An intelligent decision-making method for regional irrigation coupled with crop growth process simulation

Abstract

The application provides a regional irrigation intelligent decision-making method coupled with crop growth process simulation, belongs to the field of agricultural technology, and adopts an agricultural production system simulator to simulate the relationship between irrigation water and yield, so that the relationship considers the yield of crops under rain-fed conditions; a rating system of the original economic-social-ecological multidimensional development level of each region is constructed, the influence of the multidimensional system on the optimization of planting structure is considered; the obtained irrigation water-yield function relationship and multidimensional evaluation indexes are input into the constructed model; and the best planting and irrigation water scheme is obtained through the constructed economic benefit model, environmental effect model and resource utilization efficiency model. The application can realize the sustainable development of agriculture on the basis of optimizing the structure of water and soil resources.

Description

Technical Field

[0001] This invention belongs to the field of agricultural technology, and in particular relates to a regional irrigation intelligent decision-making method coupled with crop growth process simulation. Background Technology

[0002] Rational allocation of agricultural water and soil resources is an effective means of increasing production. Existing fixed planting patterns may not be optimal. Therefore, this study, considering economic, environmental, and resource utilization efficiency goals, no longer sets specific planting ratios for each crop. Instead, it uses a constructed model to find the optimal planting structure and irrigation water volume, achieving a balance across multiple objectives. However, this process also needs to consider the advantages and convenience of developing the existing planting structure in the region. A multi-dimensional evaluation index encompassing economic, social, and ecological dimensions has been established to account for the impact of existing planting structure development on the model. Summary of the Invention

[0003] The purpose of this invention is to address the problems existing in the prior art by providing a regional irrigation intelligent decision-making method coupled with crop growth process simulation. This method uses an agricultural production system simulator to simulate the relationship between irrigation water volume and yield, establishing a relationship that considers crop yield under rain-fed conditions. It also constructs a rating system for the original economic, social, and ecological multi-dimensional development levels of various regions, considering the impact of the multi-dimensional system on planting structure optimization. The obtained irrigation water volume-yield function relationship and multi-dimensional evaluation indicators are input into the constructed model. Through the constructed economic benefit model, environmental effect model, and resource utilization efficiency model, the optimal planting and irrigation water scheme is obtained, thereby achieving sustainable agricultural development based on optimizing the water and soil resource structure.

[0004] The specific technical solution is as follows:

[0005] A regional irrigation intelligent decision-making method coupled with crop growth process simulation includes the following steps:

[0006] S1: Basic Data Collection; Using remote sensing information technology, the Agricultural Production System Simulator (APSIM) model was used to simulate crop yields at a 1km×1km scale across the country, simulating the functional relationship between yield and water quantity for three crops: rice, corn, and soybeans; During the APSIM model simulation, national land parameters and meteorological data were input, and based on the input information, the yield relationships of various crops in different regions were obtained:

[0007] YA ik =aIQ ik +Yrain ik

[0008] In the formula, i is the partition index, i = 1...I; k is the crop type, k = 1...K; YA ikIt is the yield per unit area of ​​crop k in zone i, kg / hm² 2 IQ ik The irrigation water amount for crop k in partition i is the decision variable, m. 3 / hm 2 Yrain ik Crop yield under non-irrigation conditions for crop k in zone i, kg / hm 2 ;

[0009] S2: Construct the objective function;

[0010] (1) Construct an economic objective function. The economic objective is the net income, which is the difference between the profits obtained from selling the harvested crop and the costs incurred during the planting process.

[0011] maxEB=EI-C

[0012] In the formula, EB represents the net income of the crop, in yuan; EI represents the income, in yuan; and C represents the planting cost, in yuan.

[0013]

[0014] In the formula, χ ik PR represents the loss coefficient for planting crop k in partition i; ik Indicates the price of crop k in region i, in yuan / kg; A ik hm represents the planting area of ​​crop k in zone i in the first year. 2 ;

[0015] Planting costs:

[0016] C = CGF + CWF + CPF

[0017] In the formula, CGF represents the cost of grain cultivation, expressed in yuan / hm². 2 CWF represents the cost of water used for grain production, in yuan; CPF represents the cost of electricity consumed for irrigation, in yuan.

[0018]

[0019] In the formula, This represents the fertilizer price for crop k in region i, expressed in yuan / kg. This represents the fertilizer application rate for crop k in region i, expressed in kg / hm². 2 ; This represents the pesticide price for crop k in region i, expressed in yuan / kg. This represents the pesticide application rate for crop k in region i, expressed in kg / hm². 2 ; This represents the price of diesel fuel for agricultural machinery in crop k of region i, expressed in yuan / kg. This represents the amount of diesel fuel used by agricultural machinery for crop k in zone i, in kg / hm².2 ; This represents the price of agricultural film for crop k in region i, expressed in yuan / kg. This represents the amount of agricultural film used for crop k in zone i, in kg / hm². 2 ; This represents the seed price of crop k in zone i for the first year, in yuan / kg; This represents the seed usage of crop k in partition i, in kg / hm². 2 ; This represents the labor cost per person for crop k in partition i; This represents the amount of labor used for crop k in partition i, in people / hm. 2 ;

[0020]

[0021] In the formula, Wpr i This represents the water price in zone i, in yuan / m³. 3 IQ ik The irrigation water amount for crop k in partition i is the decision variable, m. 3 / hm 2 ;

[0022]

[0023] In the formula, Wpw i Pw represents the electricity price in partition i, in kWh / yuan; i This represents the electricity consumption per cubic meter of water in partition i, in kWh / m³. 3 ;

[0024] (2) Greenhouse gas emission (GHG) targets, quantifying CO2, CH4 and N2O emissions during planting activities; CO2 emissions are generated by the use of materials; CH4 emissions come from paddy fields; N2O emissions include soil emissions and emissions from fertilizer application;

[0025]

[0026]

[0027]

[0028]

[0029]

[0030] In the formula, This represents carbon dioxide emissions, expressed in kgCO. 2 ; This indicates methane emissions from rice paddies, expressed in kgCH4. Indicates the impact of nitrous oxide emissions, kgN2O; κ fer This represents the carbon dioxide emission factor from fertilizers, expressed as kgCO2 / kg; κ pes κ represents the carbon dioxide emission factor of pesticides, kgCO2 / kg; mac κ represents the carbon dioxide emission factor of fuel, kgCO2 / kg; film The carbon dioxide emission factor of agricultural film is expressed as kgCO2 / kg; κ lab κ represents the anthropogenic carbon dioxide emission factor, kgCO2 / person; pw The carbon dioxide emission factor for electricity is expressed as kgCO2 / kWh. This represents the methane emissions per unit area, expressed in kgCH4 / hm². 2 ; The direct N2O emissions during soil nitrification and denitrification in crop k of partition i are represented (this part was obtained through APSIM simulation), kgN2O / hm. 2 ; Indirect N2O emissions during soil nitrification and denitrification processes in crop k of zone i, kg N2O / hm 2 N ik This is the total soil nitrogen application per hectare per two years for crop k in zone i, in kg / hm². 2 ;

[0031] (3) Water use efficiency target is an indicator that measures the relationship between crop yield and water consumption, and is also one of the comprehensive indicators for evaluating the suitability of plant growth under water deficit. This indicator is expressed by dividing yield by water consumption in the classic way:

[0032]

[0033] In the formula, WUE is water use efficiency;

[0034] S3: Set the model boundary: The model boundary constraints include irrigation water constraints, food security constraints, land policy constraints, and the constraint that decision variables should not be negative;

[0035] (1) Irrigation water constraints

[0036] The allocation of irrigation water should not exceed the irrigation water supply of each zone;

[0037]

[0038] In the formula, Q represents the total available water volume, m 3 η represents irrigation water use efficiency;

[0039] (2) Food security

[0040] The total grain output must meet the needs of the population and the volume of imports and exports. This constraint is expressed as:

[0041]

[0042] In the formula, EX k This represents the amount of grain (in kg) that crop k needs to be exported; IM k PO represents the amount of grain imported from abroad for crop k, in kg; PO represents the population that needs to be satisfied, in people; FD represents the food demand, in kg / person.

[0043] (3) Land Policy

[0044] Optimize the existing planting plan so that the total planted area is less than the maximum allowed planting area in each region; this constraint is expressed as follows:

[0045]

[0046] In the formula, This represents the maximum amount of land available for all crop cultivation, expressed in hectares (hm). 2 ;

[0047] (4) Decision variables should not be negative;

[0048] A ik ≥0

[0049] IQ ik ≥0

[0050] S4: Model Solving: The study area was divided into 1km×1km grids using R language, and the spatial grid was solved using a cellular automata multi-objective algorithm. With regional economic-environment-resource efficiency as the objective function, grid-point crop planting structure and irrigation water volume as decision variables, and irrigation water volume, food security and land policy as constraints, a regional crop water and soil resource spatial optimization model was constructed by loosely coupling the regional crop model APSIM.

[0051] S5: Loss coefficient evaluation index: In the process of adjusting the planting structure, the impact of economic, social and ecological dimensions on the planting of various crops should also be considered.

[0052] (1) Economic dimension, the indicators include total output value, net benefit, demand rate, profit rate, price, and economic benefit per unit area;

[0053] (2) Social dimension, the indicators include yield per unit area, labor productivity, arable land pressure index, income stability, matching degree of engineering settings, technological development, and labor utilization rate;

[0054] (3) Ecological dimension, indicators include energy use, soil, ecological environment, and application of pesticides and fertilizers;

[0055] S6: The indicators of the economic-social-ecological dimensions constructed in S5 are tested using the analytic hierarchy process (AHP) to calculate the risk weights of each dimension and indicator.

[0056]

[0057] In the formula, X n It is the risk score result of each indicator; C n This indicates the results of each indicator;

[0058] The final risk value R is calculated by multiplying the expert's overall score for each indicator by the weight value of that indicator.

[0059]

[0060] In the formula, P j w represents the expert comprehensive score assigned to the j-th indicator in the indicator layer; uj This represents the composite weight, i.e., the overall priority weight of the j-th element to the target layer;

[0061] For each crop in each region, steps S4 and S5 are calculated, and χ is finally obtained. ik .

[0062] The present invention has the following advantages:

[0063] (1) Use an agricultural production system simulator to simulate the relationship between crop yield and irrigation water volume;

[0064] (2) Explore the optimal planting structure by considering three objectives: economy, environment and resource utilization efficiency;

[0065] (3) Considering the original development level of each region, construct a multi-dimensional evaluation system and explore the impact of the original development level of the region on the adjustment of planting structure. Detailed Implementation

[0066] The specific technical solutions of the present invention will be described with reference to the embodiments.

[0067] The specific technical solution of this invention: a regional irrigation intelligent decision-making method coupled with crop growth process simulation, comprising the following steps:

[0068] S1: Basic Data Collection; Using remote sensing information technology, the Agricultural Production System Simulator (APSIM) model is used to simulate crop yields at a 1km × 1km scale across the country, simulating the functional relationship between yield and water quantity for three crops: rice, corn, and soybeans. During the APSIM model simulation, information such as national land parameters and meteorological data is required as input. Based on the input information, the yield relationships of various crops in different regions are obtained:

[0069] YA ik =aIQ ik +Yrain ik

[0070] In the formula, i is the partition index, i = 1...I; k is the crop type, k = 1...K; YA ik It is the yield per unit area of ​​crop k in zone i, kg / hm² 2 IQ ik The irrigation water amount (decision variable) for crop k in partition i, m 3 / hm 2 Yrain ik Crop yield under non-irrigation conditions for crop k in zone i, kg / hm 2 .

[0071] S2: Construct the objective function.

[0072] (1) Construct an economic objective function. The economic objective mainly refers to net income, which is the difference between the benefits obtained from selling the harvested crop and the costs incurred during the planting process.

[0073] maxEB=EI-C

[0074] In the formula, EB represents the net income of the crop, in yuan; EI represents the income, in yuan; and C represents the planting cost, in yuan.

[0075]

[0076] In the formula, χ ik PR represents the loss coefficient for planting crop k in partition i; ik Indicates the price of crop k in region i, in yuan / kg; A ik hm represents the planting area of ​​crop k in zone i in the first year. 2 .

[0077] Planting costs:

[0078] C = CGF + CWF + CPF

[0079] In the formula, CGF represents the cost of grain cultivation, expressed in yuan / hm². 2 CWF represents the cost of water used for grain production, in yuan; CPF represents the cost of electricity consumed for irrigation, in yuan.

[0080]

[0081] In the formula, This represents the fertilizer price for crop k in region i, expressed in yuan / kg. This represents the fertilizer application rate for crop k in region i, expressed in kg / hm². 2 ; This represents the pesticide price for crop k in region i, expressed in yuan / kg. This represents the pesticide application rate for crop k in region i, expressed in kg / hm². 2 ; This represents the price of diesel fuel for agricultural machinery in crop k of region i, expressed in yuan / kg. This represents the amount of diesel fuel used by agricultural machinery for crop k in zone i, in kg / hm². 2 ; This represents the price of agricultural film for crop k in region i, expressed in yuan / kg. This represents the amount of agricultural film used for crop k in zone i, in kg / hm². 2 ; This represents the seed price of crop k in zone i for the first year, in yuan / kg; This represents the seed usage of crop k in partition i, in kg / hm². 2 ; This represents the labor cost per person for crop k in partition i; This represents the amount of labor used for crop k in partition i, in people / hm. 2 .

[0082]

[0083] In the formula, Wpr i This represents the water price in zone i, in yuan / m³. 3 IQ ik Let m represent the irrigation water amount (decision variable) for crop k in partition i. 3 / hm 2 .

[0084]

[0085] In the formula, Wpw i Pw represents the electricity price in partition i, in kWh / yuan; i This represents the electricity consumption per cubic meter of water in partition i, in kWh / m³. 3 .

[0086] (2) Greenhouse gas emissions (GHG) targets primarily quantify CO2, CH4, and N2O emissions during planting activities. CO2 emissions are generated by the use of materials. CH4 emissions mainly originate from paddy fields. N2O emissions primarily include soil emissions and emissions from fertilizer application.

[0087]

[0088]

[0089]

[0090]

[0091]

[0092] In the formula, This represents carbon dioxide emissions, expressed in kgCO. 2 ; This indicates methane emissions from rice paddies, expressed in kgCH4. Indicates the impact of nitrous oxide emissions, kgN2O; κ fer This represents the carbon dioxide emission factor from fertilizers, expressed as kgCO2 / kg; κ pes κ represents the carbon dioxide emission factor of pesticides, kgCO2 / kg; mac κ represents the carbon dioxide emission factor of fuel, kgCO2 / kg; film The carbon dioxide emission factor of agricultural film is expressed as kgCO2 / kg; κ lab κ represents the anthropogenic carbon dioxide emission factor, kgCO2 / person; pw The carbon dioxide emission factor for electricity is expressed as kgCO2 / kWh. This represents the methane emissions per unit area, expressed in kgCH4 / hm². 2 ; The direct N2O emissions during soil nitrification and denitrification in crop k of partition i are represented (this part was obtained through APSIM simulation), kgN2O / hm. 2 ; Indirect N2O emissions during soil nitrification and denitrification processes in crop k of zone i, kg N2O / hm 2 N ik This is the total soil nitrogen application per hectare per two years for crop k in zone i, in kg / hm². 2 .

[0093] (3) Water use efficiency target is an indicator that measures the relationship between crop yield and water consumption. It is also one of the comprehensive indicators for evaluating the suitability of plant growth under water deficit. This indicator is expressed by the classic yield divided by water consumption.

[0094]

[0095] In the formula, WUE is water use efficiency.

[0096] S3: Set model boundaries: Model boundary constraints include irrigation water constraints, food security constraints, land policy constraints, and the constraint that decision variables should not be negative.

[0097] (1) Irrigation water constraints

[0098] The allocation of irrigation water should not exceed the irrigation water supply of each zone.

[0099]

[0100] In the formula, Q represents the total available water volume, m 3 η represents irrigation water use efficiency.

[0101] (2) Food security

[0102] The total grain output must meet the needs of the population and the volume of imports and exports. This constraint can be expressed as:

[0103]

[0104] In the formula, EX k This represents the amount of grain (in kg) that crop k needs to be exported; IM k PO represents the amount of grain imported from abroad for crop k, in kg; PO represents the population that needs to be satisfied, in people; FD represents the food demand, in kg / person.

[0105] (3) Land Policy

[0106] To find the best planting results and optimize existing planting plans, the total planted area must be less than the maximum allowed planting area in each region. This constraint can be expressed as follows:

[0107]

[0108] In the formula, This represents the maximum amount of land available for all crop cultivation, expressed in hectares (hm). 2 .

[0109] (4) Decision variables should not be negative.

[0110] A ik ≥0

[0111] IQ ik ≥0

[0112] S4: Model Solving: The study area was divided into 1km×1km grids using R language, and a cellular automata multi-objective algorithm was employed for spatial grid solving. With regional economic-environment-resource efficiency as the objective function, grid-point crop planting structure and irrigation water volume as decision variables, and irrigation water volume, food security, and land policy as constraints, a regional crop water and soil resource spatial optimization model was constructed using a loosely coupled regional crop model APSIM. The optimization model aims to optimize regional water and soil resources as the final objective, balancing the conflict between available regional water resources and agricultural production, and avoiding water waste and damage to the agricultural economy caused by the optimization results.

[0113] S5: Loss coefficient evaluation index: In the process of adjusting the planting structure, it is also necessary to consider the impact of economic, social and ecological dimensions on the planting of various crops.

[0114] (1) Economic dimension. One of the main purposes of farmers planting crops is to make a profit, so high-profit crops will be the first choice for growers. Therefore, the indicators in Table 1 are selected as economic dimension indicators.

[0115] Table 1 Relevant Indicators of the Economic Dimension

[0116]

[0117] (2) Social Dimension. Social benefits reflect the overall function, long-term and short-term benefits of crop cultivation patterns, as well as the amount of edible products that can be provided to society. At the same time, the indicators should be quantifiable. Therefore, the indicators in Table 2 are selected as social dimension indicators.

[0118] Table 2. Relevant Indicators of the Social Dimension

[0119]

[0120]

[0121] (3) Ecological dimension. Ecological benefits are measured from the perspective of ecological balance. Therefore, the indicators in Table 3 are selected as ecological dimension indicators.

[0122] Table 3. Relevant indicators of the ecological dimension

[0123]

[0124] S6: The indicators of the economic-social-ecological dimensions constructed in S5 are tested using the analytic hierarchy process (AHP) to calculate the risk weights of each dimension and indicator.

[0125]

[0126] In the formula, X n The risk scores for each indicator are shown in Table 4, and their significance is illustrated in Table 4; C n This indicates the results of each indicator.

[0127] Table 4. Significance of Risk Scores

[0128]

[0129] The final risk value R is calculated by multiplying the expert's overall score for each indicator by the weight value of that indicator.

[0130]

[0131] In the formula, P j w represents the expert comprehensive score assigned to the j-th indicator in the indicator layer; ujThis represents the composite weight, which is the overall priority weight of the j-th element to the target layer.

[0132] For each crop in each region, steps S4 and S5 are calculated, and χ is finally obtained. ik .

Claims

1. A regional irrigation intelligent decision-making method coupled with crop growth process simulation, characterized in that, The process includes the following: An agricultural production system simulator was used to simulate the relationship between irrigation water volume and yield, and the established relationship took into account the crop yield under rain-fed conditions. Construct a rating system for the original economic, social and ecological multi-dimensional development levels of various regions, taking into account the impact of the multi-dimensional system on the optimization of planting structure; The obtained irrigation water-yield function relationship and multidimensional evaluation indicators are input into the constructed model; the optimal planting and irrigation water scheme is obtained through the constructed economic benefit model, environmental effect model and resource utilization efficiency model.

2. The regional irrigation intelligent decision-making method coupled with crop growth process simulation according to claim 1, characterized in that, Specifically, it includes the following steps: S1: Basic Data Collection; Using remote sensing information technology, the Agricultural Production System Simulator (APSIM) model was used to simulate crop yields at a 1km×1km scale across the country, simulating the functional relationship between yield and water quantity for three crops: rice, corn, and soybeans; During the APSIM model simulation, national land parameters and meteorological data were input, and based on the input information, the yield relationships of various crops in different regions were obtained: YA ik =aIQ ik +Yrain ik In the formula, i is the partition index, i = 1...I; k is the crop type, k = 1...K; YA ik It is the yield per unit area of ​​crop k in zone i, kg / hm² 2 ; IQ ik The irrigation water amount for crop k in partition i is the decision variable, m. 3 / hm 2 Yrain ik Crop yield under non-irrigation conditions for crop k in zone i, kg / hm 2 ; S2: Construct the objective function; (1) Construct an economic objective function. The economic objective is the net income, which is the difference between the profits obtained from selling the harvested crop and the costs incurred during the planting process. max EB = EI - C In the formula, EB represents the net income of the crop, in yuan; EI represents the income, in yuan; and C represents the planting cost, in yuan. In the formula, χ ik PR represents the loss coefficient for planting crop k in partition i; ik Indicates the price of crop k in region i, in yuan / kg; A ik hm represents the planting area of ​​crop k in zone i in the first year. 2 ; Planting costs: C = CGF + CWF + CPF In the formula, CGF represents the cost of grain cultivation, expressed in yuan / hm². 2 CWF represents the cost of water used for grain production, in yuan; CPF represents the cost of electricity consumed for irrigation, in yuan. In the formula, This represents the fertilizer price for crop k in region i, expressed in yuan / kg. This represents the fertilizer application rate for crop k in region i, expressed in kg / hm². 2 ; This represents the pesticide price for crop k in region i, expressed in yuan / kg. This represents the pesticide application rate for crop k in region i, expressed in kg / hm². 2 ; This represents the price of diesel fuel for agricultural machinery in crop k of region i, expressed in yuan / kg. This represents the amount of diesel fuel used by agricultural machinery for crop k in zone i, in kg / hm². 2 ; This represents the price of agricultural film for crop k in region i, expressed in yuan / kg. This represents the amount of agricultural film used for crop k in zone i, in kg / hm². 2 ; This represents the seed price of crop k in zone i for the first year, in yuan / kg; This represents the seed usage of crop k in partition i, in kg / hm². 2 ; This represents the labor cost per person for crop k in partition i; This represents the amount of labor used for crop k in partition i, in people / hm. 2 ; In the formula, Wpr i This represents the water price in zone i, in yuan / m³. 3 ; IQ ik The irrigation water amount for crop k in partition i is the decision variable, m. 3 / hm 2 ; In the formula, Wpw i Pw represents the electricity price in partition i, in kWh / yuan; i This represents the electricity consumption per cubic meter of water in partition i, in kWh / m³. 3 ; (2) Greenhouse gas emission (GHG) targets, quantifying CO2, CH4 and N2O emissions during planting activities; CO2 emissions are generated by the use of materials; CH4 emissions come from paddy fields; N2O emissions include soil emissions and emissions from fertilizer application; In the formula, This represents carbon dioxide emissions, expressed in kgCO. 2 ; This indicates methane emissions from rice paddies, expressed in kgCH4. Indicates the impact of nitrous oxide emissions, kgN2O; κ fer This represents the carbon dioxide emission factor from fertilizers, expressed as kgCO2 / kg; κ pes κ represents the carbon dioxide emission factor of pesticides, kgCO2 / kg; mac κ represents the carbon dioxide emission factor of fuel, kgCO2 / kg; film The carbon dioxide emission factor of agricultural film is expressed as kgCO2 / kg; κ lab κ represents the anthropogenic carbon dioxide emission factor, kgCO2 / person; pw The carbon dioxide emission factor for electricity is expressed as kgCO2 / kWh. This represents the methane emissions per unit area, expressed in kgCH4 / hm². 2 ; The direct N2O emissions during soil nitrification and denitrification in crop k of partition i are represented (this part was obtained through APSIM simulation), kgN2O / hm. 2 ; Indirect N2O emissions during soil nitrification and denitrification processes in crop k of zone i, kg N2O / hm 2 ; N ik This is the total soil nitrogen application per hectare per two years for crop k in zone i, in kg / hm². 2 ; (3) Water use efficiency target is an indicator that measures the relationship between crop yield and water consumption, and is also one of the comprehensive indicators for evaluating the suitability of plant growth under water deficit. This indicator is expressed by dividing yield by water consumption in the classic way: In the formula, WUE is water use efficiency; S3: Set model boundaries: Model boundary constraints include irrigation water constraints, food security constraints, land policy constraints, and the constraint that decision variables should not be negative; (1) Irrigation water constraints The allocation of irrigation water should not exceed the irrigation water supply of each zone; In the formula, Q represents the total available water volume, m 3 η represents irrigation water use efficiency; (2) Food security The total grain output must meet the needs of the population and the volume of imports and exports. This constraint is expressed as: In the formula, EX k This represents the amount of grain (in kg) that crop k needs to be exported; IM k PO represents the amount of grain imported from abroad for crop k, in kg; PO represents the population that needs to be satisfied, in people; FD represents the food demand, in kg / person. (3) Land Policy Optimize the existing planting plan so that the total planted area is less than the maximum allowed planting area in each region; this constraint is expressed as follows: In the formula, This represents the maximum amount of land available for all crop cultivation, expressed in hectares (hm). 2 ; (4) Decision variables should not be negative; A ik ≥0 IQ ik ≥0 S4: Model Solving: The study area was divided into 1km×1km grids using R language, and the spatial grid was solved using a cellular automata multi-objective algorithm. With regional economic-environment-resource efficiency as the objective function, grid-point crop planting structure and irrigation water volume as decision variables, and irrigation water volume, food security and land policy as constraints, a regional crop water and soil resource spatial optimization model was constructed by loosely coupling the regional crop model APSIM.

3. The regional irrigation intelligent decision-making method coupled with crop growth process simulation according to claim 2, characterized in that, It also includes the following steps: S5: Loss coefficient evaluation index: In the process of adjusting the planting structure, the impact of economic, social and ecological dimensions on the planting of various crops should also be considered. (1) Economic dimension, the indicators include total output value, net benefit, demand rate, profit rate, price, and economic benefit per unit area; (2) Social dimension, the indicators include yield per unit area, labor productivity, arable land pressure index, income stability, matching degree of engineering settings, technological development, and labor utilization rate; (3) Ecological dimension, indicators include energy use, soil, ecological environment, and application of pesticides and fertilizers; S6: The indicators of the economic-social-ecological dimensions constructed in S5 are tested using the analytic hierarchy process (AHP) to calculate the risk weights of each dimension and indicator. In the formula, X n It is the risk score result of each indicator; C n This indicates the results of each indicator; The final risk value R is calculated by multiplying the expert's overall score for each indicator by the weight value of that indicator. In the formula, P j w represents the expert comprehensive score assigned to the j-th indicator in the indicator layer; uj This represents the composite weight, i.e., the overall priority weight of the j-th element to the target layer; For each crop in each region, steps S4 and S5 are calculated, and χ is finally obtained. ik .

Images