Black soil area land utilization optimization method and device, computer equipment and storage medium

Abstract

The invention relates to a black soil area land utilization optimization method and device, computer equipment and a storage medium. According to the black soil area land utilization optimization method, through linear fusion of objective weights and subjective weights, the problem of weight distortion caused by abnormal dispersion of original data is effectively solved, and meanwhile, personal prejudice possibly existing in a subjective scoring method is also corrected; economic indexes and ecological indexes can reflect objective distribution rules of data in an evaluation system, and strategic business logic of black soil protection can be met. Through the constructed dual-objective optimization model, a previous land utilization mode which purely aims at pursuing crop yield maximization is changed, and at the same time, a non-dominated solution set is solved by using a non-dominated sorting algorithm, and a plurality of possible schemes for optimal balance between economy and ecology are provided. A weighted standardization matrix is constructed by using the first comprehensive weight and the second comprehensive weight, and a target solution conforming to ideal balance can be screened out from the non-dominated solution set.

Description

Technical Field

[0001] This invention relates to the field of agricultural big data information technology, and more specifically, to a method, apparatus, computer equipment, and storage medium for optimizing land use in black soil regions. Background Technology

[0002] As a major grain-producing area in my country, the black soil region plays an irreplaceable strategic role in ensuring national food security and promoting sustainable agricultural development, thanks to its fertile soil texture and excellent tillage performance. However, in recent years, affected by factors such as intensive farming, monoculture, and excessive fertilization, the region generally faces prominent problems such as a continuous decline in soil organic matter content, accelerated soil structure degradation, and increased risk of soil erosion, leading to a gradual decline in land productivity and a continuous deterioration of the regional ecological environment. Therefore, it is essential to optimize land use in the black soil region to improve land productivity and the regional ecological environment.

[0003] With the development of information technologies such as remote sensing, soil monitoring sensors, agricultural machinery operation records, and meteorological data, the agricultural sector has gradually accumulated multi-source, multi-scale, and long-term agricultural big data. This type of data can characterize soil property changes, crop growth processes, climate fluctuations, and cultivation management measures in both spatial and temporal dimensions, providing a more refined and continuous information foundation for regional-scale farmland quality assessment and land use decisions.

[0004] At the practical level of land use optimization, existing technologies for land use optimization still do not fully utilize agricultural big data. Many methods still rely on statistical summary data or limited sample data and focus on single objectives such as increasing yield or maximizing economic benefits. They lack comprehensive consideration of maintaining soil quality and protecting ecological functions, resulting in land use schemes that fail to reflect the significant spatial differences within the black soil region and fail to balance economic and ecological benefits, leading to low land utilization rates. Summary of the Invention

[0005] In view of the above analysis, the embodiments of the present invention aim to provide a method, apparatus, computer equipment and storage medium for optimizing land use in black soil areas, so as to solve one or more of the above-mentioned problems existing in the prior art.

[0006] To achieve the above objectives, this application provides a land use optimization method for black soil regions, comprising the following steps: Acquire soil big data, crop yield data, management configuration parameters, and meteorological big data for the target black soil region; Based on soil big data, crop yield data, management configuration parameters and meteorological big data, multiple economic benefit indicators and multiple ecological benefit indicators are calculated. Calculate the first objective weight and the first subjective weight of each economic benefit indicator, and calculate the second objective weight and the second subjective weight of each ecological benefit indicator. Based on the first objective weight and the first subjective weight of each economic benefit indicator, the first comprehensive weight of each economic benefit indicator is obtained, and based on the second objective weight and the second subjective weight of each ecological benefit indicator, the second comprehensive weight of each ecological benefit indicator is obtained. Based on the comprehensive weights of various ecological benefit indicators, soil quality parameters are obtained, and a dual-objective optimization model is constructed with the goals of maximizing crop yield and maximizing soil quality parameters. Solve the biobjective optimization model to obtain the nondominated solution set; Construct ideal and negative ideal standardized matrices, and based on the first and second comprehensive weights, construct a weighted standardized matrix for any solution in the non-dominated solution set; Based on the first distance metric between the weighted normalized matrix and the ideal normalized matrix, and the second distance metric between the weighted normalized matrix and the negative ideal normalized matrix, the objective solution in the non-dominated solution set is selected and output; whereby the objective solution is used to optimize land use.

[0007] In one embodiment, the step of calculating the first objective weight of each economic benefit indicator includes: The economic efficiency indicators are standardized to obtain multiple dimensionless economic indicator values. Calculate the first weight value of any dimensionless economic indicator; Based on the first weight value, the first information entropy value is obtained, and based on the first information entropy value, the first difference coefficient is calculated. By processing the first difference coefficient, the first objective weight of the economic benefit indicator is obtained.

[0008] In one embodiment, the first comprehensive weight is obtained based on the following formula: in, The weighted fusion coefficient; As the first overall weight; As the first subjective weight; It is the first objective weight.

[0009] In one embodiment, the first subjective weight is obtained by processing each economic benefit indicator using the analytic hierarchy process or expert scoring method.

[0010] In one embodiment, the step of calculating the second objective weight of each ecological benefit indicator includes: By standardizing the various ecological benefit indicators, multiple dimensionless ecological indicator values ​​are obtained. Calculate the second weighting value of any dimensionless ecological indicator; Based on the second weight value, the second information entropy value is obtained, and based on the second information entropy value, the second difference coefficient is calculated. The second difference coefficient is processed to obtain the second objective weight.

[0011] In one embodiment, the step of solving the biobjective optimization model to obtain the non-dominated solution set includes: An adaptive non-dominated sorting genetic algorithm is used to solve the bi-objective optimization model and obtain the Pareto optimal solution set. The current crossover probability and the current mutation probability of the adaptive non-dominated sorting genetic algorithm are both obtained based on the current iteration number and the preset maximum iteration number.

[0012] In one embodiment, the step of constructing a weighted normalization matrix for any solution in the non-dominated solution set based on a first comprehensive weight and a second comprehensive weight includes: Normalize the comprehensive economic benefits and comprehensive ecological benefits corresponding to the solutions in the non-dominated solution set to obtain the current dimensionless economic indicators and current dimensionless ecological indicators; among them, the comprehensive economic benefits are obtained according to the first comprehensive weight solution; the comprehensive ecological benefits are obtained according to the second comprehensive weight solution. Based on the current dimensionless ecological indicators and current dimensionless economic indicators, a weighted standardized matrix is ​​obtained; On one hand, embodiments of the present invention provide a land use optimization device for black soil regions, comprising: The acquisition module is used to acquire soil big data, crop yield data, management configuration parameters, and meteorological big data for the target black soil region. The indicator calculation module is used to calculate multiple economic benefit indicators and multiple ecological benefit indicators based on soil big data, crop yield data, management configuration parameters and meteorological big data. The first weight calculation module is used to calculate the first objective weight and the first subjective weight of each economic benefit indicator, and to calculate the second objective weight and the second subjective weight of each ecological benefit indicator. The second weight calculation module is used to obtain the first comprehensive weight of each economic benefit indicator based on the first objective weight and the first subjective weight of each economic benefit indicator, and to obtain the second comprehensive weight of each ecological benefit indicator based on the second objective weight and the second subjective weight of each ecological benefit indicator. The model building module is used to obtain soil quality parameters based on the comprehensive weights of various ecological benefit indicators, and to build a dual-objective optimization model with the goals of maximizing crop yield and maximizing soil quality parameters. The solver module is used to solve the bi-objective optimization model and obtain the non-dominated solution set. The first evaluation module is used to construct the ideal standardized matrix and the negative ideal standardized matrix, and based on the first comprehensive weight and the second comprehensive weight, constructs a weighted standardized matrix for any solution in the non-dominated solution set; The second evaluation module is used to select and output the target solution in the non-dominated solution set based on the first distance metric between the weighted standardized matrix and the ideal standardized matrix, and the second distance metric between the weighted standardized matrix and the negative ideal standardized matrix; wherein the target solution is used to optimize land use.

[0013] On one hand, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method.

[0014] On the other hand, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0015] One of the above technical solutions has the following advantages and beneficial effects: The aforementioned land use optimization method for black soil regions effectively solves the weight distortion problem caused by abnormal dispersion of the original data by linearly fusing objective and subjective weights. It also corrects potential personal biases inherent in subjective scoring methods, ensuring that economic and ecological indicators reflect both the objective distribution patterns of the data and the strategic business logic of black soil protection within the evaluation system. The constructed dual-objective optimization model changes the previous land use pattern that solely pursued maximizing crop yield. Furthermore, the non-dominated solution set obtained using the non-dominated sorting algorithm provides multiple possible solutions for the optimal trade-off between economy and ecology. A weighted standardization matrix constructed using the first and second comprehensive weights can screen out target solutions that meet the ideal balance from the non-dominated solution set. In addition, this application focuses on the dual objectives of yield and soil quality during the optimization stage, reducing the computational complexity and solution set degradation risk associated with optimizing too many objectives. Since yield is the core physical carrier of output value and input-output ratio, using yield as the objective ensures that the search process covers the optimal production potential. By introducing economic benefit indicators such as output value and cost into the back-end decision-making and screening process, the synergy between global potential search and refined value screening is achieved, which not only ensures solution efficiency, but also compensates for the detailed information of the economic dimension through multi-criteria decision-making. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0018] Figure 1 This is a first schematic flowchart of a land use optimization method in a black soil region according to one embodiment; Figure 2 This is a schematic flowchart illustrating the steps for calculating the first objective weights of each economic benefit indicator in one embodiment. Figure 3 This is a schematic flowchart illustrating the steps for calculating the second objective weights of each ecological benefit indicator in one embodiment; Figure 4 This is a schematic flowchart illustrating the steps of constructing a weighted normalization matrix for any solution in the non-dominated solution set based on a first comprehensive weight and a second comprehensive weight, in one embodiment. Detailed Implementation

[0019] To facilitate understanding of this application, a more complete description will be provided below with reference to the accompanying drawings, which illustrate embodiments of the present application. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that the disclosure of this application will be thorough and complete.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0021] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustration and has no specific meaning in itself. Therefore, "module" and "part" may be used interchangeably.

[0022] It is understood that the term "connection" in the following embodiments should be understood as "electrical connection," "communication connection," etc., if the connected circuits, modules, units, etc., have electrical signal or data transmission with each other.

[0023] When used herein, the singular forms of “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising,” “including,” or “having,” etc., specify the presence of the stated feature, whole, step, operation, component, part, or combination thereof, but do not preclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof.

[0024] In one embodiment, such as Figure 1 As shown, a land use optimization method for black soil regions is provided, including the following steps: S110: Acquire soil big data, crop yield data, management configuration parameters, and meteorological big data for the target black soil region; Among these, soil big data refers to soil-related physicochemical properties, including organic matter content, total nitrogen, available phosphorus, available potassium, pH value, bulk density, and aggregate content. Crop yield data refers to the output data and planting area of ​​each crop within a historical planting cycle; crops can include corn, soybeans, wheat, etc. Management configuration parameters refer to decision variables for human intervention in farmland systems, including fertilizer application intensity (nitrogen, phosphorus, and potassium fertilizers), irrigation water volume, tillage methods (deep plowing, no-till, reduced tillage), crop rotation systems (continuous cropping or crop rotation patterns), and agricultural labor and machinery costs. Meteorological big data refers to external environmental data affecting crop growth and soil evolution, including cumulative precipitation, daily average temperature, effective accumulated temperature, sunshine duration, and evapotranspiration intensity.

[0025] Specifically, soil big data can be obtained from real-time monitoring by ground sensors, laboratory sampling and testing results, or it can be obtained based on soil attribute grid data retrieved from remote sensing. Crop yield data can be obtained from yield spatial distribution maps estimated based on NDVI (Normalized Difference Vegetation Index); meteorological big data can be provided by meteorological stations.

[0026] Furthermore, the acquired data needs to be preprocessed. Specifically, the collected data can be formatted and spatially registered, outliers can be removed, and missing data can be filled in using spatial interpolation methods (such as Kriging interpolation or inverse distance weighting). All data should be standardized in terms of spatial resolution, time scale, and coordinate system to establish an integrated land-crop-management database.

[0027] S120 calculates multiple economic and ecological benefit indicators based on soil big data, crop yield data, management configuration parameters, and meteorological big data. Among them, economic benefit indicators are used to characterize the production efficiency and economic benefits of farmland systems, and can include crop yield, output value (the product of crop yield and market unit price), and input-output ratio (the revenue generated per unit cost). Ecological benefit indicators are used to characterize the ecological quality and environmental sustainability of farmland systems, and can include the soil organic matter content improvement rate, erosion sensitivity, nutrient balance index, and soil structure stability.

[0028] Specifically, crop yield refers to the output per unit area of ​​farmland, expressed in tons per hectare. This indicator can be obtained through remote sensing estimation, statistical surveys, or field yield measurements. If multiple crops are present, the overall yield is calculated by weighting the crop planting area. : ; in, For crops production, This represents the planting area of ​​the crop.

[0029] The output value The product of crop yield and its market price, expressed in yuan per hectare, is calculated using the following formula: ; in, For crops The market unit price. For multiple crops, the same area-weighted calculation can be used.

[0030] Input-output ratio The economic output obtained per unit of economic input is defined as: ; in, Agricultural input costs per unit area include the costs of seeds, fertilizers, pesticides, irrigation, machinery, and labor.

[0031] Soil organic matter content increase rate This indicator reflects the degree of improvement in soil organic matter, and the calculation formula is as follows: ; in, The current soil organic matter content (g·kg) -1 ), This represents the baseline content. This indicator can be obtained through laboratory testing or extraction from soil databases.

[0032] Erosion sensitivity, an index used to reflect the susceptibility of soil to water erosion, is characterized by the soil erodibility factor K value, and the calculation formula is as follows: ; in, Organic matter content (%) For particle size parameters, For structural levels, This is the penetration level. A higher value indicates that the soil is more susceptible to erosion.

[0033] Nutrient balance index This indicator is used to characterize the balance between nutrient input and output, and the calculation formula is: ; in, Nutrient input for fertilizer, organic matter and residue return (kg·ha) -1 ), Nutrient output absorbed by crops (kg·ha) -1 When NBI > 0, it indicates nutrient accumulation; when NBI < 0, it indicates nutrient deficiency.

[0034] Soil structural stability, an index used to characterize soil's resistance to erosion and its ability to retain soil, is expressed as the average weight diameter (mm²). )express: ; in, The median diameter (mm) of soil particles. This represents the mass fraction (%) of that particle size. A higher value indicates a more stable structure.

[0035] S130, calculate the first objective weight and the first subjective weight of each economic benefit indicator, and calculate the second objective weight and the second subjective weight of each ecological benefit indicator. Specifically, such as Figure 2 As shown, the steps for calculating the first objective weight of each economic benefit indicator include: S210, standardizing each economic benefit indicator to obtain multiple dimensionless economic indicator values; S220, calculating the first proportion value of any dimensionless economic indicator value; S230, obtaining the first information entropy value based on the first proportion value, and calculating the first difference coefficient based on the first information entropy value; S240, processing the first difference coefficient to obtain the first objective weight of the economic benefit indicator.

[0036] Specifically, each indicator is standardized to obtain dimensionless indicator values. , , , , , , Standardization can be performed using Z-score standardization or other methods in this field. Assuming there are m samples and n indicators, the standardized data matrix is ​​as follows: .

[0037] Then, calculate the first weight value of any dimensionless economic indicator: ; in, Indicates the first The sample at the th The percentage of each indicator, i.e., the first weight value.

[0038] In the step of obtaining the first information entropy value based on the first weight value, the first information entropy value is calculated based on the following formula. : ; Where, constant ,like Then let .

[0039] In the step of calculating the first difference coefficient based on the first information entropy value, the first difference coefficient is calculated based on the following formula. : ; Finally, in the step of processing the first difference coefficient to obtain the first objective weight of the economic benefit indicator, the first objective weight is calculated based on the following formula: ; in, Indicators Objective weight, .

[0040] Furthermore, the second objective weight can also be obtained by referring to the above content. In one example, the first and second subjective weights are obtained by processing the economic benefit indicators using the analytic hierarchy process (AHP) or expert scoring method. Specifically, if the AHP is used, a judgment matrix can be constructed. ,satisfy: ; Perform eigenvalue decomposition on the judgment matrix and extract the eigenvector corresponding to the largest eigenvalue. and normalize: ; Then, a consistency check is performed: ; As a consistency indicator, it measures deviation. To what extent, The largest eigenvalue n of this judgment matrix is ​​the order of the judgment matrix. It is a random consistency indicator. It is the consistency ratio, when At that time, the agreement was passed.

[0041] The steps for using the expert scoring method are as follows: Let the first... The expert gave the first Each indicator is scored as follows Then the average score of this indicator for: ; in, The total number of experts was normalized.

[0042] S140. Based on the first objective weight and the first subjective weight of each economic benefit indicator, the first comprehensive weight of each economic benefit indicator is obtained, and based on the second objective weight and the second subjective weight of each ecological benefit indicator, the second comprehensive weight of each ecological benefit indicator is obtained. In one embodiment, the first comprehensive weight is obtained based on the following formula: ; in, This is the weighting fusion coefficient, typically taken as 0.5 to 0.7 to balance subjective and objective influences; As the first overall weight; As the first subjective weight; It is the first objective weight.

[0043] S150, based on the comprehensive weight of various ecological benefit indicators, obtains soil quality parameters, and constructs a dual-objective optimization model with the goals of maximizing crop yield and maximizing soil quality parameters; Among them, the comprehensive soil quality index is a weighted sum of comprehensive soil quality indicators (dimensionless): ; in, Indicates the original ecological indicators Standardization was performed to ensure that all indicators had the same dimensions before weighted synthesis, and The larger the value, the better the soil quality.

[0044] Furthermore, the maximum total crop yield: ; for Crop planting area For crops The output. Decision variables. , is a decision vector for planting crops or management measures on arable land, which may include crop type selection, fertilizer application per unit area, irrigation water volume, and planting area allocation.

[0045] And maximizing soil quality: ; The above bi-objective optimization model The constraints include land area constraints ( Resource constraints The study area is divided into three categories: crop management constraints and environmental safety constraints. A represents the total available arable land area, and B represents the available budget or resources. Crop management constraints are used to limit the configuration of various crops on different plots to meet the requirements of basic agronomic systems and production conditions. These constraints are set based on actual planting conditions and include, but are not limited to: allowing only one main crop on the same plot within the same production cycle; setting a reasonable range for the overall planting scale of various crops in the study area to avoid excessive concentration or compression of a single crop; restricting the planting of specific crops on some unsuitable plots based on topography, soil, and infrastructure conditions; setting continuous planting restrictions for crops that require crop rotation to prevent long-term monoculture leading to soil degradation and pest accumulation; and configuring high-water-demand or high-input crops only on plots with appropriate irrigation and cultivation conditions to ensure that the land use plan meets the actual requirements of agricultural production and management. Environmental safety constraints are used to limit the land use intensity of each plot to not exceeding its ecological carrying capacity. These constraints are set according to the actual regional conditions and include, but are not limited to: controlling the potential soil erosion risk of each plot to not exceed a preset safety threshold; avoiding highly disturbing farming practices in erosion-sensitive plots; limiting the proportion of high-nutrient-input farming practices in environmentally sensitive areas to reduce nitrogen and phosphorus loss and non-point source pollution risks; prioritizing land use practices conducive to soil restoration and fertility improvement for plots with low soil fertility or declining organic matter; limiting the scale of water-intensive crops in water-constrained areas to prevent excessive consumption of groundwater and surface water; and reducing farming intensity or adopting protective farming practices in plots surrounding rivers, ditches, and ecological buffer zones to maintain regional ecological security.

[0046] S160, Solve the bi-objective optimization model to obtain the non-dominated solution set; Specifically, the non-dominated solution set consists of all "non-dominated solutions," meaning that no other solution is superior to this solution in all objectives. The solution can be obtained using a non-dominated sorting genetic algorithm or other methods in this field, as long as the non-dominated solution set can be obtained. Each solution corresponds to a land use scheme.

[0047] S170, construct the ideal standardized matrix and the negative ideal standardized matrix, and construct the weighted standardized matrix for any solution in the non-dominated solution set based on the first comprehensive weight and the second comprehensive weight; Specifically, the TOPSIS method is used to construct the ideal normalized matrix and the negative ideal normalized matrix. Ideal Normalized Matrix Negative ideal standardized matrix .

[0048] For solutions in the non-dominated solution set, the comprehensive ecological and economic benefits corresponding to the land use schemes for these solutions can be calculated as follows: ; ; in, For comprehensive economic benefits, For comprehensive ecological benefits.

[0049] in, , , As the first overall weight, to The second comprehensive weight is used. The calculated comprehensive ecological and economic benefit indicators are normalized to eliminate the influence of different indicator dimensions. Then, weights are assigned to the comprehensive ecological and economic benefit indicators, with the sum of the weights being 1. The comprehensive economic and ecological benefits of each solution are multiplied by their corresponding weights to obtain the weighted standardized matrix. .

[0050] S180, based on the first distance metric between the weighted normalized matrix and the ideal normalized matrix. And the second distance metric between the weighted normalized matrix and the negative ideal normalized matrix. Select the objective solution from the non-dominated solution set and output it; the objective solution is used to optimize land use.

[0051] The distance metric can be Euclidean distance. Based on the first and second distance metrics, the relative proximity can be calculated. : ; The greater the relative similarity, the closer the solution is to the ideal state in balancing economic and ecological objectives. Based on the relative similarity, a target solution is selected from the non-dominated solution set and output for land optimization.

[0052] The aforementioned land use optimization method for black soil regions effectively solves the weight distortion problem caused by abnormal dispersion of the original data by linearly fusing objective and subjective weights. It also corrects potential personal biases inherent in subjective scoring methods, ensuring that economic and ecological indicators reflect both the objective distribution patterns of the data and the strategic business logic of black soil protection within the evaluation system. The constructed dual-objective optimization model changes the previous land use pattern that solely pursued maximizing crop yield. Furthermore, the non-dominated solution set obtained using the non-dominated sorting algorithm provides multiple possible solutions for the optimal trade-off between economics and ecology. A weighted standardization matrix constructed using the first and second comprehensive weights can filter out target solutions that meet the ideal balance from the non-dominated solution set. In addition, this application focuses on the dual objectives of yield and soil quality during the optimization stage, reducing the computational complexity and solution set degradation risk associated with optimizing too many objectives. Since yield is the core physical quantity for output value and input-output ratio, using yield as the objective ensures that the search process covers the optimal production potential. If economic benefit indicators are used as the objective, the yield factor would be calculated three times, greatly reducing the influence of ecological benefit indicators. By introducing economic benefit indicators such as output value and cost into the back-end decision-making and screening process, the synergy between global potential search and refined value screening is achieved, which not only ensures solution efficiency, but also compensates for the detailed information of the economic dimension through multi-criteria decision-making.

[0053] In one embodiment, the steps described above for obtaining the first comprehensive weight are as follows: ; in, The weighted fusion coefficients are fixed if the currently collected data is highly noisy (objective weights are unreliable) or if experts are unfamiliar with a specific area (subjective weights are unreliable). The value of the value can lead to distortion in the final weights. Furthermore, the high correlation between economic indicators can cause a weighting effect. The correlation coefficient matrix of the original data can be used to correct the objective function of the game theory, thereby eliminating the weight bias caused by the high correlation between economic indicators (such as output and output value). First, calculate the Pearson correlation coefficient matrix between the n indicators. , ,in Indicators and indicators The degree of linear correlation between them. Based on the correlation coefficient matrix. Constructing a redundancy correction matrix , .

[0054] Based on the redundancy correction matrix, a Nash equilibrium objective function is constructed in the Markov set space to find the combination coefficients that minimize the deviation between the comprehensive weights and the basic weights. ; in, Represents objective weight, Represents subjective weight. For the first One weight to be compared.

[0055] Solving the above function yields the original coefficients. Specifically, the objective function can be transformed into a system of linear equations in matrix form: ; And by solving, we can obtain , .

[0056] After normalization, the comprehensive weight is obtained. .

[0057] This method can be applied to the calculation of the comprehensive weight of various ecological or economic benefit indicators.

[0058] In one embodiment, such as Figure 3 As shown, the steps for calculating the second objective weights of each ecological benefit indicator include: S310 standardizes the various ecological benefit indicators to obtain multiple dimensionless ecological indicator values. S320, the second weighting value for calculating any dimensionless ecological indicator value; S330, based on the second weight value, obtain the second information entropy value, and based on the second information entropy value, calculate the second difference coefficient; S340, process the second difference coefficient to obtain the second objective weight.

[0059] For a detailed description of the second objective weight, please refer to the content on the first objective weight.

[0060] In one embodiment, the step of solving the biobjective optimization model to obtain the non-dominated solution set includes: An adaptive non-dominated sorting genetic algorithm is used to solve the bi-objective optimization model and obtain the Pareto optimal solution set. The current crossover probability and the current mutation probability of the adaptive non-dominated sorting genetic algorithm are both obtained based on the current iteration number and the preset maximum iteration number.

[0061] Specifically, a non-dominated sorting genetic algorithm is used to solve the bi-objective model. The algorithm first initializes multiple individuals with random land use schemes and calculates their yield and soil quality target values. In each generation, the algorithm compares the two objective function values ​​of each individual and determines the superiority of the solution based on the non-dominated relationship. If solution A is not inferior to solution B in all objectives and is superior to solution B in at least one objective, then A is considered to dominate B. To maintain population diversity, individuals within the same non-dominated layer are sorted based on crowding distance. Crowding distance... ,in This represents the m-th objective function value.

[0062] During the iteration process, the algorithm generates new individuals through selection, crossover, and mutation operations, and selects the Pareto optimal solution set based on the non-dominated sorting principle. To improve the algorithm's stability and global search capability, the crossover and mutation probabilities are adaptively adjusted according to the convergence status. The adjustment formulas are as follows: Crossover probability: ; Mutation probability: ; in, Let the current iteration algebra be... This is the maximum number of iterations set.

[0063] In one embodiment, such as Figure 4 As shown, the steps for constructing a weighted normalization matrix for any solution in the non-dominated solution set based on the first and second comprehensive weights include: S410, normalize the comprehensive economic benefits and comprehensive ecological benefits corresponding to the solutions in the non-dominated solution set to obtain the current dimensionless economic indicators and current dimensionless ecological indicators; among them, the comprehensive economic benefits are obtained according to the first comprehensive weight solution; the comprehensive ecological benefits are obtained according to the second comprehensive weight solution. Specifically, for solutions in the non-dominated solution set, the comprehensive ecological and economic benefits corresponding to the land use schemes for those solutions can be calculated as follows: ; ; in, For comprehensive economic benefits, For comprehensive ecological benefits.

[0064] For the overall weight, where, , , As the first overall weight, to This serves as the second comprehensive weight. The calculated comprehensive ecological and economic benefit indicators are normalized to eliminate the influence of different indicator dimensions.

[0065] S420, based on current dimensionless ecological indicators and current dimensionless economic indicators, yields a weighted standardized matrix; Specifically, weights are then assigned to the comprehensive ecological and economic benefit indicators, with the sum of the weights being 1. The comprehensive economic and ecological benefits of each solution are multiplied by their respective weights to obtain a weighted standardized matrix. .

[0066] In one embodiment, a land use optimization device for black soil regions is provided, comprising: The acquisition module is used to acquire soil big data, crop yield data, management configuration parameters, and meteorological big data for the target black soil region. The indicator calculation module is used to calculate multiple economic benefit indicators and multiple ecological benefit indicators based on soil big data, crop yield data, management configuration parameters and meteorological big data. The first weight calculation module is used to calculate the first objective weight and the first subjective weight of each economic benefit indicator, and to calculate the second objective weight and the second subjective weight of each ecological benefit indicator. The second weight calculation module is used to obtain the first comprehensive weight of each economic benefit indicator based on the first objective weight and the first subjective weight of each economic benefit indicator, and to obtain the second comprehensive weight of each ecological benefit indicator based on the second objective weight and the second subjective weight of each ecological benefit indicator. The model building module is used to obtain soil quality parameters based on the comprehensive weights of various ecological benefit indicators, and to build a dual-objective optimization model with the goals of maximizing crop yield and maximizing soil quality parameters. The solver module is used to solve the bi-objective optimization model and obtain the non-dominated solution set. The first evaluation module is used to construct the ideal standardized matrix and the negative ideal standardized matrix, and based on the first comprehensive weight and the second comprehensive weight, constructs a weighted standardized matrix for any solution in the non-dominated solution set; The second evaluation module is used to select and output the target solution in the non-dominated solution set based on the first distance metric between the weighted standardized matrix and the ideal standardized matrix, and the second distance metric between the weighted standardized matrix and the negative ideal standardized matrix; wherein the target solution is used to optimize land use.

[0067] Specific limitations regarding the land use optimization device for black soil regions can be found in the limitations of the land use optimization method for black soil regions mentioned above, and will not be repeated here. Each module in the aforementioned land use optimization device for black soil regions can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module. It should be noted that the module division in this embodiment is illustrative and only represents a logical functional division; other division methods may be used in actual implementation.

[0068] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps: Acquire soil big data, crop yield data, management configuration parameters, and meteorological big data for the target black soil region; Based on soil big data, crop yield data, management configuration parameters and meteorological big data, multiple economic benefit indicators and multiple ecological benefit indicators are calculated. Calculate the first objective weight and the first subjective weight of each economic benefit indicator, and calculate the second objective weight and the second subjective weight of each ecological benefit indicator. Based on the first objective weight and the first subjective weight of each economic benefit indicator, the first comprehensive weight of each economic benefit indicator is obtained, and based on the second objective weight and the second subjective weight of each ecological benefit indicator, the second comprehensive weight of each ecological benefit indicator is obtained. Based on the comprehensive weights of various ecological benefit indicators, soil quality parameters are obtained, and a dual-objective optimization model is constructed with the goals of maximizing crop yield and maximizing soil quality parameters. Solve the biobjective optimization model to obtain the nondominated solution set; Construct ideal and negative ideal standardized matrices, and based on the first and second comprehensive weights, construct a weighted standardized matrix for any solution in the non-dominated solution set; Based on the first distance metric between the weighted normalized matrix and the ideal normalized matrix, and the second distance metric between the weighted normalized matrix and the negative ideal normalized matrix, the objective solution in the non-dominated solution set is selected and output; whereby the objective solution is used to optimize land use.

[0069] In one embodiment, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, performs the following steps: Acquire soil big data, crop yield data, management configuration parameters, and meteorological big data for the target black soil region; Based on soil big data, crop yield data, management configuration parameters and meteorological big data, multiple economic benefit indicators and multiple ecological benefit indicators are calculated. Calculate the first objective weight and the first subjective weight of each economic benefit indicator, and calculate the second objective weight and the second subjective weight of each ecological benefit indicator. Based on the first objective weight and the first subjective weight of each economic benefit indicator, the first comprehensive weight of each economic benefit indicator is obtained, and based on the second objective weight and the second subjective weight of each ecological benefit indicator, the second comprehensive weight of each ecological benefit indicator is obtained. Based on the comprehensive weights of various ecological benefit indicators, soil quality parameters are obtained, and a dual-objective optimization model is constructed with the goals of maximizing crop yield and maximizing soil quality parameters. Solve the biobjective optimization model to obtain the nondominated solution set; Construct ideal and negative ideal standardized matrices, and based on the first and second comprehensive weights, construct a weighted standardized matrix for any solution in the non-dominated solution set; Based on the first distance metric between the weighted normalized matrix and the ideal normalized matrix, and the second distance metric between the weighted normalized matrix and the negative ideal normalized matrix, the objective solution in the non-dominated solution set is selected and output; whereby the objective solution is used to optimize land use.

[0070] In specific implementations, the embodiments of this application can be referred to the above embodiments, and have corresponding technical effects. It is understood that the embodiments described herein can be implemented using hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in this application, or combinations thereof.

[0071] For software implementation, the techniques described herein can be implemented by units that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented in the processor or external to the processor.

[0072] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0073] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0074] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0075] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0076] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0077] If the aforementioned function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks. It should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. In the absence of further restrictions, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0078] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of this application. It should be understood that the above description is only a specific embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A land use optimization method for black soil regions, characterized in that, include: Acquire soil big data, crop yield data, management configuration parameters, and meteorological big data for the target black soil region; Based on the soil big data, crop yield data, management configuration parameters, and meteorological big data, multiple economic benefit indicators and multiple ecological benefit indicators are calculated. Calculate the first objective weight and the first subjective weight of each of the economic benefit indicators, and calculate the second objective weight and the second subjective weight of each of the ecological benefit indicators; Based on the first objective weight and the first subjective weight of each of the economic benefit indicators, the first comprehensive weight of each of the economic benefit indicators is obtained, and based on the second objective weight and the second subjective weight of each of the ecological benefit indicators, the second comprehensive weight of each of the ecological benefit indicators is obtained. Based on the comprehensive weights of the ecological benefit indicators, soil quality parameters are obtained, and a dual-objective optimization model is constructed with the goals of maximizing crop yield and maximizing soil quality parameters. Solve the biobjective optimization model to obtain the non-dominated solution set; Construct an ideal standardized matrix and a negative ideal standardized matrix, and based on the first comprehensive weight and the second comprehensive weight, construct a weighted standardized matrix for any solution in the non-dominated solution set; Based on the first distance metric between the weighted normalized matrix and the ideal normalized matrix, and the second distance metric between the weighted normalized matrix and the negative ideal normalized matrix, a target solution is selected from the non-dominated solution set and output; wherein, the target solution is used to optimize land use.

2. The land use optimization method for black soil regions according to claim 1, characterized in that, The steps for calculating the first objective weight of each of the aforementioned economic benefit indicators include: The economic benefit indicators are standardized to obtain multiple dimensionless economic indicator values. Calculate the first weight value of any of the dimensionless economic indicators mentioned above; Based on the first weight value, a first information entropy value is obtained, and based on the first information entropy value, a first difference coefficient is calculated; Process the first difference coefficient to obtain the first objective weight of the economic benefit indicator.

3. The land use optimization method for black soil regions according to claim 2, characterized in that, The first comprehensive weight is obtained based on the following formula: in, The weighted fusion coefficient; As the first overall weight; As the first subjective weight; It is the first objective weight.

4. The land use optimization method for black soil areas according to claim 2, characterized in that, The first subjective weight is obtained by processing each of the economic benefit indicators using the analytic hierarchy process or expert scoring method.

5. The land use optimization method for black soil regions according to claim 1, characterized in that, The steps for calculating the second objective weights of each of the aforementioned ecological benefit indicators include: The ecological benefit indicators described above are standardized to obtain multiple dimensionless ecological indicator values. Calculate the second weighting value of any of the dimensionless ecological index values; Based on the second weight value, a second information entropy value is obtained, and based on the second information entropy value, a second difference coefficient is calculated; The second difference coefficient is processed to obtain the second objective weight.

6. The land use optimization method for black soil regions according to claim 1, characterized in that, The steps for solving the biobjective optimization model to obtain the non-dominated solution set include: An adaptive non-dominated sorting genetic algorithm is used to solve the bi-objective optimization model to obtain the Pareto optimal solution set; wherein, the current crossover probability and the current mutation probability of the adaptive non-dominated sorting genetic algorithm are both obtained based on the current iteration generation and the preset maximum iteration generation.

7. The land use optimization method for black soil regions according to claim 1, characterized in that, The step of constructing a weighted normalization matrix for any solution in the non-dominated solution set based on the first comprehensive weight and the second comprehensive weight includes: The comprehensive economic benefits and comprehensive ecological benefits corresponding to the solutions in the non-dominated solution set are normalized to obtain the current dimensionless economic indicators and current dimensionless ecological indicators; wherein, the comprehensive economic benefits are obtained based on the first comprehensive weight and the solution; the comprehensive ecological benefits are obtained based on the second comprehensive weight and the solution; Based on the current dimensionless ecological indicators and the current dimensionless economic indicators, the weighted standardized matrix is ​​obtained.

8. A land use optimization device for black soil regions, characterized in that, include: The acquisition module is used to acquire soil big data, crop yield data, management configuration parameters, and meteorological big data for the target black soil region. The indicator calculation module is used to calculate multiple economic benefit indicators and multiple ecological benefit indicators based on the soil big data, the crop yield data, the management configuration parameters, and the meteorological big data. The first weight calculation module is used to calculate the first objective weight and the first subjective weight of each of the economic benefit indicators, and to calculate the second objective weight and the second subjective weight of each of the ecological benefit indicators. The second weight calculation module is used to obtain the first comprehensive weight of each economic benefit indicator based on the first objective weight and the first subjective weight of each economic benefit indicator, and to obtain the second comprehensive weight of each ecological benefit indicator based on the second objective weight and the second subjective weight of each ecological benefit indicator. The model building module is used to obtain soil quality parameters based on the comprehensive weights of the ecological benefit indicators, and to construct a dual-objective optimization model with the goals of maximizing crop yield and maximizing soil quality parameters. The solution module is used to solve the bi-objective optimization model and obtain the non-dominated solution set; The first evaluation module is used to construct an ideal standardized matrix and a negative ideal standardized matrix, and to construct a weighted standardized matrix for any solution in the non-dominated solution set based on the first comprehensive weight and the second comprehensive weight. The second evaluation module is used to select and output the target solution in the non-dominated solution set based on the first distance metric between the weighted standardized matrix and the ideal standardized matrix, and the second distance metric between the weighted standardized matrix and the negative ideal standardized matrix; wherein the target solution is used to optimize land use.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images