP i s are the measured and simulated values ​​of aboveground dry matter accumulation of wheat and corn respectively; TWSO i m and TWSO i s are the measured value and simulated value of wheat / maize yield respectively; n is the sampling times of wheat / maize leaf area index and aboveground dry matter accumulation in the measured sampling or experiment; m is the sampling times of wheat / maize yield.

6. The rolling correction intelligent irrigation decision method for regional wheat-corn rotation system according to claim 1 is characterized in that: The step S2 comprises: S201: Data input: input the data required by the distributed growth localization model of the wheat-maize rotation system in the planned year into the crop model, including meteorological data, soil data, field management data and localization model parameters, to create a distributed growth localization model of the wheat-maize rotation system suitable for the planned year; determine the objective function: determine the optimization objectives, namely, maximizing crop yield, minimizing irrigation water and maximizing economic effect; S202: Set constraints: Take the upper and lower limits of soil volume moisture content and regional water supply conditions as constraints, and consider the soil allocation characteristics and water complementarity in the wheat-corn rotation system: At the end of the winter wheat growing season, the soil moisture reserve should be sufficient to meet its moisture demand when entering the corn growing season, in order to ensure the limitation of available resources in actual production and ensure the normal growth of wheat and corn; The relationship formula between wheat and maize soil moisture content: SM cron (t0)=SM wheat (t1)+SM(t2,t3) Where: SM cron (t0) is the soil moisture content at the beginning of the maize growth period; SM wheat (t1) is the soil moisture content at the time of winter wheat harvest; ΔSM(t2, t3) is the change in soil moisture between the end of winter wheat growth and the beginning of corn growth, including the effects of precipitation, evaporation and irrigation; S203: Water resource allocation and complementarity among crops: Combined with the seasonal characteristics of wheat-corn rotation, the water resource demand of winter wheat and summer corn in the optimization model is allocated according to the soil moisture conditions in different crop growth periods; S204: Effect of returning straw to the field on soil water infiltration and irrigation demand: In the distributed growth localization model of the wheat-maize rotation system, the improvement effect of returning straw to the field on soil porosity and infiltration rate after the maize growing season is considered; The relationship between returning summer corn straw to the field and the soil volume moisture content of winter wheat in the early stage is as follows: SM t =SM0+SM s -SM e SM s =ΔSOM×S water Where SM t is the initial soil volumetric moisture content of winter wheat; SM0 is the initial soil volumetric moisture content of winter wheat; SM s is the change in soil volume moisture content caused by returning straw to the field; SM e is the amount of soil water evaporation; ΔSOM is the amount of straw returned to the field; S water is the coefficient of soil organic matter's ability to retain water; S205: Model coupling: coupling the distributed growth localization model of the wheat-jade rotation system with the multi-objective optimization model, transferring the decision variable crop input data of the optimization model to the distributed growth localization model of the wheat-jade rotation system, and feeding back the yield, irrigation water volume and economic benefits of the distributed growth localization model of the wheat-jade rotation system to the optimization model after the operation is completed; S206: Model solution: NSGA-Ⅱ algorithm is used to solve the optimization model and output the Pareto optimal solution set of irrigation system under regional high-resolution grid; S207: TOPSIS comprehensive evaluation method selection: Pareto solution set selection, and use TOPSIS comprehensive evaluation method to further select the Pareto solution set.

7. The rolling correction intelligent irrigation decision method for regional wheat-corn rotation system according to claim 6 is characterized in that: The step S207 includes: S2071: Determine the evaluation indicators: clarify the decision-making goals and select relevant evaluation indicators, that is, the larger the crop yield value, the better, the smaller the irrigation value, the better, and the larger the economic benefit value, the better; S2072: Construct a normalized decision matrix: The original data is sorted and normalized, and the crop yield, irrigation volume and economic benefit data in the Pareto solution set are sorted into a decision matrix Di×j, where i represents the number of Pareto solution sets, and j represents the number of decision targets. Each row of the matrix is ​​an alternative plan, and the linear normalization method is used to convert the data into a unified scale; Determine the weights of evaluation indicators: Different weight combinations are made for each evaluation indicator based on the decision maker's preference, which can be divided into a long-term irrigation system plan for wheat-jade rotation system in high water efficiency and economic benefit areas, a long-term irrigation system plan for wheat-jade rotation system in high yield and economic benefit areas, and a long-term irrigation system plan for wheat-jade rotation system in water-saving and economic benefit areas; S2073: Calculate positive and negative ideal solutions: Calculate the distance from each alternative solution to the positive and negative ideal solutions; S2074: Sorting: Calculate the relative proximity of each alternative plan to the positive and negative ideal solutions, and sort the alternative plans according to the relative proximity. The one with the largest value is the best long-term irrigation decision plan for the regional wheat-maize rotation system under the preference angle.

8. The rolling correction intelligent irrigation decision method for regional wheat-corn rotation system according to claim 1 is characterized in that: The objective function of the regional spatial long-term irrigation decision optimization model is as follows: Obj1=maxTWSO Obj2=minI Obj3=maxNEB Where, TWSO is the wheat / corn yield per unit area; I is the irrigation water per unit area; NEB is the economic benefit of wheat / corn per unit area; The constraints of the distributed growth localization model of the regional wheat-maize rotation system are as follows: Soil moisture constraints: SM min ≤SM≤SM max Where SM represents the soil moisture content in the root zone, SM min and SM max Respectively represent the lower and upper limits of soil moisture content in the root zone; Irrigation water constraints: I<R In the formula, I is the irrigation water per unit area; R is the available water per unit area; Production Constraints: ΣTWSO·A=TWSO REG Where, TWSO REG It is the grain demand in the area where the irrigation district is located.

9. The rolling correction intelligent irrigation decision method for regional wheat-corn rotation system according to claim 1 is characterized in that: The step S3 comprises: S301: Apply the regional long-term irrigation system as the reference long-term irrigation system to the study area, and set the corresponding aboveground biomass under the reference long-term irrigation system as the reference aboveground biomass; S302: Obtain remote sensing images of the irrigation decision area through satellite platforms or drones, and obtain aboveground biomass and leaf area index crop data through regression model inversion; obtain real-time soil data by arranging soil moisture monitors in the irrigation decision area; obtain hydrological data through a series of runoff monitoring data from the hydrological station; obtain real-time meteorological data by setting up a small meteorological station in the irrigation decision area; obtain field management data through real-time input of agricultural management measures by field managers, and agricultural management measures include: single irrigation amount, irrigation date, fertilization amount, and fertilization date; S303: After the winter wheat harvest or the summer corn harvest is completed, the impact of the real-time meteorological condition changes on the wheat and corn phenological period is explored by reading the driving data in real time, and the future meteorological data is input into the distributed growth localization model of the regional wheat and corn rotation system, and the optimal sowing date of summer corn or winter wheat is explored with the goal of maximizing the yield; S304: Input the real-time driving data into the distributed growth localization model of the regional wheat-maize rotation system, and determine whether to modify the reference irrigation system through the constraints. The grid points that do not meet any of the three constraints need to re-determine the irrigation system, and the grid points that meet the constraints follow the reference irrigation system. The specific constraints are as follows: Biomass constraints during the period: K·Bio≥Bio R In the formula, K is the correction coefficient; Bio is the biomass of the period; R is the biomass of the period under the reference irrigation regime; Water supply constraints: Q S ≥Q D In the formula, Q S is the water supply; Q D is the water requirement; Water demand decision error constraint: In the formula, I R is the total irrigation amount in the current period, P is the rainfall in the current period; ET is the water demand in the current period; S305: For grids that need to update the irrigation system, the irrigation system for the next 15 days is re-determined. To ensure the efficiency of the model operation, the particle swarm algorithm is used to solve the model, and an adaptive correction decision model is constructed with the goal of maximizing the biomass in the time period and minimizing the water demand decision error.

Images