Regional planting and breeding combination optimization method and system based on multi-objective optimization

Abstract

The invention discloses a regional planting and breeding combination optimization method and system based on multi-objective optimization, and relates to the technical field of agriculture, and the method comprises the steps: calculating an average effect value of each target index based on an average value of each target index in each experimental group and a control group; calculating an average effect value of the economic profit based on the economic profit of each experimental group; fitting the relationship between the average effect value of each target index and the economic profit and the proportion of the organic fertilizer replacing the chemical fertilizer to obtain an effect value target function corresponding to each target index and the economic profit; determining a comprehensive objective function, obtaining an optimal organic fertilizer replacement chemical fertilizer proportion by adopting a non-dominated sorting genetic algorithm, and determining a target area type; calculating a suitability index based on the soil bearing capacity, the transportation cost and the environmental sensitivity; when the suitability index is larger than a threshold value, a new farm is arranged in the target area, and regional planting and breeding combination is achieved. According to the application, the matching problem of returning the livestock and poultry manure and the livestock and poultry manure to the field in the region is solved.

Description

Technical Field

[0001] The present application relates to the field of agricultural technology, and in particular to a method and system for regional crop-livestock integration optimization based on multi-objective optimization. Background Art

[0002] At present, the optimization of regional integrated planting and breeding technologies can provide a scientific basis for actions such as reducing the use of chemical fertilizers, resource utilization of livestock and poultry breeding waste, and control of non-point source pollution. It is also the key to the development of regional green agriculture.

[0003] Currently, the implementation of organic fertilizer substitution technology is primarily focused on fruit, vegetable, and tea production, where chemical fertilizer application rates are excessive. However, there are regional differences in the amount of livestock and poultry waste and the carrying capacity of livestock and poultry manure for fruit, vegetable, and tea production. Furthermore, fruit, vegetable, and tea production have limited capacity to absorb organic fertilizer. Current technology implementation fails to fully consider the large potential for livestock and poultry waste absorption by grain crops and cash crops, which have a large distribution area. This is detrimental to the effective implementation of regional organic fertilizer substitution technology, and it also fails to effectively achieve the multi-objective coordinated regulation of agronomic, environmental, economic, and soil health benefits after organic fertilizer substitution. Furthermore, the current "Technical Guidelines for Calculating the Carrying Capacity of Livestock and Poultry Manure Land" only uses nitrogen and phosphorus balance as a constraint, and does not coordinate multi-dimensional objectives such as yield stability, economic feasibility, environmental pollution, and soil health. Spatial adaptability is insufficient, and a precise matching mechanism for manure absorption and crop types has not been established.

[0004] Therefore, it is necessary to provide a regional integrated planting and breeding optimization method based on multi-objective optimization to solve the above problems. Summary of the Invention

[0005] The purpose of this application is to provide a regional farming and breeding integration optimization method and system based on multi-objective optimization, which solves the matching problem of regional livestock and poultry manure and livestock and poultry manure returned to the fields.

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

[0007] In a first aspect, the present application provides a method for optimizing regional planting and breeding integration based on multi-objective optimization, comprising:

[0008] Obtain statistical values of target indicators in a control group, the ratio of organic fertilizer to chemical fertilizer in multiple experimental groups, and statistical values of target indicators in multiple experimental groups; the target indicators include: crop yield, environmental benefits, and soil health; the statistical values include: mean, standard deviation, and number of replicates; wherein, the control group's area uses only chemical fertilizers as fertilizers, and the experimental groups' areas use chemical fertilizers and / or organic fertilizers with different ratios of organic fertilizer to chemical fertilizers as fertilizers, and the target indicators are the indicators affected by the replacement of chemical fertilizers with organic fertilizers;

[0009] Based on the statistical values of each target indicator in the area where each experimental group is located and the statistical values of each target indicator in the area where the control group is located, the average effect value of each target indicator in each experimental group is calculated;

[0010] Determine the economic profit of the region where each experimental group is located, and calculate the average effect value of economic profit under each experimental group based on the economic profit of the region where each experimental group is located;

[0011] Based on the average effect value of each target indicator in all experimental groups and the proportion of organic fertilizer replacing chemical fertilizer in all experimental groups, the effect value objective function between each target indicator and the proportion of organic fertilizer replacing chemical fertilizer was obtained;

[0012] Based on the average effect value of economic profit in all experimental groups and the proportion of organic fertilizer replacing chemical fertilizer in all experimental groups, the effect value objective function between economic profit and the proportion of organic fertilizer replacing chemical fertilizer was obtained;

[0013] Adopting the analytic hierarchy process, based on each of the effect value objective functions, a comprehensive objective function is determined;

[0014] A non-dominated sorting genetic algorithm is used to optimize and solve the comprehensive objective function to obtain the optimal ratio of organic fertilizer to chemical fertilizer;

[0015] Based on the optimal ratio of organic fertilizer to chemical fertilizer and the current breeding volume, determining the regional type to which the target area belongs; the regional type is an overloaded area, a balanced area, or a potential area;

[0016] Calculate the suitability index of the target area based on the soil carrying capacity score, transportation cost score, and environmental sensitivity score of the target area;

[0017] When the suitability index of the target area is greater than the threshold, new farms will be arranged in the target area to achieve regional integration of planting and breeding.

[0018] In one embodiment, the average effect size of each target indicator in each experimental group is calculated based on the statistical value of each target indicator in the region where each experimental group is located and the statistical value of each target indicator in the region where the control group is located, specifically including:

[0019] Calculate the effect size of each target indicator in each experimental group based on the average value of each target indicator in the area where each experimental group is located and the average value of each target indicator in the area where the control group is located;

[0020] Calculate the variance of the effect size of each target indicator in each experimental group based on the standard deviation and number of repetitions of each target indicator in the area where each experimental group is located, as well as the standard deviation and number of repetitions of each target indicator in the area where the control group is located.

[0021] Based on the effect values of all target indicators in each experimental group and the variance of the corresponding effect values, the average effect value of each target indicator in each experimental group is calculated.

[0022] In one embodiment, determining the economic profit of the region where each experimental group is located specifically includes:

[0023] Determine the average yield of each type of crop in the region where each experimental group is located based on the national average yield and yield change rate of each type of crop grown in the region where each experimental group is located;

[0024] Based on the average yield of each type of crop and the price of each type of crop grain in the area where each experimental group is located, determine the average income of each type of crop in the area where each experimental group is located;

[0025] The economic profit of each experimental group region is determined based on the average cost of each type of crop in the region and the average income of each type of crop in the region; the average cost of each type of crop in the region includes: seed cost, fertilizer cost, agricultural machinery cost, pesticide cost, labor cost and other indirect costs.

[0026] In one embodiment, the average effect value of economic profit in each experimental group is calculated based on the economic profit of the region where each experimental group is located, specifically including:

[0027] Based on the average economic profit of the region where each experimental group is located and the average economic profit of the region where the control group is located, calculate the effect value of economic profit in each experimental group;

[0028] Based on the effect value of economic profit in each experimental group, the average effect value of economic profit in each experimental group is calculated.

[0029] In one embodiment, a hierarchical analysis method is used to determine a comprehensive objective function based on each of the effect value objective functions, specifically including:

[0030] Adopting the hierarchical analysis method, based on each of the effect value objective functions, determining the weight coefficient corresponding to each effect value objective function;

[0031] The comprehensive objective function is determined based on each effect value objective function and the corresponding weight coefficient.

[0032] In one embodiment, the expression of the comprehensive objective function F is:

[0033]

[0034] in, is the indicator variable corresponding to the i-th effect value objective function; a iis the weight coefficient corresponding to the i-th effect value objective function; f i is the expression of the i-th effect value objective function, and m is the total number of effect value objective functions.

[0035] In one embodiment, based on the optimal ratio of organic fertilizer to chemical fertilizer and the current breeding volume, determining the region type to which the target region belongs specifically includes:

[0036] Determine the theoretical carrying capacity of the target area based on the optimal ratio of organic fertilizer to chemical fertilizer, the nutrient requirements per unit area of each crop / land type, the sown area of each crop / land type, and the nutrient supply per unit pig equivalent; the nutrient requirements per unit area of each crop / land type are determined by the crop yield per unit area and the nutrient requirements per unit yield;

[0037] Determine whether the target area is overloaded based on the current breeding volume and the theoretical carrying capacity of the target area; the current breeding volume is determined by the livestock and poultry inventory and the pig equivalent conversion coefficient;

[0038] Determine the relationship between the theoretical bearing capacity and overload rate of the target area and obtain the judgment result;

[0039] Based on the judgment result, the area type to which the target area belongs is determined.

[0040] In one embodiment, determining the area type to which the target area belongs based on the judgment result specifically includes:

[0041] When the judgment result is that the current breeding volume > theoretical carrying capacity × 0.8, the target area is determined to be an overloaded area;

[0042] When the judgment result is theoretical carrying capacity × 0.8 < current breeding volume < theoretical carrying capacity, the target area is determined to be a balanced area;

[0043] When the judgment result is that the current breeding volume < theoretical carrying capacity × 0.8, the regional type of the target area is determined to be a potential area.

[0044] In one embodiment, the suitability index of the target area is calculated based on the soil bearing capacity score, transportation cost score, and environmental sensitivity score of the target area, specifically including:

[0045] Determine the soil bearing capacity score of the target area based on the remaining capacity ratio of the theoretical bearing capacity of the target area;

[0046] Determine a transportation cost score for the target area based on the distance manure is transported to the target area;

[0047] Determine the environmental sensitivity score of the target area based on the distance between the target area and the ecological red line;

[0048] The analytic hierarchy process was used to determine the weights corresponding to the soil carrying capacity, transportation cost and environmental sensitivity of the target area.

[0049] The suitability index of the target area is determined based on the soil carrying capacity score, transportation cost score, and environmental sensitivity score of the target area and their corresponding weights.

[0050] In a second aspect, the present application provides a regional planting and breeding integration optimization system based on multi-objective optimization, wherein the regional planting and breeding integration optimization system based on multi-objective optimization is used to implement the regional planting and breeding integration optimization method based on multi-objective optimization, and the regional planting and breeding integration optimization system based on multi-objective optimization includes:

[0051] a data acquisition unit, configured to acquire statistical values of target indicators in a control group, the ratio of organic fertilizer to chemical fertilizer in multiple experimental groups, and statistical values of target indicators in multiple experimental groups; the target indicators include: crop yield, environmental benefits, and soil health; the statistical values include: mean, standard deviation, and number of replicates; wherein, the control group's area uses only chemical fertilizers as fertilizers, and the experimental groups' areas use chemical fertilizers and / or organic fertilizers with different ratios of organic fertilizer to chemical fertilizers as fertilizers, and the target indicators are indicators affected by the replacement of chemical fertilizers with organic fertilizers;

[0052] A first average effect value determination unit is used to calculate the average effect value of each target indicator in each experimental group based on the statistical value of each target indicator in the area where each experimental group is located and the statistical value of each target indicator in the area where the control group is located;

[0053] The second average effect value determination unit is used to determine the economic profit of the region where each experimental group is located, and calculate the average effect value of the economic profit under each experimental group based on the economic profit of the region where each experimental group is located;

[0054] The first function fitting unit is used to fit the average effect value of each target indicator in all experimental groups and the ratio of organic fertilizer replacing chemical fertilizer in all experimental groups, so as to obtain the effect value target function between each target indicator and the ratio of organic fertilizer replacing chemical fertilizer;

[0055] The second function fitting unit is used to fit the average effect value of economic profit in all experimental groups and the ratio of organic fertilizer replacing chemical fertilizer in all experimental groups to obtain the effect value objective function between economic profit and the ratio of organic fertilizer replacing chemical fertilizer;

[0056] A comprehensive objective function determination unit, configured to determine a comprehensive objective function based on each of the effect value objective functions by adopting a hierarchical analysis method;

[0057] An optimal organic fertilizer-to-chemical fertilizer ratio determination unit is configured to optimize and solve the comprehensive objective function using a non-dominated sorting genetic algorithm to obtain an optimal organic fertilizer-to-chemical fertilizer ratio;

[0058] A region type determination unit is configured to determine the region type to which the target region belongs based on the optimal ratio of organic fertilizer to chemical fertilizer and the current breeding volume; the region type is an overloaded region, a balanced region, or a potential region;

[0059] a suitability index determination unit, configured to calculate a suitability index of a target area based on a soil bearing capacity score, a transportation cost score, and an environmental sensitivity score of the target area;

[0060] The farm location determination unit is used to layout new farms in the target area when the suitability index of the target area is greater than the threshold, so as to achieve regional integration of planting and breeding.

[0061] According to the specific embodiments provided in this application, this application has the following technical effects:

[0062] This application discloses a regional crop-livestock integration optimization method and system based on multi-objective optimization. This application also includes major food and cash crops in the scope of organic fertilizer application, uses a comprehensive objective function to achieve multi-objective optimization of regional agronomic, economic, environmental benefits and soil health, and proposes the optimal ratio of organic fertilizer to chemical fertilizer for different crops, which is conducive to solving the matching problem of regional livestock and poultry manure and livestock and poultry manure returned to the fields, and also provides data support for the specific and effective regulatory measures in the region's crop-livestock integration technology, and also plays a positive role in the prevention and control of regional agricultural non-point source pollution. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0064] Figure 1 A schematic flow chart of a regional crop-livestock integration optimization method based on multi-objective optimization provided in one embodiment of the present application. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0066] This application addresses the problem of mismatch between regional livestock and poultry breeding volume and land carrying capacity, and proposes a method for synergistically regulating regional planting and breeding technology from the perspectives of agronomic benefits, environmental benefits, economic benefits and soil health, based on the optimal ratio of organic fertilizer to chemical fertilizer based on the fertilization situation of major regional crops and the sown area, livestock and poultry breeding volume and major crops.

[0067] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0068] In an exemplary embodiment, Figure 1 As shown, a method for regional integrated planting and breeding optimization based on multi-objective optimization is provided, which includes the following steps.

[0069] Step S1, obtaining statistical values of target indicators in the control group, the ratio of organic fertilizer replacing chemical fertilizer in multiple experimental groups, and statistical values of target indicators in multiple experimental groups; the target indicators include: crop yield, environmental benefits (ammonia volatilization, N2O emissions, runoff and leaching nitrogen loss, CH4 emissions, etc.) and soil health (soil pH, soil organic matter, microbial biomass carbon, microbial biomass nitrogen, microbial diversity, microbial richness, heavy metals and soil nutrients, etc.); statistical values include: mean, standard deviation and number of replicates; wherein, in the area where the control group is located, all chemical fertilizers are used as fertilizers, and in the area where each experimental group is located, chemical fertilizers and / or organic fertilizers with different ratios of organic fertilizer replacing chemical fertilizers are used as fertilizers, and the target indicators are indicators affected after organic fertilizers replace chemical fertilizers; the areas where the experimental group and the control group are located only differ in fertilizers and locations.

[0070] Specifically, we searched for keywords such as "organic fertilizer," "fertilizer," "yield," "crops (including corn, rice, wheat, rapeseed, cotton, potatoes, etc.)," "nitrogen," "N2O emissions," "ammonia volatilization," "nitrogen runoff," or "nitrogen leaching" in databases such as Web of Science and CNKI to obtain data related to the impact of replacing chemical fertilizers with organic fertilizers on target indicators and obtain the above-mentioned multiple sets of statistical values.

[0071] The statistical values of the above target indicators in the control group and the statistical values of the target indicators in multiple experimental groups can be obtained as follows:

[0072] 1. Search strategy design

[0073] Chinese database (CNKI) using advanced search mode:

[0074] Search field combination: Topic = ("organic fertilizer replacement" OR "chemical fertilizer reduction") AND ("yield" OR "economic benefit" OR "soil health" OR "environmental pollution" OR "greenhouse gas").

[0075] Time range: 2010-2025 (priority given to literature published in the past five years).

[0076] Check "Core Journals" and "CSSCI Source Journals".

[0077] English database (Web of Science) using subject search and citation tracking:

[0078] Search formula: TS = ("organic fertilizer substitution" OR "chemical fertilizer reduction") AND ("yield" OR "economic benefit" OR "soil health" OR "environmental pollution" OR "GHG emissions"). Here, "organic fertilizer substitution" refers to organic fertilizer substitution; "chemical fertilizer reduction" refers to chemical fertilizer reduction; "yield" refers to yield; "economic benefit" refers to economic benefit; "soil health" refers to soil health; "environmental pollution" refers to environmental pollution; and "GHG emission" refers to greenhouse gas emissions.

[0079] Screening conditions: Document type: Article; Subject area: Agriculture, Environmental Science.

[0080] 2. Literature screening criteria

[0081] Initial screening criteria:

[0082] 1) The article contains a clear replacement ratio or can be obtained by calculation (e.g., 30%, 50%, etc.).

[0083] 2) Include at least one target indicator (such as yield, greenhouse gases or soil health, etc.).

[0084] 3) The experimental data are complete (mean ± standard deviation or raw data must be provided).

[0085] 4) The study should include a control group (purified fertilizer) and a treatment group (organic fertilizer replacement), with ≥2 replicates for each group.

[0086] 5) These studies must clearly specify the use of animal manure and synthetic fertilizer nutrients.

[0087] Fine screening standards:

[0088] 1) Field test data (not simulated data) should be given priority.

[0089] 2) Journal impact factor ≥ 3.0 (WoS) or selected into CSCD / Peking University core journals.

[0090] 3) Eliminate duplicate data (multiple observations from the same study).

[0091] 3. Integrate the data obtained after literature screening and calculate the effect value based on the integrated data.

[0092] The data from the literature screening were integrated into an Excel spreadsheet for further analysis, resulting in the integrated data table shown in Table 1. Essential data included the proportion of organic fertilizer replacing chemical fertilizer (corresponding to the replacement ratio in Table 1), the statistical values of the target indicator in the control group, and the statistical values of the target indicator in multiple experimental groups. Additionally, the table included data on crop type and organic fertilizer type. Graphical data extraction was performed using GetData software (version 2.26) to digitize the chart data.

[0093] Table 1 Integrated data table

[0094]

[0095]

[0096] Step S2, calculating the average effect value of each target indicator in each experimental group based on the statistical value of each target indicator in the area where each experimental group is located and the statistical value of each target indicator in the area where the control group is located.

[0097] As an optional implementation, step S2 specifically includes:

[0098] Step S21 , calculating the effect value of each target indicator in each experimental group based on the average value of each target indicator in the area where each experimental group is located and the average value of each target indicator in the area where the control group is located.

[0099] Specifically, the effect values of each target indicator in each experimental group are used to compare the changes in benefits under different proportions of organic fertilizer replacing chemical fertilizer and the application of chemical fertilizer alone (that is, the increase in benefits of the experimental group compared to the application of chemical fertilizer alone, a negative effect value indicates a decrease in benefits, and a positive effect value indicates an increase in benefits). The response ratio is the ratio of the target indicators of the experimental group to the control group, and the effect value is the natural logarithm of the response ratio. The effect value lnRR of any target indicator in each experimental group is:

[0100]

[0101] Among them, Xe and X c They represent the average value of any target indicator X in the area where the experimental groups are located and the average value in the area where the control group is located; RR represents the response ratio.

[0102] Step S22, calculating the variance of the effect value of each target indicator in each experimental group based on the standard deviation and number of repetitions of each target indicator in the area where each experimental group is located and the standard deviation and number of repetitions of each target indicator in the area where the control group is located.

[0103]

[0104] Among them, v is the variance of the effect value of any target indicator in each experimental group, S c and S e represents the standard deviation of any target indicator in the region where each experimental group is located and the standard deviation of any target indicator in the region where the control group is located; n c and n e They represent the number of repetitions of any target indicator in the area where each experimental group is located and the number of repetitions of any target indicator in the area where the control group is located.

[0105] Step S23 , calculating the average effect value of each target indicator in each experimental group based on each effect value (single effect value) of all target indicators in each experimental group and the variance of the corresponding effect value (single effect value).

[0106]

[0107] in, is the weighted average effect size, g is the number of comparisons in the experimental group (i.e., the number of individual effect sizes in the experimental group), and w k is the weighting factor of the kth experimental group in the experimental group.

[0108]

[0109] Among them, v k is the variance of k in the experimental group.

[0110] The metafor package in R language was used to calculate the individual effect value and average effect value of each target indicator in each experimental group (i.e., different groups with different ratios of organic fertilizer replacing chemical fertilizer).

[0111] Step S3: Determine the economic profit of the region where each experimental group is located, and calculate the average effect value of the economic profit in each experimental group based on the economic profit of the region where each experimental group is located.

[0112] As an optional implementation, in step S3, determining the economic profit of the region where each experimental group is located specifically includes:

[0113] Step S31: Determine the average yield of each type of crop in the region where each experimental group is located based on the national average yield and yield change rate of each type of crop grown in the region where each experimental group is located. The average yield of any type of crop in the region where each experimental group is located is:

[0114] Y i,av =Y i ×(1+y i ) (5)

[0115] Among them, Y i,av is the average yield of crop type i under different ratios of organic fertilizer replacing chemical fertilizer (kg ha -1 );Y i is the national average yield of crop type i (kg ha -1 );y i is the yield change rate of the i-th type of crop under different proportions of organic fertilizer replacing chemical fertilizer.

[0116] Step S32: Based on the average yield of each type of crop and the price of each type of crop grain in the area where each experimental group is located, determine the average income of each type of crop in the area where each experimental group is located. The average income of each type of crop in the area where each experimental group is located is as follows:

[0117]

[0118] Among them, Income represents the average income of various crops (CNY ha -1 );P i is the price of the i-th type of crop grains.

[0119] Step S33: Determine the economic profit of each experimental group region based on the average cost of each type of crop and the average income of each type of crop in each experimental group region. The average cost of each type of crop in each experimental group region includes seed costs, fertilizer costs, agricultural machinery costs, pesticide costs, labor costs, and other indirect costs. These cost data are obtained from statistical yearbooks and field survey data.

[0120] The economic profit EP of the region where each experimental group is located is as follows:

[0121] EP=Income-Cost (7)

[0122] Among them, EP is the economic profit of crops (i.e. the economic profit of the region where each experimental group is located) (CNY ha -1 ); Cost is the average cost of various crops in the region where each experimental group is located, and its expression is as follows:

[0123] Cost=S+F+M+P+L+I (8)

[0124] Among them, S, F, M, P, L and I represent seed cost, fertilizer cost, agricultural machinery cost, pesticide cost, labor cost and other indirect costs respectively (CNY ha -1 ).

[0125] As an optional implementation, in step S3, based on the economic profit of the region where each experimental group is located, the average effect value of the economic profit in each experimental group is calculated, specifically including:

[0126] Step S34, calculating the effect value of economic profit in each experimental group based on the average value of economic profit in the region where each experimental group is located and the average value of economic profit in the region where the control group is located.

[0127] The effect value of economic profit in each experimental group is calculated according to formula (3), where Xe and Xc represent the average economic profit of the region where each experimental group is located and the average economic profit of the region where the control group is located, respectively.

[0128] Step S35 , calculating the average effect value of economic profit in each experimental group based on the effect value of economic profit in each experimental group.

[0129] Step S4, fitting the average effect value of each target indicator in all experimental groups and the ratio of organic fertilizer replacing chemical fertilizer in all experimental groups, to obtain the effect value objective function between each target indicator and the ratio of organic fertilizer replacing chemical fertilizer.

[0130] Step S5, fitting the average effect value of economic profit in all experimental groups and the ratio of organic fertilizer replacing chemical fertilizer in all experimental groups to obtain the effect value objective function between economic profit and the ratio of organic fertilizer replacing chemical fertilizer.

[0131] Specifically, the average effect value of each target indicator and the average effect value of economic profit under all experimental groups at different organic fertilizer replacement ratio gradients were calculated and fitted with the relationship between them and the organic fertilizer replacement ratio to establish the corresponding effect value objective function. The gradient range must cover the full replacement interval (0%-100%) and contain at least 5 gradient points to ensure continuous representation from pure fertilizer mode to complete organic substitution; the gradient interval should preferably adopt a proportional increment design.

[0132] When fitting, use Excel to make a scatter plot and add trend lines and corresponding formulas. Select R 2 The curve with the highest R square and the best fit is used as the effect value objective function of the current target indicator.

[0133] Step S6: using the analytic hierarchy process to determine the comprehensive objective function based on each of the effect value objective functions.

[0134] As an optional implementation, step S6 specifically includes:

[0135] Step S61 : using the analytic hierarchy process to determine the weight coefficient corresponding to each effect value objective function based on each effect value objective function.

[0136] Specifically, 1) build a hierarchical structure:

[0137] Target layer: maximize comprehensive benefits.

[0138] Criteria layers: yield, economics, soil health, nitrogen pollution, greenhouse gas emissions.

[0139] Solution layer: replacement ratio (0% to 100%).

[0140] 2) Judgment matrix generation:

[0141] Expert Scoring: Invite 5-10 experts in fields such as agronomy, environment, and economics to compare the importance of target indicators on a scale of 1-9 to generate a judgment matrix. This section primarily determines the relative importance of target indicators at different criterion levels to the target level indicators (i.e., the weight coefficients corresponding to each effect value objective function). The main criteria are shown in Table 2:

[0142] Table 2 Main standards

[0143] Yield 9 8 7 6 5 4 3 2 1 2 3 4 5 6 7 8 9 Economic benefits Yield 9 8 7 6 5 4 3 2 1 2 3 4 5 6 7 8 9 Soil health Yield 9 8 7 6 5 4 3 2 1 2 3 4 5 6 7 8 9 Nitrogen pollution Yield 9 8 7 6 5 4 3 2 1 2 3 4 5 6 7 8 9 greenhouse gas emissions Economic benefits 9 8 7 6 5 4 3 2 1 2 3 4 5 6 7 8 9 Soil health Economic benefits 9 8 7 6 5 4 3 2 1 2 3 4 5 6 7 8 9 Nitrogen pollution Economic benefits 9 8 7 6 5 4 3 2 1 2 3 4 5 6 7 8 9 greenhouse gas emissions Soil health 9 8 7 6 5 4 3 2 1 2 3 4 5 6 7 8 9 Nitrogen pollution Soil health 9 8 7 6 5 4 3 2 1 2 3 4 5 6 7 8 9 greenhouse gas emissions Nitrogen pollution 9 8 7 6 5 4 3 2 1 2 3 4 5 6 7 8 9 greenhouse gas emissions

[0144] Among them, the judgment matrix is shown in Table 3.

[0145] Table 3 Schematic diagram of judgment matrix

[0146]

[0147]

[0148] As shown in Table 3, the values of the judgment matrix indicate that yield is five times more important than greenhouse gas emissions, six times more important than nitrogen pollution, and eight times more important than soil health.

[0149] 3) Use Yaahp software to automatically calculate the weight coefficient:

[0150] Input the judgment matrix, select the eigenvalue method to calculate the weight vector, and check the consistency ratio (CR) (the condition is CR < 0.1).

[0151] Step S62: determining the comprehensive objective function based on each effect value objective function and the corresponding weight coefficient.

[0152] As an optional implementation, in step S62, the expression of the comprehensive objective function F is:

[0153]

[0154] in, is the indicator variable corresponding to the j-th effect value objective function, -1 means that the current effect value objective function needs to be minimized. 1 means the current effect value objective function needs to be maximized; a j is the weight coefficient (also called importance coefficient) corresponding to the j-th effect value objective function; f j is the expression of the j-th effect value objective function.

[0155] Furthermore, set the constraints:

[0156] A multi-dimensional benefit evaluation system is established based on key indicators such as crop yield and economic profit in the initial state (when the ratio of organic fertilizer replacing chemical fertilizer x=0) as the baseline.

[0157] For example, when the original yield is 500 kg / mu, the yield corresponding to any proportion x of organic fertilizer replacing chemical fertilizer must satisfy y(x) ≥ 500 kg / mu. If the measured data shows that the yield falls below the baseline value for the first time when x = 75%, the upper limit of the proportion of organic fertilizer replacing chemical fertilizer is immediately adjusted to 75%. In other words, the constraint condition is: in principle, when organic fertilizer replaces chemical fertilizer at a proportion x to replace part of the chemical fertilizer, the crop yield, economic profit and other indicators cannot be lower than the crop yield and economic profit when using chemical fertilizer alone.

[0158] Step S7: using a non-dominated sorting genetic algorithm to optimize and solve the comprehensive objective function to obtain the optimal ratio of organic fertilizer to chemical fertilizer.

[0159] Specifically, the NSGA-II Pareto front is output and the proportion with the highest comprehensive score is selected.

[0160] The non-dominated sorting genetic algorithm (NSGA-II) was used to optimize the comprehensive objective function to find the optimal ratio of organic fertilizer to chemical fertilizer. Specifically, within a given range of organic fertilizer to chemical fertilizer ratios, the ratios with lower fitness (comprehensive objective function values) were gradually eliminated, while those with higher fitness were retained for the next generation. After N generations of selection, the ratio with the highest fitness was ultimately selected, thus achieving the optimization goal.

[0161] Step S8, based on the optimal ratio of organic fertilizer to chemical fertilizer and the current breeding volume, determine the regional type to which the target area belongs; the regional type is an overloaded area, a balanced area or a potential area.

[0162] As an optional implementation, step S8 specifically includes:

[0163] Step S81, determining the theoretical carrying capacity of the target area based on the optimal ratio of organic fertilizer to chemical fertilizer, the nutrient demand per unit area of each crop / land type, the sown area of each crop / land type, and the nutrient supply per unit pig equivalent; wherein the nutrient demand per unit area of the crop / land type is determined by the crop yield per unit area and the nutrient demand per unit yield.

[0164] The calculation formula for the theoretical bearing capacity of the target area is as follows:

[0165]

[0166] Among them, A i is the sown area of the i-th type of crops (hectares), N i is the nutrient requirement per unit area of the i-th crop / land type (kg / year / hectare), N i = crop yield per unit area × nutrient requirement per unit yield (e.g. wheat requires 3.0 kg of nitrogen per 100 kg of yield); x 优 The ratio of manure to fertilizer (i.e. the optimal ratio of organic fertilizer to chemical fertilizer); the nutrient supply per unit pig is: nitrogen 7.0 kg / head·year, phosphorus 1.2 kg / head·year.

[0167] Step S82: Determine the relationship between the current breeding volume and the theoretical carrying capacity of the target area to obtain a determination result; the current breeding volume is determined by the livestock and poultry inventory and the pig equivalent conversion coefficient.

[0168] The calculation formula for the current breeding volume is as follows:

[0169] Current breeding volume (pig equivalent) = ∑ (livestock and poultry inventory × pig equivalent conversion coefficient) (11)

[0170] Among them, the pig equivalent conversion coefficient is: 100 pigs = 15 dairy cows / 30 beef cattle / 250 sheep / 2,500 poultry.

[0171] Step S83: Determine the area type to which the target area belongs based on the judgment result.

[0172] As an optional implementation, step S84 specifically includes:

[0173] Step S841: When the judgment result is that the current breeding volume is greater than the theoretical carrying capacity × 0.8, the area type of the target area is determined to be an overloaded area.

[0174] Step S842: When the judgment result is theoretical carrying capacity × 0.8 < current breeding volume < theoretical carrying capacity, the area type to which the target area belongs is determined to be a balance area.

[0175] In step S843, when the judgment result is that the current breeding volume is less than the theoretical carrying capacity × 0.8, the target area is determined to be a potential area. The regional classification standard table is shown in Table 4.

[0176] Table 4 Regional classification standards

[0177] Region Type Conditions (current breeding volume) Management measures Overload zone >Theoretical bearing capacity×0.8 Prohibition of new additions, mandatory treatment facilities Balance Zone Theoretical bearing capacity × 0.8 ~ theoretical bearing capacity Limit new additions and optimize the planting and breeding cycle potential area <Theoretical bearing capacity × 0.8 Allowing new additions and layout of ecological farms

[0178] Based on the division of overload areas, balance areas and potential areas, hierarchical dynamic regulation is implemented to ensure that breeding resources match the ecological carrying capacity.

[0179] 1) Overload area:

[0180] Inventory optimization:

[0181] Mandatory emission reduction: prohibiting the construction / expansion of farms, implementing an "equal replacement" mechanism for existing overloaded farms (one farm must be closed before a new one can be built), and giving priority to eliminating small and medium-sized individual farms that do not meet the standards for manure and sewage treatment.

[0182] Fully quantitative treatment of manure and sewage: supporting construction of regional centralized anaerobic fermentation tanks (volume ≥ 5000m 3 ) and organic fertilizer production lines to ensure that the harmless treatment rate of manure and sewage is ≥95%, and the treatment products are allocated across regions to potential areas for consumption.

[0183] Precise reduction algorithm: Based on the overload rate, the farms are subject to step-by-step production restrictions according to the overload ratio (e.g. overload rate 120% → production reduction 20%).

[0184] 2) Balance zone:

[0185] Structural upgrades:

[0186] Integration of farming and breeding: It is mandatory for farms to sign manure disposal agreements with surrounding planting entities, configure a farming and breeding cycle unit based on "1 10,000-head pig farm + 500 mu of farmland", and the on-site manure return rate must be ≥80%.

[0187] Substitution ratio linkage: Based on the optimal ratio of organic fertilizer to chemical fertilizer, the breeding density is dynamically adjusted: the allowed breeding volume = theoretical carrying capacity.

[0188] Technology upgrade subsidies: Farms that use emission reduction technologies such as low-protein feed and fermentation bed farming will be given a 30% equipment purchase subsidy.

[0189] 3) Potential Area:

[0190] Incremental boot:

[0191] Access to ecological farms: Newly built farms must meet the "three distances and one supporting" requirements (1km away from residential areas, 2km away from water sources, within the ecological red line, and equipped with a manure return network), and the number of live pigs per unit land must be ≤10 heads / mu.

[0192] Cross-regional coordination mechanism: establish a manure trading platform between overloaded areas and potential areas, price the manure according to the nitrogen and phosphorus content (such as nitrogen 7 yuan / kg), and the overloaded areas pay ecological compensation to the potential areas.

[0193] Flexible reserve for carrying capacity: The upper limit of the allowed breeding volume is 90% of the theoretical carrying capacity, and 10% buffer capacity is reserved to deal with sudden environmental risks.

[0194] Step S9: Calculate the suitability index of the target area based on the soil bearing capacity score, transportation cost score, and environmental sensitivity score of the target area.

[0195] As an optional implementation, step S9 specifically includes:

[0196] Step S91: determining the soil bearing capacity of the target area based on the remaining capacity ratio of the theoretical bearing capacity of the target area.

[0197] Step S92: determining the transportation cost of the target area based on the manure transportation distance of the target area.

[0198] Step S93: determining the environmental sensitivity of the target area based on the distance between the target area and the ecological red line.

[0199] Step S94: using the analytic hierarchy process to determine the weights corresponding to the soil bearing capacity, transportation cost, and environmental sensitivity of the target area.

[0200] Step S95: determining the suitability index of the target area based on the soil bearing capacity, transportation cost, and environmental sensitivity of the target area and corresponding weights.

[0201] As an optional implementation, step S95 specifically includes:

[0202] Step S951: Determine the soil bearing capacity score of the target area based on the remaining capacity ratio of the theoretical bearing capacity of the target area.

[0203] Soil bearing capacity score: The remaining capacity of the theoretical bearing capacity accounts for 10 points (10 points for ≥20%, and 2 points will be deducted for every 5% decrease) to obtain the soil bearing capacity of the target area.

[0204] Step S952: Determine the transportation cost score of the target area based on the manure transportation distance of the target area.

[0205] Transportation cost score: The transportation distance of manure (≤5km is 10 points, and 1 point is deducted for each additional km) is used to obtain the transportation cost of the target area.

[0206] Step S953: Determine the environmental sensitivity score of the target area based on the distance between the target area and the ecological red line.

[0207] Environmental sensitivity score: The environmental sensitivity score of the target area is obtained by calculating the distance from the ecological red line (10 points for distances ≥ 2 km and 3 points for every 0.5 km reduction).

[0208] Step S954: using the analytic hierarchy process to determine the weights corresponding to the soil bearing capacity, transportation cost, and environmental sensitivity of the target area.

[0209] Step S955: determining the suitability index of the target area based on the soil bearing capacity score, transportation cost score, and environmental sensitivity score of the target area and the corresponding weights.

[0210] Specifically, in order to quantify the priority of farm site selection, a multidimensional suitability evaluation model is constructed (i.e., the suitability index of the target area is calculated). The expression of the suitability index of the target area is:

[0211] Suitability index = w1 × soil carrying capacity score + w2 × transportation cost score + w3 × environmental sensitivity score (12)

[0213] Among them, w1=0.5, w2=0.3, w3=0.2.

[0214] Step S10: When the suitability index of the target area is greater than a threshold, a new farm is arranged in the target area to achieve regional integration of planting and breeding.

[0215] Specifically, based on the suitability index of the target area, a heat map of regional aquaculture land is generated, and new farms are preferentially arranged in areas with a suitability index ≥8 points.

[0216] This application constructs a "multi-objective synergy" regional crop-livestock integration optimization method, breaking through the single environmental constraint and incorporating agronomic benefits (yield), economic benefits (cost-benefit), environmental benefits (ammonia volatilization, N2O emissions, runoff and leaching nitrogen losses, etc.), and soil health (soil organic matter, pH, etc.) into a unified decision-making framework to address the implementation difficulties caused by the fragmentation of objectives.

[0217] A dynamic weight allocation mechanism was established. Based on the key objectives of phased regional development strategies (such as ecological restoration and industrial upgrading), a multi-objective optimization function (i.e., a comprehensive objective function) was used to adaptively adjust the priority weights of agronomic, environmental, and economic indicators. For example, during the key period of attacking ecologically fragile areas, the weight of nitrogen and phosphorus loss control was increased to 0.45±0.05, and the weight of soil health was set at 0.30±0.03. During the period of increasing agricultural output, the weight of the environment was dynamically lowered to 0.35, while the weight of economic benefits was simultaneously raised to 0.40, achieving dynamic alignment between regional goals and resource allocation.

[0218] Ensure precise spatial matching of planting and breeding: Identify the spatial coupling relationship between high-carrying-capacity crop concentration areas and high-manure and sewage output areas, and adjust the breeding layout to maximize the absorption potential.

[0219] Based on the same inventive concept, the embodiments of the present application also provide a regional planting and breeding integration optimization system based on multi-objective optimization for implementing the aforementioned regional planting and breeding integration optimization method based on multi-objective optimization. The implementation solution provided by this system is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the regional planting and breeding integration optimization system based on multi-objective optimization provided below can be found in the above-mentioned limitations of the regional planting and breeding integration optimization method based on multi-objective optimization, and will not be repeated here.

[0220] In an exemplary embodiment, a regional planting-livestock integration optimization system based on multi-objective optimization is provided, including:

[0221] The data acquisition unit is used to obtain the statistical value of the target indicator in the control group, the ratio of organic fertilizer replacing chemical fertilizer in multiple experimental groups, and the statistical value of the target indicator in multiple experimental groups; the target indicators include: crop yield, environmental benefits and soil health; the statistical values include: mean value, standard deviation and number of replicates; wherein, in the area where the control group is located, all chemical fertilizers are used as fertilizers, and in the area where each experimental group is located, chemical fertilizers and / or organic fertilizers with different ratios of organic fertilizer replacing chemical fertilizers are used as fertilizers, and the target indicators are indicators affected after organic fertilizers replace chemical fertilizers.

[0222] The first average effect value determination unit is used to calculate the average effect value of each target indicator in each experimental group based on the statistical value of each target indicator in the area where each experimental group is located and the statistical value of each target indicator in the area where the control group is located.

[0223] The second average effect value determination unit is used to determine the economic profit of the region where each experimental group is located, and calculate the average effect value of the economic profit under each experimental group based on the economic profit of the region where each experimental group is located.

[0224] The first function fitting unit is used to fit the average effect value of each target indicator in all experimental groups and the ratio of organic fertilizer replacing chemical fertilizer in all experimental groups to obtain the effect value target function between each target indicator and the ratio of organic fertilizer replacing chemical fertilizer.

[0225] The second function fitting unit is used to fit the average effect value of economic profit in all experimental groups and the ratio of organic fertilizer replacing chemical fertilizer in all experimental groups to obtain the effect value objective function between economic profit and the ratio of organic fertilizer replacing chemical fertilizer.

[0226] The comprehensive objective function determination unit is used to determine the comprehensive objective function based on each of the effect value objective functions by adopting the hierarchical analysis method.

[0227] The optimal organic fertilizer replacement fertilizer ratio determination unit is used to optimize and solve the comprehensive objective function using a non-dominated sorting genetic algorithm to obtain the optimal organic fertilizer replacement fertilizer ratio.

[0228] The regional type determination unit is used to determine the regional type to which the target area belongs based on the optimal ratio of organic fertilizer to chemical fertilizer and the current breeding volume; the regional type is an overloaded area, a balanced area or a potential area.

[0229] The suitability index determination unit is used to calculate the suitability index of the target area based on the soil bearing capacity score, transportation cost score and environmental sensitivity score of the target area.

[0230] The farm location determination unit is used to layout new farms in the target area when the suitability index of the target area is greater than the threshold, so as to achieve regional integration of planting and breeding.

[0231] 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, stored data, displayed data, 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 relevant data must comply with relevant regulations.

[0232] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may 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 may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0233] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0234] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, 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.

[0235] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for regional integrated planting and breeding optimization based on multi-objective optimization, characterized in that: The regional planting and breeding integration optimization method based on multi-objective optimization includes: Obtain statistical values of target indicators in a control group, the ratio of organic fertilizer to chemical fertilizer in multiple experimental groups, and statistical values of target indicators in multiple experimental groups; the target indicators include: crop yield, environmental benefits, and soil health; the statistical values include: mean, standard deviation, and number of replicates; wherein, the control group's area uses only chemical fertilizers as fertilizers, and the experimental groups' areas use chemical fertilizers and / or organic fertilizers with different ratios of organic fertilizer to chemical fertilizers as fertilizers, and the target indicators are the indicators affected by the replacement of chemical fertilizers with organic fertilizers; Based on the statistical values of each target indicator in the area where each experimental group is located and the statistical values of each target indicator in the area where the control group is located, the average effect value of each target indicator in each experimental group is calculated; Determine the economic profit of the region where each experimental group is located, and calculate the average effect value of economic profit under each experimental group based on the economic profit of the region where each experimental group is located; Based on the average effect value of each target indicator in all experimental groups and the proportion of organic fertilizer replacing chemical fertilizer in all experimental groups, the effect value objective function between each target indicator and the proportion of organic fertilizer replacing chemical fertilizer was obtained; Based on the average effect value of economic profit in all experimental groups and the proportion of organic fertilizer replacing chemical fertilizer in all experimental groups, the effect value objective function between economic profit and the proportion of organic fertilizer replacing chemical fertilizer was obtained; Adopting the analytic hierarchy process, based on each of the effect value objective functions, a comprehensive objective function is determined; A non-dominated sorting genetic algorithm is used to optimize and solve the comprehensive objective function to obtain the optimal ratio of organic fertilizer to chemical fertilizer; Based on the optimal ratio of organic fertilizer to chemical fertilizer and the current breeding volume, determining the regional type to which the target area belongs; the regional type is an overloaded area, a balanced area, or a potential area; Calculate the suitability index of the target area based on the soil carrying capacity score, transportation cost score, and environmental sensitivity score of the target area; When the suitability index of the target area is greater than the threshold, new farms will be arranged in the target area to achieve regional integration of planting and breeding.

2. The method for regional planting and breeding integration optimization based on multi-objective optimization according to claim 1, characterized in that: Based on the statistical values of each target indicator in the area where each experimental group is located and the statistical values of each target indicator in the area where the control group is located, the average effect value of each target indicator in each experimental group is calculated, including: Calculate the effect size of each target indicator in each experimental group based on the average value of each target indicator in the area where each experimental group is located and the average value of each target indicator in the area where the control group is located; Calculate the variance of the effect size of each target indicator in each experimental group based on the standard deviation and number of repetitions of each target indicator in the area where each experimental group is located, as well as the standard deviation and number of repetitions of each target indicator in the area where the control group is located. Based on the effect values of all target indicators in each experimental group and the variance of the corresponding effect values, the average effect value of each target indicator in each experimental group is calculated.

3. The method for regional planting and breeding integration optimization based on multi-objective optimization according to claim 1, characterized in that: Determine the economic profit of each experimental group's region, including: Determine the average yield of each type of crop in the region where each experimental group is located based on the national average yield and yield change rate of each type of crop grown in the region where each experimental group is located; Based on the average yield of each type of crop and the price of each type of crop grain in the area where each experimental group is located, determine the average income of each type of crop in the area where each experimental group is located; The economic profit of each experimental group region is determined based on the average cost of each type of crop in the region and the average income of each type of crop in the region; the average cost of each type of crop in the region includes: seed cost, fertilizer cost, agricultural machinery cost, pesticide cost, labor cost and other indirect costs.

4. The method for regional planting and breeding integration optimization based on multi-objective optimization according to claim 3 is characterized in that: Based on the economic profits of the regions where each experimental group is located, the average effect value of economic profits in each experimental group is calculated, including: Based on the average economic profit of the region where each experimental group is located and the average economic profit of the region where the control group is located, calculate the effect value of economic profit in each experimental group; Based on the effect value of economic profit in each experimental group, the average effect value of economic profit in each experimental group is calculated.

5. The method for regional planting and breeding integration optimization based on multi-objective optimization according to claim 4 is characterized in that: The analytic hierarchy process is used to determine the comprehensive objective function based on the effect value objective functions, which specifically includes: Adopting the hierarchical analysis method, based on each of the effect value objective functions, determining the weight coefficient corresponding to each effect value objective function; The comprehensive objective function is determined based on each effect value objective function and the corresponding weight coefficient.

6. The method for regional planting and breeding integration optimization based on multi-objective optimization according to claim 5 is characterized in that: The expression of the comprehensive objective function F is: in, is the indicator variable corresponding to the i-th effect value objective function; a i is the weight coefficient corresponding to the i-th effect value objective function; f i is the expression of the i-th effect value objective function, and m is the total number of effect value objective functions.

7. The method for regional planting and breeding integration optimization based on multi-objective optimization according to claim 1, characterized in that: Based on the optimal ratio of organic fertilizer to chemical fertilizer and the current livestock production, determine the regional type to which the target area belongs, including: Determine the theoretical carrying capacity of the target area based on the optimal ratio of organic fertilizer to chemical fertilizer, the nutrient requirements per unit area of each crop / land type, the sown area of each crop / land type, and the nutrient supply per unit pig equivalent; the nutrient requirements per unit area of each crop / land type are determined by the crop yield per unit area and the nutrient requirements per unit yield; Determine the relationship between the current breeding volume and the theoretical carrying capacity of the target area and obtain the judgment result; the current breeding volume is determined by the livestock and poultry inventory and the pig equivalent conversion coefficient; Based on the judgment result, the area type to which the target area belongs is determined.

8. The method for regional planting and breeding integration optimization based on multi-objective optimization according to claim 7 is characterized in that: Based on the judgment result, determining the area type to which the target area belongs includes: When the judgment result is that the current breeding volume > theoretical carrying capacity × 0.8, the target area is determined to be an overloaded area; When the judgment result is theoretical carrying capacity × 0.8 < current breeding volume < theoretical carrying capacity, the target area is determined to be a balanced area; When the judgment result is that the current breeding volume < theoretical carrying capacity × 0.8, the regional type of the target area is determined to be a potential area.

9. The method for regional planting and breeding integration optimization based on multi-objective optimization according to claim 7, characterized in that: The suitability index of the target area is calculated based on the soil carrying capacity score, transportation cost score, and environmental sensitivity score of the target area, including: Determine the soil bearing capacity score of the target area based on the remaining capacity ratio of the theoretical bearing capacity of the target area; Determine a transportation cost score for the target area based on the distance manure is transported to the target area; Determine the environmental sensitivity score of the target area based on the distance between the target area and the ecological red line; The analytic hierarchy process was used to determine the weights corresponding to the soil carrying capacity, transportation cost and environmental sensitivity of the target area. The suitability index of the target area is determined based on the soil carrying capacity score, transportation cost score, and environmental sensitivity score of the target area and their corresponding weights.

10. A regional planting and breeding integration optimization system based on multi-objective optimization, characterized in that: The regional planting and breeding integration optimization system based on multi-objective optimization is used to implement the regional planting and breeding integration optimization method based on multi-objective optimization according to any one of claims 1 to 9, and the regional planting and breeding integration optimization system based on multi-objective optimization includes: a data acquisition unit, configured to acquire statistical values of target indicators in a control group, the ratio of organic fertilizer to chemical fertilizer in multiple experimental groups, and statistical values of target indicators in multiple experimental groups; the target indicators include: crop yield, environmental benefits, and soil health; the statistical values include: mean, standard deviation, and number of replicates; wherein, the control group's area uses only chemical fertilizers as fertilizers, and the experimental groups' areas use chemical fertilizers and / or organic fertilizers with different ratios of organic fertilizer to chemical fertilizers as fertilizers, and the target indicators are indicators affected by the replacement of chemical fertilizers with organic fertilizers; A first average effect value determination unit is used to calculate the average effect value of each target indicator in each experimental group based on the statistical value of each target indicator in the area where each experimental group is located and the statistical value of each target indicator in the area where the control group is located; The second average effect value determination unit is used to determine the economic profit of the region where each experimental group is located, and calculate the average effect value of the economic profit under each experimental group based on the economic profit of the region where each experimental group is located; The first function fitting unit is used to fit the average effect value of each target indicator in all experimental groups and the ratio of organic fertilizer replacing chemical fertilizer in all experimental groups, so as to obtain the effect value target function between each target indicator and the ratio of organic fertilizer replacing chemical fertilizer; The second function fitting unit is used to fit the average effect value of economic profit in all experimental groups and the ratio of organic fertilizer replacing chemical fertilizer in all experimental groups to obtain the effect value objective function between economic profit and the ratio of organic fertilizer replacing chemical fertilizer; A comprehensive objective function determination unit is used to determine a comprehensive objective function based on each of the effect value objective functions by adopting a hierarchical analysis method; An optimal organic fertilizer-to-chemical fertilizer ratio determination unit is configured to optimize and solve the comprehensive objective function using a non-dominated sorting genetic algorithm to obtain an optimal organic fertilizer-to-chemical fertilizer ratio; A region type determination unit is configured to determine the region type to which the target region belongs based on the optimal ratio of organic fertilizer to chemical fertilizer and the current breeding volume; the region type is an overloaded region, a balanced region, or a potential region; a suitability index determination unit, configured to calculate a suitability index of a target area based on a soil bearing capacity score, a transportation cost score, and an environmental sensitivity score of the target area; The farm location determination unit is used to layout new farms in the target area when the suitability index of the target area is greater than the threshold, so as to achieve regional integration of planting and breeding.

Images