A method for selecting a planting site for superior szechuan pickled mustard

Abstract

The application discloses a kind of superior pickled vegetable planting site selection calculation methods, determine core index, and the index is positively normalized and negatively normalized processing;Determine initial weight by analytic hierarchy process, and correct weight according to the correlation degree of index and historical superior rate;First, the comprehensive score of each candidate plot is calculated by weighted summation method, then the score is corrected by combining the spatial correlation degree of plot and surrounding verified superior pickled vegetable planting plot, to obtain the comprehensive score;The final planting site is determined by sorting and screening the candidate plot according to the corrected comprehensive score and field verification, while the dynamic weight model parameter is adjusted through the deviation analysis of superior rate after trial planting.The application has the beneficial effects of avoiding the fluctuation of superior rate caused by index loss, eliminating the interference of data difference on evaluation results, reducing the interference of non-key indicators, improving the rationality of site selection, avoiding the waste of resources such as seeds, fertilizers and manpower caused by unsuitable plot in traditional experience site selection.

Description

Technical Field

[0001] This invention relates to a calculation method, and more specifically, to a calculation method for selecting high-quality pickled mustard tuber planting sites. Background Technology

[0002] In the pickled mustard tuber planting industry, the rate of high-quality products is the core factor determining planting benefits and product market competitiveness. The scientific selection of planting sites is a key prerequisite for ensuring the rate of high-quality pickled mustard tubers. In the current technology, the selection of pickled mustard tuber planting sites mostly relies on the experience and judgment of growers, mainly based on single or a few intuitive factors such as soil fertility and irrigation conditions in a local area. There is a lack of systematic integrated analysis of multi-dimensional indicators that affect the growth and quality of pickled mustard tubers, which leads to strong subjectivity and low accuracy in site suitability assessment. This often results in problems such as large fluctuations in the rate of high-quality products and waste of resources due to incomplete consideration of indicators. As agricultural planting moves towards precision and standardization, traditional experience-based site selection faces several challenges. First, different varieties of pickled mustard tuber have significantly different requirements for their growing environment. For example, crisp and tender pickled mustard tuber is more sensitive to the proportion of clay particles in the soil and the duration of sunshine, while high-fiber pickled mustard tuber relies more on organic matter content and temperature stability during the growth cycle. Traditional methods cannot differentiate the weighting of indicators based on variety characteristics, making it difficult to accurately match varieties with plots. Second, the value of historical planting data has not been fully explored, and the correlation between various environmental indicators and the rate of high-quality products cannot be quantified through data analysis, resulting in a lack of scientific data support for site selection. At the same time, the spatial correlation between the plot and surrounding high-quality planting areas is not included in the evaluation system, ignoring the synergistic or restrictive effects of the regional microenvironment on the growth of pickled mustard tuber, further reducing the scientificity and reliability of site selection. Third, although some existing agricultural land site selection methods have introduced a small number of quantitative indicators, there are problems such as inconsistent standardization of indicators, a single method for determining weights, and a lack of scoring calibration mechanisms. These issues prevent the formation of a complete technical system from indicator screening, standardization, weight calculation to comprehensive scoring and dynamic optimization, making it difficult to effectively guide the accurate selection of high-quality pickled mustard tuber planting sites.

[0003] Therefore, those skilled in the art are dedicated to providing a calculation method for selecting high-quality pickled mustard tuber planting sites that can effectively solve the above-mentioned technical problems. Summary of the Invention

[0004] To achieve the above objectives, the present invention provides a method for selecting and calculating high-quality pickled mustard tuber planting sites, comprising the following steps: S1: Identify the core indicators and perform positive and negative standardization on them; S2: Determine the initial weights using the analytic hierarchy process, adjust the weights based on the demand for the target pickled mustard tuber variety, and correct the weights based on the correlation between the indicators and the historical high-quality rate. S3: First, calculate the comprehensive score of each candidate plot using the weighted summation method, and then adjust the score by combining the spatial correlation between the plot and the surrounding verified high-quality planting plots to obtain the comprehensive score; S4: The final planting sites are determined by sorting and screening candidate plots according to the revised comprehensive score and verifying them on-site. At the same time, the parameters of the dynamic weight model are adjusted by analyzing the deviation of the high-quality rate after trial planting.

[0005] Furthermore, the core indicators include six categories: soil indicators, climate indicators, hydrological indicators, topographic indicators, ecological indicators, and historical indicators; the positive standardization and the negative standardization are used to convert the original values ​​of the indicators into values ​​within the range of [0,1]; the dynamic weights are used to dynamically reflect the weight values ​​of each core indicator to the selection of high-quality pickled mustard tuber planting areas after combining the initial weights of the analytic hierarchy process, the adjustment of the target pickled mustard tuber variety demand, and the correction of the correlation between the indicators and the historical high-quality rate. Spatial correlation is an indicator used to assess the degree of spatial correlation between candidate plots and high-quality planting areas by defining a buffer zone centered on the candidate plots and combining the number of verified high-quality planting plots and the average rate of high-quality planting within the buffer zone.

[0006] Furthermore, the formula for positively standardizing the indicators is as follows:

[0007] in Represented as the first The first candidate land parcel The original value of each indicator; and Representing the first of all candidate land parcels The maximum and minimum values ​​of the indicator; The formula for negative standardization of the indicator is:

[0008] Standardized index values All are in the range [0,1].

[0009] Furthermore, the soil indicators include soil pH value, organic matter content, available potassium content, and clay content; the climate indicators include average annual precipitation, average daily temperature during the growth cycle, and sunshine duration; the hydrological indicators include groundwater depth and irrigation water mineralization; the topographic indicators include slope and aspect; the ecological indicators include the distance to industrial pollution surrounding the planting area and soil heavy metal content; and the historical indicators include the previous average yield per mu of pickled mustard tuber in the planting area and the rate of high-quality products.

[0010] Furthermore, in S2, based on the analytic hierarchy process (AHP), an evaluation team composed of evaluation experts conducts pairwise comparisons of the six indicator layers and the importance of each indicator, constructs a judgment matrix, and obtains the initial weight vector after passing a consistency test. ; in This represents the initial weight vector determined by the analytic hierarchy process (AHP). These are the initial weight vectors. Multiple weight elements in the index, where n is the total number of indicators; Based on the quality requirements of the target pickled mustard tuber variety, a variety requirement coefficient is set. ,in For indicator serial number, Adjust the initial weights: And on Normalization was performed; correlation coefficients of historical planting data were introduced. Calculate the first The Pearson correlation coefficient between the indicator and the historical excellent product rate, if the first... If the absolute value of the Pearson correlation coefficient between a given indicator and the historical high-quality rate is ≥0.6, then the indicator has a significant impact on the quality of pickled mustard tubers. A correlation coefficient is then set. If the absolute value of the correlation coefficient If the correlation coefficient is low, then this indicator has a generally moderate impact on the quality of pickled mustard tuber. If the absolute value of the correlation coefficient is less than 0.3, it indicates that the indicator has a weak impact on the quality of pickled mustard tuber. Therefore, a correlation coefficient should be set. ; The index number represents the final dynamic weight. Normalize again; in : Represents the final dynamic weight vector obtained after correction based on historical data feedback; , , This represents the weight vector obtained after adjusting for variety demand weights. The weight elements in the table correspond to the 1st, 2nd, ... 1st weight elements, respectively. The adjusted weights of each indicator; , , This indicates that after introducing historical planting data, for the 1st, 2nd... th... The correlation coefficients for each indicator are set; furthermore, the comprehensive score for each candidate plot calculated by weighted summation in S3 specifically includes: S31: Extract the index data from S1 that have undergone positive and negative standardization, and denot it as a matrix. ,in Indicates the number of candidate land parcels. This represents the total number of core indicators. This total number is the sum of all specific indicator items under the six categories of indicators (soil, climate, hydrology, topography, ecology, and history) involved in S2, and is adjusted according to the actual number of indicator items. value, Indicates the first The first candidate land parcel The standardized values ​​of the indicators are taken in the range [0,1]; the final dynamic weight vector determined in S2 is extracted. .

[0011] Furthermore, it also includes S32, which will The core indicators are divided into six indicator layers according to the six categories of indicators in S2, denoted as G1, G2, ..., G6. Among them, G1 is the soil indicator layer, G2 is the climate indicator layer, G3 is the hydrological indicator layer, G4 is the topographic indicator layer, G5 is the ecological indicator layer, and G6 is the historical indicator layer. Representing the The index layer contains Specific indicators; From the dynamic weight vector Extract the weight subsets corresponding to each indicator layer, denoted as . The weight subsets of each indicator layer are then subjected to secondary normalization to obtain the hierarchical normalized weights. ,satisfy The quadratic normalization formula is: ; For each candidate plot Calculate the stratified scores across the six indicator layers. The formula is: ,in Indicates the first The first candidate land parcel in the Class Indicator Layer The standardized value of the indicator; The scores of the six indicator layers are then weighted and summed again according to the importance coefficient of each indicator layer to obtain the candidate land parcels. Basic composite score The calculation formula is: .

[0012] Furthermore, it also includes S33, for each candidate plot. The Each indicator, calculate its contribution. The formula is: This value reflects the actual contribution of a single indicator to the overall score of the land parcel; Based on the historical contribution data of high-quality planting plots, a contribution threshold is determined. ; Contribution threshold The method for determining the value is as follows: collect all indicator contribution data of historical high-quality planting plots, perform cluster analysis on the data using the K-means clustering algorithm, and take the lowest cluster center value in the clustering results as the value. If the historical data sample size is less than 100 groups, the median method is used, taking the median of the contribution data of all historical indicators as the median. ; For candidate land parcels All metrics, retain Let the effective indicators be denoted as the set of effective indicators. The dynamic weights corresponding to the effective indicators are normalized three times to obtain the effective weights. ,in The number of valid indicators is calculated using the following formula: Calculate the basic score after screening. The expression is .

[0013] Furthermore, based on S33, the basic scores after screening are finally calibrated to obtain the comprehensive score of the candidate plots, specifically including the candidate plots' scores. Centered on the target area, a buffer zone was established, and the number of verified high-quality planting plots within the buffer zone was counted. and average yield Spatial correlation The calculation formula is: ,in This represents the maximum number of premium planting plots within the buffer zone of all candidate plots. This represents the maximum average premium rate across all verified premium-quality planting plots. The value range is [0,1]; Determine the spatial correlation correction factor ,according to The size setting correction factor is: if If the value is ≥0.8, the spatial adaptability of the land parcel is extremely strong. =1.05; if 0.5≤ If the value is less than 0.8, then the spatial adaptability of the land parcel is moderate. =1.0; if If the value is less than 0.5, the spatial adaptability of the land parcel is relatively weak. =0.95, and finally calculate the comprehensive score; the calculation of the comprehensive score for, , The value range is [0,1]; Further, the specific steps for the deviation analysis of the superior product rate after trial planting in S4 are as follows: calculate the deviation value between the actual superior product rate and the predicted superior product rate of the trial planting plot, wherein the deviation value is the actual superior product rate minus the predicted superior product rate; if the deviation value is ≤5%, the dynamic weight model parameters do not need to be adjusted; if the deviation value is greater than 5% and less than and less than 10%, the correlation coefficient with the superior product rate is adjusted. The weight of the indicator is adjusted by ±5% for the value of 1.1; if the deviation is greater than 10%, the weight determination process in step S2 is repeated.

[0014] The present invention has the following beneficial effects: 1. This invention covers the key factors affecting the growth and quality of pickled mustard tubers. Compared with the traditional single consideration of soil fertility and irrigation conditions, it achieves a comprehensive assessment of the suitability of the plot, avoiding fluctuations in the rate of high-quality products due to missing indicators. Furthermore, it adopts positive and negative standardization formulas to uniformly convert the original values ​​of indicators of different dimensions to the [0,1] range. For example, positive standardization is suitable for indicators where the higher the value of organic matter content, the more suitable it is, while negative standardization is suitable for indicators where the lower the value of soil heavy metal content, the more suitable it is. This eliminates the interference of data differences on the assessment results and allows for direct comparative analysis of indicator data from different plots. 2. In view of the different characteristics of different varieties of pickled mustard tuber, such as the high sensitivity of crisp and tender pickled mustard tuber to the proportion of clay particles in the soil and the duration of sunshine, the variety demand coefficient of the corresponding indicators can be set to 1.1-1.2 to increase their weight ratio; high fiber pickled mustard tuber focuses on organic matter content and temperature stability, and the weight of such indicators can be adjusted accordingly to achieve the matching of variety and plot, and avoid the problem of site selection and variety demand being out of sync caused by traditional methods. 3. Divide the indicators into 6 indicator layers and set the importance coefficient of the indicator layer according to the needs of the variety. For example, in the case of crisp and tender pickled mustard tuber, the soil indicator layer coefficient is set to 0.3 (higher than 0.25 for non-crisp and tender type), and the climate indicator layer coefficient is set to 0.25. By calculating the basic score through layered weighting, we can further focus on the core needs of the variety and make the scoring results more in line with the growth characteristics of the target variety. 4. Introduce a correlation coefficient based on historical planting data. Use the Pearson correlation coefficient to quantify the correlation between indicators and historical high-quality yield, and adjust the weights accordingly. For example, if the absolute value of the correlation coefficient between an indicator and the high-quality yield is ≥0.6, the correlation coefficient is set to 1.1 to strengthen its influence on site selection; if the correlation coefficient is <0.3, it is set to 0.9 to reduce interference from non-critical indicators. 5. Delineate a buffer zone centered on the candidate plot, calculate the spatial correlation by combining the number of high-quality plots within the buffer zone with the average high-quality rate, and adjust the score by correction factors, such as the possibility that the surrounding high-quality plot concentration area may have a more suitable soil microbial environment and microclimate, to further improve the rationality of site selection and avoid the bias caused by isolated evaluation of a single plot. 6. By analyzing the deviation between the actual and predicted high-quality product rates after trial planting, the weight model parameters are dynamically adjusted. No adjustment is needed when the deviation is ≤5%, the weights of highly correlated indicators are fine-tuned when the deviation is 5%-10%, and the weights are recalculated when the deviation is >10%. As planting data accumulates, the model can continuously adapt to new situations such as changes in regional environment and variety improvement, and maintain a high accuracy in site selection in the long term. 7. Based on historical data, the contribution threshold is determined, low-contribution indicators are eliminated, and the weights are normalized three times to reduce the interference of redundant data on the calculation, improve the scoring efficiency, and avoid diluting the core requirements by unimportant indicators. Through comprehensive scoring and ranking and on-site verification, highly adaptable plots are selected first, which has the beneficial effect of avoiding the waste of resources such as seeds, fertilizers, and manpower caused by unsuitable plots in traditional site selection. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the calculation method for selecting planting sites for high-quality pickled mustard tubers according to the present invention. Detailed Implementation

[0016] The present invention will be further described below with reference to the accompanying drawings and embodiments: In the description of this invention, it should be noted that the terms "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0017] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "setting," and "connection" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0018] like Figure 1 As shown, a method for selecting a high-quality pickled mustard tuber planting site includes the following steps: S1: Identify the core indicators and perform positive and negative standardization on them; S2: Determine the initial weights using the analytic hierarchy process, adjust the weights based on the demand for the target pickled mustard tuber variety, and correct the weights based on the correlation between the indicators and the historical high-quality rate. S3: First, calculate the comprehensive score of each candidate plot using the weighted summation method, and then adjust the score by combining the spatial correlation between the plot and the surrounding verified high-quality planting plots to obtain the comprehensive score; S4: The final planting sites are determined by sorting and screening candidate plots according to the revised comprehensive score and verifying them on-site. At the same time, the parameters of the dynamic weight model are adjusted by analyzing the deviation of the high-quality rate after trial planting.

[0019] The core indicators include six categories: soil indicators, climate indicators, hydrological indicators, topographic indicators, ecological indicators, and historical indicators. These six indicators have a key impact on the growth and quality formation of high-quality pickled mustard tubers and are quantifiable parameters used to assess the suitability of candidate planting sites. The positive standardization and the negative standardization are used to convert the original value of the index into a value in the range [0,1]. The larger the index value after positive standardization and the smaller the index value after negative standardization, the more suitable the standardization treatment is for the plot to grow high-quality pickled mustard tuber.

[0020] Dynamic weights are used to dynamically reflect the weight values ​​of each core indicator to the selection of high-quality pickled mustard tuber planting areas after combining the initial weights of the analytic hierarchy process, the adjustment of the target pickled mustard tuber variety demand, and the correction of the correlation between the indicators and the historical high-quality rate. Spatial correlation is assessed by defining a buffer zone centered on the candidate plots. When determining the size of the buffer zone, it is necessary to consider the actual geographical characteristics of pickled mustard tuber cultivation and the scale of regional cultivation. The preferred range for the buffer zone radius is 500-2000 meters. If the cultivation area is a plain with contiguous planting, the buffer zone radius can be set to 1500-2000 meters. If the cultivation area is a mountainous area with scattered plots, the buffer zone radius can be set to 500-1000 meters. The number of verified high-quality planting plots and the average rate of high-quality products within the buffer zone are used to evaluate the degree of spatial correlation between the candidate plots and the high-quality planting areas.

[0021] The formula for positive standardization of the indicators is:

[0022] in Represented as the first The first candidate land parcel The original value of each indicator; and Representing the first of all candidate land parcels The maximum and minimum values ​​of the indicator; The formula for negative standardization of the indicator is:

[0023] Standardized index values All are in the range [0,1].

[0024] The soil indicators include soil pH, organic matter content, available potassium content, and clay content; the climate indicators include average annual precipitation, average daily temperature during the growth cycle, and sunshine duration; the hydrological indicators include groundwater depth and irrigation water mineralization; the topographic indicators include slope and aspect; the ecological indicators include the distance to industrial pollution surrounding the planting area and soil heavy metal content; and the historical indicators include the previous average yield per mu of pickled mustard tuber in the planting area and the rate of high-quality products.

[0025] In step S2, based on the analytic hierarchy process (AHP), an evaluation team composed of assessment experts compares the importance of each of the six indicator layers pairwise, constructs a judgment matrix, and obtains the initial weight vector after passing a consistency test. ; in This represents the initial weight vector determined by the analytic hierarchy process (AHP). These are the initial weight vectors. Multiple weight elements in the index, where n is the total number of indicators; Based on the quality requirements of the target pickled mustard tuber variety, such as the soil clay content and sunshine duration for crisp and tender pickled mustard tuber, and the organic matter content and growth cycle temperature for high-fiber pickled mustard tuber, a variety requirement coefficient is set. ,in For indicator serial number, Adjust the initial weights: And on Perform normalization; ensure the total weights are 1.

[0026] Introducing the correlation coefficient of historical planting data Calculate the first The Pearson correlation coefficient between the indicator and the historical excellent product rate, if the first... If the absolute value of the Pearson correlation coefficient between a given indicator and the historical high-quality rate is ≥0.6, then the indicator has a significant impact on the quality of pickled mustard tubers. A correlation coefficient is then set. If the absolute value of the correlation coefficient If the correlation coefficient is low, then this indicator has a generally moderate impact on the quality of pickled mustard tuber. If the absolute value of the correlation coefficient is less than 0.3, it indicates that the indicator has a weak impact on the quality of pickled mustard tuber. Therefore, a correlation coefficient should be set. ; The index number represents the final dynamic weight. Normalize again; in : Represents the final dynamic weight vector obtained after feedback and correction of historical data; used for subsequent comprehensive scoring of candidate plots, reflecting the importance of each indicator in the selection of high-quality pickled mustard tuber planting sites after combining historical planting data.

[0027] , , This represents the weight vector obtained after adjusting for variety demand weights. The weight elements in the table correspond to the 1st, 2nd, ... 1st weight elements, respectively. The adjusted weights of each indicator; , , This indicates that after introducing historical planting data, for the 1st, 2nd... th... The correlation coefficient is set for the first indicator; this coefficient is based on the first... The correlation coefficient between the indicator and the historical excellent product rate is used to determine the value: if the absolute value of the correlation coefficient is ≥0.6, =1.1; if the absolute value of the correlation coefficient is 1.1; , =1.0; if the absolute value of the correlation coefficient is <0.3, =0.9.

[0028] The calculation of the comprehensive score for each candidate land parcel using the weighted summation method in S3 specifically includes: S31: Extract the index data from S1 that have undergone positive and negative standardization, and denot it as a matrix. ,in Indicates the number of candidate land parcels. This represents the total number of core indicators. This total number is the sum of the specific indicator items under the six categories of indicators (soil, climate, hydrology, topography, ecology, and history) involved in S2. There are 4 soil indicators, 3 climate indicators, 2 hydrological indicators, 2 topographic indicators, 2 ecological indicators, and 2 historical indicators, totaling 15 items. This number may be adjusted based on the actual number of indicator items. value, Indicates the first The first candidate land parcel The standardized values ​​of the indicators are taken in the range [0,1]; the final dynamic weight vector determined in S2 is extracted. .

[0029] It also includes S32, which will The core indicators are divided into six indicator layers according to the six categories of indicators in S2, denoted as G1, G2, ..., G6. Among them, G1 is the soil indicator layer, G2 is the climate indicator layer, G3 is the hydrological indicator layer, G4 is the topographic indicator layer, G5 is the ecological indicator layer, and G6 is the historical indicator layer. Representing the The index layer contains Specific indicators; From the dynamic weight vector Extract the weight subsets corresponding to each indicator layer. Recorded as The weight subsets of each indicator layer are then subjected to secondary normalization to obtain the hierarchical normalized weights. ,satisfy The quadratic normalization formula is: ; For each candidate plot Calculate the stratified scores across the six indicator layers. The formula is: ,in Indicates the first The first candidate land parcel in the Class Indicator Layer The standardized values ​​of the indicators are obtained; the stratified scores of the six indicator layers are then weighted and summed again according to the indicator layer importance coefficient to obtain the candidate plots. Basic composite score Among them, the importance coefficient of the indicator layer The importance coefficient of the indicator layer is determined based on the core needs of the target pickled mustard tuber variety. Must meet and For example, in the cultivation scenario of crisp and tender pickled mustard tuber, let's set... (Soil index layer) = 0.3, (Climate index layer) = 0.25, (Hydrological index layer) = 0.2 (Topographic index layer) = 0.1 (Ecological indicator layer) = 0.1 (Historical indicator layer) = 0.05; This is used to determine the importance coefficient of the indicator layer. At that time, in addition to the scene of crisp and tender pickled mustard tuber, set up (Soil index layer) = 0.25, (Climate index layer) = 0.3, (Hydrological index layer) = 0.18, (Topographic index layer) = 0.12, (Ecological indicator layer) = 0.1, (Historical indicator layer) = 0.05, to meet the selection requirements for different varieties of pickled mustard tuber planting areas. The calculation formula is as follows: .

[0030] It also includes S33, for each candidate parcel The Each indicator, calculate its contribution. The formula is: This value reflects the actual contribution of a single indicator to the overall score of the land parcel; Based on the historical contribution data of high-quality planting plots, a contribution threshold is determined. ; Contribution threshold The method for determining the value is as follows: collect all indicator contribution data of historical high-quality planting plots, perform cluster analysis on the data using the K-means clustering algorithm, and take the lowest cluster center value in the clustering results as the value. If the historical data sample size is less than 100 groups, the median method is used, taking the median of the contribution data of all historical indicators as the median. ; For candidate land parcels All metrics, retain Let the effective indicators be denoted as the set of effective indicators. The dynamic weights corresponding to the effective indicators are normalized three times to obtain the effective weights. ,in The number of valid indicators is calculated using the following formula: Calculate the basic score after screening. The expression is .

[0031] Based on S33, the basic scores after screening are finally calibrated to obtain the comprehensive score of the candidate plots, specifically including the candidate plots' scores. Centered on the target area, a buffer zone was established, and the number of verified high-quality planting plots within the buffer zone was counted. and average yield Spatial correlation The calculation formula is: ,in This represents the maximum number of premium planting plots within the buffer zone of all candidate plots. This represents the maximum average premium rate across all verified premium-quality planting plots. The maximum value is taken after counting the number of verified high-quality planting plots within the buffer zone of all candidate plots. By collecting the average premium yield data from all verified premium planting plots and taking the maximum value, the calculation logic is made clear. The value range is [0,1]; Determine the spatial correlation correction factor ,according to The size setting correction factor is: if If the value is ≥0.8, the spatial adaptability of the land parcel is extremely strong. =1.05; if 0.5≤ If the value is less than 0.8, then the spatial adaptability of the land parcel is moderate. =1.0; if If the value is less than 0.5, the spatial adaptability of the land parcel is relatively weak. =0.95, and finally calculate the comprehensive score; the calculation of the comprehensive score for, , The value ranges from [0,1]. A higher score indicates that the candidate plot is more suitable for planting high-quality pickled mustard tubers.

[0032] The specific steps for the deviation analysis of the superior product rate after trial planting in S4 are as follows: Calculate the deviation between the actual superior product rate and the predicted superior product rate of the trial planting plot. The deviation is the actual superior product rate minus the predicted superior product rate. If the deviation is ≤5%, the dynamic weight model parameters do not need to be adjusted. If the deviation is greater than 5% and less than or ≤10%, the correlation coefficient with the superior product rate is adjusted. The weight of the indicator is adjusted by ±5% for the value of 1.1; if the deviation is greater than 10%, the weight determination process in step S2 is repeated.

[0033] This invention identifies six categories of core indicators that play a crucial role in the growth and quality of premium pickled mustard tubers, comprising 15 quantifiable parameters. These include: soil indicators (such as soil pH, organic matter content, available potassium content, and clay content) to determine soil fertility and structure, influencing root development and nutrient absorption; climate indicators (including average annual precipitation, average daily temperature during the growth cycle, and sunshine duration) to regulate photosynthesis, growth rate, and quality formation; hydrological indicators (including groundwater depth and irrigation water mineralization) to ensure adequate water supply and prevent excessive or poor-quality water from negatively impacting growth; topographic indicators (such as slope and aspect) to affect drainage, sunlight reception, and ease of cultivation; ecological indicators (such as distance from industrial pollution sources and soil heavy metal content) to mitigate pollution risks and ensure the safety and quality of the pickled mustard tubers; and historical indicators (such as the previous average yield per acre and the rate of premium-quality pickled mustard tubers in the planting area) to provide historical reference. The evaluation process is as follows: The original values ​​of the indicators are converted into standardized values ​​within the range of [0,1] to eliminate dimensional differences. Positive standardization is suitable for indicators where larger values ​​indicate stronger suitability, such as organic matter content and sunshine duration. Negative standardization is suitable for indicators where smaller values ​​indicate stronger suitability, such as soil heavy metal content and irrigation water mineralization. A three-step method—initial weight calculation, variety requirement adjustment, and historical data correction—is used to determine a weight vector that dynamically reflects the importance of each indicator. An evaluation expert group is formed to compare the importance of the six major indicator categories and 15 specific indicators pairwise, constructing a judgment matrix. The judgment matrix is ​​then subjected to a consistency check to ensure logical consistency, and the initial weight vector is obtained after passing the check. A variety requirement coefficient is set based on the core quality requirements of the target pickled mustard tuber variety, with a value ranging from 0.8 to 1.2. For example, for crisp and tender pickled mustard tubers, the focus is on the proportion of clay particles in the soil and the duration of sunshine, and the variety requirement coefficient for the corresponding indicators can be set to 1.1-1.2; for high-fiber pickled mustard tubers, the focus is on the organic matter content and the temperature during the growth cycle, and the variety requirement coefficient for the corresponding indicators can be set to 1.1-1.2. After adjusting the initial weights using the variety demand coefficient, the adjusted weights are normalized to ensure the total weights equal to 1. The Pearson correlation coefficient between each indicator and the historical high-quality rate is calculated, and a correlation coefficient is set based on the absolute value of the coefficient. If the absolute value of the correlation coefficient is not less than 0.6, it indicates that the indicator has a significant impact on quality, and the correlation coefficient is set to 1.1. If the absolute value of the correlation coefficient is between 0.3 and 0.6, it indicates that the indicator has a moderate impact on quality, and the correlation coefficient is set to 1.0. If the absolute value of the correlation coefficient is less than 0.3, it means that the indicator has a weak impact on quality, and the correlation coefficient is set to 0.9. The weights adjusted for variety demand are corrected using the correlation coefficient, and after normalization, the final dynamic weight vector is obtained. The final comprehensive score of the candidate plots is obtained through a three-level calculation process: basic score calculation, effective indicator screening, and spatial correlation correction. The 15 core indicators are divided into 6 indicator layers according to six categories. A subset of weights corresponding to each indicator layer is extracted from the dynamic weights and subjected to secondary normalization to ensure that the sum of weights within each indicator layer is 1. Then, for each candidate plot, the score of each indicator layer is calculated according to the stratified weights. Next, the importance coefficient of the indicator layer is determined according to the variety requirements. This coefficient must sum to 1 and be between 0 and 1. Specifically, for the crisp and tender pickled mustard tuber scenario, the importance coefficients are set as follows: soil indicator layer 0.3, climate indicator layer 0.25, hydrological indicator layer 0.2, topographic indicator layer 0.1, ecological indicator layer 0.1, and historical indicator layer 0.05; for the non-crisp and tender pickled mustard tuber scenario, the values ​​are: soil indicator layer 0.25, climate indicator layer 0.3, hydrological indicator layer 0.18, topographic indicator layer 0.12, ecological indicator layer 0.1, and historical indicator layer 0.05. The basic comprehensive score is obtained by weighted summation according to the importance coefficients of the indicator layers. The actual contribution of a single indicator to the overall score of a plot is calculated by multiplying the indicator's dynamic weight by its standardized value. Then, a contribution threshold is determined. If the historical sample size of contribution data for high-quality planting plots is no less than 100 groups, K-means clustering is used, and the lowest cluster center value is taken as the threshold. If the sample size is less than 100 groups, the median method is used, and the median of all historical data is taken as the threshold. Indicators with a contribution value not lower than the threshold are retained as valid indicators. The dynamic weights corresponding to the valid indicators are normalized three times, and then the weighted sum of the normalized weights and the standardized value of the indicator is calculated to obtain the basic score after screening. A buffer zone is delineated centered on the candidate plots. The buffer zone radius for contiguous planting areas in plains is set at 1500-2000 meters, and for scattered planting areas in mountainous areas, it is set at 500-1000 meters. The number of verified high-quality planting plots and the average rate of high-quality production within the statistical buffer were determined, and the maximum number and maximum average rate of high-quality production among all candidate plots were identified. Based on this, spatial correlation was calculated, with values ​​ranging from 0 to 1. A higher value indicates a stronger association between the plot and the high-quality planting area. A spatial correlation correction factor was determined based on the spatial correlation. If the spatial correlation is not less than 0.8, the plot has extremely strong spatial suitability, and the correction factor is set to 1.05; if the spatial correlation is between 0.5 and 0.8, the plot has moderate spatial suitability, and the correction factor is set to 1.0; if the spatial correlation is less than 0.5, the plot has weak spatial suitability, and the correction factor is set to 0.95. The correction factor was multiplied by the basic score after screening to obtain the final comprehensive score, with a score ranging from 0 to 1. A higher score indicates a more suitable plot for high-quality pickled mustard tuber cultivation. Candidate plots are ranked from highest to lowest based on their final comprehensive scores, with high-scoring plots being prioritized. High-scoring plots undergo on-site verification to confirm the authenticity of indicators, such as soil sampling and testing, and on-site investigation of pollution conditions, to determine the final planting sites. The deviation between the actual and predicted high-quality yield rates of the trial plots is calculated; if the deviation is less than 5%, no model parameter adjustments are needed. If the deviation is greater than 5% but less than 10%, the weights of indicators with a correlation coefficient of 1.1 are fine-tuned by ±5%. If the deviation is greater than 10%, the dynamic weight determination step is repeated to update the weight vector and optimize the model.

[0034] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A calculation method for selecting planting sites for high-quality pickled mustard tuber, characterized in that, Includes the following steps: S1: Identify the core indicators and perform positive and negative standardization on them; S2: Determine the initial weights using the analytic hierarchy process, adjust the weights based on the demand for the target pickled mustard tuber variety, and correct the weights based on the correlation between the indicators and the historical high-quality rate. S3: First, calculate the comprehensive score of each candidate plot using the weighted summation method, and then adjust the score by combining the spatial correlation between the plot and the surrounding verified high-quality planting plots to obtain the comprehensive score; S4: The final planting sites are determined by sorting and screening candidate plots according to the revised comprehensive score and verifying them on-site. At the same time, the parameters of the dynamic weight model are adjusted by analyzing the deviation of the high-quality rate after trial planting.

2. The method for selecting and calculating planting sites for premium pickled mustard tuber as described in claim 1, characterized in that: The core indicators include six categories: soil indicators, climate indicators, hydrological indicators, topographic indicators, ecological indicators, and historical indicators. The positive standardization and the negative standardization are used to convert the original value of the index into a value in the range [0,1]. Dynamic weights are used to dynamically reflect the weight values ​​of each core indicator to the selection of high-quality pickled mustard tuber planting areas after combining the initial weights of the analytic hierarchy process, the adjustment of the target pickled mustard tuber variety demand, and the correction of the correlation between the indicators and the historical high-quality rate. Spatial correlation is an indicator used to assess the degree of spatial correlation between candidate plots and high-quality planting areas by defining a buffer zone centered on the candidate plots and combining the number of verified high-quality planting plots and the average rate of high-quality planting within the buffer zone.

3. The method for selecting and calculating planting sites for high-quality pickled mustard tuber as described in claim 2, characterized in that: The formula for positive standardization of the indicators is: ; in Represented as the first The first candidate land parcel The original value of each indicator; and Representing the first of all candidate land parcels The maximum and minimum values ​​of the indicator; The formula for negative standardization of the indicator is: ; Standardized index values All are in the range [0,1].

4. The method for selecting and calculating planting sites for high-quality pickled mustard tuber as described in claim 3, characterized in that: The soil indicators include soil pH, organic matter content, available potassium content, and clay content; the climate indicators include average annual precipitation, average daily temperature during the growth cycle, and sunshine duration; the hydrological indicators include groundwater depth and irrigation water mineralization; the topographic indicators include slope and aspect; the ecological indicators include the distance to industrial pollution surrounding the planting area and soil heavy metal content; and the historical indicators include the previous average yield per mu of pickled mustard tuber in the planting area and the rate of high-quality products.

5. The method for selecting and calculating planting sites for high-quality pickled mustard tuber as described in claim 4, characterized in that: In step S2, based on the analytic hierarchy process (AHP), an evaluation team composed of assessment experts compares the importance of each of the six indicator layers pairwise, constructs a judgment matrix, and obtains the initial weight vector after passing a consistency test. ; in This represents the initial weight vector determined by the analytic hierarchy process (AHP). These are the initial weight vectors. Multiple weight elements in the index, where n is the total number of indicators; Based on the quality requirements of the target pickled mustard tuber variety, a variety requirement coefficient is set. ,in For indicator serial number, Adjust the initial weights: And on Perform normalization processing; Introducing the correlation coefficient of historical planting data Calculate the first The Pearson correlation coefficient between the indicator and the historical excellent product rate, if the first... If the absolute value of the Pearson correlation coefficient between a given indicator and the historical high-quality rate is ≥0.6, then the indicator has a significant impact on the quality of pickled mustard tubers. A correlation coefficient is then set. If the absolute value of the correlation coefficient If the correlation coefficient is low, then this indicator has a generally moderate impact on the quality of pickled mustard tuber. If the absolute value of the correlation coefficient is less than 0.3, it indicates that the indicator has a weak impact on the quality of pickled mustard tuber. Therefore, a correlation coefficient should be set. ; The index number represents the final dynamic weight. Normalize again; in : Represents the final dynamic weight vector obtained after correction based on historical data feedback; , , This represents the weight vector obtained after adjusting for variety demand weights. The weight elements in the table correspond to the 1st, 2nd, ... 1st weight elements, respectively. The adjusted weights of each indicator; , , This indicates that after introducing historical planting data, for the 1st, 2nd... th... The correlation coefficient is set for each indicator.

6. The method for selecting and calculating planting sites for high-quality pickled mustard tuber as described in claim 5, characterized in that: The calculation of the comprehensive score for each candidate land parcel using the weighted summation method in S3 specifically includes: S31: Extract the index data from S1 that have undergone positive and negative standardization, and denot it as a matrix. ,in Indicates the number of candidate land parcels. This represents the total number of core indicators, which is the sum of the specific indicator items under the six categories of indicators (soil, climate, hydrology, topography, ecology, and history) involved in S2; adjustments will be made based on the actual number of indicator items. value, Indicates the first The first candidate land parcel The standardized values ​​of the indicators are taken in the range [0,1]; the final dynamic weight vector determined in S2 is extracted. .

7. The method for selecting and calculating planting sites for premium pickled mustard tuber as described in claim 6, characterized in that: It also includes S32, which will The core indicators are divided into six indicator layers according to the six categories of indicators in S2, denoted as G1, G2, ..., G6. Among them, G1 is the soil indicator layer, G2 is the climate indicator layer, G3 is the hydrological indicator layer, G4 is the topographic indicator layer, G5 is the ecological indicator layer, and G6 is the historical indicator layer. Representing the The index layer contains Specific indicators; From the dynamic weight vector Extract the weight subsets corresponding to each indicator layer. Recorded as The weight subsets of each indicator layer are then subjected to secondary normalization to obtain the hierarchical normalized weights. ,satisfy The quadratic normalization formula is: ; For each candidate plot Calculate the stratified scores across the six indicator layers. The formula is: ,in Indicates the first The first candidate land parcel in the Class Indicator Layer The standardized value of the indicator; The scores of the six indicator layers are then weighted and summed again according to the importance coefficient of each indicator layer to obtain the candidate land parcels. Basic composite score The calculation formula is: .

8. The method for selecting and calculating planting sites for premium pickled mustard tuber as described in claim 7, characterized in that: It also includes S33, for each candidate parcel The Each indicator, calculate its contribution. , The formula is: ; Based on the historical contribution data of high-quality planting plots, a contribution threshold is determined. ; Contribution threshold The method for determining the value is as follows: collect all indicator contribution data of historical high-quality planting plots, perform cluster analysis on the data using the K-means clustering algorithm, and take the lowest cluster center value in the clustering results as the value. If the historical data sample size is less than 100 groups, the median method is used, taking the median of the contribution data of all historical indicators as the median. ; For candidate land parcels All metrics, retain Let the effective indicators be denoted as the set of effective indicators. The dynamic weights corresponding to the effective indicators are normalized three times to obtain the effective weights. ,in The number of valid indicators is calculated using the following formula: Calculate the basic score after screening. The expression is .

9. The method for selecting planting sites for premium pickled mustard tuber as described in claim 8, characterized in that: Based on S33, the basic scores after screening are finally calibrated to obtain the comprehensive score of the candidate plots, specifically including the candidate plots' scores. Centered on the target area, a buffer zone was established, and the number of verified high-quality planting plots within the buffer zone was counted. and average yield Spatial correlation The calculation formula is: ,in This represents the maximum number of premium planting plots within the buffer zone of all candidate plots. This represents the maximum average premium rate across all verified premium-quality planting plots. The value range is [0,1]; Determine the spatial correlation correction factor ,according to The size setting correction factor is: if If the value is ≥0.8, the spatial adaptability of the land parcel is extremely strong. =1.05; if 0.5≤ If the value is less than 0.8, then the spatial adaptability of the land parcel is moderate. =1.0; if If the value is less than 0.5, the spatial adaptability of the land parcel is relatively weak. =0.95, and finally calculate the comprehensive score; the calculation of the comprehensive score for, , The value range is [0,1].

10. The method for selecting and calculating planting sites for high-quality pickled mustard tuber as described in claim 9, characterized in that: The specific steps for the deviation analysis of the superior product rate after trial planting in S4 are as follows: Calculate the deviation between the actual superior product rate and the predicted superior product rate of the trial planting plot. The deviation is the actual superior product rate minus the predicted superior product rate. If the deviation is ≤5%, the dynamic weight model parameters do not need to be adjusted; if the deviation is greater than 5% and less than or ≤10%, the correlation coefficient with the superior product rate is adjusted. The weight of the indicator is adjusted by ±5% for the value of 1.1; if the deviation is greater than 10%, the weight determination process in step S2 is repeated.

Images