Tobacco planting soil fertility evaluation method

Abstract

The invention discloses a tobacco planting soil fertility evaluation method, and relates to the technical field of soil fertility evaluation methods, and the method comprises the following steps: determining a total data set of soil evaluation indexes, determining a minimum data set, and calculating the weight of each evaluation index in the minimum data set through an entropy weight method; a membership function is constructed, a soil fertility suitability index method is adopted to construct a soil fertility evaluation model, and a soil fertility suitability index SFI is obtained through calculation. The method has the advantages that the influence of various evaluation indexes on the soil fertility and the dynamic adjustment of the critical value and the optimal value of the membership function are comprehensively considered, the soil fertility evaluation model can be dynamically adjusted along with real-time monitoring data, and the evaluation result is more accurate. The soil fertility evaluation model can be used for evaluating the soil fertility of a to-be-detected area, and can also be used as a basis for improving soil.

Description

Technical Field

[0001] The invention relates to the technical field of soil fertility evaluation methods, and in particular to a tobacco-planting soil fertility evaluation method. Background Art

[0002] The long-term sustainable development of modern tobacco agriculture is closely related to soil environmental conditions. The evaluation of tobacco-growing soil fertility is of great significance for creating a good soil environment to promote tobacco growth and development. However, most of the current tobacco-growing soil fertility evaluation systems use a single evaluation method, which is limited to the static changes of a single indicator of soil fertility. Due to the differences in crops planted, crops have different needs for soil nutrient distribution and fertility. Therefore, it is difficult to achieve the best evaluation system adapted to the target area and crops using the existing single soil fertility evaluation method, resulting in inaccurate soil fertilizer evaluation. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a tobacco-growing soil fertility evaluation method, which takes into account the influence of multiple evaluation indicators on soil fertility and the dynamic adjustment of the critical value and optimal value of the membership function, and the evaluation result is more accurate.

[0004] In order to solve the above technical problems, the technical solution of the present invention is a method for evaluating tobacco-growing soil fertility, which collects soil samples from the area to be tested, detects the test data of each evaluation index in the minimum data set MDS of each sample, and inputs the test data into a soil fertility evaluation model for fertility evaluation; The method for constructing the soil fertility evaluation model comprises the following steps: S1, confirm the full data set TDS of soil evaluation indicators; S2. Determine the minimum data set MDS: S3, using the entropy weight method to calculate the weight of each evaluation index in the minimum data set; S4, constructing a membership function: according to the positive response or negative response of each evaluation index to soil fertility, determining the type of membership function adapted to each evaluation index, and then determining the initial critical value and optimal value of each membership function, thereby obtaining the membership function corresponding to each evaluation index; S5, calculating the membership value: calculating the membership value of each evaluation index; S6. Use the soil fertility suitability index method to construct a soil fertility evaluation model and calculate the soil fertility suitability index SFI.

[0005] Furthermore, the method of determining the minimum data set MDS in S2 comprises the following steps: S21, evaluation index grouping: perform principal component analysis on all evaluation indicators in the full data set, select principal components that meet the conditions, and group the evaluation indicators according to their loads on different principal components; S22, screening evaluation indicators: S221, according to the Norm value of each evaluation index, eliminate the evaluation index whose Norm value is less than 10% Normmax; wherein Normmax refers to the maximum value of the calculated Norm values ​​of all evaluation indexes; S222, for the selected indicators, calculate the correlation coefficient between the evaluation indicators in each group. When the correlation between different evaluation indicators in the same group is less than or equal to 0.3, all evaluation indicators in the group enter the minimum data set MDS; when the correlation between two evaluation indicators in the same group is greater than 0.3, the evaluation indicator with a relatively large Norm value among the two evaluation indicators is selected to enter the minimum data set MDS; Furthermore, the full data set TDS includes: pH, SOM, AN, AP, AK, Zn, B, Cl, and Mg of the soil; and the minimum data set MDS includes: pH, SOM, AP, AK, B, and Cl of the soil.

[0006] Furthermore, the condition for screening the principal components in step S21 is to select the principal components whose cumulative contribution rate is greater than or equal to 80% or to select the principal components whose eigenvalue is greater than 1.

[0007] Furthermore, the specific method for grouping the evaluation indicators in step S21 is: if the load of the evaluation indicator on only one principal component is greater than or equal to 0.5 or the loads on all principal components are less than 0.5, then the evaluation indicator is classified into the principal component corresponding to the maximum load value, and all the evaluation indicators classified into the same principal component are judged as a group; if the load of the evaluation indicator on at least two principal components is greater than or equal to 0.5, then the maximum correlation coefficient between the evaluation indicator and other evaluation indicators in the group is calculated, and the indicator is classified into a group with a low maximum correlation coefficient.

[0008] Furthermore, the calculation method for determining the weight by the entropy weight method in step S3 is: ; Where, k = 1 / ln(m); ;i=1,2,...,m; j=1,2,...,n; Represents the original data of i samples and j evaluation indicators; represent After standardized data; , where W jis the weight of the j-th indicator; j=1,2,…,n.

[0009] The above will Standardized processing to obtain The process is: If the evaluation index is a positive index, that is, the larger the index value, the better the index, then the standardized formula is: ; If the evaluation index is a negative index, that is, the smaller the index value, the better the index, the standardized formula is: ; in Represents all sample data of the jth indicator.

[0010] Furthermore, the AP, AK, and B contents are matched with S-type membership functions; and the pH value, SOM, and Cl are matched with parabolic membership functions.

[0011] Furthermore, the calculation formula for constructing a soil fertility evaluation model using the soil fertility suitability index method in S6 is: ; j = 1, 2, ..., n; Where: SFI represents soil fertility suitability index; N j represents the membership value of the jth evaluation index; W j Represents the weight of the jth evaluation index.

[0012] Furthermore, in step S4, the critical value and the optimal value of the membership function corresponding to each evaluation index are dynamically adjusted, and the method of dynamic adjustment includes the following steps: 1. Analyze the real-time monitoring data of each evaluation indicator and determine whether it exceeds the range of historical monitoring data; 2. If the result of step 1 is exceeded, calculate the ratio of the real-time monitoring data exceeding the limit value of the historical monitoring data range; 3. Set the critical value and optimal value adjustment gradient of each membership function in advance, and set the corresponding relationship between the adjustment gradient and the excess ratio; Fourth, according to the corresponding relationship between the excess ratio and the adjustment gradient, the critical value and the optimal value of each membership function are re-determined to obtain a new membership function; 5. Compare the accuracy of the new membership function and the original membership function. If the new membership function has higher accuracy, use the new membership function to replace the original membership function; if the original membership function has higher accuracy, do not update the membership function.

[0013] Furthermore, the method for determining the accuracy in step five includes comparative experiment method, cross-validation method, expert evaluation method, actual application effect evaluation or statistical test method.

[0014] Beneficial effects of the present invention: The present invention constructs a soil fertility evaluation model, comprehensively considers the influence of multiple evaluation indicators on soil fertility, and proposes a screening method for a minimum data set, thereby avoiding redundancy between indicators. The present invention also takes into account the dynamic adjustment of the critical value and the optimal value of the membership function in the soil fertility evaluation model, so that the soil fertility evaluation model can be dynamically adjusted with real-time monitoring data, and the evaluation result is more accurate. The soil fertility evaluation model can be used to evaluate the soil fertility of the area to be tested, and can also be used as a basis for improving the soil. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The principal component analysis and Norm value calculation results of the embodiment; Figure 2 The correlation coefficient results between the 9 evaluation indicators in the full data set in the embodiment; Figure 3 are the initial critical values ​​and optimal values ​​of the S-type and parabolic membership functions matched by each evaluation index in the embodiment. DETAILED DESCRIPTION

[0016] The specific embodiments of the present invention are further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0017] A tobacco-growing soil fertility evaluation method includes collecting soil samples from the area to be tested, testing the test data of each evaluation index in the minimum data set MDS of each sample, and inputting the test data into a soil fertility evaluation model for fertility evaluation; The method for constructing the soil fertility evaluation model comprises the following steps: S1. Confirm the full data set TDS of soil evaluation indicators. In this embodiment, the full data set TDS includes: pH, SOM, AN, AP, AK, Zn, B, Cl, and Mg of the soil.

[0018] The effectiveness of soil nutrients and their morphological transformation are closely related to soil pH. The optimum soil pH range for tobacco growth is 5.5-6.5. SOM is an important source of soil nutrition for tobacco. Its content directly affects the growth, development, yield and quality of tobacco, and plays a very important role in improving soil physical and chemical properties and microbial energy supply. AP is one of the essential macronutrients for tobacco. Due to the low utilization rate of phosphorus fertilizer in flue-cured tobacco, tobacco-growing soil has a more serious phosphorus surplus than general farmland. Tobacco is a potassium-loving crop. AK, as an important quality element of tobacco, restricts the overall improvement of tobacco leaf quality. AN is a key factor limiting the productivity of agricultural ecosystems, and has the dual effects of promoting productivity and affecting environmental quality. Zn is a component and activator of multiple enzymes in flue-cured tobacco, and is involved in the synthesis of chlorophyll, protein and auxin. Zn deficiency will cause tobacco plants to be short and grow slowly. B can increase the transpiration rate and photosynthesis of leaves. B deficiency in tobacco plants will cause the terminal buds to die and the leaves to shrink and curl. Tobacco is still a Cl-sensitive crop. Cl Too high a content will reduce the quality of flue-cured tobacco; Mg is an important component of chlorophyll and is essential for tobacco photosynthesis. Mg deficiency will hinder chlorophyll synthesis and accelerate decomposition, thereby reducing photosynthesis function.

[0019] In this embodiment, the sampling site is located in Honghe Hani and Yi Autonomous Prefecture, Yunnan Province, China, which belongs to the plateau subtropical monsoon climate zone. Honghe Prefecture is one of the high-quality tobacco producing areas in the country, with outstanding "sweet and fragrant" style and excellent "yellow, bright and soft" quality. In order to ensure the reliability of each annual data, soil sample collection and sample determination are organized by Honghe Prefecture Tobacco Company. The surface 0-20cm soil of 6 counties (cities) in Honghe Prefecture, including Mile City, Luxi County, Jianshui County, Shiping County, Gejiu City, and Mengzi City, is collected. Sampling is completed in March-April each year. The number of sampling points in each county (city) from 2011 to 2021 is shown in the following table: Statistics of sampling points in each county (city) years Maitreya Luxi Shiping Jianshui Mengzi Gejiu All states 2011 64 50 50 50 31 10 255 2012 79 50 54 60 40 15 298 2013 65 60 45 50 12 10 242 2014 87 76 42 39 23 10 277 2015 71 70 50 45 30 13 279 2016 72 70 50 45 30 13 280 2017 240 240 165 70 50 15 780 2018 251 246 166 76 68 21 828 2019 192 226 176 76 54 21 755 2020 263 231 181 83 66 22 846 2021 361 354 218 124 80 18 1155 S2. Determine the minimum data set MDS: When evaluating the difference in soil fertility, the more evaluation indicators are selected, the more comprehensive the soil fertility can be reflected. However, there is generally correlation or even overlap between the various soil attributes, which causes redundancy between indicators and increases the cost of data acquisition. Therefore, it is necessary to screen soil indicators when evaluating soil fertility. Generally, appropriate evaluation indicator screening methods are selected according to different evaluation purposes and regions to obtain the minimum data set MDS; S21. Grouping of evaluation indicators: Perform principal component analysis on all evaluation indicators in the full data set, select the principal components that meet the conditions, and group the evaluation indicators according to the loads of each evaluation indicator on different principal components; the condition for selecting the principal component is to select the principal component with a cumulative contribution rate greater than or equal to 80%, and the condition can also be adjusted to the principal component with an eigenvalue greater than 1 as needed. The specific method for grouping each evaluation indicator is as follows: if the load of the evaluation indicator on only one principal component is greater than or equal to 0.5 or the loads on all principal components are less than 0.5, then the evaluation indicator is classified into the principal component corresponding to the maximum load value, and all evaluation indicators classified into the same principal component are judged as a group; if the load of the evaluation indicator on at least two principal components is greater than or equal to 0.5, then calculate the maximum correlation coefficient between the evaluation indicator and other evaluation indicators in the group, and classify the indicator into a group with a low maximum correlation coefficient.

[0020] In this example, the RStudio 4.2.0 software was used to perform principal component analysis on the 9 preliminary evaluation indicators, and the 9 evaluation indicators were divided into 5 groups according to the load of the indicators on different PCs. Figure 1 According to the above grouping method, the 9 evaluation indicators are divided into 5 groups, the first group is SOM and AN, the second group is pH, AK, Mg, the third group is Cl, the fourth group is AP, Zn, and the fifth group is B.

[0021] S22, screening evaluation indicators: S221. Eliminate evaluation indicators whose Norm values ​​are less than 10% Normmax according to the Norm values ​​of the evaluation indicators; wherein Normmax refers to the maximum value of the calculated Norm values ​​of all evaluation indicators; in this embodiment, the Normmax value is 1.07, and the Norm values ​​of all indicators are greater than 10% Normmax.

[0022] S222, for the selected indicators, calculate the correlation coefficient between the evaluation indicators in each group. When the correlation between different evaluation indicators in the same group is less than or equal to 0.3, all evaluation indicators in the group enter the minimum data set MDS; when the correlation between two evaluation indicators in the same group is greater than 0.3, the evaluation indicator with a relatively large Norm value among the two evaluation indicators is selected to enter the minimum data set MDS; In this embodiment, the correlation coefficient results between the 9 evaluation indicators are as follows: Figure 2As shown. In the first group, the correlation between SOM and AN is greater than 0.3, and the Norm of SOM is greater than AN, so AN is eliminated and SOM is included in the minimum data set. In the second group, the correlation between pH and Mg is greater than 0.3, and the Norm of pH is greater than Mg, so Mg is eliminated and pH is included in the minimum data set. In the fourth group, the correlation between Zn and AP is greater than 0.3, and the Norm of AP is greater than Zn, so Zn is eliminated and AP is included in the minimum data set. The final minimum data set MDS includes: pH, SOM, AP, AK, B, Cl, a total of 6 evaluation indicators.

[0023] S3. Use the entropy weight method to calculate the weight of each evaluation index in the minimum data set; the calculation method is: ; Where, k = 1 / ln(m); ; i=1, 2,..., m; j=1, 2,..., n; Represents the original data of i samples and j evaluation indicators; represent After standardized data; , where W j is the weight of the j-th indicator; j=1, 2, ..., n.

[0024] The above will Standardized processing to obtain The process is: If the evaluation index is a positive index, that is, the larger the index value, the better the index, then the standardized formula is: ; If the evaluation index is a negative index, that is, the smaller the index value, the better the index, the standardized formula is: ; in Represents all sample data of the jth indicator.

[0025] The weight results calculated for each evaluation index in this embodiment are as follows: index SOM (g / kg) AP (mg / kg) AK (mg / kg) Cl (mg / kg) pH B (mg / kg) Weight 0.099 0.277 0.166 0.296 0.139 0.023 S4, constructing a membership function: according to the positive response or negative response of each evaluation index to soil fertility, determining the type of membership function adapted to each evaluation index, and then determining the initial critical value and optimal value of each membership function, thereby obtaining the membership function corresponding to each evaluation index; In this embodiment, the AP, AK, and B contents are matched with an S-type membership function: the pH value, SOM, and Cl are matched with a parabolic membership function; The expression of the S-type membership function is as follows:

[0026] The expression of the parabolic membership function is as follows:

[0027] In the formula: x is the measured value of each indicator, x4 and x1 are the upper and lower critical values ​​of each indicator, respectively, and x3 and x2 are the upper and lower optimal values ​​of each indicator; In this embodiment, the initial critical value and optimal value of the membership function of each evaluation index are preliminarily determined as follows: Figure 3 As shown; S5, calculating the membership value: calculating the membership value of each evaluation index; S6. Use the soil fertility suitability index method to construct a soil fertility evaluation model and calculate the soil fertility suitability index SFI. The calculation formula is: ; j = 1, 2, ..., n; Where: SFI represents soil fertility suitability index; N j represents the membership value of the jth evaluation index; W j Represents the weight of the jth evaluation index.

[0028] Furthermore, in step S4, the critical value and the optimal value of the membership function corresponding to each evaluation index are dynamically adjusted, and the method of dynamic adjustment includes the following steps: 1. Analyze the real-time monitoring data of each evaluation indicator and determine whether it exceeds the range of historical monitoring data; 2. If the result of step 1 is exceeded, calculate the ratio of the real-time monitoring data exceeding the limit value of the historical monitoring data range; 3. Set the critical value and optimal value adjustment gradient of each membership function in advance, and set the corresponding relationship between the adjustment gradient and the excess ratio; Fourth, according to the corresponding relationship between the excess ratio and the adjustment gradient, the critical value and the optimal value of each membership function are re-determined to obtain a new membership function; 5. Compare the accuracy of the new membership function and the original membership function. If the new membership function has higher accuracy, use the new membership function to replace the original membership function; if the original membership function has higher accuracy, do not update the membership function.

[0029] Furthermore, the method for determining the accuracy in step five includes comparative experiment method, cross-validation method, expert evaluation method, actual application effect evaluation or statistical test method.

[0030] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the described embodiments. For those skilled in the art, various changes, modifications, substitutions and variations of these embodiments are made without departing from the principles and spirit of the present invention, and still fall within the scope of protection of the present invention.

Claims

1. A method for evaluating tobacco-growing soil fertility, characterized in that: Collect soil samples from the area to be tested, test the test data of each evaluation index in the minimum data set MDS of each sample, and input the test data into the soil fertility evaluation model for fertility evaluation; The method for constructing the soil fertility evaluation model comprises the following steps: S1, confirm the full data set TDS of soil evaluation indicators; S2. Determine the minimum data set MDS: S3, using the entropy weight method to calculate the weight of each evaluation index in the minimum data set; S4, constructing a membership function: according to the positive response or negative response of each evaluation index to soil fertility, determining the type of membership function adapted to each evaluation index, and then determining the initial critical value and optimal value of each membership function, thereby obtaining the membership function corresponding to each evaluation index; S5, calculating the membership value: calculating the membership value of each evaluation index; S6. Use the soil fertility suitability index method to construct a soil fertility evaluation model and calculate the soil fertility suitability index SFI.

2. The tobacco-growing soil fertility evaluation method according to claim 1, characterized in that: The method of step S2, determining the minimum data set MDS, comprises the following steps: S21, evaluation index grouping: perform principal component analysis on all evaluation indicators in the full data set, select principal components that meet the conditions, and group the evaluation indicators according to their loads on different principal components; S22, screening evaluation indicators: S221, according to the Norm value of each evaluation index, eliminate the evaluation index whose Norm value is less than 10% Normmax; wherein Normmax refers to the maximum value of the calculated Norm values ​​of all evaluation indexes; S222. For the selected indicators, the correlation coefficients between the evaluation indicators in each group are calculated. When the correlations between different evaluation indicators in the same group are less than or equal to 0.3, all evaluation indicators in the group enter the minimum data set MDS; when the correlation between two evaluation indicators in the same group is greater than 0.3, the evaluation indicator with a relatively large Norm value among the two evaluation indicators is selected to enter the minimum data set MDS.

3. The tobacco-growing soil fertility evaluation method according to claim 2, characterized in that: The full data set TDS includes soil pH, SOM, AN, AP, AK, Zn, B, Cl, and Mg; the minimum data set MDS includes soil pH, SOM, AP, AK, B, and Cl.

4. The tobacco-growing soil fertility evaluation method according to claim 2, characterized in that: The condition for screening the principal components in step S21 is to select the principal components whose cumulative contribution rate is greater than or equal to 80% or to select the principal components whose eigenvalue is greater than 1.

5. The tobacco-growing soil fertility evaluation method according to claim 2, characterized in that: The specific method for grouping the evaluation indicators in step S21 is as follows: if the load of an evaluation indicator on only one principal component is greater than or equal to 0.5 or the loads on all principal components are less than 0.5, the evaluation indicator is classified into the principal component corresponding to the maximum load value, and all evaluation indicators classified into the same principal component are judged as a group; if the load of an evaluation indicator on at least two principal components is greater than or equal to 0.5, the maximum correlation coefficient between the evaluation indicator and other evaluation indicators in the group is calculated, and the indicator is classified into a group with a low maximum correlation coefficient.

6. The tobacco-growing soil fertility evaluation method according to claim 1, characterized in that: The calculation method of determining the weight by the entropy weight method in step S3 is: ； In the formula, k=1 / ln(m); ;i=1,2,...,m;j=1,2,...,n; Represents the original data of i samples and j evaluation indicators; represent After standardized data; , where W j is the weight of the j-th indicator; j=1, 2, ..., n.

7. The tobacco-growing soil fertility evaluation method according to claim 3, characterized in that: The AP, AK, and B are matched with an S-type membership function; the pH value, SOM, and Cl are matched with a parabolic membership function.

8. The tobacco-growing soil fertility evaluation method according to claim 1, characterized in that: The calculation formula for constructing the soil fertility evaluation model using the soil fertility suitability index method in S6 is: ;j=1,2,...,n; Where: SFI represents soil fertility suitability index; N j represents the membership value of the jth evaluation index; W j Represents the weight of the jth evaluation index.

9. The tobacco-growing soil fertility evaluation method according to claim 1, characterized in that: In step S4, the critical value and the optimal value of the membership function corresponding to each evaluation index are dynamically adjusted. The method of dynamic adjustment includes the following steps:

1. Analyze the real-time monitoring data of each evaluation indicator and determine whether it exceeds the range of historical monitoring data; 2. If the result of step 1 is exceeded, calculate the ratio of the real-time monitoring data exceeding the limit value of the historical monitoring data range; 3. Set the critical value and optimal value adjustment gradient of each membership function in advance, and set the corresponding relationship between the adjustment gradient and the excess ratio; Fourth, according to the corresponding relationship between the excess ratio and the adjustment gradient, the critical value and the optimal value of each membership function are re-determined to obtain a new membership function; 5. Compare the accuracy of the new membership function and the original membership function. If the new membership function has higher accuracy, use the new membership function to replace the original membership function; if the original membership function has higher accuracy, do not update the membership function.

10. The tobacco-growing soil fertility evaluation method according to claim 9, characterized in that: The methods for determining accuracy in step five include comparative experiment method, cross-validation method, expert evaluation method, actual application effect evaluation or statistical test method.

Images