Water body composite pollution source risk assessment method and device based on evidence weight method

Abstract

The invention provides a water body composite pollution source risk assessment method and device based on an evidence weight method. The method comprises the following steps: acquiring pollutant detection data of each pollution source along a water transfer project; according to the detection data of each pollutant of the pollution source i and the sampling weight of each pollutant of the pollution source i, determining a sampling contribution value of the pollution source i, selecting a pollution source contribution value from N sampling contribution values of the pollution source, and selecting a pollutant weight from N sampling weights of the pollutants; according to the contribution value of each pollution source and the sampling weight of each pollution source, determining a sampling contribution value of the water transfer project, selecting a water transfer project contribution value from N sampling contribution values of the water transfer project, and selecting a pollution source weight from N second sampling weights of the pollution sources; and generating a pollution risk assessment report according to the pollutant weight, the pollution source weight, the pollution source contribution value and the water transfer project contribution value. The risk assessment method provided by the invention is high in adaptability, simple and convenient to operate and capable of improving the water delivery safety.

Description

Technical Field

[0001] The present application relates to the technical field of pollution source risk assessment, and in particular to a method and device for risk assessment of composite pollution sources in water bodies based on a weight of evidence method. Background Art

[0002] With the rapid development of long-distance water diversion projects, water quality safety issues have become increasingly prominent, and it is particularly important to conduct scientific assessments of pollution source risks. The water quality safety of water diversion projects is affected by the water quality of multiple pollution sources, including the water quality of source water, the water quality of water transported along the route, and the water quality of reservoirs.

[0003] In practice, the source water quality risks mainly involve unstable source water quality, soil erosion, natural disasters, and agricultural non-point source pollution; the water quality of water along the line involves garbage dumping, illegal discharge of industrial sewage, agricultural non-point source pollution, emergencies, and natural disasters; the reservoir water quality risks include uncontrollable factors such as endogenous pollution (including equipment failure, etc.) and abnormal biological proliferation. These risk factors need to be analyzed in depth to complete the risk assessment of pollution sources of water diversion projects, determine the main pollution sources, and provide a theoretical basis for water quality management in the water diversion project basin. Summary of the invention

[0004] In view of this, the purpose of the embodiments of the present application is to provide a method and device for risk assessment of complex pollution sources in water bodies based on the weight of evidence method, which has strong adaptability, is easy to operate, and can improve the safety of water transfer in water diversion projects.

[0005] In a first aspect, an embodiment of the present application provides a water body composite pollution source risk assessment method based on the weight of evidence method, the risk assessment method comprising: Obtain pollutant detection data of each pollution source along the target water diversion project; among them, the pollution sources include source water, water transfer along the line, and reservoirs; the pollutants to be detected of each pollution source include permanganate index, chemical oxygen demand, five-day biochemical oxygen demand, ammonia nitrogen, total phosphorus, total nitrogen, copper, zinc, fluoride, arsenic, lead, fecal coliform group, sulfate, chloride, nitrate, iron, and manganese; Determine the first sampling contribution value of pollution source i according to the detection data of each pollutant of pollution source i and the first sampling weight of each pollutant of pollution source i, select the contribution value of pollution source i from the N first sampling contribution values ​​of pollution source i, and select the weight of pollutant j of pollution source i from the N first sampling weights of pollutant j of pollution source i; According to the contribution values ​​of each pollution source along the target water diversion project and the second sampling weights of each pollution source, the second sampling contribution value of the target water diversion project is determined, the contribution value of the target water diversion project is selected from the N second sampling contribution values ​​of the target water diversion project, and the weight of pollution source i is selected from the N second sampling weights of pollution source i; A pollution risk assessment report for the target water diversion project is generated based on the pollutant weight of the pollution source, the pollution source weight, the pollution source contribution value and the N first sampling contribution values ​​of the pollution source, the contribution value of the target water diversion project and the N second sampling contribution values ​​of the target water diversion project.

[0006] In a possible implementation, the obtaining of pollutant detection data of each pollution source along the target water diversion project includes: At any testing time point, collect the concentration of the pollutants to be tested from each pollution source along the target water diversion project; Preprocessing the collected pollutant concentrations, converting the pollutant concentrations after removing invalid characters into floating point numbers for numerical calculation; The ratio of the pollutant concentration after pretreatment to the associated pollutant concentration standard value is used as the standardized pollutant concentration; The average value of the standardized pollutant concentration of pollutant j from pollution source i at each detection time point is used as the detection data of pollutant j from pollution source i.

[0007] In a possible implementation, the determining the first sampling contribution value of pollution source i according to the detection data of each pollutant of pollution source i and the first sampling weight of each pollutant of pollution source i, selecting the contribution value of pollution source i from the N first sampling contribution values ​​of pollution source i, and selecting the weight of pollutant j of pollution source i from the N first sampling weights of pollutant j of pollution source i, includes: Step 1.1: The first sampling weight p of pollutant j of pollution source i in the first sampling ij(1) is the preset initial pollutant weight; the first sampling weight p of pollutant j of pollution source i sampled for the (n-1)th time is ij(n-1) The detection data X of pollutant j from pollution source i ij The standardized result of the product of is used as the first sampling weight p of pollutant j of pollution source i sampled at the nth time ij(n) ; Step 1.2: The first sampling weight p of pollutant j of pollution source i sampled at the nth time ij(n) And the detection data X of pollutant j from pollution source i ij ,use , calculate the first sampling contribution value WQI of the pollution source i of the nth sampling i(n) , where k is the total number of pollutants, n=1,2,3,…,N, and N is the specified number of sampling times; Step 1.3: Repeat steps 1.1 and 1.2 until the specified number of sampling times N is completed, and the first sampling contribution value WQI of N pollution sources i is obtained i(n) ; Step 1.4: Based on the first sample contribution value WQI of the N samples of pollution source ii(n) The frequency of occurrence of pollution source i determines the contribution value WQI i ; Step 1.5: Compare the contribution value WQI of pollution source i i The first sampling weight p of pollutant j of pollution source i for the nth sampling with the same sampling times ij(n) , determine the weight p of pollutant j of pollution source i ij .

[0008] In a possible implementation, the second sampling contribution value of the target water diversion project is determined according to the contribution value of each pollution source along the target water diversion project and the second sampling weight of each pollution source, the contribution value of the target water diversion project is selected from the N second sampling contribution values ​​of the target water diversion project, and the weight of the pollution source i is selected from the N second sampling weights of the pollution source i, including: Step 2.1: The second sampling weight q of the pollution source i in the first sampling i(1) is the preset initial pollution source weight; the second sampling weight q of the pollution source i sampled for the (n-1)th time is i(n-1) The first sampling contribution value WQI of the pollution source i sampled at the (n-1)th time i(n-1) The standardized result of the average value is used as the second sampling weight q of the pollution source i of the nth sampling i(n) ; Step 2.2: The second sampling weight q of the pollution source i sampled at the nth time i(n) And the first sampling contribution value WQI of the pollution source i of the nth sampling i(n) ,use , calculate the second sampling contribution value WQI of the target water diversion project sampled at the nth time (n) , where g is the total number of pollution sources, n=1,2,3,…,N, and N is the specified number of sampling times; Step 2.3: Repeat steps 2.1 and 2.2 until the specified number of sampling times N is completed, and the second sampling contribution value WQI of N target water diversion projects is obtained. (n) ; Step 2.4: Based on the second sampling contribution value WQI of the target water diversion project N times of sampling (n) The frequency of occurrence of the target water diversion project is used to determine the contribution value WQI; Step 2.5: Set the second sampling weight q of the pollution source i with the same sampling times as the contribution value WQI of the target water diversion project i(n) , determined as the weight q of pollution source i i .

[0009] In a possible implementation, the generation of a pollution risk assessment report for a target water diversion project based on the pollutant weight of the pollution source, the pollution source weight, the pollution source contribution value and the N first sampling contribution values ​​of the pollution source, the target water diversion project contribution value and the N second sampling contribution values ​​of the target water diversion project includes: According to the weight p of pollutant j of pollution source i ij , determine the main pollutants, secondary pollutants, and weakly associated pollutants of pollution source i; according to the contribution value WQI of pollution source i i , and the preset pollution source contribution value classification rules, determine the pollution level of pollution source i; generate N first sampling contribution values ​​WQI of pollution source i i(n) Distribution map of According to the weight q of pollution source i i , determine the main pollution sources, secondary pollution sources, and weakly associated pollution sources of the target water diversion project; determine the pollution level of the target water diversion project based on the contribution value WQI of the target water diversion project and the preset target water diversion project contribution value classification rules; generate N second sampling contribution values ​​WQI of the target water diversion project (n) Distribution map of .

[0010] In a possible implementation manner, the preset initial pollution source weights of source water, water transfer along the line, and reservoir are 0.4, 0.4, and 0.2, respectively; the preset initial pollutant weights of permanganate index, chemical oxygen demand, five-day biochemical oxygen demand, ammonia nitrogen, total phosphorus, total nitrogen, copper, zinc, fluoride, arsenic, lead, fecal coliform, sulfate, chloride, nitrate, iron, and manganese are 0.06, 0.07, 0.06, 0.10, 0.09, 0.09, 0.04, 0.04, 0.03, 0.09, 0.09, 0.06,0.04, 0.04, 0.06, 0.02, 0.02, respectively.

[0011] In a possible implementation, the risk assessment method further includes: Obtain the location of the water area where the target water diversion project flows, the water area flow, the scale of factories, residences, and public facilities along the route, and the scale of ecological protection areas, nature reserves, and park green spaces along the route, and generate corresponding feature vectors; The K-means clustering method is used to cluster the target water diversion projects and the water diversion projects that have been completed according to the characteristic vector of the target water diversion project, the pollutant weight of the pollution source, the pollution source weight, the pollution source contribution value, and the contribution value of the target water diversion project; Based on the treatment measures of completed water diversion projects of the same category as the target water diversion project, reference treatment measures for the target water diversion project are generated.

[0012] In a second aspect, an embodiment of the present application provides a risk assessment device for composite pollution sources of water bodies based on the weight of evidence method, the risk assessment device comprising: The data acquisition module is used to obtain the pollutant detection data of each pollution source along the target water diversion project; the pollution sources include source water, water transfer along the line, and reservoirs; the pollutants to be detected from each pollution source include permanganate index, chemical oxygen demand, five-day biochemical oxygen demand, ammonia nitrogen, total phosphorus, total nitrogen, copper, zinc, fluoride, arsenic, lead, fecal coliform group, sulfate, chloride, nitrate, iron, and manganese; A first selection module is used to determine a first sampling contribution value of pollution source i according to the detection data of each pollutant of pollution source i and the first sampling weights of each pollutant of pollution source i, select the contribution value of pollution source i from the N first sampling contribution values ​​of pollution source i, and select the weight of pollutant j of pollution source i from the N first sampling weights of pollutant j of pollution source i; The second selection module is used to determine the second sampling contribution value of the target water diversion project according to the contribution value of each pollution source along the target water diversion project and the second sampling weight of each pollution source, select the contribution value of the target water diversion project from the N second sampling contribution values ​​of the target water diversion project, and select the weight of pollution source i from the N second sampling weights of pollution source i; The report generation module is used to generate a pollution risk assessment report for a target water diversion project based on the pollutant weight of the pollution source, the pollution source weight, the pollution source contribution value and the N first sampling contribution values ​​of the pollution source, the contribution value of the target water diversion project and the N second sampling contribution values ​​of the target water diversion project.

[0013] In a third aspect, an embodiment of the present application provides an electronic device comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory through the bus, and the processor executes the machine-readable instructions to execute the steps of the method for risk assessment of complex pollution sources in water bodies based on the weight of evidence method as described in any one of the first aspects.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for risk assessment of complex pollution sources in water bodies based on the weight of evidence method as described in any one of the first aspects are executed.

[0015] The water body complex pollution source risk assessment method and device based on the evidence weight method provided in the embodiment of the present application have strong adaptability, simple operation, and can improve the safety of water transfer projects.

[0016] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A flow chart of a water body composite pollution source risk assessment method based on the weight of evidence method provided in an embodiment of the present application is shown; Figure 2 A flow chart of another water body composite pollution source risk assessment method based on the weight of evidence method provided in an embodiment of the present application is shown; Figure 3 A flow chart of another water body composite pollution source risk assessment method based on the weight of evidence method provided in an embodiment of the present application is shown; Figure 4 A schematic diagram of pollution source weights provided in an embodiment of the present application is shown; Figure 5 A schematic diagram of water source pollutant weights provided in an embodiment of the present application is shown; Figure 6 The WQI distribution diagram of the Jiaodong water diversion project provided in the embodiment of the present application is shown; Figure 7 The water source WQI distribution diagram provided by the embodiment of the present application is shown; Figure 8 A schematic diagram of the structure of a water body composite pollution source risk assessment device based on the weight of evidence method provided in an embodiment of the present application is shown; Fig. 9 A schematic diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0019] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0020] At present, with the rapid development of long-distance water diversion projects, water quality safety issues have become increasingly prominent, and it is particularly important to conduct scientific assessments of pollution source risks. The water quality safety of water diversion projects is affected by the water quality of multiple pollution sources, including the water quality of source water, the water quality of water transported along the line, and the water quality of reservoirs.

[0021] In practice, the source water quality risks mainly involve unstable source water quality, soil erosion, natural disasters, and agricultural non-point source pollution; the water quality of water along the line involves garbage dumping, illegal discharge of industrial sewage, agricultural non-point source pollution, emergencies, and natural disasters; the reservoir water quality risks include uncontrollable factors such as endogenous pollution (including equipment failure, etc.) and abnormal biological proliferation. These risk factors need to be analyzed in depth to complete the risk assessment of pollution sources of water diversion projects, determine the main pollution sources, and provide a theoretical basis for water quality management in the water diversion project basin.

[0022] Based on the above problems, the embodiments of the present application provide a method and device for risk assessment of complex pollution sources in water bodies based on the weight of evidence method, which has strong adaptability, easy operation, and can improve the safety of water transfer in water diversion projects.

[0023] The defects existing in the above solutions are the results obtained by the inventor after practice and careful research. Therefore, the process of discovering the above problems and the solutions proposed by this application for the above problems below should be the contributions made by the inventor to this application during the application process.

[0024] The technical solutions in the present application will be clearly and completely described below in conjunction with the drawings in the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0025] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0026] To facilitate understanding of this embodiment, a method for risk assessment of complex pollution sources in water bodies based on the weight of evidence method disclosed in an embodiment of the present application is first introduced in detail.

[0027] See also Figure 1 As shown, Figure 1 A flow chart of a water body composite pollution source risk assessment method based on the weight of evidence method provided in an embodiment of the present application, the risk assessment method comprising: S101. Obtain pollutant detection data of each pollution source along the target water diversion project; among which, pollution sources include source water, water transfer along the line, and reservoirs; the pollutants to be detected of each pollution source include permanganate index, chemical oxygen demand, five-day biochemical oxygen demand, ammonia nitrogen, total phosphorus, total nitrogen, copper, zinc, fluoride, arsenic, lead, fecal coliform, sulfate, chloride, nitrate, iron, and manganese.

[0028] The pollution sources along the water diversion project water supply line include source water, water supply along the line, and reservoirs (the total number of pollution sources g=3). The detection data of the pollutants to be detected for each pollution source are obtained respectively. The pollutants to be detected include at least the above 17 types, among which chemical oxygen demand is referred to as "COD", five-day biochemical oxygen demand is referred to as "BOD5", ammonia nitrogen is referred to as "NH3-N", total phosphorus (in terms of P), total nitrogen (lakes and reservoirs are in terms of N), fluoride (in terms of F - ), sulfate (as SO4 2- Chloride (as Cl - The test data of different pollutants have the same dimension. For different pollutants, the test data can be used to compare the concentration. The larger the test data, the higher the pollutant concentration.

[0029] S102. Determine the first sampling contribution value of pollution source i based on the detection data of each pollutant of pollution source i and the first sampling weights of each pollutant of pollution source i, select the contribution value of pollution source i from the N first sampling contribution values ​​of pollution source i, and select the weight of pollutant j of pollution source i from the N first sampling weights of pollutant j of pollution source i.

[0030] For any pollution source i, the detection data of k pollutants of pollution source i are obtained, and a 1×k-dimensional vector (vector 1) is formed by the detection data of the k pollutants of pollution source i; the weights of the k pollutants of pollution source i are sampled. In order to distinguish them from the sampling weights of pollution source i in the following text, the sampling weights of the k pollutants of pollution source i are called the first sampling weights, and the sampling weights of pollution source i are called the second sampling weights. The first sampling weights of the k pollutants of pollution source i form another 1×k-dimensional vector (vector 2), and the sum of the first sampling weights of the k pollutants of pollution source i is 1.

[0031] The dot product calculation result of vector 1 and vector 2 is used as the sampling contribution value of pollution source i. In order to distinguish it from the sampling contribution value of the target water diversion project in the following text, the sampling contribution value of pollution source i is called the first sampling contribution value, and the sampling contribution value of the target water diversion project is called the second sampling contribution value.

[0032] It is necessary to sample the weights of the k pollutants of pollution source i N times. There are N first sampling weights for pollutant j of pollution source i, and the N first sampling weights are normally distributed. Accordingly, the N first sampling contribution values ​​of pollution source i are calculated, and the N first sampling contribution values ​​are also normally distributed. According to the normal distribution of the N first sampling contribution values ​​of pollution source i, one first sampling contribution value is selected from the N first sampling contribution values ​​as the contribution value of pollution source i. Optionally, the first sampling contribution value with the highest frequency is used as the contribution value of pollution source i. The first sampling weight of pollutant j of pollution source i that is consistent with the sampling number of the contribution value of pollution source i is used as the weight of pollutant j of pollution source i. For example, the first sampling contribution value of the 213th (213≤N) sampling is used as the contribution value of pollution source i, and the first sampling weight of the k pollutants of pollution source i sampled at the 213th time is used as the weight of the k pollutants of pollution source i.

[0033] After determining the contribution values ​​of the g pollution sources respectively, the contribution values ​​of the pollution sources are normalized, and the ratio of the contribution value of pollution source i to the sum of the contribution values ​​of the g pollution sources is taken as the final contribution value of pollution source i, so that the contribution value of pollution source i is between 0 and 1.

[0034] It should be noted that the weights of the same pollutants from different pollution sources are unrelated and may be different in value. For example, the weight of the permanganate index of source water is 0.03, and the weight of the permanganate index of the reservoir is 0.05. There is no correlation between the calculation processes of these two weights. The greater the weight of pollutant j of pollution source i, the greater the impact of pollutant j on the water quality of pollution source i. Pollutants j with large weights are regarded as the main pollutants of pollution source i, pollutants j with larger weights are regarded as secondary pollutants of pollution source i, and pollutants j with smaller weights are regarded as weakly associated pollutants of pollution source i. The pollution level of the pollution source and the water pollution situation can be determined based on the contribution value of the pollution source.

[0035] S103. Determine the second sampling contribution value of the target water diversion project based on the contribution value of each pollution source along the target water diversion project and the second sampling weight of each pollution source, select the contribution value of the target water diversion project from the N second sampling contribution values ​​of the target water diversion project, and select the weight of pollution source i from the N second sampling weights of pollution source i.

[0036] The weights of the g pollution sources are sampled, which are called the second sampling weights of the pollution sources. The second sampling weights of the g pollution sources form a 1×g-dimensional vector (vector 3), and the sum of the second sampling weights of the g pollution sources is 1. Through the calculation in step S102, the normalized contribution values ​​of the g pollution sources are obtained, and the contribution values ​​of the g pollution sources form another 1×g-dimensional vector (vector 4), and the sum of the contribution values ​​of the g pollution sources is 1. The dot product calculation result of vector 3 and vector 4 is used as the second sampling contribution value of the target water diversion project.

[0037] The weights of g pollution sources are sampled N times. Here, the number of sampling times of the weight of pollution source i is consistent with the number of sampling times of the weight of pollutant j of pollution source i in step S102. There are N second sampling weights for pollution source i, and the N second sampling weights are normally distributed. Accordingly, N second sampling contribution values ​​of the target water diversion project are calculated, and the N second sampling contribution values ​​are also normally distributed. According to the normal distribution of the N second sampling contribution values ​​of the target water diversion project, one second sampling contribution value is selected from the N second sampling contribution values ​​as the contribution value of the target water diversion project. Optionally, the second sampling contribution value with the highest frequency is used as the contribution value of the target water diversion project. The second sampling weight of pollution source i that is consistent with the sampling times of the contribution value of the target water diversion project is used as the weight of pollution source i. For example, the second sampling contribution value of the 167th (167≤N) sampling is used as the contribution value of the target water diversion project, and the second sampling weight of pollution source i of the 167th sampling is used as the weight of pollution source i.

[0038] The larger the weight of pollution source i, the greater the impact of pollution source i on the water quality of the target water diversion project. The g types of pollution sources are sorted from large to small according to the pollution source weights to obtain the main pollution sources, secondary pollution sources, and weakly associated pollution sources. The pollution level and water quality pollution of the target water diversion project can be determined according to the contribution value of the target water diversion project. Optionally, the corresponding relationship between WQI classification, water quality, and WQI value is: Grade I, clean, 0.1; Grade II, relatively clean, 0.1-0.3; Grade III, slightly polluted, 0.3-0.5; Grade IV, moderately polluted, 0.5-1.0; Grade V, heavily polluted, 1.0-5.0; Grade VI, severely polluted, greater than 5.0.

[0039] S104. Generate a pollution risk assessment report for the target water diversion project based on the pollutant weight of the pollution source, the pollution source weight, the pollution source contribution value and the N first sampling contribution values ​​of the pollution source, the contribution value of the target water diversion project and the N second sampling contribution values ​​of the target water diversion project.

[0040] The pollution risk assessment report of the target water diversion project includes the risk assessment results of the water body complex pollution sources. Specifically, it includes: the contribution value of the target water diversion project, which reflects the overall water quality pollution of the target water diversion project; the contribution value of the pollution source, which reflects the water quality pollution of a certain pollution source; the pollution source weight, which reflects the degree of influence of each pollution source on the water quality safety of the entire target water diversion project; the pollutant weight of the pollution source, which reflects the degree of influence of each pollutant on the water quality safety of a certain pollution source; the N second sampling contribution values ​​of the target water diversion project, which reflects the normal distribution of the N sampling contribution values ​​of the project; the N first sampling contribution values ​​of the pollution source, which reflects the normal distribution of the N sampling contribution values ​​of the pollution source.

[0041] The water body complex pollution source risk assessment method based on the evidence weight method provided in the embodiment of the present application has strong adaptability, simple operation, and can improve the safety of water transfer projects.

[0042] For further information, see Figure 2 As shown, Figure 2 A flowchart of another water body composite pollution source risk assessment method based on the weight of evidence method provided in an embodiment of the present application, wherein the pollutant detection data of each pollution source along the target water diversion project is obtained, including: S1011. At any detection time point, collect the concentration of the pollutants to be detected from each pollution source along the target water diversion project.

[0043] In order to improve the accuracy of pollutant detection data, the concentration of the same pollutant from the same pollution source is measured multiple times at multiple detection time points. The concentrations of different pollutants have different dimensions.

[0044] S1012. Preprocess the collected pollutant concentrations, and convert the pollutant concentrations from which invalid characters have been removed into floating-point numbers for numerical calculation.

[0045] Remove invalid symbols such as “>”, “<”, “≥”, and “≤” from the collected pollutant concentration data and convert them into floating point numbers to ensure that the data can be used for numerical calculations.

[0046] S1013. The ratio of the pollutant concentration after pretreatment to the associated pollutant concentration standard value is used as the standardized pollutant concentration.

[0047] A concentration standard value is set for each pollutant to standardize the concentration of each pollutant. For a certain pollutant, the ratio of the concentration of the pollutant after pretreatment obtained in step 1012 to the concentration standard value of the pollutant is used as the standardized concentration of the pollutant.

[0048] S1014. The average value of the standardized pollutant concentrations of the pollutant j of the pollution source i at each detection time point is used as the detection data of the pollutant j of the pollution source i.

[0049] The average value of the standardized pollutant concentrations of the same pollutant of the same pollution source at multiple detection time points is used as the detection data of the pollutant of the pollution source. The pollutant detection data obtained by processing in steps S1012 to S1014 have the same dimension.

[0050] As a possible implementation method, in the water complex pollution source risk assessment method based on the evidence weight method provided in the embodiment of the present application, Monte Carlo simulation is used to determine the pollutant weights, pollution source contribution values, pollution source weights and target water diversion project contribution values.

[0051] Specifically, step S102 determines the first sampling contribution value of pollution source i according to the detection data of each pollutant of pollution source i and the first sampling weights of each pollutant of pollution source i, selects the contribution value of pollution source i from the N first sampling contribution values ​​of pollution source i, and selects the weight of pollutant j of pollution source i from the N first sampling weights of pollutant j of pollution source i, including: Step 1.1: The first sampling weight p of pollutant j of pollution source i in the first sampling ij(1) is the preset initial pollutant weight; the first sampling weight p of pollutant j of pollution source i sampled for the (n-1)th time is ij(n-1) The detection data X of pollutant j from pollution source i ij The standardized result of the product of is used as the first sampling weight p of pollutant j of pollution source i sampled at the nth time ij(n) .

[0052] Refer to the public data on the impact of pollutants on water quality along the target water diversion project, and combine the experience of water quality management to set the initial pollutant weights. For example, the initial weights of permanganate index, chemical oxygen demand, five-day biochemical oxygen demand, ammonia nitrogen, total phosphorus, total nitrogen, copper, zinc, fluoride, arsenic, lead, fecal coliform group, sulfate, chloride, nitrate, iron, and manganese are set as: 0.06, 0.07, 0.06, 0.10, 0.09, 0.09, 0.04, 0.04, 0.03, 0.09, 0.09, 0.06,0.04, 0.04, 0.06, 0.02, 0.02. The standardization process is to make the sum of the first sampling weights of k pollutants of pollution source i equal to 1.

[0053] Step 1.2: The first sampling weight p of pollutant j of pollution source i sampled at the nth time ij(n) And the detection data X of pollutant j from pollution source i ij ,use , calculate the first sampling contribution value WQI of the pollution source i of the nth sampling i(n) , where k is the total number of pollutants, n=1,2,3,…,N, and N is the specified number of sampling times.

[0054] Step 1.3: Repeat steps 1.1 and 1.2 until the specified number of sampling times N is completed, and the first sampling contribution value WQI of N pollution sources i is obtained i(n) .

[0055] Set the sampling times N according to actual work needs, for example, set N=1000.

[0056] Step 1.4: Based on the first sample contribution value WQI of the N samples of pollution source i i(n) The frequency of occurrence of pollution source i determines the contribution value WQI i .

[0057] Optionally, the first sampling contribution value WQI with the highest occurrence frequency of pollution source i is i(n) , as the contribution value WQI of pollution source i i .

[0058] Step 1.5: Compare the contribution value WQI of pollution source i i The first sampling weight p of pollutant j of pollution source i for the nth sampling with the same sampling times ij(n) , determine the weight p of pollutant j of pollution source i ij .

[0059] In step S103, according to the contribution values ​​of each pollution source along the target water diversion project and the second sampling weights of each pollution source, the second sampling contribution value of the target water diversion project is determined, the contribution value of the target water diversion project is selected from the N second sampling contribution values ​​of the target water diversion project, and the weight of the pollution source i is selected from the N second sampling weights of the pollution source i, including: Step 2.1: The second sampling weight q of the pollution source i in the first sampling i(1) is the preset initial pollution source weight; the second sampling weight q of the pollution source i sampled for the (n-1)th time is i(n-1) The first sampling contribution value WQI of the pollution source i sampled at the (n-1)th time i(n-1) The standardized result of the average value is used as the second sampling weight q of the pollution source i of the nth sampling i(n) .

[0060] Refer to the public data on the impact of pollution sources along the target water diversion project on water quality, and combine the experience of water quality management to set the initial pollution source weights. For example, the initial weights of source water, water transfer along the line, and reservoir are set to 0.4, 0.4, and 0.2 respectively. The purpose of standardization is to make the sum of the second sampling weights of g types of pollution sources equal to 1.

[0061] Step 2.2: The second sampling weight q of the pollution source i sampled at the nth time i(n) And the first sampling contribution value WQI of the pollution source i of the nth sampling i(n) ,use , calculate the second sampling contribution value WQI of the target water diversion project sampled at the nth time (n) , where g is the total number of pollution sources, n=1,2,3,…,N, and N is the specified number of sampling times.

[0062] Step 2.3: Repeat steps 2.1 and 2.2 until the specified number of sampling times N is completed, and the second sampling contribution value WQI of N target water diversion projects is obtained. (n) .

[0063] Step 2.4: Based on the second sampling contribution value WQI of the target water diversion project N times of sampling (n) The frequency of occurrence is used to determine the contribution value WQI of the target water diversion project.

[0064] Optionally, the second sampling contribution value WQI with the highest occurrence frequency of the target water diversion project is (n) , as the contribution value WQI of the target water diversion project.

[0065] Step 2.5: Set the second sampling weight q of the pollution source i with the same sampling times as the contribution value WQI of the target water diversion project i(n) , determined as the weight q of pollution source ii .

[0066] Further, in the water body composite pollution source risk assessment method based on the evidence weight method provided in the embodiment of the present application, step S104 generates a pollution risk assessment report of the target water diversion project according to the pollutant weight of the pollution source, the pollution source weight, the pollution source contribution value and the N first sampling contribution values ​​of the pollution source, the target water diversion project contribution value and the N second sampling contribution values ​​of the target water diversion project, including: According to the weight p of pollutant j of pollution source i ij , determine the main pollutants, secondary pollutants, and weakly associated pollutants of pollution source i; according to the contribution value WQI of pollution source i i , and the preset pollution source contribution value classification rules, determine the pollution level of pollution source i; generate N first sampling contribution values ​​WQI of pollution source i i(n) Distribution diagram; according to the weight q of pollution source i i , determine the main pollution sources, secondary pollution sources, and weakly associated pollution sources of the target water diversion project; determine the pollution level of the target water diversion project based on the contribution value WQI of the target water diversion project and the preset target water diversion project contribution value classification rules; generate N second sampling contribution values ​​WQI of the target water diversion project (n) The contribution value distribution graph has a horizontal axis that represents the contribution value, and a vertical axis that represents the frequency of the contribution value.

[0067] Furthermore, when conducting water quality management in the watershed of the target water diversion project, water quality management measures that have been used in other water diversion projects can be referred to. Other water diversion projects with high similarity to the target water diversion project are selected as reference water diversion projects for water quality management measures. When determining the similarity, it is necessary to consider the geographical location information of the water diversion project, the water flow information, the pollution of water quality by factories and residences on both sides of the water diversion project basin, and the restoration of water quality by forests, grasslands and green spaces on both sides of the basin, and try to select the characteristics of the water diversion project as comprehensively as possible to improve the accuracy of the selected reference water diversion project. See Figure 3 As shown, Figure 3 A flow chart of another water body composite pollution source risk assessment method based on the weight of evidence method provided in an embodiment of the present application, wherein the risk assessment method further comprises:

[0068] S301. Obtain the location of the water area through which the target water diversion project flows, the water area flow, the scale of factories, residences, and public facilities along the line, and the scale of ecological protection areas, nature reserves, and park green spaces along the line, and generate corresponding feature vectors.

[0069] The acquired data of the water area flow location of the water diversion project, the water area flow, the scale of factories, residences, public facilities along the line, the scale of ecological protection areas, nature reserves, and parks and green spaces along the line are processed to obtain multi-dimensional feature vectors that can be processed by computers, and generate feature vectors for the target water diversion project and other water diversion projects that have been completed.

[0070] S302. Using K-means clustering method, cluster the target water diversion project and the water diversion project that has been completed according to the characteristic vector of the target water diversion project, the pollutant weight of the pollution source, the pollution source weight, the pollution source contribution value, and the contribution value of the target water diversion project.

[0071] The characteristic vector of the water diversion project, the pollutant weight of the pollution source, the pollution source weight, the pollution source contribution value, and the target water diversion project contribution value are processed into a multi-dimensional clustering input vector, and the dimension of the clustering input vector is greater than the dimension of the project characteristic vector; the clustering input vectors of the target water diversion project and the water diversion project that has been completed are input, and the K-means clustering method is used to set the K value to obtain the K-type water diversion project. Here, the K value can be set to the total number of water diversion projects that have been completed, or the K value can be calculated by K=a×A, where a is the adjustment coefficient, the value range of a is (0,1], and A is the total number of water diversion projects that have been completed. The a value can be selected according to actual needs.

[0072] S303. Generate reference governance measures for the target water diversion project based on governance measures of completed water diversion projects of the same type as the target water diversion project.

[0073] The completed water diversion project of the same category as the target water diversion project shall be determined as the reference water diversion project. If there is only one reference water diversion project of the same category as the target water diversion project, the control measures of the reference water diversion project shall be determined as the reference control measures of the target water diversion project; if there are multiple reference water diversion projects of the same category as the target water diversion project, the control measures consistent with the multiple reference water diversion projects shall be determined as the reference control measures of the target water diversion project.

[0074] Taking the Jiaodong water diversion project as an example, the evaluation process of the embodiment of the present application is described as follows: (1) Data collection and preprocessing 1) Data reading: Read the pollutant concentrations collected from 9 different time points and obtain 9 data files (data1.csv to data9.csv).

[0075] 2) Remove invalid characters: Traverse each data file, remove the “>”, “<”, “≥”, and “≤” symbols, and convert them into floating-point numbers to ensure that the data can be used for numerical calculations.

[0076] 3) Set standard values: Set standard value arrays (standard_val1 and standard_val2) for each of the 17 pollutants to standardize the concentration of each pollutant. It should be noted that the standardization array is a two-dimensional array with 17 rows and 1 column, containing 17 standard values ​​of the original data; since the Class III standard value of total nitrogen (lake reservoir, in N) is 0.05, which is different from the other normal standard values ​​of 0.2, the standard value array is set to 2 categories.

[0077] (2) Data standardization and average value calculation 1) Standardization: Divide the concentration of each pollutant by the corresponding standard value so that the data can be compared in the same dimension.

[0078] 2) Calculate the average value: average the standardized data of each pollution source to obtain data1_avg, data2_avg and data3_avg, which represent the average pollutant concentrations of the water source, water delivery route and reservoir, respectively, that is, the detection data of pollutant j of pollution source i in step S101.

[0079] (3) Monte Carlo simulation sampling 1) Simulation sampling times: Set the simulation sampling times to 10,000 times (N=10,000) to ensure the reliability of the results.

[0080] 2) Pollution source weight sampling: Use normal distribution (norm.rvs) to generate sampling data of pollution source weights according to the initial pollution source weights (source_weights), and standardize them so that the sum of the weights of each sampling is 1.

[0081] 3) Pollutant weight sampling: Use normal distribution (norm.rvs) to generate pollutant weight sampling data based on the initial 17 pollutant weights (pollutant_weights), and standardize them so that the sum of the weights of each sampling is 1.

[0082] (4) Risk contribution (contribution value of pollution source i WQI i )calculate 1) Calculate the risk contribution of each pollution source: For each pollution source, use the corresponding standardized average value and the pollutant weight obtained by sampling to perform dot product calculation to obtain the risk contribution of risk_source1 (water source), risk_source2 (water transmission route) and risk_source3 (reservoir) under each sampling.

[0083] 2) Risk normalization: Divide the values ​​of risk_source1, risk_source2, and risk_source3 by their sum to ensure that the relative proportion of each risk contribution is between 0 and 1.

[0084] (5) Calculate the overall WQI Weighted summation: The standardized risk contribution under each sampling is calculated by the dot product of the pollution source weight obtained by sampling to obtain the overall WQI value under this sampling (wqi_samples).

[0085] (6) Posterior weight calculation 1) Posterior weight of pollution source: Calculate weights_source_samples and the mean of the risk contribution of each pollution source, and standardize them to obtain the posterior weight of the pollution source, which is q in the above text. i .

[0086] 2) Posterior weights of pollutants: By multiplying weights_pollutant_samples with data1_avg, data2_avg and data3_avg, the posterior weights of pollutants in different pollution sources are calculated and standardized, that is, p in the above text ij .

[0087] (7) Result output and visualization 1) Output posterior weights and WQI statistics: Output the posterior weights of pollution sources and pollutants, and the mean and standard deviation of WQI.

[0088] 2) Visualize pollution source weights: Use a bar chart to display the posterior weight of each pollution source, see Figure 4 As shown, Figure 4 The pollution source weight diagram provided in the embodiment of the present application is Figure 4 In the model, pollution sources include water sources, water delivery routes, and reservoirs. The pollution source (posteriori) weight of water sources is 0.427, the pollution source (posteriori) weight of water delivery routes is 0.382, and the pollution source (posteriori) weight of reservoirs is 0.191.

[0089] 3) Visualization of 17 pollutant weights: Display the posterior weight of each pollutant in the water source, water delivery route and reservoir. Here, take the water source as an example, see Figure 5 As shown, Figure 5 The schematic diagram of water source pollutant weights provided in the embodiment of the present application is shown in Figure 5 In the figure, the pollutant (posterior) weights of the permanganate index, chemical oxygen demand, five-day biochemical oxygen demand, ammonia nitrogen, total phosphorus, total nitrogen, copper, zinc, fluoride, arsenic, lead, fecal coliform, sulfate, chloride, nitrate, iron, and manganese of the pollution source (water source) are shown respectively.

[0090] 4) WQI distribution diagram: Draw the histogram and KDE curve of the overall WQI sample distribution to analyze the overall distribution trend of the water quality index. Figure 6 As shown, Figure 6 The WQI distribution diagram of the Jiaodong water diversion project provided in the embodiment of this application is Figure 6 , the normal distribution of the WQI values ​​of the Jiaodong water diversion project obtained by 10,000 samplings is shown.

[0091] 5) WQI distribution of individual pollution sources: Draw the WQI distribution map of water sources, water delivery routes and reservoirs to analyze the impact of each pollution source. Here, take the water source as an example, see Figure 7 As shown, Figure 7 The water source WQI distribution diagram provided in the embodiment of the present application is Figure 7 In the figure, the normal distribution of the water source contribution value (water source WQI value) of the Jiaodong Water Diversion Project obtained from 10,000 samplings is shown. For water source pollutants, TN: has the highest weight, reaching 65.2%, indicating that TN is the main pollutant in the water source and has a significant impact on water quality; permanganate index and chemical oxygen demand (COD): account for 4.62% and 6.07% respectively, which are secondary pollutants; other indicators: such as total phosphorus, sulfate, chloride, etc. have smaller weights and have relatively minor impacts on water quality, and are weakly associated pollutants.

[0092] Based on the same inventive concept, the embodiments of the present application also provide a water body complex pollution source risk assessment device based on the weight of evidence method corresponding to the water body complex pollution source risk assessment method based on the weight of evidence method. Since the principle of solving the problem by the device in the embodiments of the present application is similar to the water body complex pollution source risk assessment method based on the weight of evidence method in the embodiments of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0093] See also Figure 8 As shown, Figure 8 A schematic diagram of a water body composite pollution source risk assessment device based on the weight of evidence method provided in an embodiment of the present application, the risk assessment device comprising: The data acquisition module 801 is used to obtain the pollutant detection data of each pollution source along the target water diversion project; wherein the pollution sources include source water, water transfer along the line, and reservoirs; the pollutants to be detected of each pollution source include permanganate index, chemical oxygen demand, five-day biochemical oxygen demand, ammonia nitrogen, total phosphorus, total nitrogen, copper, zinc, fluoride, arsenic, lead, fecal coliform, sulfate, chloride, nitrate, iron, and manganese.

[0094] The first selection module 802 is used to determine the first sampling contribution value of pollution source i based on the detection data of each pollutant of pollution source i and the first sampling weights of each pollutant of pollution source i, select the contribution value of pollution source i from the N first sampling contribution values ​​of pollution source i, and select the weight of pollutant j of pollution source i from the N first sampling weights of pollutant j of pollution source i.

[0095] The second selection module 803 is used to determine the second sampling contribution value of the target water diversion project based on the contribution value of each pollution source along the target water diversion project and the second sampling weight of each pollution source, select the contribution value of the target water diversion project from the N second sampling contribution values ​​of the target water diversion project, and select the weight of pollution source i from the N second sampling weights of pollution source i.

[0096] The report generation module 804 is used to generate a pollution risk assessment report for the target water diversion project based on the pollutant weight of the pollution source, the pollution source weight, the pollution source contribution value and the N first sampling contribution values ​​of the pollution source, the contribution value of the target water diversion project and the N second sampling contribution values ​​of the target water diversion project.

[0097] In a possible implementation, the data acquisition module 801, when acquiring pollutant detection data of each pollution source along the target water diversion project, includes: At any testing time point, collect the concentration of the pollutants to be tested from each pollution source along the target water diversion project; Preprocessing the collected pollutant concentrations, converting the pollutant concentrations after removing invalid characters into floating point numbers for numerical calculation; The ratio of the pollutant concentration after pretreatment to the associated pollutant concentration standard value is used as the standardized pollutant concentration; The average value of the standardized pollutant concentration of pollutant j from pollution source i at each detection time point is used as the detection data of pollutant j from pollution source i.

[0098] In a possible implementation, the first selection module 802, when determining the first sampling contribution value of pollution source i according to the detection data of each pollutant of pollution source i and the first sampling weight of each pollutant of pollution source i, selecting the contribution value of pollution source i from the N first sampling contribution values ​​of pollution source i, and selecting the weight of pollutant j of pollution source i from the N first sampling weights of pollutant j of pollution source i, includes: Step 1.1: The first sampling weight p of pollutant j of pollution source i in the first sampling ij(1) is the preset initial pollutant weight; the first sampling weight p of pollutant j of pollution source i sampled for the (n-1)th time is ij(n-1) The detection data X of pollutant j from pollution source i ij The standardized result of the product of is used as the first sampling weight p of pollutant j of pollution source i sampled at the nth time ij(n) ; Step 1.2: The first sampling weight p of pollutant j of pollution source i sampled at the nth time ij(n) And the detection data X of pollutant j from pollution source i ij ,use , calculate the first sampling contribution value WQI of the pollution source i of the nth sampling i(n) , where k is the total number of pollutants, n=1,2,3,…,N, and N is the specified number of sampling times; Step 1.3: Repeat steps 1.1 and 1.2 until the specified number of sampling times N is completed, and the first sampling contribution value WQI of N pollution sources i is obtained i(n) ; Step 1.4: Based on the first sample contribution value WQI of the N samples of pollution source i i(n) The frequency of occurrence of pollution source i determines the contribution value WQI i ; Step 1.5: Compare the contribution value WQI of pollution source i i The first sampling weight p of pollutant j of pollution source i for the nth sampling with the same sampling times ij(n) , determine the weight p of pollutant j of pollution source i ij .

[0099] In a possible implementation, the second selection module 803, when determining the second sampling contribution value of the target water diversion project according to the contribution value of each pollution source along the target water diversion project and the second sampling weight of each pollution source, selecting the contribution value of the target water diversion project from the N second sampling contribution values ​​of the target water diversion project, and selecting the weight of pollution source i from the N second sampling weights of pollution source i, includes: Step 2.1: The second sampling weight q of the pollution source i in the first sampling i(1) is the preset initial pollution source weight; the second sampling weight q of the pollution source i sampled for the (n-1)th time is i(n-1) The first sampling contribution value WQI of the pollution source i sampled at the (n-1)th time i(n-1) The standardized result of the average value is used as the second sampling weight q of the pollution source i of the nth sampling i(n) ; Step 2.2: The second sampling weight q of the pollution source i sampled at the nth time i(n) And the first sampling contribution value WQI of the pollution source i of the nth sampling i(n) ,use , calculate the second sampling contribution value WQI of the target water diversion project sampled at the nth time (n) , where g is the total number of pollution sources, n=1,2,3,…,N, and N is the specified number of sampling times; Step 2.3: Repeat steps 2.1 and 2.2 until the specified number of sampling times N is completed, and the second sampling contribution value WQI of N target water diversion projects is obtained. (n) ; Step 2.4: Based on the second sampling contribution value WQI of the target water diversion project N times of sampling(n) The frequency of occurrence of the target water diversion project is used to determine the contribution value WQI; Step 2.5: Set the second sampling weight q of the pollution source i with the same sampling times as the contribution value WQI of the target water diversion project i(n) , determined as the weight q of pollution source i i .

[0100] In a possible implementation, the report generation module 804, when generating a pollution risk assessment report of a target water diversion project according to the pollutant weight of the pollution source, the pollution source weight, the pollution source contribution value and the N first sampling contribution values ​​of the pollution source, the target water diversion project contribution value and the N second sampling contribution values ​​of the target water diversion project, includes: According to the weight p of pollutant j of pollution source i ij , determine the main pollutants, secondary pollutants, and weakly associated pollutants of pollution source i; according to the contribution value WQI of pollution source i i , and the preset pollution source contribution value classification rules, determine the pollution level of pollution source i; generate N first sampling contribution values ​​WQI of pollution source i i(n) Distribution map of According to the weight q of pollution source i i , determine the main pollution sources, secondary pollution sources, and weakly associated pollution sources of the target water diversion project; determine the pollution level of the target water diversion project based on the contribution value WQI of the target water diversion project and the preset target water diversion project contribution value classification rules; generate N second sampling contribution values ​​WQI of the target water diversion project (n) Distribution map of .

[0101] In a possible implementation manner, the preset initial pollution source weights of source water, water transfer along the line, and reservoir are 0.4, 0.4, and 0.2, respectively; the preset initial pollutant weights of permanganate index, chemical oxygen demand, five-day biochemical oxygen demand, ammonia nitrogen, total phosphorus, total nitrogen, copper, zinc, fluoride, arsenic, lead, fecal coliform, sulfate, chloride, nitrate, iron, and manganese are 0.06, 0.07, 0.06, 0.10, 0.09, 0.09, 0.04, 0.04, 0.03, 0.09, 0.09, 0.06,0.04, 0.04, 0.06, 0.02, 0.02, respectively.

[0102] In a possible implementation, the risk assessment device further includes: The feature vector generation module is used to obtain the location of the water area through which the target water diversion project flows, the flow rate of the water area, the scale of factories, residences, and public facilities along the line, and the scale of ecological protection areas, nature reserves, and park green spaces along the line, and generate corresponding feature vectors; The clustering module is used to cluster the target water diversion project and the water diversion project that has been completed by using the K-means clustering method according to the characteristic vector of the target water diversion project, the pollutant weight of the pollution source, the pollution source weight, the pollution source contribution value, and the contribution value of the target water diversion project; The reference control measures generation module is used to generate reference control measures for the target water diversion project based on the control measures of the completed water diversion projects that belong to the same category as the target water diversion project.

[0103] The water body complex pollution source risk assessment device based on the evidence weight method provided in the embodiment of the present application has strong adaptability and is easy to operate, and can improve the safety of water transfer in water diversion projects.

[0104] See also Fig. 9 As shown, Fig. 9 A schematic diagram of an electronic device provided in an embodiment of the present application, the electronic device 900 includes: a processor 901, a memory 902 and a bus 903, the memory 902 stores machine-readable instructions executable by the processor 901, when the electronic device is running, the processor 901 communicates with the memory 902 via the bus 903, the processor 901 executes the machine-readable instructions to perform the steps of the water complex pollution source risk assessment method based on the weight of evidence method as described above.

[0105] Specifically, the above-mentioned memory 902 and processor 901 can be general-purpose memory and processor, which are not specifically limited here. When the processor 901 runs the computer program stored in the memory 902, it can execute the above-mentioned water body complex pollution source risk assessment method based on the evidence weight method.

[0106] Corresponding to the above-mentioned method for risk assessment of complex water pollution sources based on the weight of evidence method, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for risk assessment of complex water pollution sources based on the weight of evidence method are executed.

[0107] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0108] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0109] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0110] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0111] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A water body composite pollution source risk assessment method based on the weight of evidence method, characterized in that: The risk assessment method includes: Obtain pollutant detection data of each pollution source along the target water diversion project; among them, the pollution sources include source water, water transfer along the line, and reservoirs; the pollutants to be detected of each pollution source include permanganate index, chemical oxygen demand, five-day biochemical oxygen demand, ammonia nitrogen, total phosphorus, total nitrogen, copper, zinc, fluoride, arsenic, lead, fecal coliform group, sulfate, chloride, nitrate, iron, and manganese; Determine the first sampling contribution value of pollution source i according to the detection data of each pollutant of pollution source i and the first sampling weight of each pollutant of pollution source i, select the contribution value of pollution source i from the N first sampling contribution values ​​of pollution source i, and select the weight of pollutant j of pollution source i from the N first sampling weights of pollutant j of pollution source i; According to the contribution values ​​of each pollution source along the target water diversion project and the second sampling weights of each pollution source, the second sampling contribution value of the target water diversion project is determined, the contribution value of the target water diversion project is selected from the N second sampling contribution values ​​of the target water diversion project, and the weight of pollution source i is selected from the N second sampling weights of pollution source i; A pollution risk assessment report for the target water diversion project is generated based on the pollutant weight of the pollution source, the pollution source weight, the pollution source contribution value and the N first sampling contribution values ​​of the pollution source, the contribution value of the target water diversion project and the N second sampling contribution values ​​of the target water diversion project.

2. The water body composite pollution source risk assessment method based on the evidence weight method according to claim 1 is characterized in that: The acquisition of pollutant detection data of various pollution sources along the target water diversion project includes: At any testing time point, collect the concentration of the pollutants to be tested from each pollution source along the target water diversion project; Preprocessing the collected pollutant concentrations, converting the pollutant concentrations after removing invalid characters into floating point numbers for numerical calculation; The ratio of the pollutant concentration after pretreatment to the associated pollutant concentration standard value is used as the standardized pollutant concentration; The average value of the standardized pollutant concentration of pollutant j from pollution source i at each detection time point is used as the detection data of pollutant j from pollution source i.

3. The water body composite pollution source risk assessment method based on the evidence weight method according to claim 1 is characterized in that: The method of determining the first sampling contribution value of pollution source i according to the detection data of each pollutant of pollution source i and the first sampling weights of each pollutant of pollution source i, selecting the contribution value of pollution source i from the N first sampling contribution values ​​of pollution source i, and selecting the weight of pollutant j of pollution source i from the N first sampling weights of pollutant j of pollution source i includes: Step 1.1: The first sampling weight p of pollutant j of pollution source i in the first sampling ij(1) is the preset initial pollutant weight; the first sampling weight p of pollutant j of pollution source i sampled for the (n-1)th time is ij(n-1) The detection data X of pollutant j from pollution source i ij The standardized result of the product of is used as the first sampling weight p of pollutant j of pollution source i sampled at the nth time ij(n) ; Step 1.2: The first sampling weight p of pollutant j of pollution source i sampled at the nth time ij(n) And the detection data X of pollutant j from pollution source i ij ,use , calculate the first sampling contribution value WQI of the pollution source i of the nth sampling i(n) , where k is the total number of pollutants, n=1,2,3,…,N, and N is the specified number of sampling times; Step 1.3: Repeat steps 1.1 and 1.2 until the specified number of sampling times N is completed, and the first sampling contribution value WQI of N pollution sources i is obtained i(n) ; Step 1.4: Based on the first sample contribution value WQI of the N samples of pollution source i i(n) The frequency of occurrence of pollution source i determines the contribution value WQI i ; Step 1.5: Compare the contribution value WQI of pollution source i i The first sampling weight p of pollutant j of pollution source i for the nth sampling with the same sampling times ij(n) , determine the weight p of pollutant j of pollution source i ij .

4. The water body composite pollution source risk assessment method based on the evidence weight method according to claim 1 is characterized in that: The second sampling contribution value of the target water diversion project is determined according to the contribution value of each pollution source along the target water diversion project and the second sampling weight of each pollution source, the contribution value of the target water diversion project is selected from the N second sampling contribution values ​​of the target water diversion project, and the weight of the pollution source i is selected from the N second sampling weights of the pollution source i, including: Step 2.1: The second sampling weight q of the pollution source i in the first sampling i(1) is the preset initial pollution source weight; the second sampling weight q of the pollution source i sampled for the (n-1)th time is i(n-1) The first sampling contribution value WQI of the pollution source i sampled at the (n-1)th time i(n-1) The standardized result of the average value is used as the second sampling weight q of the pollution source i of the nth sampling i(n) ; Step 2.2: The second sampling weight q of the pollution source i sampled at the nth time i(n) And the first sampling contribution value WQI of the pollution source i of the nth sampling i(n) ,use , calculate the second sampling contribution value WQI of the target water diversion project sampled at the nth time (n) , where g is the total number of pollution sources, n=1,2,3,…,N, and N is the specified number of sampling times; Step 2.3: Repeat steps 2.1 and 2.2 until the specified number of sampling times N is completed, and the second sampling contribution value WQI of N target water diversion projects is obtained. (n) ; Step 2.4: Based on the second sampling contribution value WQI of the target water diversion project N times of sampling (n) The frequency of occurrence of the target water diversion project is used to determine the contribution value WQI; Step 2.5: Set the second sampling weight q of the pollution source i with the same sampling times as the contribution value WQI of the target water diversion project i(n) , determined as the weight q of pollution source i i .

5. The water body composite pollution source risk assessment method based on the evidence weight method according to claim 1 is characterized in that: The pollution risk assessment report of the target water diversion project is generated according to the pollutant weight of the pollution source, the pollution source weight, the pollution source contribution value and the N first sampling contribution values ​​of the pollution source, the contribution value of the target water diversion project and the N second sampling contribution values ​​of the target water diversion project, including: According to the weight p of pollutant j of pollution source i ij , determine the main pollutants, secondary pollutants, and weakly associated pollutants of pollution source i; according to the contribution value WQI of pollution source i i , and the preset pollution source contribution value classification rules, determine the pollution level of pollution source i; generate N first sampling contribution values ​​WQI of pollution source i i(n) Distribution map of According to the weight q of pollution source i i , determine the main pollution sources, secondary pollution sources, and weakly associated pollution sources of the target water diversion project; determine the pollution level of the target water diversion project based on the contribution value WQI of the target water diversion project and the preset target water diversion project contribution value classification rules; generate N second sampling contribution values ​​WQI of the target water diversion project (n) Distribution map of .

6. The water body composite pollution source risk assessment method based on the weight of evidence method according to claim 3 or claim 4 is characterized in that: The preset initial pollution source weights of source water, water transfer along the line, and reservoir are 0.4, 0.4, and 0.2, respectively; the preset initial pollutant weights of permanganate index, chemical oxygen demand, five-day biochemical oxygen demand, ammonia nitrogen, total phosphorus, total nitrogen, copper, zinc, fluoride, arsenic, lead, fecal coliform, sulfate, chloride, nitrate, iron, and manganese are 0.06, 0.07, 0.06,0.10, 0.09, 0.09, 0.04, 0.04, 0.03, 0.09, 0.09, 0.06, 0.04, 0.04, 0.06, 0.02,0.02, respectively.

7. The water body composite pollution source risk assessment method based on the weight of evidence method according to claim 1 is characterized in that: The risk assessment method further comprises: Obtain the location of the water area where the target water diversion project flows, the water area flow, the scale of factories, residences, and public facilities along the route, and the scale of ecological protection areas, nature reserves, and park green spaces along the route, and generate corresponding feature vectors; The K-means clustering method is used to cluster the target water diversion projects and the water diversion projects that have been completed according to the characteristic vector of the target water diversion project, the pollutant weight of the pollution source, the pollution source weight, the pollution source contribution value, and the contribution value of the target water diversion project; Based on the treatment measures of completed water diversion projects of the same category as the target water diversion project, reference treatment measures for the target water diversion project are generated.

8. A water body composite pollution source risk assessment device based on the evidence weight method, characterized in that: The risk assessment device comprises: The data acquisition module is used to obtain the pollutant detection data of each pollution source along the target water diversion project; the pollution sources include source water, water transfer along the line, and reservoirs; the pollutants to be detected from each pollution source include permanganate index, chemical oxygen demand, five-day biochemical oxygen demand, ammonia nitrogen, total phosphorus, total nitrogen, copper, zinc, fluoride, arsenic, lead, fecal coliform group, sulfate, chloride, nitrate, iron, and manganese; A first selection module is used to determine a first sampling contribution value of pollution source i according to the detection data of each pollutant of pollution source i and the first sampling weights of each pollutant of pollution source i, select the contribution value of pollution source i from the N first sampling contribution values ​​of pollution source i, and select the weight of pollutant j of pollution source i from the N first sampling weights of pollutant j of pollution source i; The second selection module is used to determine the second sampling contribution value of the target water diversion project according to the contribution value of each pollution source along the target water diversion project and the second sampling weight of each pollution source, select the contribution value of the target water diversion project from the N second sampling contribution values ​​of the target water diversion project, and select the weight of pollution source i from the N second sampling weights of pollution source i; The report generation module is used to generate a pollution risk assessment report for a target water diversion project based on the pollutant weight of the pollution source, the pollution source weight, the pollution source contribution value and the N first sampling contribution values ​​of the pollution source, the contribution value of the target water diversion project and the N second sampling contribution values ​​of the target water diversion project.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of the method for risk assessment of complex pollution sources in water bodies based on the weight of evidence method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the method for risk assessment of composite pollution sources in water bodies based on the weight of evidence method as described in any one of claims 1 to 7.

Images