Soil quality evaluation method and device

Abstract

The invention provides a soil quality evaluation method and device, and relates to the technical field of soil monitoring. The method comprises the following steps: acquiring weight information and membership information of a plurality of target indexes corresponding to target soil; determining a soil quality index according to the weight information and the membership degree information; and evaluating the target soil quality according to the soil quality index. The method is beneficial for improving the matching degree of the soil quality evaluation indexes and the target soil, avoiding interference of irrelevant redundant evaluation indexes on quality evaluation of the target soil, reducing the data processing amount in the quality evaluation process of the target soil, simplifying the soil quality evaluation steps, shortening the time consumption of soil quality evaluation and improving the quality evaluation efficiency of the target soil. And the soil quality evaluation precision and evaluation efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of soil monitoring, and in particular to a soil quality evaluation method and device. Background Art

[0002] Soil quality assessment aims to evaluate the quality and health of soil. At present, in the relevant technologies, there are many soil quality assessment indicators and complicated soil quality assessment steps, which leads to problems such as long soil quality assessment process and poor accuracy. Summary of the invention

[0003] The embodiment of the present application provides a soil quality evaluation method and device. The present application determines a soil quality index based on weight information and membership information of a target indicator corresponding to the target soil, and evaluates the target soil quality based on the soil quality index, which is beneficial to improving the matching degree between the soil quality evaluation indicator and the target soil, avoiding interference of irrelevant redundant evaluation indicators on the quality evaluation of the target soil, reducing the amount of data processing in the target soil quality evaluation process, simplifying the soil quality evaluation steps, shortening the soil quality evaluation time, and improving the soil quality evaluation accuracy and evaluation efficiency.

[0004] In a first aspect, the present application proposes a soil quality evaluation method, comprising: Obtaining weight information and membership information of multiple target indicators corresponding to the target soil; Determine the soil quality index according to the weight information and the membership degree information; Evaluate the target soil quality according to the soil quality index.

[0005] In some feasible implementations, before obtaining the weight information and the membership information of the plurality of target indicators corresponding to the target soil, the method further includes: Generate attribute analysis results of multiple target indicators based on principal component analysis; Generate a minimum data set based on the attribute analysis results; Determine the common factor variance matrix based on the minimum data set; Determine the weight information based on the common factor variance matrix.

[0006] In some feasible implementations, determining the weight information according to the common factor variance matrix further includes: Determine the weight information according to the following formula:

[0007] in, For the The weight of the target indicator, For the The factor loadings of the target indicators are is the sum of the factor loadings of all target indicators.

[0008] In some feasible implementations, before obtaining the weight information and the membership information of the plurality of target indicators corresponding to the target soil, the method further includes: Determine membership information according to the membership function; The membership functions include: S-type membership function, inverse S-type membership function and parabolic membership function; Among them, the S-type membership function corresponds to the following function: ; The inverse S-type membership function corresponds to the following function: ; The parabolic membership function corresponds to the following function: ; in, is the target indicator value, is the first threshold of the target index value, is the second threshold of the target index value, is the first baseline value of the target indicator value, It is the second baseline value of the target indicator value.

[0009] In some feasible implementations, determining the membership information according to the membership function includes: Under the condition that it is determined that soil quality increases with the increase of the target index content, the membership information of the target index is determined according to the S-type membership function; Under the condition that it is determined that soil quality decreases with the increase of target index content, the membership information of the target index is determined according to the inverse S-type membership function; In the case where it is determined that soil quality increases with the increase of the target indicator content and then the soil quality decreases with the increase of the target indicator content, the membership information of the target indicator is determined according to the parabolic membership function.

[0010] In some feasible implementations, determining the soil quality index according to the weight information and the membership information includes: The soil quality index is determined according to the following formula:

[0011] in, is the soil quality index, For the The weight of the target indicator, For the The membership degree of a target indicator.

[0012] In some feasible implementations, before executing the above-mentioned acquisition of weight information and membership information of multiple target indicators corresponding to the target soil, the above-mentioned method further includes: Based on the random forest algorithm, correlation analysis method and sensitivity-anti-sensitivity analysis method, multiple target indicators are determined.

[0013] In some feasible implementations, the above multiple target indicators include: soil alkaline nitrogen 、Chloride ion , soil organic matter , soil moisture content , conductivity 、Fluoride ion , and / or, available manganese .

[0014] In some feasible implementations, evaluating the target soil quality according to the soil quality index includes: In the case where the fluctuation trend of the soil quality index of the target soil shows a downward trend, it is determined that the quality of the target soil is deteriorated; In the case that the fluctuation trend of the soil quality index of the target soil has an upward trend, it is determined that the target soil quality has a target period improvement, wherein the target period corresponds to the upward trend band; When the fluctuation range of the soil quality index of the target soil is greater than or equal to a first threshold value and less than or equal to a second threshold value, it is determined that the physical and chemical properties of the target soil are degraded, wherein the first threshold value and the second threshold value are determined according to the target reagent.

[0015] In a second aspect, the present application proposes a soil quality evaluation device, comprising: An acquisition unit, used to acquire weight information and membership information of multiple target indicators corresponding to the target soil; A determination unit, used for determining a soil quality index according to weight information and membership information; The evaluation unit is used to evaluate the target soil quality according to the soil quality index.

[0016] The present application proposes a soil quality evaluation method and device. The method includes: obtaining weight information and membership information of multiple target indicators corresponding to the target soil; determining the soil quality index according to the weight information and membership information; and evaluating the target soil quality according to the soil quality index. The present application is conducive to improving the matching degree between the soil quality evaluation index and the target soil, avoiding interference of irrelevant redundant evaluation indicators on the quality evaluation of the target soil, reducing the amount of data processing in the target soil quality evaluation process, simplifying the soil quality evaluation steps, shortening the soil quality evaluation time, and improving the soil quality evaluation accuracy and evaluation efficiency.

[0017] Other advantages, objectives and features of the present application will be reflected in part through the following description, and in part will be understood by those skilled in the art through study and practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the exemplary embodiments below. The accompanying drawings are only for the purpose of illustrating exemplary embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 A schematic diagram of a process of soil quality evaluation method provided in an embodiment of the present application; Figure 2 a is a schematic diagram of a random forest model provided in an embodiment of the present application; Figure 2 b is a schematic diagram of a correlation analysis result provided in an embodiment of the present application; Figure 3 A schematic diagram of sensitivity results provided in the embodiments of the present application; Figure 4 A schematic diagram of changes in soil physical and chemical properties provided for the implementation of this application; Figure 5 A schematic diagram of the soil quality index provided in the embodiment of the present application; Figure 6 A structural schematic diagram of a soil quality evaluation method and device provided in this application. DETAILED DESCRIPTION

[0019] In order to better understand the technical solutions provided by the embodiments of this specification, the technical solutions of the embodiments of this specification are described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0020] 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 that there is 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 the process, method, article or equipment including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements limited by the statement "comprise one..." do not exclude the existence of other identical elements in the process, method, article or equipment including the elements. The term "more than two" includes two or more than two situations.

[0021] Soil quality assessment aims to evaluate the quality and health of soil. At present, in the relevant technologies, there are many soil quality assessment indicators and complicated soil quality assessment steps, which leads to problems such as long soil quality assessment process and poor accuracy.

[0022] In view of this, the embodiments of the present application provide a soil quality evaluation method and device, which determines the soil quality index according to the weight information and membership information of the target indicator corresponding to the target soil, and evaluates the target soil quality according to the soil quality index, which is conducive to improving the matching degree between the soil quality evaluation index and the target soil, avoiding the interference of irrelevant redundant evaluation indicators on the quality evaluation of the target soil, reducing the amount of data processing in the target soil quality evaluation process, simplifying the soil quality evaluation steps, shortening the soil quality evaluation time, and improving the soil quality evaluation accuracy and evaluation efficiency.

[0023] According to a first aspect of an embodiment of the present application, the present application provides a soil quality evaluation method. Figure 1 The following is a flow chart of a soil quality evaluation method 10 provided in an embodiment of the present application. Figure 1 As shown, method 10 comprises the following steps: Step S1: Obtain weight information and membership information of multiple target indicators corresponding to the target soil.

[0024] Exemplarily, the target indicators may include physical indicators, chemical indicators, biological indicators, etc. The weight information and membership information correspond to the target indicators. The weight information may be determined based on principal component analysis.

[0025] It should be noted that the above-mentioned multiple target indicators can be determined according to the characteristics of the target soil, the type of the target soil, the irrigation method of the target soil, and / or the purpose of soil quality evaluation.

[0026] For example, when the purpose of soil quality evaluation is to promote agricultural production, the above-mentioned multiple target indicators may include: soil fertility, pH value, and organic matter content, etc. When the purpose of soil quality evaluation is environmental protection, the above-mentioned multiple target indicators may include: soil heavy metal content and pesticide residues, etc. When the purpose of soil quality evaluation is land reclamation, the above-mentioned multiple target indicators may include: soil structure, porosity, and salt content, etc. When the purpose of soil quality evaluation is to promote urban greening, the above-mentioned multiple target indicators may include: soil air permeability and water retention capacity, etc.

[0027] Exemplarily, the above-mentioned multiple target indicators can also be determined according to the test results of the target soil. Specifically, the target soil of the target area can be collected, for example, typical soil of Shendong Mining Area (39°29′11″N, 110°00′23″E) in Inner Mongolia, China, and water samples containing the above-mentioned target indicators can also be collected, for example, real mine wastewater of Shendong Mining Area, for testing.

[0028] It should be noted that a control experiment can be conducted on the above target soil. Specifically, mine water (MW) is divided into two types: one is the original mine water MW1 extracted from the underground coal mining area of ​​the mine; the other is the pre-treated mine water MW2 obtained by adding the reagents polyaluminium chloride (PAC) and polyacrylamide (PAM) for precipitation and filtering through quartz stone. It should be noted that when collecting water samples, stirring or interference should be avoided as much as possible. The above water samples should be collected in polyethylene bottles, stored in a low temperature and dark environment, and sent to the laboratory as soon as possible.

[0029] Specifically, mathematical statistics software can be used to analyze the physical and chemical indicators of the target soil to determine multiple target indicators corresponding to the target soil. The mathematical statistics software may include: Excel 2019, SPSS 26, Origin 2021, and "randomForest" in R language, etc.

[0030] For example, Figure 4 A schematic diagram of changes in soil physical and chemical properties provided for the implementation of this application.

[0031] It should be noted that Figure 4 The horizontal axis in is the irrigation cycle, where I0 is before irrigation, I1 is one irrigation cycle, I2 is two irrigation cycles, and I3 is three irrigation cycles. Figure 4 The vertical axis in is the content value corresponding to each target indicator.

[0032] Among them, Figure 4(ac) It can be seen that the target indicators corresponding to the target soil can include: soil moisture content (SMC), electrical conductivity (EC) and soil acidity (pH). Specifically, after MW irrigation, the soil moisture content (SMC) and electrical conductivity (EC) increased significantly, while the soil acidity (pH) decreased significantly.

[0033] Depend on Figure 4 (dg) It can be seen that the target indicators corresponding to the target soil can also include soil nutrient indicators, such as soil organic matter (SOM), soil alkali-hydrolyzed nitrogen (SAN) and soil available phosphorus (SAP). Specifically, after MW1 irrigation, soil organic matter (SOM), soil alkali-hydrolyzed nitrogen (SAN) and soil available phosphorus (SAP) increased significantly, while soil available potassium (SAK) did not change significantly.

[0034] Depend on Figure 4 (h) It can be seen that the target indicators corresponding to the target soil can also include: Fluoride ion, Specifically, the soil fluoride ion (Fluoride ion, ) in most cases showed a gradually increasing trend.

[0035] Depend on Figure 4 (i) It can be seen that the target indicators corresponding to the target soil may also include: Chloride ion, ). Specifically, usually, chloride ion (Chloride ion, ) content continued to increase.

[0036] Depend on Figure 4(j) It can be seen that the target indicators corresponding to the target soil may also include: Available iron (AFe). Specifically, under normal circumstances, the content of Available iron (AFe) gradually increases with the increase of irrigation time series.

[0037] Depend on Figure 4 (k) It can be seen that the target indicators corresponding to the target soil can also include: Available manganese (Amn). Specifically, the Available manganese (Amn) content under MW1 irrigation conditions increased significantly from 0.24 g / kg to 0.36 g / kg, while the Available manganese (Amn) content under MW2 irrigation conditions first increased to 0.26 g / kg and then decreased to 0.22 g / kg.

[0038] Depend on Figure 4 (ln) It can be seen that the target indicators corresponding to the target soil can also include: catalase (CAT), invertase (INV) and urease (UE). Specifically, MW irrigation significantly affected soil enzyme activity. Catalase (CAT) activity increased significantly after irrigation and gradually increased with the irrigation time series. Invertase (INV) and urease (UE) activities showed a trend of first increasing and then decreasing. Among them, invertase (INV) changed significantly during I2 and I3.

[0039] In some feasible implementations, before executing the above-mentioned obtaining of the weight information and the membership information of the multiple target indicators corresponding to the target soil, the above-mentioned method 10 further includes: Step S1-a: Determine multiple target indicators based on the random forest algorithm, correlation analysis method and sensitivity-anti-sensitivity analysis method.

[0040] Exemplarily, the random forest algorithm can be used to determine the random forest feature importance evaluation result, and based on the feature importance ranking result in the above random forest feature importance evaluation result, multiple soil indicators that play a key role in predicting soil quality are determined as the above target indicators.

[0041] Exemplarily, the importance of a target feature in a random forest algorithm can be determined by randomly changing a feature value of the target feature and calculating the error of a test data set before and after the feature value change, that is, the out-of-bag errors (errOOB) of the target feature.

[0042] Specifically, the importance of the above target features can be determined according to the following formula: (1) in, is the number of times the target feature appears in the random forest; is the out-of-bag error calculated after adding noise interference; is the original out-of-bag error calculated before adding noise interference.

[0043] It should be noted that Figure 2 a is a schematic diagram of a random forest model provided in an embodiment of the present application. Figure 2 As shown in a, the random forest model can be used to quantify the effect of target indicators on soil quality index. Specifically, an indicator with a contribution rate greater than 5% can be selected as the above target indicator. Figure 2 a It can be seen that for soil quality index The indicators with the largest contribution rates include soil organic matter (SOM), chloride ion ( )、Soil alkali-hydrolyzed nitrogen (SAN), electrical conductivity (EC), soil moisture content (SMC), fluoride ion (Fluoride ion, ), Available manganese (AMn), Available iron (AFe) and soil pH (potential hydrogen). Among them, the contribution rate of soil organic matter (SOM) is 9.67; Chloride ion ( ) corresponds to a contribution rate of 9.61; soil alkali-hydrolyzed nitrogen (SAN) corresponds to a contribution rate of 9.49; electrical conductivity (EC) corresponds to a contribution rate of 9.14; soil moisture content (SMC) corresponds to a contribution rate of 8.92; fluoride ion (Fluoride ion, ) was 7.01; the corresponding contribution rate of available manganese (AMn) was 6.29; the corresponding contribution rate of available iron (AFe) was 5.75; and the corresponding contribution rate of soil acidity (potential hydrogen, pH) was 5.66.

[0044] Based on this, the random forest algorithm is used to determine the above-mentioned multiple target indicators, which can accurately capture the complex nonlinear relationship between soil indicators and soil quality, make up for the shortcomings of traditional linear models, and make the screened target indicators not only applicable to the linear relationship between soil indicators and soil quality, but also applicable to the more complex interaction relationship between soil indicators and soil quality, which is conducive to improving the determination accuracy of target indicators, thereby further improving the determination accuracy of soil quality index, and further improving the accuracy and efficiency of soil quality evaluation.

[0045] It should be noted that the above soil quality index can be analyzed based on the correlation analysis method according to the soil indicators. Based on the positive and negative impacts, the above-mentioned multiple target indicators are determined.

[0046] Among them, correlation analysis can be used to determine the correlation, correlation direction and closeness of soil indicators. For example, when the p-value is less than 0.05, it can be determined that the soil indicator is related to the above soil quality index. If the p-value is less than 0.01, it can be determined that the soil index is significantly correlated with the soil quality index. If the correlation is extremely significant, the above soil index can be determined as the target index. It should be noted that when the above p-value is less than 0.05, it means that the difference between samples is caused by a sampling error of less than 0.05; when the above p-value is less than 0.01, it means that the difference between samples is caused by a sampling error of less than 0.01.

[0047] Among them, the correlation coefficient Used to measure the correlation between two variables. The value range of is greater than or equal to -1 and less than or equal to 1. It should be noted that the correlation coefficient The larger the absolute value of , the stronger the correlation between the two variables. Among them, the positive correlation coefficient is used to indicate positive correlation, and the negative correlation coefficient is used to indicate negative correlation.

[0048] It should be noted that Figure 2 b is a schematic diagram of a correlation analysis result provided in an embodiment of the present application. Figure 2 b shows that soil quality index It is significantly negatively correlated with most soil indicators, such as soil alkali-hydrolyzed nitrogen (SAN), with a corresponding correlation coefficient is -0.98, and the corresponding p-value is less than 0.001; Chloride ion, ) Corresponding correlation coefficient is -0.95, and the corresponding p-value is less than 0.001; the correlation coefficient of soil moisture content (SMC) is -0.92, and the corresponding p-value is less than 0.001; the corresponding correlation coefficient of electrical conductivity (EC) The correlation coefficient of soil organic matter (SOM) is -0.92, and the corresponding p-value is less than 0.001. is -0.91, and the corresponding p-value is less than 0.01; Fluoride ion, ) corresponding to the correlation coefficient The corresponding p-value is -0.74, and the corresponding correlation coefficient of available manganese (Amn) is less than 0.01. is -0.65, and the corresponding p-value is less than 0.05. It should be noted that soil acidity (potential hydrogen, pH) and soil quality index The relationship between soil pH and soil quality is significantly positively correlated. Based on this, it is determined that soil pH (potential hydrogen, pH) will not have an adverse effect on soil quality, and the soil pH (potential hydrogen, pH) will not be used as the above target indicator.

[0049] Based on this, the correlation analysis method can effectively identify the linear correlation between key indicators and soil quality. After the random forest model selects important features as primary target indicators, the correlation analysis method can further accurately select target indicators based on the significance of the linear relationship between the primary target indicators and the target variables, thereby further improving the accuracy of determining the target indicators.

[0050] It should be noted that the sensitivity and anti-sensitivity of soil indicators respectively reflect the degree of sensitivity of each target indicator to changes in specific reference values.

[0051] For example, Figure 3 A schematic diagram of sensitivity results provided for an embodiment of the present application. Specifically, taking soil organic matter (SOM) as an example, all soil indicators can be standardized, and all values ​​measured in different scales and units can be adjusted to a universal scale of 1 to 0. Specifically, in the case where the soil indicator decreases proportionally with the increase in the content of soil organic matter (SOM), if more than half of the points are below the red line, it is considered that the soil indicator is sensitive to the decrease in soil organic matter (SOM), and the above soil indicator is determined to be a sensitivity indicator. In this case, the above soil indicator can be determined as a target indicator. On the contrary, if less than half of the points are below the red line, it is considered that the soil indicator is not sensitive to the decrease in soil organic matter (SOM), and the above soil indicator is determined to be an anti-sensitivity indicator, then the above soil indicator is eliminated from the target standard. Figure 3 It is indicated that soil available iron AFe is an anti-sensitivity indicator. It should be noted that the above sensitive indicators respond more quickly to changes in soil quality, which helps to quickly identify soil quality problems in actual monitoring.

[0052] Based on this, the sensitivity-anti-sensitivity analysis method can screen out more sensitive soil indicators as the above-mentioned target indicators, which is conducive to improving the stability and reliability of the target indicators, and is conducive to improving the response speed of the soil quality index to the target soil quality assessment, thereby further improving the evaluation efficiency of soil quality evaluation.

[0053] Based on this, the above method, based on the random forest algorithm, is conducive to accurately screening target indicators based on the importance of soil indicators, thereby improving the prediction accuracy of the soil quality index; based on the correlation analysis method, it is conducive to accurately screening target indicators based on the positive and negative correlation of soil indicators, so that the screened target indicators can not only be used to accurately predict soil quality, but also can be used to explain the driving factors of soil quality changes; based on the sensitivity-anti-sensitivity analysis method, it is conducive to verifying the response speed and robustness of the target indicators. Based on this, based on the random forest algorithm, correlation analysis method and sensitivity-anti-sensitivity analysis method, multiple target indicators are determined, which can realize the multi-dimensional accurate screening of key indicators in the soil quality assessment process based on the importance, correlation and sensitivity of soil indicators. As target indicators, the screening process of target indicators is more comprehensive and accurate, which is conducive to further providing accurate data support for the determination of soil quality index, so as to improve the evaluation accuracy and evaluation efficiency of target soil quality.

[0054] It should be noted that, in some feasible implementations, before step S1: obtaining weight information and membership information of multiple target indicators corresponding to the target soil, the above method includes: Step S1-b: Based on principal component analysis, generate attribute analysis results of multiple target indicators.

[0055] For example, the statistical analysis software (Statistical Package for the Social Sciences, SPSS) can be used to generate the attribute analysis results of the above-mentioned multiple target indicators based on principal component analysis. The above-mentioned attribute analysis results may include: principal component analysis results, standardized load results, i.e., Norm value results, eigenvalue results, contribution rate results, and cumulative contribution rate results.

[0056] Step S1-c: Generate a minimum data set (MDS) based on the attribute analysis results.

[0057] It should be noted that the corresponding target indicator can be selected according to the sum of the absolute values ​​of the eigenvalues ​​and the standardized loads in the attribute analysis results, that is, the Norm value, to generate the above minimum data set.

[0058] For example, the corresponding target indicator can be selected according to the preset characteristic value threshold and the preset standardized load threshold, i.e., the preset Norm value, to generate the above minimum data set. The preset characteristic value threshold can be 1, and the preset standardized load threshold, i.e., the preset Norm value, can be the sum of the absolute values ​​of the maximum standardized load, i.e., 10% of the maximum Norm value.

[0059] Specifically, when the eigenvalue corresponding to the target indicator is greater than 1 and the sum of the absolute values ​​of the standardized loads corresponding to the target indicator, that is, the Norm value, is less than or equal to the sum of the absolute values ​​of the maximum standardized loads, that is, 10% of the maximum Norm value, a minimum data set (MDS) is generated based on the above target indicator. It should be noted that when the eigenvalue corresponding to the target indicator is greater than 1, the above target indicator can be used to explain at least 5% of the data variation. When the sum of the absolute values ​​of the standardized loads corresponding to the target indicator, that is, the Norm value, is less than or equal to the sum of the absolute values ​​of the maximum standardized loads, that is, 10% of the maximum Norm value, it can be confirmed that the contribution of the above target indicator is significant.

[0060] Specifically, Table 1 is an attribute analysis result table provided in an embodiment of the present application, wherein Table 1 includes: the principal component analysis results of the target indicators, the sum of the absolute values ​​of the standardized loads, i.e., the Norm value results, the eigenvalue results, the contribution rate results, and the cumulative contribution rate results.

[0061] Table 1:

[0062] As shown in Table 1, the target indicators can include the following 14 soil quality evaluation indicators: soil moisture content (SMC), soil acidity (pH), electrical conductivity (EC), soil organic matter (SOM), soil alkali-hydrolyzed nitrogen (SAN), soil available phosphorus (SAP), soil available potassium (SAK), fluoride ion (Fluoride ion, ), Chloride ion, ), Available iron (AFe), Available manganese (Amn), Catalase (CAT), Invertase (INV) and Urease (UE). Among them, the principal components with eigenvalues ​​greater than 1 may include: principal component 1, principal component 2, principal component 3 and principal component 4, wherein the above principal components 1-4 are used to represent the standardized loads of each target indicator corresponding to the above principal components 1-4, that is, factor loads, which are used to represent the degree of influence of each target indicator on the corresponding principal component. The above Norm value can be used to represent the former with eigenvalues ​​greater than 1. The above grouping is used to indicate the similarity of the performance of each target indicator corresponding to the above principal components 1-4, and the target indicators with higher similarity are grouped together. The above entry into MDS is used to indicate the selection of the corresponding target indicator to generate a minimum data set. The above eigenvalues ​​are used to indicate the eigenvalues ​​corresponding to the above principal components 1-4, and are used to reflect the amount of information contained in principal components 1-4. The above contribution rate is used to indicate the proportion of the above principal components 1-4 in the total variance. The above cumulative contribution rate is used to indicate the proportion of all principal components up to the current principal component in the total variance.

[0063] From Table 1, we can see that: Soil moisture content (SMC): It has a large positive influence on the first principal component (0.556), but has a strong negative influence on the second principal component (-0.665).

[0064] Soil acidity (potential hydrogen, pH): has a strong negative effect on the first principal component (-0.92), but has a smaller effect on other principal components.

[0065] Electrical conductivity (EC): It has a large positive influence on the first principal component (0.654) and a strong negative influence on the second principal component (-0.532).

[0066] Soil organic matter (SOM): has the largest positive influence on the first principal component (0.782), and also has a certain positive influence on the second principal component (0.419).

[0067] Soil alkali-hydrolyzed nitrogen (SAN): It has a positive effect on the first principal component (0.363) and a negative effect on the second principal component (-0.358).

[0068] Soil available phosphorus (SAP): It has a small positive effect on the first principal component (0.35) and a negative effect on the second principal component (-0.518).

[0069] Soil available potassium (SAK): It has a weak negative effect on the first principal component (-0.121) and a strong positive effect on the third principal component (0.758).

[0070] Fluoride ion ): It has a positive influence on the first principal component (0.519) and a negative influence on the third principal component (-0.485).

[0071] Chloride ion ): It has the strongest positive influence on the first principal component (0.809).

[0072] Available iron (AFe): has a positive influence on the first principal component (0.595).

[0073] Available manganese (Amn): has a positive influence on the first principal component (0.524) and a positive influence on the third principal component (0.448).

[0074] Catalase (CAT): has the largest positive influence on the first principal component (0.682) and also has a positive influence on the second principal component (0.627).

[0075] Invertase (INV): has a positive impact on the first principal component (0.316) and a stronger positive impact on the second principal component (0.648).

[0076] Urease (UE): has a positive influence on the first principal component (0.658) and a positive influence on the second principal component (0.511).

[0077] Among them, the eigenvalue of the first principal component is 3.82, and the contribution rate is 27.28%, indicating that the first principal component contains about 27.28% of the total variance. The eigenvalue of the second principal component is 2.79, and the contribution rate is 19.89%, indicating that the second principal component contains about 19.89% of the total variance. The eigenvalue of the third principal component is 1.93, and the contribution rate is 13.78%, indicating that the third principal component contains about 13.78% of the total variance. The eigenvalue of the fourth principal component is 1.74, and the contribution rate is 12.43%, indicating that the fourth principal component contains about 12.43% of the total variance.

[0078] Among them, the cumulative contribution rate of the first and second principal components reached 47.17%. The cumulative contribution rate of the first, second and third principal components reached 60.95%. The cumulative contribution rate of the first, second, third and fourth principal components reached 73.38%. Based on this, principal components 1-4 can be used to explain most of the total variance.

[0079] As shown in Table 1, according to the property analysis results of the above target indicators, due to the chloride ion ( ) The standardized load values ​​corresponding to the first and third principal components are both greater than 0.5, and they can be classified into the third principal component with lower correlation. Based on this, the target indicators whose standardized load values ​​in the above principal components 1-4 are greater than 0.5 and whose Norm values ​​are less than or equal to 10% of the maximum Norm value are: soil organic matter (SOM), electrical conductivity (EC), fluoride ion (Fluoride ion, ), Chloride ion, ) and catalase (CAT). Based on this, the soil organic matter (SOM), electrical conductivity (EC), fluoride ion ( ), Chloride ion, ) and catalase (CAT) to generate the above-mentioned minimum data set (MDS).

[0080] It should be noted that, in some feasible implementations, correlation analysis may be performed on the above target indicators to remove target indicators with smaller Norm values ​​to generate the above minimum data set (Minimum data set, MDS).

[0081] Specifically, Table 2 is a correlation analysis result table provided in an embodiment of the present application, wherein Table 2 includes: correlation coefficient matrix results of target indicators. It should be noted that, among them, ** is used to indicate significant correlation at the 0.01 level (two-tailed). * is used to indicate significant correlation at the 0.05 level (two-tailed). Based on this, soil organic matter (SOM) can be removed, and according to the above electrical conductivity (EC), fluoride ion (Fluoride ion, ), Chloride ion, ) and catalase (CAT) to generate the above-mentioned minimum data set (MDS).

[0082] Table 2:

[0083] Step S1-d: Determine the common factor variance matrix based on the minimum data set.

[0084] Exemplarily, the target indicators in the minimum data set (MDS) may be normalized to calculate the common factor variance matrix.

[0085] Step S1-e: Determine weight information according to the common factor variance matrix.

[0086] It should be noted that for target indicators with higher common factor variance, it means that the above target indicators can be well expressed by the common factors.

[0087] Based on this, the above method can accurately generate attribute analysis results of multiple target indicators based on principal component analysis; according to the attribute analysis results, the minimum data set can be accurately generated; according to the minimum data set, the common factor variance matrix can be accurately determined; according to the common factor variance matrix, the weight information of the target indicator can be accurately determined, which is conducive to avoiding the interference of irrelevant redundant evaluation indicators on the quality evaluation of the target soil, reducing the amount of data processing in the target soil quality evaluation process, and providing accurate data support for the determination of the soil quality index, so as to improve the evaluation accuracy and efficiency of the target soil quality.

[0088] It should be noted that, in some feasible implementations, step S1-d further includes determining the weight information according to the common factor variance matrix: Determine the weight information according to the following formula: (2) in, For the The weight of the target indicator, For the The factor loadings of the target indicators are is the sum of the factor loadings of all target indicators.

[0089] For example, the factor loading of the first target indicator is The factor loading of the second target indicator is 0.5. The factor loading of the third target indicator is 0.6. When is 0.7, is 1.8, then the weight of the first target indicator is 0.28, the weight of the second target indicator is 0.33, and the weight of the third target indicator is 0.39.

[0090] Based on this, the above method can accurately determine the weight of the target indicator according to the factor loading of the target indicator and the sum of the factor loadings of all target indicators, which is conducive to realizing the automated and accurate determination of the weight information of the target indicator, and is conducive to providing accurate data support for the determination of the soil quality index, so as to improve the evaluation accuracy and efficiency of the target soil quality.

[0091] In some feasible implementations, before obtaining the weight information and the membership information of the plurality of target indicators corresponding to the target soil, the method further includes: Step S1-f: Determine the membership information according to the membership function.

[0092] It should be noted that the degree of membership of the target indicator is the score of the target indicator.

[0093] The membership functions include: S-type membership function, inverse S-type membership function and parabolic membership function.

[0094] Among them, the S-type membership function corresponds to the following function: (3) The inverse S-type membership function corresponds to the following function: (4) The parabolic membership function corresponds to the following function: (5) in, is the target indicator value, is the first threshold of the target index value, is the second threshold of the target index value, is the first baseline value of the target indicator value, It is the second baseline value of the target indicator value.

[0095] Based on this, the present application can accurately determine the membership information of the target indicator based on the S-type membership function, the inverse S-type membership function and the parabolic membership function, laying a data foundation for the subsequent determination of the soil quality index based on the membership information, which is conducive to further improving the evaluation accuracy and efficiency of the target soil quality.

[0096] In some feasible implementations, step S1-f determines the membership information according to the membership function, including: Step S1-f1, when it is determined that the soil quality increases with the increase of the target indicator content, the membership information of the target indicator is determined according to the S-type membership function.

[0097] It should be noted that in most cases, soil quality increases with the increase of the target indicator level. Based on this, the above-mentioned S-type membership function, that is, the above-mentioned formula (3), can usually be used to determine the membership information of the target indicator.

[0098] Step S1-f2, when it is determined that the soil quality decreases with the increase of the target indicator content, the membership information of the target indicator is determined according to the inverse S-type membership function.

[0099] For example, when soil quality decreases as the target indicator level increases, the inverse S-type membership function, that is, the above formula (4), is used to determine the membership information of the target indicator.

[0100] Step S1-f3, when it is determined that the soil quality increases with the increase of the target indicator content and then the soil quality decreases with the increase of the target indicator content, the membership information of the target indicator is determined according to the parabolic membership function.

[0101] For example, when soil quality first increases and then decreases as the target indicator level increases, the parabolic membership function, that is, the above formula (5), is selected to determine the membership information of the above target indicator.

[0102] Based on this, the above method can accurately select the corresponding membership function according to the change of soil quality with the content of target indicators to determine the membership information of the target indicator, which is conducive to further improving the determination accuracy of the membership information of the target indicator, thereby improving the determination accuracy of the soil quality index, and further improving the evaluation accuracy and efficiency of the target soil quality.

[0103] Step S2: Determine the soil quality index based on the weight information and the membership information.

[0104] In some feasible implementations, step S2 determines the soil quality index according to the weight information and the membership information, including: The soil quality index is determined according to the following formula: (6) in, is the soil quality index, For the The weight of the target indicator, For the The membership degree of a target indicator.

[0105] It should be noted that the above soil quality index It can be used to integrate multi-dimensional soil physical and chemical indicators into a single indicator. The weight of the target indicator It can be determined according to the above formula (2). The membership degree of the target indicator According to the membership function in the above formula (3)-formula (5), Sure.

[0106] Based on this, the above method can achieve the weight of the target indicator and the degree of membership of the target indicator Accurately determine soil quality index , which is conducive to further improving the soil quality index The determination accuracy can improve the soil quality evaluation accuracy and efficiency.

[0107] Step S3: Evaluate the target soil quality according to the soil quality index.

[0108] Exemplarily, the target soil quality may be evaluated based on the value of the soil quality index and / or the changing trend of the soil quality index.

[0109] For example, Figure 5 A bar diagram of the soil quality index provided in the embodiment of the present application, wherein: Figure 5 The horizontal axis is the irrigation cycle; I0 corresponds to before irrigation; I1 corresponds to one irrigation cycle; I2 corresponds to two irrigation cycles; I3 corresponds to three irrigation cycles; I4 corresponds to four irrigation cycles; I5 corresponds to five irrigation cycles; I6 corresponds to six irrigation cycles. Figure 5 The vertical axis is the soil quality index The value of .

[0110] It should be noted that, in some feasible implementations, step S3 of evaluating the target soil quality according to the soil quality index includes: S31, when the fluctuation trend of the soil quality index of the target soil is a downward trend, determining that the target soil quality is deteriorated.

[0111] For example, by Figure 5 It can be seen that the soil quality index In the case of a gradually decreasing trend, it is determined that the soil quality of the target soil is continuously affected during the irrigation process, and the soil quality of the target soil gradually deteriorates with the increase of the irrigation time series.

[0112] S32, when the fluctuation trend of the soil quality index of the target soil has an upward trend, it is determined that the target soil quality has a target period improvement, wherein the target period corresponds to the upward trend band.

[0113] For example, by Figure 5 It can be seen that the soil quality index under MW2 irrigation is The change trend shows a more complex fluctuation characteristic. Soil quality index After the first irrigation time series I1, an increase of 3.19% occurs, which determines that there is a target period improvement in the target soil quality, where the target period corresponds to the rising trend band.

[0114] It should be noted that the above improvements may be due to the fact that certain nutrients contained in MW2 have a positive effect on the target soil in the short term, thereby promoting the initial improvement of the target soil.

[0115] S33, when the fluctuation range of the soil quality index of the target soil is greater than or equal to the first threshold and less than or equal to the second threshold, it is determined that the physical and chemical properties of the target soil are degraded, wherein the first threshold and the second threshold are determined according to the target reagent.

[0116] Exemplarily, the target reagent includes: a mine water reagent. Specifically, when the target reagent is a mine water reagent, the first threshold may be -8.43%, and the second threshold may be -35.85%.

[0117] Specifically, by Figure 5 It can be seen that under MW1 irrigation conditions, the soil quality index The change rate showed a significant decrease. The above soil quality index The range of change is -8.43%~ -35.85%, which indicates that the negative impact of MW1 irrigation on the soil quality of the target soil is more obvious. With the extension of the irrigation time series, the physical and chemical properties of the target soil have degraded to a greater extent.

[0118] It should be noted that the above-mentioned decrease may be related to the salt contained in MW1, which affects the physical structure of the target soil and thus affects the overall quality of the soil.

[0119] It should be noted that from the second irrigation time series I2 to the fifth irrigation time series I5, the soil quality index It gradually decreased from -3.70% to -23.64%, which indicates that with the continuous irrigation of MW, the target soil quality was affected by the negative cumulative effect. In the sixth irrigation time series I6, the soil quality index An upward trend reappeared, and the reduction rate was -14.82%, which confirmed the adaptive adjustment of the target soil to the long-term irrigation behavior.

[0120] Based on this, the above method can accurately evaluate the soil quality of the target soil according to the numerical changes and / or trend changes of the soil quality index of the target soil, which is conducive to objectively evaluating the soil quality of the target soil, and is conducive to further simplifying the soil quality evaluation steps, shortening the time of soil quality evaluation, and improving the accuracy and efficiency of soil quality evaluation.

[0121] Based on this, the soil quality evaluation method provided by the present application includes: obtaining weight information and membership information of multiple target indicators corresponding to the target soil; determining the soil quality index according to the weight information and membership information; and evaluating the target soil quality according to the soil quality index. The present application evaluates the target soil quality based on the soil quality index, which is conducive to improving the matching degree between the soil quality evaluation index and the target soil, avoiding the interference of irrelevant redundant evaluation indicators on the quality evaluation of the target soil, reducing the amount of data processing in the target soil quality evaluation process, simplifying the soil quality evaluation steps, shortening the soil quality evaluation time, and improving the soil quality evaluation accuracy and evaluation efficiency.

[0122] In some feasible implementations, the above multiple target indicators include: soil organic matter 、Soil chloride ions , Alkaline Nitrogen , conductivity , soil moisture content 、Fluoride ion , and / or, available manganese .

[0123] It should be noted that soil organic matter 、Soil chloride ions , Alkaline Nitrogen , conductivity , soil moisture content 、Fluoride ion , and / or, available manganese Soil Quality Index The total contribution rate reached 60.12%. The above target indicators: soil organic matter 、Soil chloride ions , Alkaline Nitrogen , conductivity , soil moisture content 、Fluoride ion , and / or, available manganese Soil Quality Index It plays an important and significant negative role and can be used as a target indicator for long-term monitoring.

[0124] Based on this, the above method defines multiple target indicators including: soil organic matter 、Soil chloride ions , Alkaline Nitrogen , conductivity , soil moisture content 、Fluoride ion , and / or, available manganese , which is conducive to further improving the determination accuracy and efficiency of soil quality index, thereby further improving the evaluation accuracy and efficiency of target soil quality.

[0125] According to a second aspect of the embodiments of the present application, a soil quality evaluation device is provided. Figure 6 A structural schematic diagram of a soil quality evaluation device 100 provided in this application is shown in FIG. Figure 6 As shown, the apparatus 100 may include: an acquisition unit 110 , a determination unit 120 , and an evaluation unit 130 .

[0126] An acquisition unit 110 is used to acquire weight information and membership information of multiple target indicators corresponding to the target soil; A determination unit 120, configured to determine a soil quality index according to the weight information and the membership information; The evaluation unit 130 is used to evaluate the target soil quality according to the soil quality index.

[0127] A person skilled in the art can understand the specific details and beneficial effects of the soil quality evaluation device by reading the above description of the soil quality evaluation method, which will not be described here for the sake of brevity.

[0128] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0129] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0130] Although the preferred embodiments of this specification have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of this specification.

[0131] Obviously, those skilled in the art can make various changes and modifications to this specification without departing from the spirit and scope of this specification. Thus, if these modifications and variations of this specification fall within the scope of the claims of this specification and their equivalents, this specification is also intended to include these modifications and variations.

Claims

1. A soil quality evaluation method, characterized in that: include: Obtaining weight information and membership information of multiple target indicators corresponding to the target soil; Determining a soil quality index according to the weight information and the membership information; According to the soil quality index, the target soil quality is evaluated.

2. The soil quality evaluation method according to claim 1, characterized in that: Before obtaining the weight information and the membership information of the plurality of target indicators corresponding to the target soil, the method further includes: Based on principal component analysis, generate attribute analysis results of the multiple target indicators; Generate a minimum data set according to the attribute analysis results; Determining a common factor variance matrix according to the minimum data set; The weight information is determined according to the common factor variance matrix.

3. The soil quality evaluation method according to claim 2, characterized in that: The determining the weight information according to the common factor variance matrix further comprises: The weight information is determined according to the following formula: ； in, For the The weight of the target indicator, For the The factor loadings of the target indicators are is the sum of the factor loadings of all the target indicators.

4. The soil quality evaluation method according to claim 3, characterized in that: Before obtaining the weight information and the membership information of the plurality of target indicators corresponding to the target soil, the method further includes: Determining the membership information according to the membership function; Wherein, the membership function includes: S-type membership function, inverse S-type membership function and parabolic membership function; The S-type membership function corresponds to the following function: ; The inverse S-type membership function corresponds to the following function: ； The parabolic membership function corresponds to the following function: ； in, is the target indicator value, is the first threshold value of the target indicator value, is the second threshold value of the target indicator value, is the first baseline value of the target indicator value, is a second baseline value of the target indicator value.

5. The soil quality evaluation method according to claim 4, characterized in that: The determining the membership information according to the membership function further comprises: In the case where it is determined that the soil quality increases with the increase of the target indicator content, determining the membership information of the target indicator according to the S-type membership function; In the case where it is determined that the soil quality decreases as the content of the target indicator increases, determining the membership information of the target indicator according to the inverse S-shaped membership function; When it is determined that the soil quality increases with the increase of the target indicator content and then the soil quality decreases with the increase of the target indicator content, the membership information of the target indicator is determined according to the parabolic membership function.

6. The soil quality evaluation method according to claim 5, characterized in that: Determining the soil quality index according to the weight information and the membership information includes: The soil quality index is determined according to the following formula: ； in, is the soil quality index, For the The weight of the target indicator, For the The degree of membership of the target indicator.

7. The soil quality evaluation method according to any one of claims 1 to 6, characterized in that: Before executing the step of obtaining weight information and membership information of a plurality of target indicators corresponding to the target soil, the method further includes: The multiple target indicators are determined based on the random forest algorithm, correlation analysis method and sensitivity-anti-sensitivity analysis method.

8. The soil quality evaluation method according to claim 7, characterized in that: The multiple target indicators include: soil alkaline nitrogen 、Chloride ion , soil organic matter , soil moisture content , conductivity 、Fluoride ion , and / or, available manganese .

9. The soil quality evaluation method according to claim 8, characterized in that: The evaluating the target soil quality according to the soil quality index comprises: In the case where the fluctuation trend of the soil quality index of the target soil shows a downward trend, determining that the quality of the target soil is deteriorated; In the case where the fluctuation trend of the soil quality index of the target soil has an upward trend, it is determined that the target soil quality has a target period improvement, wherein the target period corresponds to the upward trend band; When the fluctuation range of the soil quality index of the target soil is greater than or equal to a first threshold and less than or equal to a second threshold, it is determined that the physical and chemical properties of the target soil are degraded, wherein the first threshold and the second threshold are determined according to the target reagent.

10. A soil quality evaluation device, characterized in that: include: An acquisition unit, used to acquire weight information and membership information of multiple target indicators corresponding to the target soil; A determination unit, used for determining a soil quality index according to the weight information and the membership information; An evaluation unit is used to evaluate the target soil quality according to the soil quality index.

Images