Intelligent corn seed production land configuration method and system based on ecological environment factors

Abstract

The invention discloses an intelligent corn seed production land configuration method and system based on ecological environment factors, and relates to the technical field of agricultural information. The system comprises a data layer, a model layer and an application layer, geographic information data, meteorological data, soil data and corn variety data of a target area are collected and stored through the data layer, the weight of each index is determined by soliciting expert opinions through the model layer, and an ecological suitability evaluation model and a land suitability evaluation model are constructed. Evaluating the ecological suitability and the land suitability of the target area, and generating an optimal corn seed production land configuration scheme by using the intelligent configuration model according to set constraint conditions; and the application layer is used for visualization and providing scheme generation and scheme evaluation. The intelligent algorithm is utilized, ecological environment factors are comprehensively considered, the scientificity and rationality of configuration are improved, the configuration scheme is automatically generated, and the configuration efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of agricultural information technology, and in particular to an intelligent corn seed production land configuration method and system based on ecological environment factors. Background Art

[0002] Corn seed production is the foundation of the development of the corn industry. High-quality corn seeds are crucial to improving corn yield and quality. Traditional land allocation for corn seed production mainly relies on experience and manual planning, which has the following problems:

[0003] Highly subjective and lacking scientific basis. Traditional land allocation methods mainly rely on expert experience and historical data, lacking quantitative analysis of the relationship between ecological environmental factors and corn seed adaptability, resulting in highly subjective allocation results and difficulty in ensuring the scientificity and rationality of the allocation.

[0004] Inefficiency and high cost: Manual planning of land allocation plans is time-consuming, labor-intensive, inefficient, and requires a large amount of manpower and material resources.

[0005] It is difficult to adapt to the needs of large-scale seed production. With the rapid development of the corn industry, the demand for corn seeds continues to increase, and traditional land allocation methods are difficult to meet the needs of large-scale seed production.

[0006] Therefore, there is an urgent need for a scientific, efficient and intelligent land allocation method for corn seed production to improve land utilization, reduce seed production costs and ensure the supply of corn seeds. Summary of the invention

[0007] The purpose of the present invention is to provide an intelligent corn seed production land configuration method and system based on ecological environmental factors to solve the problems raised in the above background technology.

[0008] In order to solve the above technical problems, the present invention provides the following technical solution: an intelligent corn seed production land configuration method based on ecological environmental factors, the method comprising the following steps:

[0009] S1-1. Collect geographic information data, meteorological data, soil data and corn varieties of the target area, and pre-process the data;

[0010] S1-2. According to the ecological environment requirements of corn seed production, select key ecological environment factors, determine the weights of each key ecological environment factor, use fuzzy comprehensive evaluation method to construct an ecological suitability evaluation model, and classify the ecological suitability level of the target area;

[0011] S1-3. According to the land quality requirements for corn seed production, select key land quality factors, determine the weights of each key land quality factor, use spatial principal component analysis to construct a land suitability evaluation model, and classify the land suitability of the target area;

[0012] S1-4. Based on the ecological suitability evaluation results, land suitability evaluation results and set constraints, a multi-objective optimization model is constructed to generate the optimal land allocation plan for corn seed production;

[0013] S1-5. Evaluate the generated configuration scheme and optimize the configuration scheme based on the evaluation results.

[0014] According to the above scheme, the geographic information data includes topography, landform and hydrology; the meteorological data includes temperature, precipitation and sunshine; the soil data includes soil type, pH value and organic matter content; the corn variety includes variety characteristics, growth period and stress resistance;

[0015] The preprocessing includes data cleaning, format conversion, interpolation, space matching and time synchronization to ensure the accuracy and consistency of the data;

[0016] The data cleaning includes identifying and correcting outliers in the data, standardizing the data format, removing duplicate records, verifying the integrity of the data, and ensuring that no key information is missed;

[0017] The format conversion includes identifying the original data format and its format, converting the data into CSV or TIFF format, and ensuring that the converted data maintains the original data structure and content;

[0018] The interpolation includes identifying missing parts in the data and filling the missing data with an interpolation algorithm;

[0019] The spatial matching includes determining the spatial reference system of the data, using GIS software to perform geocoding, converting addresses or places into geographic coordinates, and performing spatial connection on the data;

[0020] The time synchronization includes standardizing the time formats of different data sources, aligning data timestamps, processing time differences, and matching unified time intervals.

[0021] According to the above scheme, the analytic hierarchy process is used to determine the weights of the key ecological environmental factors and the key land quality factors; a judgment matrix is ​​constructed, and the indicators are compared pairwise through expert opinions to determine the priority weights of the indicators, and the analytic hierarchy process element decision software is used to divide the weights; the weighted comprehensive evaluation method is used to comprehensively consider the advantages and disadvantages of each factor, and a quantitative indicator is used to concentrate them to obtain the ecological suitability and land adaptability index.

[0022] According to the above scheme, the analytic hierarchy process includes: decomposing the key ecological environment factors and the key land quality factors into three layers, the three layers including a decision layer, an intermediate layer and a scheme layer;

[0023] The decision-making level includes regional ecological suitability and regional land suitability;

[0024] The intermediate layer includes the regional ecological suitability factor and the regional land suitability factor as the first-level evaluation factors respectively; wherein the regional ecological suitability factor is a sub-factor of the regional ecological suitability, including temperature data, rainfall data, meteorological data and soil data; the regional land suitability factor is a sub-factor of the regional land suitability, including soil fertility, irrigation conditions and traffic conditions;

[0025] The scheme layer includes specific ecological factors and specific land factors as secondary evaluation factors respectively; the specific ecological factors are sub-factors under the regional ecological suitability factors; wherein the sub-factors of the temperature data include the annual maximum temperature, the annual minimum temperature, the annual average temperature, the effective accumulated temperature and the active accumulated temperature; the sub-factors under the rainfall data include the annual rainfall, the annual effective rainfall, the number of precipitation days, the distribution of precipitation intensity, the seasonality of precipitation and the pH value of precipitation; the sub-factors under the meteorological data include the number of sunshine hours, light and effective radiation and the reference crop evaporation; the sub-factors under the soil data include the soil texture structure, the organic matter content and the soil pH value; the specific land factors are sub-factors under the regional land suitability factors; wherein the soil fertility includes the topography, slope, coverage, erosion, land thickness, plough layer thickness, texture, obstacle layer, organic matter, total nitrogen, total phosphorus, total potassium, available phosphorus and available potassium; the irrigation conditions include earth channel water supply, surface flooding and efficient water-saving irrigation; the traffic conditions include roadbed strength and road width;

[0026] The construction of the judgment matrix includes soliciting expert opinions, comparing the second-level evaluation factors under each first-level evaluation factor in pairs to determine the relative importance of the second-level evaluation factors under their parent nodes; forming a comparison matrix for the second-level evaluation factors under each first-level evaluation factor, and the experts use scales to compare the two factors based on their experience and knowledge; performing consistency checks on each comparison matrix to ensure that the comparison results of the experts are reasonable and consistent; if the comparison results are found to be inconsistent, further adjustments and discussions are carried out;

[0027] Using the analytic hierarchy process decision-making software, the weight of each secondary evaluation factor relative to its parent node is calculated based on the judgment matrix passed by consistency;

[0028] Using the weighted comprehensive evaluation method, the weight of each factor is multiplied by its score or quantitative index in the actual evaluation;

[0029] The weights of all secondary evaluation factors are aggregated under the corresponding primary evaluation factors to form a complete hierarchical weight; the weights of ecological suitability and land suitability are combined to obtain the final weight of the overall decision-making layer.

[0030] According to the above scheme, the use of fuzzy comprehensive evaluation method to construct an ecological suitability evaluation model includes the following steps:

[0031] S5-1. Determine the evaluation factors and form an evaluation factor set U, where the factor value u is i is the regional ecological suitability factor and specific ecological factor; construct an evaluation set V, set the level according to the actual evaluation, and the evaluation level v in the level set j is a highly suitable area, a moderately suitable area, a low suitable area and an unsuitable area; a weight set W is constructed, and a weight vector w is concentrated in the weight set i is the weight of each key ecological and environmental factor;

[0032] S5-2. For each evaluation factor u i , it is necessary to establish its membership function Lu i (x), used to reflect the membership of the factor value x to each level in the evaluation set V, and to establish the membership function;

[0033] S5-3, the evaluation matrix R is calculated by the membership function, where r ij Indicator u i Evaluation level v j The construction process of the evaluation matrix is ​​as follows:

[0034]

[0035] S5-4, use the weight set W and the evaluation matrix R to perform fuzzy synthesis to obtain the comprehensive evaluation vector B, the formula is as follows:

[0036]

[0037] Based on the calculation results of the comprehensive evaluation, the area is divided into highly suitable areas, moderately suitable areas, low suitable areas or unsuitable areas.

[0038] According to the above scheme, the construction of land suitability evaluation model by spatial principal component analysis method includes the following steps:

[0039] S6-1. Standardize the key land quality factors to eliminate the dimensional impact between different indicators. The formula is as follows:

[0040]

[0041] Among them, z mn Represented as standardized data, xmn Represents the original data, i represents the number of samples;

[0042] S6-2. Calculate the covariance matrix of spatial data to analyze the spatial correlation between indicators. The formula is as follows:

[0043]

[0044] Where C represents the covariance matrix; Z m Represented as the normalized data vector of the mth sample, Represented as the mean vector of all sample data; (...) T Represented as a transposed matrix;

[0045] S6-3. Calculate the eigenvalue nine and eigenvector e of the covariance matrix C. The formula is as follows:

[0046] Ce=λe

[0047] S6-4. Construct a comprehensive evaluation index, the formula is as follows:

[0048] PC=W×X

[0049] Among them, PC represents the comprehensive evaluation index, W represents the weight matrix composed of feature vectors, and X represents the original data matrix;

[0050] According to the calculation results of comprehensive evaluation, the area is divided into highly suitable area, moderately suitable area, low suitable area and unsuitable area.

[0051] According to the above scheme, the constraints include land use status, variety matching, isolation requirements and specification sowing requirements;

[0052] The current land use status includes cultivated land, forest land, grassland and wetland; the variety combination includes single-cross, double-cross, triple-cross and integrated varieties; the isolation requirements include spatial isolation, temporal isolation, high-stalk crop isolation and natural barrier isolation; the isolation area is set up to avoid mixing with other corn varieties, maintain the purity of the parents, and improve the quality of hybrids; the specification sowing requirements include sowing rate, row spacing, plant spacing, sowing uniformity, sowing depth, soil covering depth and compaction degree; the sowing period of the parents is to make their flowering periods coincide. The success of corn seed production is largely determined by the combination of varieties and planting techniques. To ensure high-purity hybrid seeds, a series of measures must be taken, including the setting of isolation areas, specification sowing, adjusting the sowing period of the parents and selecting suitable varieties for hybridization, so as to effectively improve the success rate of corn seed production and seed quality.

[0053] According to the above scheme, the construction of the intelligent configuration model includes: designing the goals of the intelligent configuration model, and the goals of the intelligent configuration model include increasing crop yield, increasing the success rate of corn seed production and improving seed quality; combining the ecological suitability evaluation results, land suitability evaluation results and constraints to construct an intelligent configuration model, and the intelligent configuration model needs to meet all constraints while optimizing the designed optimization model goals; using genetic algorithms to handle multiple conflicting goals, find a set of solutions, and generate an optimal land configuration plan for corn seed production; evaluate the optimal land configuration plan for corn seed production, and analyze its rationality and feasibility; according to the evaluation results, adjust and optimize the configuration plan until the goals of the intelligent configuration model are met.

[0054] An intelligent corn seed production land configuration system based on ecological environment factors, the system includes: data layer, model layer and application layer;

[0055] The data layer includes geographic information data, meteorological data, corn variety data and soil data; the model layer includes ecological suitability evaluation model, land suitability evaluation model and intelligent configuration model; the application layer includes data visualization, solution generation and solution evaluation;

[0056] The geographic information data includes topography, landform and hydrology; the meteorological data includes temperature, precipitation and sunshine; the soil data includes soil type, pH value and organic matter content; the corn variety includes variety characteristics, growth period and stress resistance;

[0057] The ecological suitability evaluation model includes selecting temperature data, rainfall data, meteorological data and soil data according to the ecological environment requirements of corn seed production; using the hierarchical analysis method to decompose the data into a decision-making layer, an intermediate layer and a program layer, and through a judgment matrix, soliciting expert opinions to compare each index pairwise to determine the weight of each index; using the fuzzy comprehensive evaluation method to construct an ecological suitability evaluation model, and according to the calculation results of the ecological suitability evaluation model, the region is divided into a highly suitable area, a moderately suitable area, a low suitable area and an unsuitable area;

[0058] The land suitability evaluation model includes selecting soil fertility, irrigation conditions and traffic conditions according to the land quality requirements for corn seed production; using the hierarchical analysis method to determine the weight of each indicator; using the spatial principal component analysis method to construct a land suitability evaluation model, and according to the calculation results of the land suitability evaluation model, the region is divided into highly suitable areas, moderately suitable areas, low suitable areas and unsuitable areas;

[0059] The intelligent configuration model includes setting configuration constraints, wherein the constraints include utilization status, variety matching, isolation requirements and specification sowing requirements; constructing an intelligent configuration model based on ecological suitability evaluation results, land suitability evaluation results and constraints; and using the intelligent configuration model to generate an optimal corn seed production land configuration plan;

[0060] The application layer displays target area data, solution generation and solution evaluation; the target area data includes geographic information data, meteorological data, corn variety data and soil data; the solution generation includes displaying the optimal corn seed production land configuration plan generated by the intelligent configuration model; the solution evaluation includes evaluating the generated optimal corn seed production land configuration plan, analyzing its rationality and feasibility, and displaying the evaluation results to the application layer.

[0061] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0062] 1. An intelligent land allocation method for corn seed production based on ecological and environmental factors was proposed, which comprehensively considered the impact of ecological and environmental factors and land quality factors on corn seed production, and improved the scientificity and rationality of the allocation;

[0063] 2. The ecological suitability evaluation model and land suitability evaluation model were constructed to quantitatively evaluate the ecological suitability and land suitability of the target area, providing a basis for intelligent configuration;

[0064] 3. An intelligent configuration model has been constructed, which can automatically generate the optimal land configuration plan for corn seed production based on the set constraints, thereby improving the efficiency and accuracy of the configuration. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0066] Figure 1 It is a schematic diagram of the steps of the intelligent corn seed production land configuration method based on ecological environment factors of the present invention;

[0067] Figure 2 It is a schematic diagram of the process of the intelligent corn seed production land configuration system based on ecological environment factors of the present invention. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0069] See also Figure 1-Figure 2 , the present invention provides a technical solution:

[0070] According to an example of the present invention, an intelligent corn seed production land configuration method based on ecological environmental factors;

[0071] Collect geographic information data, meteorological data, soil data and corn varieties of the target area, and pre-process the data;

[0072] The geographic information data includes topography, landform and hydrology; the meteorological data includes temperature, precipitation and sunshine; the soil data includes soil type, pH value and organic matter content; the corn variety includes variety characteristics, growth period and stress resistance;

[0073] The preprocessing includes data cleaning, format conversion, interpolation, space matching and time synchronization to ensure the accuracy and consistency of the data;

[0074] The data cleaning includes identifying and correcting outliers in the data, standardizing the data format, removing duplicate records, verifying the integrity of the data, and ensuring that no key information is missed;

[0075] The format conversion includes identifying the original data format and its format, converting the data into CSV or TIFF format, and ensuring that the converted data maintains the original data structure and content;

[0076] The interpolation includes identifying missing parts in the data and filling the missing data with an interpolation algorithm;

[0077] The spatial matching includes determining the spatial reference system of the data, using GIS software to perform geocoding, converting addresses or places into geographic coordinates, and performing spatial connection on the data;

[0078] The time synchronization includes standardizing the time formats of different data sources, aligning data timestamps, processing time differences, and matching unified time intervals.

[0079] The weights of the key ecological environment factors and the key land quality factors are determined by using a hierarchical analysis method; the hierarchical analysis method includes: decomposing the key ecological environment factors and the key land quality factors into three layers, the three layers including a decision-making layer, an intermediate layer and a program layer;

[0080] The decision-making level includes regional ecological suitability and regional land suitability;

[0081] The middle layer includes the regional ecological suitability factor and the regional land suitability factor as the first-level evaluation factors respectively; wherein the regional ecological suitability factor is a sub-factor of regional ecological suitability, including temperature data, rainfall data, meteorological data and soil data; the regional land suitability factor is a sub-factor of regional land suitability, including soil fertility, irrigation conditions and traffic conditions;

[0082] The scheme layer includes specific ecological factors and specific land factors as secondary evaluation factors respectively; the specific ecological factors are sub-factors under the regional ecological suitability factors; wherein the sub-factors of the temperature data include the annual maximum temperature, the annual minimum temperature, the annual average temperature, the effective accumulated temperature and the active accumulated temperature; the sub-factors under the rainfall data include the annual rainfall, the annual effective rainfall, the number of precipitation days, the distribution of precipitation intensity, the seasonality of precipitation and the pH value of precipitation; the sub-factors under the meteorological data include the number of sunshine hours, light and effective radiation and the reference crop evaporation; the sub-factors under the soil data include the soil texture structure, the organic matter content and the soil pH value; the specific land factors are sub-factors under the regional land suitability factors; wherein the soil fertility includes the topography, slope, coverage, erosion, land thickness, plough layer thickness, texture, obstacle layer, organic matter, total nitrogen, total phosphorus, total potassium, available phosphorus and available potassium; the irrigation conditions include earth channel water supply, surface flooding and efficient water-saving irrigation; the traffic conditions include roadbed strength and road width;

[0083] Construct a judgment matrix, compare each indicator pairwise through expert opinions, determine the priority weight of the indicator, and use the analytic hierarchy process decision-making software to divide the weight;

[0084] The construction of the judgment matrix includes soliciting expert opinions, comparing the second-level evaluation factors under each first-level evaluation factor in pairs to determine the relative importance of the second-level evaluation factors under their parent nodes; forming a comparison matrix for the second-level evaluation factors under each first-level evaluation factor, and the experts use scales to compare the two factors based on their experience and knowledge; performing consistency checks on each comparison matrix to ensure that the comparison results of the experts are reasonable and consistent; if the comparison results are found to be inconsistent, further adjustments and discussions are carried out;

[0085] Using the analytic hierarchy process decision-making software, the weight of each secondary evaluation factor relative to its parent node is calculated based on the judgment matrix passed by consistency;

[0086] The weighted comprehensive evaluation method is used to comprehensively consider the advantages and disadvantages of each factor, and a quantitative index is used to concentrate them to obtain the ecological suitability and land adaptability index;

[0087] Using the weighted comprehensive evaluation method, the weight of each factor is multiplied by its score or quantitative index in the actual evaluation;

[0088] The weights of all secondary evaluation factors are aggregated under the corresponding primary evaluation factors to form a complete hierarchical weight; the weights of ecological suitability and land suitability are combined to obtain the final weight of the overall decision-making layer. The weights of each evaluation factor indicator of the present invention are shown in Table 1:

[0089] Table 1 Weights of each evaluation factor

[0090]

[0091] The fuzzy comprehensive evaluation method is used to construct an ecological suitability evaluation model, and the ecological suitability level of the target area is divided; the fuzzy comprehensive evaluation method is used to construct an ecological suitability evaluation model, which includes the following steps: Take temperature data as an example:

[0092] S5-1. Determine the evaluation factors and form an evaluation factor set U, where the factor value u is i are regional ecological suitability factors and specific ecological factors; evaluation factor set U = {u1 = annual maximum temperature, u2 = annual minimum temperature, u3 = annual average temperature, u4 = effective accumulated temperature, u5 = active accumulated temperature};

[0093] Construct an evaluation set V, set the level according to the actual evaluation, and the evaluation level v in the level set j are highly suitable areas, moderately suitable areas, low suitable areas and unsuitable areas; the evaluation set is V = {v1 = unsuitable area, v2 = low suitable area, v3 = moderately suitable area, v4 = highly suitable area};

[0094] Construct a weight set W, where the weight vector w is i is the weight of each key ecological and environmental factor; the weight set is W = {w1 = 0.0311, w2 = 0.0305, w3 = 0.1125, w4 = 0.0441, w5 = 0.0274};

[0095] S5-2. For each evaluation factor u i , it is necessary to establish its membership function Lu i (x) is used to reflect the membership of the factor value x to each level in the evaluation set V and establish a membership function; for example, based on the collected temperature data, we can get the annual maximum temperature membership: 0.2; the annual minimum temperature membership: 0.3; the annual average temperature membership: 0.8; the effective accumulated temperature membership: 0.6; the active accumulated temperature membership: 0.5;

[0096] S5-3, the evaluation matrix R is calculated by the membership function, where r ijIndicator u i Evaluation level v j The construction process of the evaluation matrix is ​​as follows:

[0097]

[0098] S5-4, use the weight set W and the evaluation matrix R to perform fuzzy synthesis to obtain the comprehensive evaluation vector B, the formula is as follows:

[0099]

[0100] Then the temperature data comprehensive evaluation vector B is calculated as (0.2×0.0311+0.3×0.0305+0.8×0.1125+0.6×0.0441+0.5×0.0274)×0.2456;

[0101] According to the above method, the comprehensive evaluation vectors of rainfall data, meteorological data and soil data are calculated at the same time, and added together to obtain the calculation result of the comprehensive evaluation of ecological suitability;

[0102] Based on the calculation results of the comprehensive evaluation, the area is divided into highly suitable areas, moderately suitable areas, low suitable areas or unsuitable areas.

[0103] According to the land quality requirements for corn seed production, key land quality factors were selected, the weights of each key land quality factor were determined, and a land suitability evaluation model was constructed using spatial principal component analysis to classify the land suitability of the target area.

[0104] The construction of land suitability evaluation model using spatial principal component analysis method includes the following steps: Taking irrigation conditions as an example: The irrigation condition data of three regions are obtained as shown in Table 2:

[0105] Table 2 Irrigation condition data

[0106]

[0107] S6-1. Standardize the key land quality factors, eliminate the dimensional impact between different indicators, and calculate the average value and standard deviation:

[0108] Earth canal water supply:

[0109]

[0110]

[0111] Surface irrigation:

[0112]

[0113]

[0114] Efficient water-saving irrigation:

[0115]

[0116]

[0117] Calculate the normalized data:

[0118] z 11 =(500-550) / s 11 , z 21 =(600-550) / s 11 , z 31 =(550-550) / s 11 ,

[0119] z 12 =(200-230) / s 12 , z 22 =(250-230) / s 12 , z 32 =(230-230) / s 12 ,

[0120] z 13 =(300-325) / s 13 , z 23 =(350-325) / s 13 , z 33 =(320-325) / s 13 ;

[0121] S6-2. Calculate the covariance matrix of spatial data to analyze the spatial correlation between indicators and construct a standardized data matrix:

[0122]

[0123] Compute the mean vector:

[0124]

[0125] Compute the covariance matrix:

[0126]

[0127] Where C represents the covariance matrix; Z m Represented as the normalized data vector of the mth sample, Represented as the mean vector of all sample data; (…) T Represented as a transposed matrix;

[0128] S6-3. Calculate the eigenvalue λ and eigenvector e of the covariance matrix C. The formula is as follows:

[0129] Ce=λe

[0130] S6-4. Construct a comprehensive evaluation index, the formula is as follows:

[0131] PC=W×X

[0132] Among them, PC represents the comprehensive evaluation index, W represents the weight matrix composed of feature vectors, and X represents the original data matrix;

[0133] According to the calculation results of comprehensive evaluation, the area is divided into highly suitable area, moderately suitable area, low suitable area and unsuitable area.

[0134] According to the ecological suitability evaluation results, land suitability evaluation results and set constraints, a multi-objective optimization model is constructed to generate the optimal land allocation plan for corn seed production;

[0135] The constraints include land use status, variety matching, isolation requirements and specification sowing requirements;

[0136] The current land use status includes cultivated land, forest land, grassland and wetland; the variety combination includes single-cross, double-cross, triple-cross and integrated varieties; the isolation requirements include spatial isolation, temporal isolation, high-stalk crop isolation and natural barrier isolation; the isolation area is set up to avoid mixing with other corn varieties, maintain the purity of the parents, and improve the quality of hybrids; the specification sowing requirements include sowing rate, row spacing, plant spacing, sowing uniformity, sowing depth, soil covering depth and compaction degree; the sowing period of the parents is to make their flowering periods coincide. The success of corn seed production is largely determined by the combination of varieties and planting techniques. To ensure high-purity hybrid seeds, a series of measures must be taken, including the setting of isolation areas, specification sowing, adjusting the sowing period of the parents and selecting suitable varieties for hybridization, so as to effectively improve the success rate of corn seed production and seed quality.

[0137] Evaluate the generated configuration scheme and optimize the configuration scheme according to the evaluation results;

[0138] According to the above scheme, the construction of the intelligent configuration model includes: designing the goals of the intelligent configuration model, and the goals of the intelligent configuration model include increasing crop yield, increasing the success rate of corn seed production and improving seed quality; combining the ecological suitability evaluation results, land suitability evaluation results and constraints to construct an intelligent configuration model, and the intelligent configuration model needs to meet all constraints while optimizing the designed optimization model goals; using genetic algorithms to handle multiple conflicting goals, find a set of solutions, and generate an optimal land configuration plan for corn seed production; evaluate the optimal land configuration plan for corn seed production, and analyze its rationality and feasibility; according to the evaluation results, adjust and optimize the configuration plan until the goals of the intelligent configuration model are met.

[0139] According to an example of the present invention, an intelligent corn seed production land configuration system based on ecological environment factors includes: a data layer, a model layer and an application layer;

[0140] The data layer includes geographic information data, meteorological data, corn variety data and soil data; the model layer includes ecological suitability evaluation model, land suitability evaluation model and intelligent configuration model; the application layer includes data visualization, solution generation and solution evaluation; geographic information data includes topography, landform and hydrology;

[0141] Meteorological data include temperature, precipitation and sunshine; soil data include soil type, pH value and organic matter content; corn varieties include variety characteristics, growth period and stress resistance;

[0142] The ecological suitability evaluation model includes selecting temperature data, rainfall data, meteorological data and soil data according to the ecological environment requirements of corn seed production; using the hierarchical analysis method to decompose the data into decision-making layer, intermediate layer and program layer, and through the judgment matrix, soliciting expert opinions to compare each index pairwise and determine the weight of each index; using the fuzzy comprehensive evaluation method to construct the ecological suitability evaluation model, according to the calculation results of the ecological suitability evaluation model, the region is divided into highly suitable areas, moderately suitable areas, low suitable areas and unsuitable areas;

[0143] The land suitability evaluation model includes selecting soil fertility, irrigation conditions and transportation conditions according to the land quality requirements for corn seed production; using the hierarchical analysis method to determine the weight of each indicator; using the spatial principal component analysis method to construct the land suitability evaluation model, and according to the calculation results of the land suitability evaluation model, the region is divided into highly suitable areas, moderately suitable areas, low suitable areas and unsuitable areas;

[0144] The intelligent configuration model includes setting configuration constraints, which include utilization status, variety matching, isolation requirements and specification sowing requirements; constructing an intelligent configuration model based on the ecological suitability evaluation results, land suitability evaluation results and constraints; using the intelligent configuration model, generating the optimal corn seed production land configuration plan;

[0145] The application layer displays target area data, solution generation and solution evaluation; the target area data includes geographic information data, meteorological data, corn variety data and soil data; solution generation includes displaying the optimal corn seed production land configuration plan generated by the intelligent configuration model; solution evaluation includes evaluating the generated optimal corn seed production land configuration plan, analyzing its rationality and feasibility, and displaying the evaluation results to the application layer.

[0146] It should be noted that, in this article, relational terms such as first and second, etc. are only used 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. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0147] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent corn seed production land allocation method based on ecological environmental factors, characterized by: The method comprises the following steps: S1-1. Collect geographic information data, meteorological data, soil data and corn varieties of the target area, and pre-process the data; S1-2. According to the ecological environment requirements of corn seed production, select key ecological environment factors, determine the weights of each key ecological environment factor, use fuzzy comprehensive evaluation method to construct an ecological suitability evaluation model, and classify the ecological suitability level of the target area; S1-3. According to the land quality requirements for corn seed production, select key land quality factors, determine the weights of each key land quality factor, use spatial principal component analysis to construct a land suitability evaluation model, and classify the land suitability of the target area; S1-4. Based on the ecological suitability evaluation results, land suitability evaluation results and set constraints, a multi-objective optimization model is constructed to generate the optimal land allocation plan for corn seed production; S1-5. Evaluate the generated configuration scheme and optimize the configuration scheme based on the evaluation results.

2. The intelligent corn seed production land configuration method based on ecological environment factors according to claim 1 is characterized in that: The geographic information data includes topography, landform and hydrology; the meteorological data includes temperature, precipitation and sunshine; the soil data includes soil type, pH value and organic matter content; the corn variety includes variety characteristics, growth period and stress resistance; The preprocessing includes data cleaning, format conversion, interpolation and missing data filling, spatial matching and time synchronization; The data cleaning includes identifying and correcting outliers in the data, standardizing the data format, removing duplicate records, verifying the integrity of the data, and ensuring that no key information is missed; The format conversion includes identifying the original data format and its format, converting the data into CSV or TIFF format, and ensuring that the converted data maintains the original data structure and content; The interpolation includes identifying missing parts in the data and filling the missing data with an interpolation algorithm; The spatial matching includes determining the spatial reference system of the data, using GIS software to perform geocoding, converting addresses or places into geographic coordinates, and performing spatial connection on the data; The time synchronization includes standardizing the time formats of different data sources, aligning data timestamps, processing time differences, and matching unified time intervals.

3. The intelligent corn seed production land configuration method based on ecological environment factors according to claim 1 is characterized by: The analytic hierarchy process is used to determine the weights of the key ecological environmental factors and the key land quality factors; a judgment matrix is ​​constructed, and the indicators are compared pairwise through expert opinions to determine the priority weights of the indicators, and the analytic hierarchy process element decision software is used to divide the weights; the weighted comprehensive evaluation method is used to comprehensively consider the advantages and disadvantages of each factor, and a quantitative indicator is used to concentrate them to obtain the ecological suitability and land adaptability index.

4. The intelligent corn seed production land configuration method based on ecological environment factors according to claim 3 is characterized by: The analytic hierarchy process includes: decomposing the key ecological environment factors and the key land quality factors into three layers, the three layers including a decision-making layer, an intermediate layer and a program layer; The decision-making level includes regional ecological suitability and regional land suitability; The intermediate layer includes the regional ecological suitability factor and the regional land suitability factor as the first-level evaluation factors respectively; wherein the regional ecological suitability factor is a sub-factor of the regional ecological suitability, including temperature data, rainfall data, meteorological data and soil data; the regional land suitability factor is a sub-factor of the regional land suitability, including soil fertility, irrigation conditions and traffic conditions; The scheme layer includes specific ecological factors and specific land factors as secondary evaluation factors respectively; the specific ecological factors are sub-factors under the regional ecological suitability factors; wherein the sub-factors of the temperature data include the annual maximum temperature, the annual minimum temperature, the annual average temperature, the effective accumulated temperature and the active accumulated temperature; the sub-factors under the rainfall data include the annual rainfall, the annual effective rainfall, the number of precipitation days, the distribution of precipitation intensity, the seasonality of precipitation and the pH value of precipitation; the sub-factors under the meteorological data include the number of sunshine hours, light and effective radiation and the reference crop evaporation; the sub-factors under the soil data include the soil texture structure, the organic matter content and the soil pH value; the specific land factors are sub-factors under the regional land suitability factors; wherein the soil fertility includes the topography, slope, coverage, erosion, land thickness, plough layer thickness, texture, obstacle layer, organic matter, total nitrogen, total phosphorus, total potassium, available phosphorus and available potassium; the irrigation conditions include earth channel water supply, surface flooding and efficient water-saving irrigation; the traffic conditions include roadbed strength and road width; The construction of the judgment matrix includes soliciting expert opinions, comparing the second-level evaluation factors under each first-level evaluation factor in pairs to determine the relative importance of the second-level evaluation factors under their parent nodes; forming a comparison matrix for the second-level evaluation factors under each first-level evaluation factor, and the experts use scales to compare the two factors based on their experience and knowledge; performing consistency checks on each comparison matrix to ensure that the comparison results of the experts are reasonable and consistent; if the comparison results are found to be inconsistent, further adjustments and discussions are carried out; Using the analytic hierarchy process decision-making software, the weight of each secondary evaluation factor relative to its parent node is calculated based on the judgment matrix passed by consistency; Using the weighted comprehensive evaluation method, the weight of each factor is multiplied by its score or quantitative index in the actual evaluation; The weights of all secondary evaluation factors are aggregated under the corresponding primary evaluation factors to form a complete hierarchical weight; the weights of ecological suitability and land suitability are combined to obtain the final weight of the overall decision-making layer.

5. The intelligent corn seed production land configuration method based on ecological environment factors according to claim 1 is characterized by: The use of the fuzzy comprehensive evaluation method to construct an ecological suitability evaluation model includes the following steps: S5-1. Determine the evaluation factors and form an evaluation factor set U, where the factor value u is i is the regional ecological suitability factor and specific ecological factor; construct an evaluation set V, set the level according to the actual evaluation, and the evaluation level v in the level set j is a highly suitable area, a moderately suitable area, a low suitable area and an unsuitable area; a weight set W is constructed, and a weight vector w is concentrated in the weight set i is the weight of each key ecological and environmental factor; S5-2. For each evaluation factor u i , it is necessary to establish its membership function Lu i (x), used to reflect the membership of the factor value x to each level in the evaluation set V, and to establish the membership function; S5-3, the evaluation matrix R is calculated by the membership function, where r ij Indicator u i Evaluation level v j The construction process of the evaluation matrix is ​​as follows: S5-4, use the weight set W and the evaluation matrix R to perform fuzzy synthesis to obtain the comprehensive evaluation vector B, the formula is as follows: Based on the calculation results of the comprehensive evaluation, the area is divided into highly suitable areas, moderately suitable areas, low suitable areas or unsuitable areas.

6. The intelligent corn seed production land configuration method based on ecological environment factors according to claim 1 is characterized by: The method of constructing a land suitability evaluation model using spatial principal component analysis includes the following steps: S6-1. Standardize the key land quality factors to eliminate the dimensional impact between different indicators. The formula is as follows: Among them, z mn Represented as standardized data, x mn Represents the original data, i represents the number of samples; S6-2. Calculate the covariance matrix of spatial data to analyze the spatial correlation between indicators. The formula is as follows: Where C represents the covariance matrix; Z m Represented as the normalized data vector of the mth sample, Represented as the mean vector of all sample data; (…) T Represented as a transposed matrix; S6-3. Calculate the eigenvalue λ and eigenvector e of the covariance matrix C. The formula is as follows: Ce=λe S6-4. Construct a comprehensive evaluation index, the formula is as follows: PC=W×X Among them, PC represents the comprehensive evaluation index, W represents the weight matrix composed of feature vectors, and X represents the original data matrix; According to the calculation results of comprehensive evaluation, the area is divided into highly suitable area, moderately suitable area, low suitable area and unsuitable area.

7. The intelligent corn seed production land configuration method based on ecological environment factors according to claim 1 is characterized by: The constraints include land use status, variety matching, isolation requirements and specification sowing requirements; The current land use status includes cultivated land, forest land, grassland and wetland; the variety combinations include single-cross varieties, double-cross varieties, triple-cross varieties and integrated varieties; the isolation requirements include spatial isolation, temporal isolation, tall-stem crop isolation and natural barrier isolation; the standard sowing requirements include sowing rate, row spacing, plant spacing, sowing uniformity, sowing depth, soil covering depth and compaction degree.

8. The intelligent corn seed production land configuration method based on ecological environment factors according to claim 1 is characterized by: The construction of the intelligent configuration model includes designing the goal of the intelligent configuration model, wherein the goal of the intelligent configuration model includes increasing crop yield, increasing the success rate of corn seed production, and improving seed quality; combining the ecological suitability evaluation results, the land suitability evaluation results, and the constraints, to construct the intelligent configuration model, wherein the intelligent configuration model needs to meet all the constraints while optimizing the designed optimization model goals; Genetic algorithms are used to handle multiple conflicting objectives, find a set of solutions, and generate the optimal land allocation plan for corn seed production. The optimal land allocation plan for corn seed production is evaluated and its rationality and feasibility are analyzed. Based on the evaluation results, the allocation plan is adjusted and optimized until the goals of the intelligent configuration model are met.

9. An intelligent corn seed production land allocation system based on ecological environment factors, characterized by: The system includes: data layer, model layer and application layer; The data layer includes geographic information data, meteorological data, corn variety data and soil data; the model layer includes ecological suitability evaluation model, land suitability evaluation model and intelligent configuration model; the application layer includes data visualization, solution generation and solution evaluation; The geographic information data includes topography, landform and hydrology; the meteorological data includes temperature, precipitation and sunshine; the soil data includes soil type, pH value and organic matter content; the corn variety includes variety characteristics, growth period and stress resistance; The ecological suitability evaluation model includes selecting temperature data, rainfall data, meteorological data and soil data according to the ecological environment requirements of corn seed production; using the hierarchical analysis method to decompose the data into a decision-making layer, an intermediate layer and a program layer, and through a judgment matrix, soliciting expert opinions to compare each index pairwise to determine the weight of each index; using the fuzzy comprehensive evaluation method to construct an ecological suitability evaluation model, and according to the calculation results of the ecological suitability evaluation model, the region is divided into a highly suitable area, a moderately suitable area, a low suitable area and an unsuitable area; The land suitability evaluation model includes selecting soil fertility, irrigation conditions and traffic conditions according to the land quality requirements for corn seed production; using the hierarchical analysis method to determine the weight of each indicator; using the spatial principal component analysis method to construct a land suitability evaluation model, and according to the calculation results of the land suitability evaluation model, the region is divided into highly suitable areas, moderately suitable areas, low suitable areas and unsuitable areas; The intelligent configuration model includes setting configuration constraints, wherein the constraints include utilization status, variety matching, isolation requirements and specification sowing requirements; constructing an intelligent configuration model based on ecological suitability evaluation results, land suitability evaluation results and constraints; and using the intelligent configuration model to generate an optimal corn seed production land configuration plan; The application layer displays target area data, solution generation and solution evaluation; the target area data includes geographic information data, meteorological data, corn variety data and soil data; the solution generation includes displaying the optimal corn seed production land configuration plan generated by the intelligent configuration model; the solution evaluation includes evaluating the generated optimal corn seed production land configuration plan, analyzing its rationality and feasibility, and displaying the evaluation results to the application layer.

Images