Multi-target space optimization method for regional water-adaptive planting structure and related device

Abstract

The invention discloses a regional water-adaptive planting structure multi-target space optimization method and a related device, and relates to the technical field of crop planting optimizing.The method comprises the following steps that firstly, according to remote sensing evapotranspiration water consumption data and crop growth periods, evapotranspiration water consumption in each growth period is calculated; and grading the crop moisture suitability by using a fuzzy membership function. Constructing a multi-objective optimization model and solving a result combination; a cellular attribute conversion rule is formulated by combining the moisture suitability level and the neighborhood state, the cellular state and the attribute are input into the cellular automaton model, iterative calculation is carried out until stability or preset times are reached, and a preliminary spatial pattern is generated; and inputting the preliminary spatial pattern, the crop moisture suitability grade, the neighborhood state and the social economic and natural driving factors into a Dyna-CLUE model to obtain an adjustment result, feeding back the adjustment result to a cellular automaton model to recalculate a conversion rule until convergence, and outputting a spatial distribution diagram of the planting structure. The planting structure space layout with water saving, high efficiency and high adaptability can be realized.

Description

Technical Field

[0001] This application relates to the field of crop planting optimization technology, and in particular to a multi-objective spatial optimization method and related apparatus for regional water-suitable planting structure. Background Technology

[0002] Optimizing regional crop planting structure is a comprehensive solution to address resource constraints, environmental pressures, climate change, and changing market demands. Through optimizing crop planting structure, resource utilization efficiency can be improved, water, soil, and energy waste can be reduced, economic resilience can be enhanced, benefits and risks can be balanced, ecological sustainability can be promoted, environmental risks can be reduced, and regional and national food security can be ensured. Regional crop planting structure optimization technology has also evolved from single-objective, static models to complex systems involving multi-objective, spatiotemporal dynamic optimization.

[0003] With the increasing severity of climate change and agricultural water scarcity, the concept of "water-suitable planting" has emerged and gained growing attention. "Water-suitable planting" refers to adjusting crop planting structures based on local water resources to achieve water conservation and high yields. While the theoretical origins of this concept can be traced back to mid-20th-century research in agricultural water resource management, the systematic methodology explicitly named "water-suitable planting" was primarily developed and refined by Chinese scientists through agricultural practices in arid and semi-arid regions. Optimizing water-suitable planting structures is a key measure for achieving efficient water resource utilization, ensuring food security, and promoting the green transformation of agriculture. It is of great significance to regional sustainable development, especially in arid and semi-arid regions where water resources are scarce and exhibit significant temporal and spatial variations. Optimizing water-suitable planting structures is crucial for ensuring stable regional food production and efficient water resource utilization. Studies have shown that crop water use efficiency is closely related to planting structure. Existing methods for optimizing regional crop planting structure lack a systematic consideration of water suitability and are inaccurate in assessing water demand. Most methods rely on empirical data or simple statistical models, making it difficult to dynamically simulate the spatiotemporal distribution of crop water requirements. Existing methods lack multi-objective collaborative optimization of water benefits and do not comprehensively consider multiple dimensions such as water use efficiency, yield stability, and economic benefits. Existing models lack spatial layout adaptability and lack spatial optimization models based on water suitability assessment, making it difficult to implement the optimization results.

[0004] Therefore, how to achieve a water-saving, efficient, and adaptable planting structure spatial layout has become a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0005] The purpose of this application is to provide a multi-objective spatial optimization method and related device for regional water-friendly planting structures, which can realize a water-saving, efficient, and highly adaptable spatial layout of planting structures.

[0006] To achieve the above objectives, this application provides the following solution:

[0007] Firstly, this application provides a multi-objective spatial optimization method for regional water-suitable planting structures, the method comprising:

[0008] Obtain remote sensing data on evapotranspiration water consumption and crop growth period in the target area.

[0009] Based on the remote sensing evapotranspiration water consumption data and the crop growth period, calculate the evapotranspiration water consumption for each growth period.

[0010] Based on the evapotranspiration water consumption at each growth stage, the crop water suitability is classified using a fuzzy membership function to obtain the crop water suitability level.

[0011] A multi-objective optimization model is constructed based on the objective function and constraints. The objective function includes maximizing water efficiency, optimizing economic benefits, and constraining food security. The constraints include water constraints, area constraints, and neighborhood constraints.

[0012] The NSGA-II genetic algorithm was used to optimize the multi-objective optimization model and solve for the optimal combination of crop planting structure results.

[0013] Based on the crop water suitability level and neighborhood status, a conversion rule for cell attributes is formulated; the cell represents a minimum planting unit; the conversion rule for cell attributes includes: water constraint rule, neighborhood influence rule, and dynamic adjustment rule.

[0014] Based on the combination of the transformation rules of the cell attributes and the crop planting structure optimization results, the current cell state and attributes are determined; the current cell state and attributes include: crop type, crop water suitability level, soil fertility, topography and slope.

[0015] The current cell state and attributes are input into the Cellular Automata (CA) model. The state at the next moment is calculated according to the transformation rules of the cell attributes. This process is repeated until a stable pattern or a preset number of iterations is reached, thereby generating a preliminary spatial pattern.

[0016] The preliminary spatial pattern, crop water suitability level, neighborhood status, socio-economic factors, and natural driving factors are input into the Dyna-CLUE (Dynamic Conversion of Land Use and its Effects) model. The Dyna-CLUE model adjusts the layout according to socio-economic goals and ecological constraints based on probability calculation formulas to obtain the adjustment results.

[0017] The adjustment results are fed back to the cellular automata model to recalculate the transformation rules of cellular attributes until convergence, and output the spatial distribution map of the planting structure.

[0018] Optionally, the expression for the fuzzy membership function is:

[0019]

[0020] Where μ(x) is the fuzzy membership degree; x is the crop evapotranspiration water consumption; a1 is the lower water threshold, i.e. the minimum water requirement that the crop can tolerate; and a2 is the upper water threshold, i.e. the maximum water requirement that the crop can withstand.

[0021] Optionally, the maximization of water efficiency includes: blue water dependence and grey water footprint.

[0022] The formula for calculating the blue water dependence is as follows:

[0023]

[0024] Where BWF_rate is the blue water dependency; ET ci Crop water requirements; A i P represents the planting area. i N represents effective precipitation; N represents crop type.

[0025] The formula for calculating the grey water footprint is as follows:

[0026]

[0027] Where GWF_grey is the greywater footprint; C max C represents the water quality standard threshold. nat It is natural runoff water quality.

[0028] Optionally, the optimal economic benefit is achieved using net revenue per unit area as the objective function; the formula for calculating net revenue per unit area is:

[0029]

[0030] Where NP represents net revenue per unit area; Y i P is the yield per unit area. price,i C is the price of the i-th crop; input,i For production costs; A i N represents the planting area; N represents the crop type.

[0031] Optionally, the expression for the food security constraint is:

[0032]

[0033] Among them, Ymaize,i Yield per unit area of ​​staple food crops; Q min A represents the minimum demand in the region. i N represents the planting area; N represents the crop type.

[0034] Optionally, the water constraint is that the total irrigation water volume is less than or equal to the available water resources in the area.

[0035] The expression for the moisture constraint is:

[0036]

[0037] Among them, ET ci Crop water requirements; A i P represents the planting area. i N represents effective precipitation; N represents crop type; W represents effective precipitation. avail This represents the total available water resources in the region.

[0038] The area constraint is that the planting area of ​​each crop is greater than or equal to the minimum guaranteed area, and the total planting area is less than or equal to the total cultivated land area.

[0039] The neighborhood constraint requires that crop distribution meet the requirements of crop rotation and water suitability.

[0040] Optionally, the probability calculation formula is:

[0041]

[0042] Where, p ij Let be the probability that cell (i, j) is converted into the target crop; β0 is the intercept term; β k X represents the regression coefficients of k factors, reflecting the contribution of each driving factor; n is the total number of driving factors; X ijk Let be the value of the k-th driving factor of cell (i, j).

[0043] Secondly, this application provides a multi-objective spatial optimization device for regional water-suitable planting structures. This device is used to implement the multi-objective spatial optimization method for regional water-suitable planting structures described in any of the above claims. The multi-objective spatial optimization device for regional water-suitable planting structures includes:

[0044] The data acquisition module is used to acquire remote sensing data on evapotranspiration water consumption and crop growth period in the target area.

[0045] The evapotranspiration water consumption calculation module is used to calculate the evapotranspiration water consumption for each growth stage based on the remote sensing evapotranspiration water consumption data and the crop growth stage.

[0046] The grading module is used to classify crop water suitability based on evapotranspiration water consumption at each growth stage using fuzzy membership functions, thus obtaining the crop water suitability level.

[0047] A multi-objective optimization model construction module is used to construct a multi-objective optimization model based on objective functions and constraints; the objective functions include: maximizing water efficiency, optimizing economic benefits, and food security constraints; the constraints include: water constraints, area constraints, and neighborhood constraints.

[0048] The optimization calculation module is used to perform optimization calculations on the multi-objective optimization model using the NSGA-II genetic algorithm to solve for the combination of crop planting structure optimization results.

[0049] The cell attribute conversion rule formulation module is used to formulate cell attribute conversion rules by combining the crop water suitability level and neighborhood status; the cell represents a minimum planting unit; the cell attribute conversion rules include: water constraint rules, neighborhood influence rules and dynamic adjustment rules.

[0050] The combination module is used to determine the current cell state and attributes based on the combination of the transformation rules of the cell attributes and the crop planting structure optimization results; the current cell state and attributes include: crop type, crop water suitability level, soil fertility, topography and slope.

[0051] The first input module is used to input the current cell state and attributes into the cellular automaton model, calculate the state at the next moment according to the transformation rules of the cell attributes, repeat until a stable pattern or a preset number of iterations is reached, and generate a preliminary spatial pattern.

[0052] The second input module is used to input the preliminary spatial pattern, crop water suitability level, neighborhood status, socio-economic factors and natural driving factors into the Dyna-CLUE model. The Dyna-CLUE model adjusts the layout according to socio-economic goals and ecological constraints based on probability calculation formulas to obtain the adjustment results.

[0053] The feedback module is used to feed the adjustment results back to the cellular automata model, recalculate the transformation rules of cellular attributes until convergence, and output the spatial distribution map of the planting structure.

[0054] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to implement the multi-objective spatial optimization method for regional water-suitable planting structures as described above.

[0055] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the multi-objective spatial optimization method for regional water-suitable planting structures described above.

[0056] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0057] This application provides a multi-objective spatial optimization method and related apparatus for regional water-suitable planting structures. The method includes: acquiring remote-sensed evapotranspiration water consumption data and crop growth stages of the target region, accurately reflecting spatial differences in regional water consumption; and simultaneously acquiring crop growth stages to provide a biological basis for subsequent phased calculation of water requirements. Based on the remote-sensed evapotranspiration water consumption data and the crop growth stages, the evapotranspiration water consumption for each growth stage is calculated, accurately capturing the water-sensitive needs of crops at key growth stages. Based on the evapotranspiration water consumption for each growth stage, a fuzzy membership function is used to classify crop water suitability, obtaining crop water suitability levels, which clarifies the degree of water suitability for specific crops in different regions. Based on objective functions and constraints, a multi-objective optimization model is constructed; the objective functions include: maximizing water efficiency, optimizing economic benefits, and food security constraints; the constraints include: water constraints, area constraints, and neighborhood constraints, avoiding ecological damage or food risks caused by a single objective. The NSGA-II genetic algorithm is used to optimize the multi-objective optimization model and solve for the optimal combination of crop planting structure results. This application can cover planting structure combinations under different objective weights. This diversity provides decision-makers with flexible selection space to meet the needs and preferences of different scenarios. Combining the crop water suitability level and neighborhood state, a transformation rule for cell attributes is formulated. The cell represents a minimum planting unit. The transformation rule for cell attributes includes: water constraint rule, neighborhood influence rule, and dynamic adjustment rule. The transformation rule transforms the abstract "neighborhood influence" and "water constraint" into computable cell state transformation logic, enabling the cellular automaton to simulate the spatial interaction of planting units. Compared with non-spatial optimization, the neighborhood rule considers the "spatial clustering effect" of crop planting, improving the spatial rationality of the layout. Based on the combination of the transformation rules of the cell attributes and the optimization results of the crop planting structure, the current cell state and attributes are determined. These current cell states and attributes include: crop type, crop water suitability level, soil fertility, topography, and slope. Cell attributes not only include crop type and water suitability but also incorporate natural factors such as soil fertility and topographic slope, comprehensively reflecting the key elements influencing the planting layout. This multi-attribute integration avoids the one-sidedness of decision-making based solely on a single factor, making the cell state closer to actual planting conditions. The current cell state and attributes are input into the cellular automaton model, and the state at the next time step is calculated according to the transformation rules of the cell attributes. This process is repeated until a stable pattern or a preset number of iterations is reached, generating a preliminary spatial pattern. The cellular automaton, through iterative calculation of the evolution of cell states, can simulate the dynamic process of the planting structure from an initial state to a stable pattern, capturing adaptive adjustments in the time dimension better than static optimization.The preliminary spatial pattern, crop water suitability level, neighborhood status, socioeconomic factors, and natural driving factors are input into the Dyna-CLUE model. The Dyna-CLUE model, based on probability calculation formulas, adjusts the layout according to socioeconomic goals and ecological constraints, yielding an adjustment result. This allows for adjustments to the preliminary spatial pattern at a regional scale, compensating for the potential deficiency of cellular automata in focusing excessively on local neighborhoods while neglecting macroeconomic constraints. The adjustment result is fed back to the cellular automata model to recalculate the transformation rules of cellular attributes until convergence, outputting a spatial distribution map of the planting structure. Through the "CA-Dyna-CLUE" feedback loop, the spatial pattern is repeatedly calibrated between "local adaptability" and "global rationality" until convergence. This closed-loop mechanism avoids the limitations of a single model, and the final output spatial distribution map possesses both spatial precision and global rationality. This application combines water suitability assessment based on high spatiotemporal resolution remote sensing data products with NSGA-II multi-objective optimization to achieve synergistic improvement in water efficiency and economic benefits. By using the CA-Dyna-CLUE coupled model, it solves the problems of low spatial resolution and poor implementation of traditional methods. By integrating constraints such as arable land red line and food security, it enhances the feasibility of the scheme. By coupling water suitability assessment, water constraint modeling and spatial optimization algorithms, it realizes a water-saving, efficient and adaptable spatial layout of planting structure. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 This is an application environment diagram of a multi-objective spatial optimization method for regional water-suitable planting structure in one embodiment of this application;

[0060] Figure 2 This is a flowchart illustrating a multi-objective spatial optimization method for regional water-suitable planting structures, provided as an embodiment of this application.

[0061] Figure 3 This is a framework diagram for multi-objective spatial optimization of regional water-suitable planting structures provided in an embodiment of this application.

[0062] Figure 4 This is a schematic diagram of the functional modules of a multi-objective spatial optimization device for regional water-suitable planting structure provided in an embodiment of this application.

[0063] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0064] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0065] This application relates to a multi-objective optimization method for regional crop water suitability planting structure based on water suitability assessment and coupled with CA and Dyna-CLUE models. It is applicable to decision support for crop planting system optimization and sustainable agricultural development in arid and semi-arid regions. The method includes: acquiring high spatiotemporal resolution remote sensing observation evapotranspiration data, soil data, and crop growth stages of the target region; calculating evapotranspiration for each growth stage; and classifying crop water suitability using fuzzy membership functions. A triple objective function of water benefit, economic benefit, and food security is set, along with constraints such as water availability, area, and neighborhood. The multi-objective optimization problem is solved using NSGA-II (second-generation non-dominated sorting genetic algorithm). Multiple planting structure optimization schemes are randomly generated, and the non-dominated solution set (Pareto front) is iteratively selected through NSGA-II to form multiple sets of planting structure optimization schemes. Using the CA model, a preliminary spatial layout is generated based on the cell state transition rule. Using the Dyna-CLUE model, the layout is adjusted according to socio-economic goals and ecological constraints. The adjustment results are fed back to the CA model, and the local transformation rule is recalculated until convergence. Finally, the planting area optimized by NSGA-II is allocated to the spatial grid to obtain the spatial distribution of different types of crops in the region.

[0066] This application addresses the shortcomings of existing technologies in terms of multi-objective trade-offs and spatial layout. Specifically targeting the water shortage and significant spatiotemporal variability of precipitation in arid and semi-arid regions, it proposes a method that, based on water suitability assessment, couples CA and Dyna-CLUE models. Through a "micro-macro" synergistic mechanism, it integrates water suitability, socio-economic constraints, and ecological protection needs into spatial layout. This solves the micro-level spatial adaptation problem, achieving grid-level precision in crop layout, while simultaneously coordinating macro-level socio-economic goals to ensure the feasibility and sustainability of the solution. Therefore, it provides a scientific and practical method for optimizing planting structures in arid and semi-arid regions.

[0067] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0068] The multi-objective spatial optimization method for regional water-suitable planting structures provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on another server. Terminal 102 can send the acquired remote sensing evapotranspiration water consumption data and crop growth period of the target area to server 104. After receiving the remote sensing evapotranspiration water consumption data and crop growth period of the target area, server 104 calculates the evapotranspiration water consumption for each growth period based on the remote sensing evapotranspiration water consumption data and the crop growth period; based on the evapotranspiration water consumption for each growth period, a fuzzy membership function is used to classify the crop water suitability, resulting in a crop water suitability level; a multi-objective optimization model is constructed based on the objective function and constraints; the objective function includes: maximizing water efficiency, optimizing economic benefits, and food security constraints; the constraints include: water constraints, area constraints, and neighborhood constraints; the NSGA-II genetic algorithm is used to optimize the multi-objective optimization model to solve for the optimal combination of crop planting structure results; combined with the crop water suitability level and neighborhood state, a conversion rule for cell attributes is formulated; the cell represents a minimum planting unit; the element... The cell attribute conversion rules include: water constraint rules, neighborhood influence rules, and dynamic adjustment rules. Based on the combination of the cell attribute conversion rules and the crop planting structure optimization results, the current cell state and attributes are determined. The current cell state and attributes include: crop type, crop water suitability level, soil fertility, topography, and slope. The current cell state and attributes are input into the cellular automaton model, and the state at the next time step is calculated according to the cell attribute conversion rules. This process is repeated until a stable pattern or a preset number of iterations is reached, generating a preliminary spatial pattern. The preliminary spatial pattern, crop water suitability level, neighborhood state, socio-economic factors, and natural driving factors are input into the Dyna-CLUE model. The Dyna-CLUE model adjusts the layout according to socio-economic goals and ecological constraints based on probability calculation formulas to obtain the adjustment results. The adjustment results are fed back to the cellular automaton model to recalculate the cell attribute conversion rules until convergence, outputting a spatial distribution map of the planting structure. Server 104 can feed back the obtained spatial distribution map of the planting structure to terminal 102. In addition, in some embodiments, the multi-objective spatial optimization method for regional water-suitable planting structure can also be implemented by the server 104 or the terminal 102 separately. For example, the terminal 102 can directly perform multi-objective spatial optimization of regional water-suitable planting structure based on the remote sensing evapotranspiration water consumption data and crop growth period of the target area. Alternatively, the server 104 can obtain the remote sensing evapotranspiration water consumption data and crop growth period of the target area from the data storage system and perform multi-objective spatial optimization of regional water-suitable planting structure based on the remote sensing evapotranspiration water consumption data and crop growth period of the target area.

[0069] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, and tablets. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers, or it can be a cloud server.

[0070] In one exemplary embodiment, such as Figure 2 As shown, a multi-objective spatial optimization method for regional water-suitable planting structure is provided. This method is executed by computer equipment, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps S1 to S10.

[0071] S1: Obtain remote sensing data on evapotranspiration water consumption and crop growth period for the target area.

[0072] S2: Calculate the evapotranspiration water consumption for each growth stage based on the remote sensing evapotranspiration water consumption data and the crop growth stage.

[0073] S3: Based on the evapotranspiration water consumption at each growth stage, the crop water suitability is classified using a fuzzy membership function to obtain the crop water suitability level.

[0074] S4: Construct a multi-objective optimization model based on the objective function and constraints; the objective function includes: maximizing water efficiency, optimizing economic benefits, and food security constraints; the constraints include: water constraints, area constraints, and neighborhood constraints.

[0075] S5: Use the NSGA-II genetic algorithm to perform optimization calculations on the multi-objective optimization model and solve for the combination of crop planting structure optimization results.

[0076] S6: Based on the crop water suitability level and neighborhood status, formulate the conversion rules for cell attributes; the cell represents a minimum planting unit; the conversion rules for cell attributes include: water constraint rules, neighborhood influence rules, and dynamic adjustment rules.

[0077] S7: Based on the combination of the transformation rules of the cell attributes and the crop planting structure optimization results, determine the current cell state and attributes; the current cell state and attributes include: crop type, crop water suitability level, soil fertility, topography and slope.

[0078] S8: Input the current cell state and attributes into the cellular automaton model, calculate the state at the next moment according to the transformation rules of cell attributes, repeat until a stable pattern or a preset number of iterations is reached, and generate a preliminary spatial pattern.

[0079] S9: Input the preliminary spatial pattern, crop water suitability level, neighborhood status, socio-economic factors and natural driving factors into the Dyna-CLUE model. The Dyna-CLUE model adjusts the layout according to socio-economic goals and ecological constraints based on the probability calculation formula to obtain the adjustment result.

[0080] S10: Feed the adjustment results back to the cellular automata model, recalculate the transformation rules of cellular attributes until convergence, and output the spatial distribution map of the planting structure.

[0081] By implementing steps S1 to S10 above, this application combines water suitability assessment based on high spatiotemporal resolution remote sensing data products with NSGA-II multi-objective optimization, achieving a synergistic improvement in water efficiency and economic benefits. Through the CA-Dyna-CLUE coupling model, it solves the problems of low spatial resolution and poor implementation of traditional methods. By integrating constraints such as arable land red line and food security, it enhances the feasibility of the scheme. By coupling water suitability assessment, water constraint modeling, and spatial optimization algorithms, it achieves a water-saving, efficient, and highly adaptable spatial layout of planting structures.

[0082] In practical applications, the following steps are included:

[0083] Step 1: Crop Water Suitability Assessment. Evapotranspiration (ET) data from MODIS16A2 were downloaded using the Google Earth Engine platform (https: / / developers.google.cn / earth-engine / ). The spatial resolution was 1 km, and the temporal resolution was 8 days. The raw data consisted of the average daily evapotranspiration (mm / d) for each 8-day period. Based on crop growth stage data, the total ET for each growth stage was calculated. Based on literature and historical measured data, and according to the correlation between crop yield and evapotranspiration, the upper and lower limits of evapotranspiration for different crop types at different growth stages in the assessment area were determined. The water suitability level was quantified using a fuzzy membership function.

[0084]

[0085] Where μ(x) is the fuzzy membership degree; x is the crop evapotranspiration water consumption (ET); a1 is the lower water threshold, i.e. the minimum water requirement that the crop can tolerate; and a2 is the upper water threshold, i.e. the maximum water requirement that the crop can withstand.

[0086] The suitability of water resources is determined based on the value of μ(x), and is divided into four levels: Level I (suitable): μ(x) ≥ 0.9; Level II (relatively suitable): 0.7 ≤ μ(x) < 0.9; Level III (generally suitable): 0.5 ≤ μ(x) < 0.7; Level IV (unsuitable): μ(x) < 0.5.

[0087] Based on ET data with a resolution of 1km, μ(x) is calculated grid by grid to generate a spatial distribution map of crop water suitability levels.

[0088] Step 2: Construction of a multi-objective optimization model based on the NSGA-II algorithm. NSGA-II (Non-dominated sorting genetic algorithm second generation) is a multi-objective optimization evolutionary algorithm that finds the Pareto optimal solution set by simulating the biological evolution process, i.e., the "best compromise solution" that weighs multiple conflicting objectives. In this application, it is applicable to the optimization of water-suitable planting structure in arid and semi-arid regions, which simultaneously considers objectives such as water efficiency, economic benefits, and food security. These objectives are mutually conflicting and are constrained by the total regional water resources, planting area, and spatial neighborhood. NSGA-II can optimize multiple objectives in parallel, without relying on preset weights, and directly generate the Pareto solution set for decision-makers to choose a solution according to their needs (such as prioritizing water conservation or increasing income). The NSGA-II algorithm is good at handling nonlinear problems, and the relationship between crop water requirements and economic benefits is complex. Genetic algorithms are good at global search. The NSGA-II algorithm can also accommodate multiple constraints, and through penalty functions or feasible solution screening, it integrates water constraints, area constraints, etc., into the evolutionary process.

[0089] The inputs to the NSGA-II algorithm include the objective function, constraints, decision variables (planting area ratios of various crops), and algorithm parameters such as population size, number of iterations, and crossover / mutation probabilities. In this application, the objective function includes:

[0090] (1) Maximizing water efficiency involves two objective functions: blue water dependency (BWF_rate), which represents the proportion of irrigation water to total water use and needs to be minimized, calculated using formula (2):

[0091]

[0092] Where BWF_rate is the blue water dependency; ET ci Crop water requirements; A i P represents the planting area. i N represents effective precipitation; N represents crop type.

[0093] The grey water footprint (GWF_grey) (Formula 3) reflects the pressure of agricultural water use on the water environment and needs to be minimized.

[0094]

[0095] Where GWF_grey is the greywater footprint; C max C represents the water quality standard threshold. nat It is natural runoff water quality.

[0096] (2) The economic benefits are optimal. The net income per unit area (NP) (Formula 4) is used as the objective function, which represents the net value of planting income after deducting costs.

[0097]

[0098] Where NP represents net revenue per unit area; Y i P is the yield per unit area. price,i C is the price of the i-th crop; input,i Production costs include the total cost of seeds, fertilizers, pesticides, mulch film, and mechanized farming.

[0099] (3) Food security constraints: the yield of staple crops (such as corn) must be greater than or equal to the region's minimum demand (Formula 5).

[0100]

[0101] Among them, T maize,i Yield per unit area of ​​staple food crops; Q min This represents the minimum demand in the region.

[0102] Due to the differences in the dimensions of different objective functions, normalization is required (Formula 6):

[0103]

[0104] Among them, F k '(x) is the normalized value of the k-th objective; F k (x) represents the original value of the k-th target; and These are the minimum and maximum values ​​of the k-th target, respectively.

[0105] After normalization, the objective functions are objectively weighted using the entropy weighting method to avoid subjective bias. First, the information entropy of each objective function is calculated:

[0106]

[0107] Among them, e j p is the information entropy of the j-th objective function; ij The percentage of the j-th objective value in the i-th solution; m is the total number of years in the sample.

[0108]

[0109] Among them, F j '(x i That is, F k '(x).

[0110] Then calculate the weighting coefficients:

[0111]

[0112] Where, λ j is the weight coefficient of the j-th objective function; l is the number of objective functions; e j The information entropy of the j-th objective function;

[0113] The constraints of the multi-objective optimization model based on the NSGA-II algorithm in this application include water constraints, area constraints, and neighborhood constraints. The water constraint (Equation 10) states that the total irrigation water volume is less than or equal to the available water resources in the region.

[0114]

[0115] Among them, W avail This represents the total available water resources in the region.

[0116] The area constraint is that the planting area of ​​each crop is greater than or equal to the minimum guaranteed area, and the total planting area is less than or equal to the total cultivated land area.

[0117] The neighborhood constraint requires that crop distribution meet the requirements of crop rotation and water suitability.

[0118] In the NSGA-II algorithm, the planting structure is first encoded as a chromosome, and an initial solution, i.e., a planting structure scheme, is randomly generated. The population is then stratified according to the Pareto front (i.e., there is no single optimal solution; multiple objectives need to be balanced to generate multiple Pareto solutions), maintaining population diversity and avoiding excessive concentration of solutions. New solutions are generated through genetic operations, and iterative optimization is performed to form multiple sets of optimal planting structure schemes. The weights λ are calculated using the entropy weight method. j Calculate the weighted score U(x) for each scheme (Formula 11):

[0119]

[0120] The scheme with the highest U(x) is selected as the final output, which is the final decision scheme. It mainly involves the area allocation of various crops, which serves as the input to the subsequent CA-Dyna-CLUE coupled model and outputs the objective function value.

[0121] Step 3: Spatial Optimization and Layout. Spatial pattern optimization is performed by coupling the CA model and the Dyna-CLUE model. The CA model is a key technology connecting water suitability assessment and spatial layout. Cellular automata are dynamic system simulation methods based on discrete spatial grids, driving global evolution through local rules. In water-suitable planting optimization, the principle is to divide the study area into a regular grid network (e.g., 1km × 1km), with each cell serving as the smallest decision unit, carrying state attributes such as crop type and water suitability level. Moore's neighborhood (8 directions) or von Neumann neighborhood (4 directions) is used to influence crop rotation and layout, and state transition logic is formulated based on water conditions and neighborhood states.

[0122] Each 1km×1km grid in the target area is a cell, and each cell represents a minimum planting unit. The state attributes of each cell include crop type (corn, soybean, millet, potato, etc.), water suitability level (Level I-IV), and other attributes such as soil fertility, topography, and slope. The model achieves dynamic iteration by defining a state transition function (Equation 12).

[0123]

[0124] in, The current state; C ij For moisture constraint; N ij This refers to the rules governing the influence of neighboring regions.

[0125] Combining crop water suitability levels and neighborhood states, cell attribute conversion rules are formulated, including water constraint rules: only cells with water suitability levels ≥ III are allowed to plant water-intensive crops, while level IV cells are forced to fallow or be replanted with drought-resistant crops; neighborhood influence rules: adjacent cells should not be continuously planted with the same crop; and dynamic adjustment rules: the planting structure is adjusted according to interannual precipitation variations. The current cell state and attributes are input into the CA model, and the state at the next time step is calculated according to the cell attribute conversion rules. This process is repeated until a stable pattern is reached or a preset number of iterations are achieved, generating a preliminary spatial pattern.

[0126] Dyna-CLUE is a land use change model based on spatial explicit logistic regression. It predicts land use patterns under multiple scenarios by quantifying the probability of influence from socioeconomic and natural driving factors. In the spatial layout optimization of suitable planting structures, the probability calculation formula (Formula 13) for the Dyna-CLUE model is as follows:

[0127]

[0128] Where, p ij Let be the probability that cell (i, j) is converted into the target crop; β0 is the intercept term; β kX represents the regression coefficients of k factors, reflecting the contribution of each driving factor; n is the total number of driving factors; X ijk Let be the value of the k-th driving factor of cell (i,j), including socio-economic factors (such as GDP, food prices, arable land red line, irrigation guarantee rate, effective irrigated area, etc.) and natural driving factors (such as precipitation, effective soil water storage, etc.).

[0129] The Dyna-CLUE model is input with water suitability level, neighborhood state, preliminary spatial pattern output from the CA model, precipitation, effective soil water storage, GDP growth rate, grain price, arable land red line, irrigation guarantee rate, and effective irrigated area. Based on probability calculation formulas, the Dyna-CLUE model adjusts the layout according to socio-economic goals and ecological constraints, then feeds the adjustment results back to the CA model to recalculate local transformation rules, outputting a new spatial pattern of planting structure. This new pattern is then input into the Dyna-CLUE model until it meets socio-economic goals and ecological constraints, ultimately forming a spatial distribution map of the planting structure. The framework diagram for multi-objective spatial optimization of regional water-suitable planting structure is shown below. Figure 3 As shown.

[0130] This application utilizes high spatiotemporal resolution remote sensing ET data products to acquire real-time dynamic data of crop water demand in a fine grid within a region, conduct regional water suitability assessment, and implement the assessment results into a 1km×1km spatial grid. This overcomes the shortcomings of traditional methods that rely on empirical data or simple statistical models and are difficult to dynamically simulate the spatiotemporal dynamics of crop water demand, thus solving the problem of low spatiotemporal resolution in traditional empirical models.

[0131] For the first time, water suitability assessment based on real-time ET observations with high spatiotemporal resolution is combined with NSGA-II multi-objective optimization to achieve synergistic improvement in water efficiency and economic benefits. The NSGA-II algorithm is used to simultaneously optimize three conflicting objectives, breaking through the limitations of traditional single-objective optimization and systematically quantifying the triple contradiction of "water conservation, increased income, and stable grain production".

[0132] Spatial pattern optimization is achieved by coupling the CA (Compatibility Analysis) model and the Dyna-CLUE model. Water suitability rules are embedded in the CA model to achieve micro-grid-level optimization, while socio-economic goals and ecological constraints are input into the Dyna-CLUE model to simulate macro-policy scenarios and generate spatial layout adjustment schemes. The adjustment results are then fed back to the CA model to recalculate local transformation rules until convergence, resulting in a spatial distribution map of the planting structure. This dynamic spatial adaptation technology based on the coupled models improves the spatial resolution of the planting structure schemes while enhancing their feasibility for implementation.

[0133] By adopting a three-pronged approach of "grid-level water suitability assessment + multi-objective optimization + spatial dynamic simulation", this approach addresses three major challenges: quantification of water suitability, spatial applicability, and policy compatibility. It provides a quantifiable, applicable, and sustainable planting optimization paradigm for agriculture in arid and semi-arid regions.

[0134] Based on the same inventive concept, this application also provides a device for implementing the multi-objective spatial optimization method for regional water-suitable planting structures as described above. The solution provided by this device is similar to the implementation scheme described in the above method. Therefore, the specific limitations of one or more embodiments of the multi-objective spatial optimization device for regional water-suitable planting structures provided below can be found in the limitations of the multi-objective spatial optimization method for regional water-suitable planting structures described above, and will not be repeated here.

[0135] In one exemplary embodiment, such as Figure 4 As shown, a multi-objective spatial optimization device for regional water-suitable planting structures is provided, the device comprising:

[0136] The data acquisition module M1 is used to acquire remote sensing data on evapotranspiration water consumption and crop growth period in the target area.

[0137] The evapotranspiration water consumption calculation module M2 is used to calculate the evapotranspiration water consumption for each growth stage based on the remote sensing evapotranspiration water consumption data and the crop growth stage.

[0138] The grading module M3 is used to classify crop water suitability based on evapotranspiration water consumption at each growth stage using a fuzzy membership function, thus obtaining the crop water suitability level.

[0139] The multi-objective optimization model construction module M4 is used to construct a multi-objective optimization model based on the objective function and constraints. The objective function includes: maximizing water efficiency, optimizing economic benefits, and food security constraints. The constraints include: water constraints, area constraints, and neighborhood constraints.

[0140] The optimization calculation module M5 is used to perform optimization calculations on the multi-objective optimization model using the NSGA-II genetic algorithm to solve for the combination of crop planting structure optimization results.

[0141] The cell attribute conversion rule formulation module M6 is used to formulate cell attribute conversion rules by combining the crop water suitability level and neighborhood status; the cell represents a minimum planting unit; the cell attribute conversion rules include: water constraint rules, neighborhood influence rules and dynamic adjustment rules.

[0142] The combination module M7 is used to determine the current cell state and attributes based on the conversion rules of the cell attributes and the crop planting structure optimization results; the current cell state and attributes include: crop type, crop water suitability level, soil fertility, topography and slope.

[0143] The first input module M8 is used to input the current cell state and attributes into the cellular automaton model, calculate the state at the next moment according to the transformation rules of the cell attributes, repeat until a stable pattern or a preset number of iterations is reached, and generate a preliminary spatial pattern.

[0144] The second input module M9 is used to input the preliminary spatial pattern, crop water suitability level, neighborhood status, socio-economic factors and natural driving factors into the Dyna-CLUE model. The Dyna-CLUE model adjusts the layout according to socio-economic goals and ecological constraints based on probability calculation formulas to obtain the adjustment results.

[0145] The feedback module M10 is used to feed the adjustment results back to the cellular automata model, recalculate the transformation rules of cellular attributes until convergence, and output the spatial distribution map of the planting structure.

[0146] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 5 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores remotely sensed evapotranspiration water consumption data and crop growth stages for the target area. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a multi-objective spatial optimization method for regional water-suitable planting structures.

[0147] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0148] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method embodiments.

[0149] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the above-described method embodiments.

[0150] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the above-described method embodiments.

[0151] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0152] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0153] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0154] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0155] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A multi-objective spatial optimization method for regional water-suitable planting structures, characterized in that, The multi-objective spatial optimization method for regional suitable planting structure includes: Acquire remote sensing data on evapotranspiration water consumption and crop growth period in the target area; Based on the remote sensing evapotranspiration water consumption data and the crop growth period, calculate the evapotranspiration water consumption for each growth period; Based on the evapotranspiration water consumption at each growth stage, the crop water suitability is classified using a fuzzy membership function to obtain the crop water suitability level. A multi-objective optimization model is constructed based on the objective function and constraints. The objective function includes: maximizing water efficiency, optimizing economic benefits, and constraining food security. The constraints include: water constraints, area constraints, and neighborhood constraints. The NSGA-II genetic algorithm was used to optimize the multi-objective optimization model and solve for the combination of crop planting structure optimization results. Based on the crop water suitability level and neighborhood status, conversion rules for cell attributes are formulated; the cell represents a minimum planting unit; the conversion rules for cell attributes include: water constraint rules, neighborhood influence rules, and dynamic adjustment rules. Based on the combination of the transformation rules of the cell attributes and the crop planting structure optimization results, the current cell state and attributes are determined; the current cell state and attributes include: crop type, crop water suitability level, soil fertility, topography and slope; The current cell state and attributes are input into the cellular automaton model, and the state at the next moment is calculated according to the transformation rules of the cell attributes. This process is repeated until a stable pattern or a preset number of iterations is reached to generate a preliminary spatial pattern. The preliminary spatial pattern, crop water suitability level, neighborhood status, socio-economic factors and natural driving factors are input into the Dyna-CLUE model. The Dyna-CLUE model adjusts the layout according to socio-economic goals and ecological constraints based on probability calculation formulas to obtain the adjustment results. The adjustment results are fed back to the cellular automata model to recalculate the transformation rules of cellular attributes until convergence, and output the spatial distribution map of the planting structure.

2. The multi-objective spatial optimization method for regional water-suitable planting structure according to claim 1, characterized in that, The expression for the fuzzy membership function is: Where μ(x) is the fuzzy membership degree; x is the crop evapotranspiration water consumption; a1 is the lower water threshold, i.e. the minimum water requirement that the crop can tolerate; and a2 is the upper water threshold, i.e. the maximum water requirement that the crop can withstand.

3. The multi-objective spatial optimization method for regional water-suitable planting structure according to claim 1, characterized in that, The water efficiency maximization includes: blue water dependence and grey water footprint; The formula for calculating the blue water dependence is as follows: Where BWF_rate is the blue water dependency; ET ci Crop water requirements; A i P represents the planting area. i N represents effective precipitation; N represents crop type. The formula for calculating the grey water footprint is as follows: Where GWF_grey is the greywater footprint; C max C represents the water quality standard threshold. nat It is natural runoff water quality.

4. The multi-objective spatial optimization method for regional water-suitable planting structure according to claim 1, characterized in that, The optimal economic benefit is defined using net revenue per unit area as the objective function; the formula for calculating net revenue per unit area is: Where NP represents net revenue per unit area; Y i P is the yield per unit area. price,i C is the price of the i-th crop; input,i For production costs; A i N represents the planting area; N represents the crop type.

5. The multi-objective spatial optimization method for regional water-suitable planting structure according to claim 1, characterized in that, The expression for the food security constraint is: Among them, Y maize,i Yield per unit area of ​​staple food crops; Q min A represents the minimum demand in the region. i N represents the planting area; N represents the crop type.

6. The multi-objective spatial optimization method for regional water-suitable planting structure according to claim 1, characterized in that, The water constraint is that the total irrigation water volume is less than or equal to the available water resources in the region. The expression for the moisture constraint is: Among them, ET ci Crop water requirements; A i P represents the planting area. i N represents effective precipitation; N represents crop type; W represents effective precipitation. avail This represents the total available water resources in the region. The area constraint is that the planting area of ​​each crop is greater than or equal to the minimum guaranteed area, and the total planting area is less than or equal to the total cultivated land area. The neighborhood constraint requires that crop distribution meet the requirements of crop rotation and water suitability.

7. The multi-objective spatial optimization method for regional water-suitable planting structure according to claim 1, characterized in that, The probability calculation formula is as follows: Where, p ij Let be the probability that cell (i, j) is converted into the target crop; β0 is the intercept term; β k X represents the regression coefficients of k factors, reflecting the contribution of each driving factor; n is the total number of driving factors; X ijk Let be the value of the k-th driving factor of cell (i, j).

8. A multi-objective spatial optimization device for regional water-suitable planting structures, characterized in that, The regional water-suitable planting structure multi-objective spatial optimization device is used to implement the regional water-suitable planting structure multi-objective spatial optimization method according to any one of claims 1-7, and the regional water-suitable planting structure multi-objective spatial optimization device includes: The data acquisition module is used to acquire remote sensing data on evapotranspiration water consumption and crop growth period in the target area; The evapotranspiration water consumption calculation module is used to calculate the evapotranspiration water consumption for each growth stage based on the remote sensing evapotranspiration water consumption data and the crop growth stage. The grading module is used to classify crop water suitability based on evapotranspiration water consumption at each growth stage using fuzzy membership functions, and obtain crop water suitability level. A multi-objective optimization model construction module is used to construct a multi-objective optimization model based on objective functions and constraints; the objective functions include: maximizing water efficiency, optimizing economic benefits, and food security constraints; the constraints include: water constraints, area constraints, and neighborhood constraints. The optimization calculation module is used to perform optimization calculations on the multi-objective optimization model using the NSGA-II genetic algorithm to solve for the combination of crop planting structure optimization results; The cell attribute conversion rule formulation module is used to formulate cell attribute conversion rules by combining the crop water suitability level and neighborhood status; the cell represents a minimum planting unit; the cell attribute conversion rules include: water constraint rules, neighborhood influence rules, and dynamic adjustment rules. The combination module is used to determine the current cell state and attributes based on the transformation rules of the cell attributes and the crop planting structure optimization results; the current cell state and attributes include: crop type, crop water suitability level, soil fertility, topography and slope; The first input module is used to input the current cell state and attributes into the cellular automaton model, calculate the state at the next moment according to the transformation rules of cell attributes, repeat until a stable pattern or a preset number of iterations is reached, and generate a preliminary spatial pattern. The second input module is used to input the preliminary spatial pattern, crop water suitability level, neighborhood status, socio-economic factors and natural driving factors into the Dyna-CLUE model. The Dyna-CLUE model adjusts the layout according to socio-economic goals and ecological constraints based on probability calculation formulas to obtain the adjustment results. The feedback module is used to feed the adjustment results back to the cellular automata model, recalculate the transformation rules of cellular attributes until convergence, and output the spatial distribution map of the planting structure.

9. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that the processor executes the computer program to implement the multi-objective spatial optimization method for regional water-suitable planting structures according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the multi-objective spatial optimization method for regional water-suitable planting structures as described in any one of claims 1-7.

Images