Water environment pollution contribution evaluation method and system

Abstract

The application provides a water environment pollution contribution evaluation method and system, and the method comprises the following steps: collecting surface water monitoring data, reading surface water collection data from a preset database through a server from a water quality station; standardizing the original data set to obtain a standardized data set; using a PCA principal component analysis model to linearly combine water quality index data in the standardized data set, obtaining the relationship between principal components and original variables, processing to obtain principal component characteristic values to obtain principal component explanation variable degree data, and obtaining principal components representing the original data set in a preset proportion; according to the principal component characteristic values, weighted average processing is performed to obtain a comprehensive water quality evaluation index; obtaining discharge outlet branch flow data, using the comprehensive water quality evaluation index and the discharge outlet branch flow data, analyzing and obtaining pollution contribution data of each discharge outlet branch, and constructing and optimizing a water quality comprehensive evaluation model. The application solves the technical problem that the evaluation factor is single and it is difficult to comprehensively evaluate the pollution situation.

Description

Technical Field

[0001] This invention relates to the field of environmental data analysis, specifically to a method and system for evaluating the contribution of water pollution. Background Technology

[0002] According to the national standard for surface water, there are 23 conventional indicators for water environment, such as COD, ammonia nitrogen, total phosphorus, total nitrogen, volatile phenols, and SS. Currently, the pollution contribution analysis of river discharge outlets often adopts the single-factor index evaluation method, such as evaluating the COD contribution of multiple tributaries into the river, analyzing the ammonia nitrogen contribution of multiple discharge outlets into the river, and analyzing the total phosphorus contribution of multiple discharge outlets into the river. The existing invention patent application document with publication number CN115034140A, entitled "A Method for Predicting the Trend of Surface Water Quality Changes Based on Key Control Factors," includes: obtaining experimental data on DO, CODMn, NH4+-N, TP, and TN at national control sections of surface water at Bahekou and Jingheqiao; calculating the comprehensive water quality index (WQI); obtaining key control factors affecting water quality through sensitivity analysis; constructing training and testing sets; constructing an LSTM model and training the model; testing the WQI on the testing set using the five water quality indicators and key control factors respectively; and predicting the WQI value changes within the next week using the five water quality indicators and key control factors respectively. The existing invention patent application document CN112836859A, entitled "An Intelligent Fusion and Analysis Method for Pollutant Monitoring Data in Estuary Areas," includes: collecting historical data on pollutants in the study area to construct a pollutant database for the study area; considering the main influencing factors, constructing a pollutant transport model; providing a background field based on existing data and the pollutant transport model; combining real-time monitoring data with an adaptive optimal interpolation algorithm (OI) to achieve data assimilation; combining time-varying amplitude fitting with machine learning; analyzing the data assimilation results; and obtaining the variation characteristics of pollutants in the estuary area. The aforementioned existing technologies, when analyzing the pollution contribution of discharge outlets and tributaries into rivers, if using single-factor index analysis, require analyzing the contribution rate of multiple indicators to the pollution contribution of a river. Furthermore, the pollution contributions of multiple indicators to a river from a single discharge outlet often differ significantly, making it difficult to comprehensively judge the pollution level of the discharge outlet / tributary. It also makes it difficult to provide a comprehensive evaluation of subsequent remediation of the discharge outlet / tributary.

[0003] In summary, existing technologies suffer from the technical problem of relying on a single evaluation factor and making it difficult to comprehensively assess pollution levels. Summary of the Invention

[0004] The technical problem to be solved by this invention is how to solve the problem of the existing technology having a single evaluation factor and being difficult to comprehensively evaluate the pollution situation.

[0005] This invention solves the above-mentioned technical problems by employing the following technical solution: A method for evaluating the contribution of water environment pollution includes:

[0006] S1. Collect surface water monitoring data, transmit it back to the pre-set database from the water quality station, and read the surface water collection data from the pre-set database to use as the raw dataset;

[0007] S2. Standardize the original dataset to obtain a standardized dataset;

[0008] S3. Using the PCA principal component analysis model, dimensionality reduction is performed on at least two water quality index data in the standardized dataset to obtain the relationship between the principal components and the original variables. Based on this, the principal component eigenvalues ​​are obtained, and the degree data of the principal component explanatory variables are obtained to obtain the principal component information representing a predetermined proportion of the original dataset. Step S3 includes:

[0009] S31. Obtain a predetermined number of original variables from the standardized dataset, and use them to linearly combine to obtain new variables;

[0010] S32. Based on the new variables and the pre-set loading matrix, process to obtain no less than two index factors, and use them to obtain the relationship between the principal components and the original variables;

[0011] S33. Based on the principal component eigenvalues, obtain the degree data of the principal component explanatory variables using preset logic, so that the data represented by the principal component information reaches the preset proportion in the original dataset.

[0012] S4. Based on the principal component eigenvalues, the comprehensive water quality evaluation index is obtained by using the pre-set weighted average logic.

[0013] S5; Obtain discharge tributary flow data, and use comprehensive water quality evaluation indicators and discharge tributary flow data to analyze and obtain pollution contribution data of each discharge tributary, so as to construct and optimize the comprehensive water quality evaluation model.

[0014] This invention calculates and processes water quality anomalies, then uses principal component analysis to reduce the dimensionality of multiple water quality indicators. Principal components representing 90% of the original water quality indicators are used, and weighted analysis is applied to form a comprehensive water quality index. This comprehensive index, combined with the flow rates of discharge outlets / tributaries, is then used to further calculate pollution fluxes and analyze the pollution contribution of discharge outlets / tributaries into rivers. This invention provides an accurate comprehensive index to evaluate the pollution contribution rate of discharge outlets / tributaries, and through comprehensive analysis, offers decision-making recommendations for the subsequent remediation of discharge outlets / tributaries. This solves the problems of single evaluation factors and difficulty in comprehensively evaluating pollution in traditional technologies.

[0015] In a more specific technical solution, step S1 includes:

[0016] S11. Transmit surface water monitoring data from the water quality station back to the pre-set database through the pre-set server, and read the raw water quality data from the pre-set database;

[0017] S12. Clean the original water quality data through query and multi-table join operations, analyze and obtain water quality anomalies, and delete water quality anomalies.

[0018] S13. When there are no outliers in the original water quality data, fill the missing water quality values ​​in the original water quality data with preset filling data.

[0019] This invention removes outliers from the analysis to ensure the model training effect, fills in missing values ​​to prevent the influence of factors such as equipment malfunction on the model training, and standardizes the cleaned dataset X to remove the influence of the dimensions of each water quality index, thereby improving the model training effect.

[0020] In more specific technical solutions, the pre-filled data includes: median water quality and mean water quality.

[0021] In a more specific technical solution, in step S2, the cleaned original dataset X is standardized using the following logic to obtain a standardized dataset X. std :

[0022] X std = (X - Xmin) / (Xmax - Xmin)

[0023] In the formula, Xmax and Xmin are the maximum and minimum values ​​of the dataset X, respectively.

[0024] This invention first calculates and processes water quality anomalies, then uses principal component analysis to reduce the dimensionality of various water quality indicators. Principal components, representing 90% of the original water quality information, are weighted to form a comprehensive water quality index. Finally, a comprehensive analysis of pollution contribution is performed in conjunction with water quantity.

[0025] In a more specific technical solution, in step S31, the original p variables are linearly combined to obtain new variables.

[0026] In a more specific technical solution, step S32 includes:

[0027] S321. Let there be p original variables x1, x2, ..., xp. Find k factors, where k <p;

[0028] S322. Use the following logic to process the original variables and the preset loading matrix to obtain the relationship between the principal components and the original variables f1, f2, ..., fk:

[0029] f1 = a 11 x1+a12 x2+a 13 x3.....+a 1p x p

[0030] f2=a 21 x1+a 22 x2+a 23 x3.....+a 2p x p

[0031] …

[0032] f k =a k1 x1+a k2 x2+a k3 x3.....+a kp x p

[0033] In the formula, a ij For the i-th principal component f i And the original j-th variable x j The correlation coefficient between them, a 11 a 12 ...a k1 a kp Let A be a load matrix of k×p.

[0034] In a more specific technical solution, step S33 involves processing the principal component eigenvalues ​​using the following logic to obtain the degree data of the principal component explanatory variables:

[0035]

[0036] In the formula, the eigenvalues ​​corresponding to the k principal components are λ1, λ2, ..., λ3, respectively. k , eigenvalues.

[0037] In a more specific technical solution, in step S4, based on the principal component eigenvalues, the expression for the comprehensive water quality evaluation index Z is obtained by weighted averaging using the following logic:

[0038]

[0039]

[0040] In the formula, A T The transpose of load evidence A is given by parameter K, which refers to the transformation of P water quality indicators into K principal components through PCA principal component analysis.

[0041] In a more specific technical solution, in step S5, X is derived from the expression of the comprehensive water quality evaluation index Z. std ×AT The comprehensive water quality evaluation indicators are obtained as follows:

[0042]

[0043] This invention calculates pollution flux using comprehensive evaluation indicators and discharge outlets / tributaries, analyzes the pollution contribution of each discharge outlet / tributary into the river, and optimizes the model based on problems found during actual model application, so that the comprehensive water quality indicators obtained by the model are closer to the actual water quality situation.

[0044] The optimized water quality evaluation model of this invention calculates and processes water quality anomalies, then uses principal component analysis to reduce the dimensionality of various water quality indicators, and uses principal components representing 90% of the original water quality indicators to form a comprehensive indicator representing water quality through weighting.

[0045] In a more specific technical solution, a water environment pollution contribution assessment system includes:

[0046] The surface water quality acquisition module is used to collect surface water monitoring data, transmit it back to the preset database from the water quality station, and read the surface water acquisition data from the preset database to use as the raw dataset.

[0047] The standardization processing module is used to standardize the original dataset to obtain a standardized dataset. The standardization processing module is connected to the surface water quality acquisition module.

[0048] The principal component information module is used to utilize the PCA principal component analysis model to perform dimensionality reduction processing on at least two water quality index data points in the standardized dataset to obtain the relationship between principal components and original variables. Based on this, principal component eigenvalues ​​are obtained, and the degree data of the principal component explanatory variables are acquired to obtain principal component information representing a predetermined proportion of the original dataset. The principal component information module is connected to the standardization processing module. The principal component information module includes:

[0049] The variable linear combination module is used to obtain a preset number of original variables from a standardized dataset and then linearly combine them to obtain new variables.

[0050] The principal component and variable relationship acquisition module is used to process and obtain no less than two index factors based on the new variables and the preset loading matrix, and to obtain the relationship between the principal components and the original variables. The principal component and variable relationship acquisition module is connected to the variable linear combination module.

[0051] The principal component data processing module is used to obtain the degree data of the principal component explanatory variables according to the principal component feature values ​​and preset logic, so that the data represented by the principal component information reaches the preset proportion in the original dataset. The principal component data processing module is connected to the principal component and variable relationship acquisition module.

[0052] The comprehensive water quality evaluation index acquisition module is used to obtain comprehensive water quality evaluation indexes based on the principal component eigenvalues ​​and using a pre-set weighted average logic. The comprehensive water quality evaluation index acquisition module is connected to the principal component information module.

[0053] The water quality analysis and model optimization module is used to obtain discharge tributary flow data. Using the comprehensive water quality evaluation index and discharge tributary flow data, it analyzes and obtains the pollution contribution data of each discharge tributary, and constructs and optimizes the comprehensive water quality evaluation model accordingly. The water quality analysis and model optimization module is connected to the comprehensive water quality evaluation index acquisition module.

[0054] Compared with existing technologies, this invention has the following advantages: This invention calculates and processes water quality anomalies, then uses principal component analysis to reduce the dimensionality of multiple water quality indicators. Principal components representing 90% of the original water quality indicators are used, and weights are applied to form a comprehensive water quality index. This comprehensive water quality index, obtained from the model, is combined with the flow rate of discharge outlets / tributaries to further calculate pollution fluxes and analyze the pollution contribution of discharge outlets / tributaries into the river. This invention can provide an accurate comprehensive index to evaluate the pollution contribution rate of discharge outlets / tributaries, and through comprehensive analysis, provide decision-making suggestions for the subsequent treatment of discharge outlets / tributaries, solving the problems of single evaluation factors and difficulty in comprehensively evaluating pollution in traditional technologies.

[0055] This invention removes outliers from the analysis to ensure the model training effect, fills in missing values ​​to prevent the influence of factors such as equipment malfunction on the model training, and standardizes the cleaned dataset X to remove the influence of the dimensions of each water quality index, thereby improving the model training effect.

[0056] This invention first calculates and processes water quality anomalies, then uses principal component analysis to reduce the dimensionality of various water quality indicators. Principal components, representing 90% of the original water quality information, are weighted to form a comprehensive water quality index. Finally, a comprehensive analysis of pollution contribution is performed in conjunction with water quantity.

[0057] This invention calculates pollution flux using comprehensive evaluation indicators and discharge rates from outlets / tributaries, analyzes the pollution contribution of each outlet / tributary into the river, and optimizes the model based on problems discovered during practical application, making the comprehensive water quality indicators obtained from the model more closely reflect actual water quality conditions. This invention solves the technical problems of existing technologies that rely on single evaluation factors and are difficult to comprehensively evaluate pollution situations. Attached Figure Description

[0058] Figure 1 This is a schematic diagram of the basic steps of a water environment pollution contribution assessment method according to Embodiment 1 of the present invention;

[0059] Figure 2This is a schematic diagram illustrating the specific steps of a water environment pollution contribution evaluation method according to Embodiment 1 of the present invention. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] Example 1

[0062] like Figure 1 As shown, the present invention provides a method and system for evaluating the contribution of water environment pollution, which includes the following basic steps:

[0063] S1. Collect surface water monitoring data, transmit it from the water quality station back to the preset database through the server, and read the surface water collection data.

[0064] In this embodiment, surface water monitoring data is transmitted from river water quality stations back to the database via a server, and data is read from the database.

[0065] In this embodiment, the original water quality data is cleaned by querying and multi-table association, and water quality anomalies are detected. In order to ensure the model training effect, the analyzed anomalies are deleted.

[0066] Secondly, the original water quality data often contains missing values ​​due to equipment malfunctions. For the missing water quality values, the median and mean water quality values ​​are used to fill in the missing values, depending on whether there are outliers in the dataset.

[0067] S2. Standardize the original dataset to obtain a standardized dataset;

[0068] In this embodiment, the cleaned dataset X is standardized to obtain a standardized dataset X. std The influence of the dimensions of each water quality indicator is removed; in the formula, Xmax and Xmin are the maximum and minimum values ​​of the dataset X, respectively.

[0069] X std = (X - Xmin) / (Xmax - Xmin)

[0070] S3. Using the PCA principal component analysis model, the water quality index data in the standardized dataset are linearly combined to obtain the relationship between the principal components and the original variables. The principal component eigenvalues ​​are processed to obtain the degree data of the principal component explanatory variables, and the principal components representing the preset proportions of the original dataset are obtained.

[0071] In this embodiment, there are 23 conventional water environmental indicators conforming to the national standard for surface water, such as COD, ammonia nitrogen, total phosphorus, total nitrogen, volatile phenol, SS, etc. At present, the single-factor index evaluation method is often used for pollution contribution analysis of river outlets, such as evaluating the COD contribution of multiple tributaries into the river, analyzing the ammonia nitrogen contribution of multiple outlets into the river, and analyzing the total phosphorus contribution of multiple outlets into the river. For the pollution contribution analysis of river outlets and tributaries, if single-factor index analysis is adopted, the pollution contribution of a river needs to be analyzed from the perspective of multiple indicators, and the pollution contribution of multiple indicators of one outlet to the river often varies greatly. It is difficult to judge the pollution degree of the outlet / tributary from a comprehensive perspective, and it is also difficult to give a comprehensive evaluation for the later regulation of outlets / tributaries. Therefore, an accurate comprehensive indicator is needed for the pollution contribution rate analysis of river outlets / tributaries to evaluate the pollution contribution of the outlets / tributaries, and decision-making suggestions are provided for the later regulation of outlets / tributaries through comprehensive analysis. Therefore, the present invention uses dimensionality reduction of water quality indicators, principal component analysis and weight generation to obtain a comprehensive indicator for the comprehensive evaluation of pollution contribution.

[0072] In this embodiment, the PCA principal component analysis model is used to reduce the dimensionality of multiple indicators in water quality, and principal components that can represent more than 85% of the information of the original data set are selected according to the eigenvalues of the principal components.

[0073] Mathematically, the original p variables are linearly combined as new variables;

[0074] Let the p original variables be x 1, x 2, ..., x p, and the k factors to be found (k<p) be f 1, f 2, ..., f k. The relationship between the principal components and the original variables is expressed as:

[0075] f1=a 11 x1+a 12 x2+a 13 x3.....+a 1p x p

[0076] f2=a 21 x1+a 22 x2+a 23 x3.....+a 2p x p

[0077] …

[0078] f k =a k1 x1+a k2 x2+a k3 x3.....+a kp x p

[0079] aij For the i-th principal component f i And the original j-th variable x j The correlation coefficient between them, such as a 21 Let f be the correlation coefficient between the second principal component f2 and the original first variable x1. Where a 11 a 12 ...a k1 a kp It is also known as the k×p load matrix A.

[0080] The eigenvalues ​​corresponding to the k principal components are λ1, λ2, ..., λ1, respectively. k The magnitude of the eigenvalues ​​reflects the importance of the corresponding principal components, such that the w value (which reflects the extent to which the principal components explain the original variables) is greater than 85%.

[0081]

[0082] S4. Based on the principal component eigenvalues, a weighted average is used to obtain the comprehensive water quality evaluation index;

[0083] In this embodiment, a comprehensive water quality evaluation index Z is obtained by weighted averaging based on the eigenvalues ​​of the principal components, where A T Provide the transpose matrix of A for the load.

[0084]

[0085] This formula proposes X std ×A T Then, it can be directly rewritten as

[0086]

[0087] S5; Obtain the discharge tributary flow data, and use the comprehensive water quality evaluation index and the discharge tributary flow data to analyze and obtain the pollution contribution data of each discharge tributary, and construct and optimize the comprehensive water quality evaluation model.

[0088] In this embodiment, the pollution flux is calculated by applying the comprehensive evaluation index and the flow of the outlet / tributary, the pollution contribution of each outlet / tributary into the river is analyzed, and the model is optimized based on the problems found in the actual application of the model, so that the comprehensive water quality index obtained by the model is more meaningful in practice.

[0089] like Figure 2 As shown, a method for evaluating the contribution of water pollution to the environment also includes the following specific steps:

[0090] S1', Perform data cleaning on surface water monitoring data;

[0091] S2', Determine abnormal water quality values;

[0092] S3' If outliers exist, remove them;

[0093] S4' If there are no outliers, fill the missing values ​​with the mean.

[0094] S5' Fill missing values ​​with the median;

[0095] S6', Dataset standardization;

[0096] S7', Principal component analysis model;

[0097] S8', Pollution assessment of river discharge;

[0098] In summary, this invention calculates and processes water quality anomalies, then uses principal component analysis to reduce the dimensionality of multiple water quality indicators. Principal components representing 90% of the original water quality indicators are used, and weighted analysis is applied to form a comprehensive water quality index. This comprehensive index, combined with the flow rates of discharge outlets / tributaries, is then used to further calculate pollution fluxes and analyze the pollution contribution of discharge outlets / tributaries into the river. This invention can provide an accurate comprehensive index to evaluate the pollution contribution rate of discharge outlets / tributaries, and through comprehensive analysis, it provides decision-making suggestions for the subsequent treatment of discharge outlets / tributaries, solving the problems of single evaluation factors and difficulty in comprehensively evaluating pollution in traditional technologies.

[0099] This invention removes outliers from the analysis to ensure the model training effect, fills in missing values ​​to prevent the influence of factors such as equipment malfunction on the model training, and standardizes the cleaned dataset X to remove the influence of the dimensions of each water quality index, thereby improving the model training effect.

[0100] This invention first calculates and processes water quality anomalies, then uses principal component analysis to reduce the dimensionality of various water quality indicators. Principal components, representing 90% of the original water quality information, are weighted to form a comprehensive water quality index. Finally, a comprehensive analysis of pollution contribution is performed in conjunction with water quantity.

[0101] This invention calculates pollution flux using comprehensive evaluation indicators and discharge rates from outlets / tributaries, analyzes the pollution contribution of each outlet / tributary into the river, and optimizes the model based on problems discovered during practical application, making the comprehensive water quality indicators obtained from the model more closely reflect actual water quality conditions. This invention solves the technical problems of existing technologies that rely on single evaluation factors and are difficult to comprehensively evaluate pollution situations.

[0102] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating the contribution of water environment pollution, characterized in that, The method includes: S1. Collect surface water monitoring data, transmit it back to the preset database from the water quality station, and read the surface water collection data from the preset database to use as the raw dataset; the preset filling data includes: water quality median and water quality mean. S1 includes: S11. The surface water monitoring data is transmitted from the water quality station back to the preset database through the preset server, and the raw water quality data is read from the preset database; S12. By querying and multi-table join operations, the original water quality data is cleaned to analyze and obtain water quality anomalies, and the water quality anomalies are deleted. S13. When there are no outliers in the original water quality data, fill the missing water quality values ​​in the original water quality data with preset filling data. S2. Standardize the original dataset to obtain a standardized dataset; S3. Using a PCA principal component analysis model, dimensionality reduction is performed on at least two water quality index data points in the standardized dataset to obtain the relationship between principal components and original variables. Based on this, principal component eigenvalues ​​are obtained, and the degree data of the principal component explanatory variables are acquired to obtain principal component information representing a predetermined proportion of the original dataset. Step S3 includes: S31. Obtain a predetermined number of original variables from the standardized dataset, and use them to linearly combine to obtain new variables; S32. Based on the new variables and the preset loading matrix, process to obtain no less than two index factors, thereby obtaining the relationship between the principal components and the original variables; S33. Based on the principal component feature values, obtain the degree data of the principal component explanatory variables using preset logic, so that the data represented by the principal component information reaches the preset proportion in the original dataset; In S33, the principal component eigenvalues ​​are processed using the following logic to obtain the degree data of the principal component explanatory variables: In the formula, the eigenvalues ​​corresponding to the k principal components are λ1, λ2, ..., λ3, respectively. k , eigenvalues; S4. Based on the principal component eigenvalues, a comprehensive water quality evaluation index is obtained by using a pre-set weighted average logic. Based on the principal component eigenvalues, the expression for the comprehensive water quality evaluation index Z is obtained by weighted averaging using the following logic: In the formula, The transpose of the principal component loading matrix A, with parameters This refers to transforming P water quality indicators into P values ​​through PCA principal component analysis. One principal component; The cleaned original dataset X is standardized using the following logic to obtain a standardized dataset. : = (X - Xmin) / (Xmax-Xmin) In the formula, Xmax and Xmin are the maximum and minimum values ​​of the dataset X, respectively; S5; Obtain the discharge tributary flow data, and use the comprehensive water quality evaluation index and the discharge tributary flow data to analyze and obtain the pollution contribution data of each discharge tributary, so as to construct and optimize the comprehensive water quality evaluation model.

2. The method for evaluating the contribution of water environment pollution according to claim 1, characterized in that, In step S31, the original p variables are linearly combined to obtain the new variable.

3. The method for evaluating the contribution of water environment pollution according to claim 1, characterized in that, Step S32 includes: S321. Let there be p original variables x1, x2, ..., xp. Find k factors, where k <p ; S322. Process the original variables and the preset loading matrix using the following logic to obtain the relationship between the principal components and the original variables f1, f2, ..., fk: … In the formula, For the i-th principal component And the original j-th variable The correlation coefficient between them Let A be a load matrix of k×p.

4. The method for evaluating the contribution of water environment pollution according to claim 1, characterized in that, In step S33, the principal component eigenvalues ​​are processed using the following logic to obtain the degree data of the principal component explanatory variables: In the formula, the eigenvalues ​​corresponding to the k principal components are λ1, λ2, ..., λ3, respectively. k , eigenvalues.

5. The method for evaluating the contribution of water environment pollution according to claim 1, characterized in that, In step S5, the expression for the comprehensive water quality evaluation index Z is derived. The comprehensive water quality evaluation index is obtained as follows: 。 6. A water environment pollution contribution assessment system, used to execute the water environment pollution contribution assessment method according to any one of claims 1 to 5, characterized in that, The system includes: The surface water quality acquisition module is used to collect surface water monitoring data, transmit it back to the preset database from the water quality station, and read the surface water acquisition data from the preset database as the raw dataset. A standardization processing module is used to standardize the original dataset to obtain a standardized dataset. The standardization processing module is connected to the surface water quality acquisition module. The principal component information module is used to utilize the PCA principal component analysis model to perform dimensionality reduction processing on at least two water quality index data in the standardized dataset to obtain the relationship between principal components and original variables. Based on this, principal component eigenvalues ​​are obtained, and the degree data of the principal component explanatory variables are acquired to obtain principal component information representing a predetermined proportion of the original dataset. The principal component information module is connected to the standardization processing module, and includes: The variable linear combination module is used to obtain a preset number of original variables from the standardized dataset and to obtain new variables by linear combination. The principal component and variable relationship acquisition module is used to process and obtain no less than two index factors based on the new variables and the preset loading matrix, thereby obtaining the relationship between the principal components and the original variables. The principal component and variable relationship acquisition module is connected to the variable linear combination module. The principal component data processing module is used to obtain the degree data of the principal component explanatory variables according to the principal component feature values ​​and preset logic, so that the data represented by the principal component information reaches the preset proportion in the original dataset. The principal component data processing module is connected to the principal component and variable relationship acquisition module. The comprehensive water quality evaluation index acquisition module is used to process the principal component feature values ​​and obtain the comprehensive water quality evaluation index using a preset weighted average logic. The comprehensive water quality evaluation index acquisition module is connected to the principal component information module. The water quality analysis and model optimization module is used to obtain the discharge outlet tributary flow data, and to analyze and obtain the pollution contribution data of each discharge outlet tributary using the comprehensive water quality evaluation index and the discharge outlet tributary flow data, so as to construct and optimize the comprehensive water quality evaluation model. The water quality analysis and model optimization module is connected to the comprehensive water quality evaluation index acquisition module.

Images