Soil and groundwater pollutant toxicity effect risk diagnosis, management and control method and system

Abstract

The invention discloses a soil and groundwater pollutant toxicity effect risk diagnosis and management and control method and system, and relates to the technical field of soil pollution analysis, and the method comprises the steps: collecting discharge data and toxicological parameters, calculating partial correlation coefficients, and constructing a pollutant causal relationship graph; the pollutants are divided into samples, toxicity effect nodes are added, a child causal relationship graph is extracted, and a pollutant father node set and a toxicity effect father node set are determined; calculating a first conditional probability of the pollutant node, calculating a second conditional probability and a third conditional probability of the toxicity effect node, and obtaining a conditional probability table of the pollutant node and a conditional probability table of the toxicity effect node; constructing a Bayesian network, obtaining joint probability distribution of pollutant combination, obtaining emission concentration to form an evidence vector, and calculating posterior probability distribution; the probabilities of the toxicity effect nodes in different states are obtained, the state corresponding to the maximum probability serves as the toxicity effect severity degree, and the pollutant node with the highest pollution weight is selected for preferential treatment.

Description

Technical Field

[0001] This application relates to the technical field of soil pollution analysis, and particularly to a method and system for diagnosing and controlling the toxicity effects risks of soil and groundwater pollutants. Background Art

[0002] With the changes in chemical production and social lifestyles, many new types of chemicals are mass-produced and used. Some of these substances are environmentally persistent, bioaccumulative, and toxic. These new pollutants enter the soil and groundwater environments through means such as atmospheric deposition, sewage irrigation, and solid waste landfill. Traditional environmental monitoring and risk assessment methods are difficult to comprehensively evaluate their hazards. Soil and groundwater are important natural resources. Once polluted, they are difficult to repair, have a long cycle, and are costly. There is an urgent need to strengthen risk early warning and pollution prevention and control.

[0003] The Chinese patent application with the publication number CN118761628A discloses a method for preferentially controlling and evaluating the water environment risks of toxic and harmful pollutants, including the following steps: evaluating the toxicity effects, detection frequencies, and exposure concentrations of each pollutant in the target environmental area: the toxicity effects include but are not limited to ecological toxicity, health toxicity, and physical and chemical properties; obtaining the risk quotient of the pollutants in the target environmental area; and setting the pollutants into three grades based on the toxicity effects, detection frequencies, and exposure concentrations of each pollutant, and the risk quotient of the pollutants in the target environmental area.

[0004] Currently, when evaluating the toxicity effects of pollutant combinations, there is a lack of a quantitative, probability-based method. It mainly relies on toxicological experimental data and expert experience judgment, and it is difficult to accurately estimate the probability of pollutant combinations causing toxicity effects under different conditions, which affects the accuracy of toxicity risk assessment. Summary of the Invention

[0005] This application aims to at least partly solve one of the technical problems in the related technologies. For this reason, one objective of this application is to propose a method and system for diagnosing and controlling the toxicity effects risks of soil and groundwater pollutants, realizing the risk control of soil and groundwater pollution.

[0006] One aspect of this application provides a method for diagnosing and controlling the toxicity effects risks of soil and groundwater pollutants, including:

[0007] Step S100: Collect the pollutant emission data and toxicological parameters of N pollution sources, calculate the partial correlation coefficients between the pollutants, and construct a pollutant causal relationship diagram based on the toxicological parameters and partial correlation coefficients;

[0008] Step S200: For the pollutant combination S to be studied in the nth pollution source, divide the pollutants into samples by combining the emission data and toxicological parameters, add toxicity effect nodes in the pollutant causal relationship diagram, extract the sub-causal relationship diagram, and determine the pollutant parent node set and toxicity effect parent node set according to the sub-causal relationship diagram;

[0009] Step S300: Calculate the first conditional probability of the pollutant nodes according to the samples, calculate the second conditional probability and the third conditional probability of the toxicity effect nodes, and obtain the conditional probability table of each pollutant node and the conditional probability table of the toxicity effect nodes in the pollutant combination S;

[0010] Step S400: Construct a Bayesian network based on the conditional probability table of the pollutant nodes and the conditional probability table of the toxicity effect nodes, obtain the joint probability distribution of the pollutant combination according to the Bayesian network, acquire the current emission concentration of the pollutant combination to form an evidence vector, and calculate the posterior probability distribution based on the evidence vector;

[0011] Step S500: Obtain the probabilities of the toxicity effect nodes in different states according to the posterior probability distribution, take the state corresponding to the maximum probability as the current severity of the toxicity effect, and when the state is greater than the state threshold, select the pollutant node with the highest pollution weight in the pollutant combination S for priority treatment.

[0012] The specific method for collecting the pollutant emission data and toxicological parameters of N pollution sources, calculating the partial correlation coefficient between pollutants, and constructing the pollutant causal relationship diagram according to the toxicological parameters and partial correlation coefficient is as follows:

[0013] Step S110: Set the statistical interval t1, collect the emission data of pollutants from N pollution sources within n1 statistical intervals. For each statistical interval, form an emission data matrix X, where the emission data of the jth pollutant of the ath pollution source is x aj ;

[0014] Step S120: For each statistical interval, collect the toxicological parameters of the pollution sources;

[0015] Step S130: For the statistical interval closest to the current time, subtract the mean of all elements in each column from each element in each column of the emission data matrix of this statistical interval to obtain the centralized matrix X c , calculate the covariance matrix X of the centralized matrix f , perform an inverse operation on the covariance matrix to obtain the precision matrix X p , calculate the partial correlation coefficient r of the pollutant pair (i, j) according to the precision matrix ij ;

[0016] Step S140: Set the partial correlation coefficient threshold. Pollutant pairs with partial correlation coefficients greater than the partial correlation coefficient threshold are determined to have significant partial correlation coefficients, and the causal relationship of this pollutant pair is discriminated according to toxicological parameters;

[0017] Step S150: Based on the directed and undirected edges between pollutants, construct a pollutant causal relationship graph. The nodes in the pollutant causal relationship graph represent pollutants, the edges represent causal relationships, and the weight of the edge is the partial correlation coefficient between pollutants.

[0018] The specific method for discriminating the causal relationship of this pollutant pair according to toxicological parameters is as follows:

[0019] Step S141: Obtain the first emission time of pollutant i and pollutant j. When the first emission time of pollutant i is earlier than that of pollutant j, and the difference in the first emission time |T j -T i | between pollutant i and pollutant j is greater than the time threshold Δt, it is determined that pollutant i is the cause of pollutant j, and a directed edge i→j is added; where, T i represents the first emission time of pollutant i, and T j represents the first emission time of pollutant j;

[0020] Step S142: If pollutant j is a metabolite of pollutant i, then pollutant i is the cause of pollutant j, and a directed edge i→j is added;

[0021] Step S143: If pollutant i and pollutant j come from the same pollution source, there is a common cause relationship between pollutant i and pollutant j, and an undirected edge i—j is added.

[0022] For the pollutant combination S to be studied in the nth pollution source, the specific method of dividing pollutants into samples by combining emission data and toxicological parameters, adding a toxicity effect node in the pollutant causal relationship graph, and extracting a sub-causal relationship graph, and determining the pollutant parent node set and the toxicity effect parent node set according to the sub-causal relationship graph is as follows:

[0023] Step S210: Determine the pollutant combination S to be studied in the nth pollution source. The pollutant combination includes pollutants S 1 、S 2 、...、S k , where k is the number of pollutants in the pollutant combination; determine the pollutants that appear in each statistical interval according to the emission data, and take all the pollutants that appear in each statistical interval and the corresponding emission data and toxicological parameters as a sample, and sort them in chronological order to obtain n1 samples; where, the emission data includes the emission concentration, and when the emission concentration of the pollutant is greater than 0, it means that the pollutant appears;

[0024] Step S220: Add a toxicity effect node "Toxicity" to the pollutant causality graph. For each sample, when the toxicological parameter of the sample is greater than the toxicity threshold, it indicates that the sample has a synergistic toxicity effect. From the pollutants S 1 、S 2 、...、S k draw directed edges pointing to the toxicity effect node, and a sub-causality graph is formed by the pollutant nodes and the toxicity effect node;

[0025] Step S230: Determine the set of toxicity effect parent nodes pa(Toxicity) and the set of pollutant parent nodes pa(S i ) in each sample according to the sub-causality graph.

[0026] The specific method for calculating the first conditional probability of the pollutant node according to the sample, calculating the second conditional probability and the third conditional probability of the toxicity effect node, and obtaining the conditional probability table of each pollutant node and the conditional probability table of the toxicity effect node in the pollutant combination S is as follows:

[0027] Step S310: In each statistical interval, if the pollutant node S i in the pollutant combination appears simultaneously with the given set of pollutant parent nodes pa(S i ), then record the state of the pollutant node S i in this statistical interval as 1, otherwise record it as 0. Count the frequency N(S i , pa(S i )) of the state being 1 in all statistical intervals, count the frequency N(pa(S i )) of the appearance of the set of pollutant parent nodes pa(S i ) in all statistical intervals, and divide the frequency of the state being 1 in all statistical intervals by the frequency of the appearance of the set of pollutant parent nodes pa(S i ) to obtain the first conditional probability P(S i |pa(S i )) of the pollutant node S i under the given set of pollutant parent nodes pa(S i );

[0028] Step S320: Obtain the conditional probability table of the pollutant node S i from the first conditional probabilities of the pollutant node S i under different sets of pollutant parent nodes;

[0029] Step S330: Count the frequency of the set of parent nodes of the toxicity effect node that satisfies the given set of parent nodes of the toxicity effect pa(Toxicity) in all statistical intervals, denoted as N(pa(Toxicity)). In the statistical intervals that satisfy the given set of parent nodes of the toxicity effect, count the frequency of the occurrence of the toxicity effect, denoted as N(Toxicity, pa(Toxicity)). Divide the frequency of the occurrence of the toxicity effect by the frequency of the set of parent nodes that satisfies the given set of parent nodes of the toxicity effect to obtain the second conditional probability P(Toxicity|pa(Toxicity)) of the toxicity effect node under the given set of parent nodes of the toxicity effect;

[0030] Step S340: Set the states of the toxicity effect node as {State 1, State 2,..., State y}, with a total of y states. Count the frequency of each state occurring in the statistical intervals that satisfy the given set of parent nodes of the toxicity effect, denoted as N(state, pa(Toxicity));

[0031] Step S350: Divide the frequency of each state occurring by the frequency of the set of parent nodes that satisfies the given set of parent nodes of the toxicity effect to obtain the third conditional probability P(state|pa(Toxicity)) of each state of the toxicity effect node under the given set of parent nodes of the toxicity effect;

[0032] Step S360: The second conditional probabilities of the toxicity effect node under different sets of parent nodes of the toxicity effect and the third conditional probabilities of each state of the toxicity effect node under different sets of parent nodes of the toxicity effect form the conditional probability table of the complete toxicity effect node.

[0033] The specific method for constructing the Bayesian network based on the conditional probability table of the pollutant node and the conditional probability table of the toxicity effect node, obtaining the joint probability distribution of the pollutant combination according to the Bayesian network, acquiring the current emission concentration of the pollutant combination to form an evidence vector, and calculating the posterior probability distribution based on the evidence vector is as follows:

[0034] Step S410: Corresponding the pollutant nodes and toxicity effect nodes in the sub-causal relationship diagram to each node in the Bayesian network, adding corresponding directed edges in the Bayesian network according to the directed edges in the sub-causal relationship diagram, and taking the conditional probability table of each pollutant node and the conditional probability table of the toxicity effect node as the parameters of the corresponding nodes in the Bayesian network;

[0035] Step S420: Combine the conditional probability tables of each pollutant node according to the Bayesian network to obtain the joint probability distribution P(Toxicity,S 1 ,S 2 ,...,S k ) of the pollutant combination S;

[0036] Step S430: Obtain the emission concentration of each pollutant in the current statistical interval, form the evidence vector E = (e 1 , e 2 ,..., e m ), substitute it into the joint probability distribution, and calculate the probability P(E) of the evidence vector E; where, e m represents the emission concentration of the m-th pollutant observed in the current statistical interval, and m is the number of types of pollutants observed in the current statistical interval;

[0037] Step S440: Based on Bayesian network inference, calculate the posterior probability distribution P(Toxicity|E) of the pollutant combination S under the given evidence vector E.

[0038] The specific method of obtaining the probability of the toxicity effect node in different states according to the posterior probability distribution, and taking the state corresponding to the maximum probability as the current severity of the toxicity effect. When the state is greater than the state threshold, select the pollutant node with the highest pollution weight in the pollutant combination S for priority treatment is as follows:

[0039] Step S510: Obtain the probability of the toxicity effect node in each state according to the posterior probability distribution;

[0040] Step S520: Find the state with the maximum probability, and take the value of this state as the current severity of the toxicity effect. When the severity of the toxicity effect is greater than the state threshold, it means that the current toxicity effect requires pollutant treatment;

[0041] Step S530: Obtain the sum of the weights of the edges of the shortest path between each pollutant node and the toxicity effect node, and combine the current emission concentration of the pollutant to calculate the pollution weight of each pollutant node in the pollutant combination;

[0042] Step S540: Take the pollutant node with the highest pollution weight as the pollutant to be treated preferentially.

[0043] One aspect of the present application provides a soil and groundwater pollutant toxicity effect risk diagnosis and control system, including:

[0044] A pollution data collection module, configured to collect pollutant emission data and toxicological parameters of N pollution sources, calculate the partial correlation coefficient between pollutants, and construct a pollutant causal relationship diagram according to the toxicological parameters and the partial correlation coefficient;

[0045] A parent node determination module, which is used for a pollutant combination S to be studied in the nth pollution source. The pollutants are divided into samples by combining emission data and toxicological parameters, a toxicity effect node is added to the pollutant causal relationship graph, and a sub-causal relationship graph is extracted. The pollutant parent node set and the toxicity effect parent node set are determined according to the sub-causal relationship graph;

[0046] A conditional probability table determination module, which is used to calculate the first conditional probability of pollutant nodes according to the samples, calculate the second conditional probability and the third conditional probability of toxicity effect nodes, and obtain the conditional probability table of each pollutant node in the pollutant combination S and the conditional probability table of the toxicity effect node;

[0047] A posterior probability calculation module, which is used to construct a Bayesian network based on the conditional probability table of pollutant nodes and the conditional probability table of toxicity effect nodes, obtain the joint probability distribution of the pollutant combination according to the Bayesian network, obtain the current emission concentration of the pollutant combination to form an evidence vector, and calculate the posterior probability distribution based on the evidence vector;

[0048] A pollution weight calculation module, which is used to obtain the probabilities of the toxicity effect node in different states according to the posterior probability distribution, take the state corresponding to the maximum probability as the current severity of the toxicity effect, and when the state is greater than the state threshold, select the pollutant node with the highest pollution weight in the pollutant combination S for priority treatment.

[0049] One aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps in the method for diagnosing and controlling the toxicity effect risk of soil and groundwater pollutants are implemented.

[0050] One aspect of the present application provides a readable storage medium, which stores a computer program. The computer program is suitable for being loaded by a processor to execute the steps in the method for diagnosing and controlling the toxicity effect risk of soil and groundwater pollutants.

[0051] The method and system for diagnosing and controlling the toxicity effect risk of soil and groundwater pollutants proposed in the present application have the following advantages compared with the prior art:

[0052] By constructing a pollutant causal relationship graph, the present application clarifies the causal relationship between pollutants, which helps to understand the toxicity mechanism of complex pollutant combinations and provides a basis for formulating targeted pollution prevention and control strategies.

[0053] By introducing toxicity effect nodes, this application intuitively represents the impact of pollutant combinations on the environment and health, quantifies the toxicity risk, provides a new idea for evaluating the harm degree of pollutant combinations, and separately divides the pollutant combination of a pollution source into sub-causal relationship diagrams, reducing the influence of irrelevant factors.

[0054] This application uses a Bayesian network for inference, can dynamically evaluate the toxicity risk of pollutant combinations based on real-time monitored pollutant emission data, and provides support for formulating dynamically adjusted pollution prevention and control strategies.

[0055] The pollution weight index of this application provides a quantitative basis for determining the pollutants to be prioritized for treatment. By preferentially controlling the pollutants with high pollution weights, the overall toxicity risk of the pollutant combination can be minimized, and the optimal allocation of pollution prevention and control resources can be achieved. Brief Description of the Drawings

[0056] Figure 1 It is the method flow chart of the soil and groundwater pollutant toxicity effect risk diagnosis and control method provided by this application;

[0057] Figure 2 It is the sub-causal relationship diagram of the synergistic toxicity effect of the soil and groundwater pollutant toxicity effect risk diagnosis and control method provided by this application;

[0058] Figure 3 It is the method flow chart for calculating the posterior probability distribution provided by this application;

[0059] Figure 4 It is the function module diagram of the soil and groundwater pollutant toxicity effect risk diagnosis and control system provided by this application. Detailed Embodiments

[0060] To better understand this application, more detailed descriptions of various aspects of this application will be made with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of the exemplary embodiments of this application and do not limit the scope of this application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0061] In the accompanying drawings, for the sake of clarity, the sizes, dimensions, and shapes of the elements have been slightly adjusted. The drawings are provided by way of example and are not drawn to an exact scale. As used herein, the terms "substantially", "about", and similar terms are used as terms of approximation and not of degree, and are intended to account for the inherent deviations in measured or calculated values that would be recognized by a person of ordinary skill in the art. Additionally, in this application, the order in which the steps of each process are described does not necessarily represent the order in which these processes occur in actual operation, unless otherwise explicitly specified or derivable from the context.

[0062] It should also be understood that expressions such as "comprising", "including", "having", "containing", and / or "including having" are open-ended rather than closed-ended expressions in this specification, which means that the stated features, elements, and / or components exist, but do not exclude the existence of one or more other features, elements, components, and / or combinations thereof. In addition, when an expression such as "at least one of..." appears after a list of listed features, it modifies the entire list of features rather than just individual elements in the list. Further, when describing the embodiments of this application, the use of "may" means "one or more embodiments of this application". And the term "exemplary" is intended to refer to an example or illustration.

[0063] Unless otherwise defined, all terms used herein (including engineering terms and scientific and technical terms) have the same meaning as commonly understood by a person of ordinary skill in the art to which this application pertains. It should also be understood that, unless explicitly stated in this application, words defined in a common dictionary should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and should not be interpreted in an idealized or overly formal sense.

[0064] It should be noted that, without conflict, the embodiments in this application and the features in the embodiments may be combined with each other. The following will describe this application in detail with reference to the accompanying drawings and in conjunction with the embodiments.

[0065] Example 1

[0066] As Figure 1 shown, the method for diagnosing and controlling the toxicity effect risk of soil and groundwater pollutants provided by this application includes:

[0067] Step S100: Collect the pollutant emission data and toxicological parameters of N pollution sources, calculate the partial correlation coefficients between pollutants, and construct a pollutant causal relationship diagram based on the toxicological parameters and partial correlation coefficients;

[0068] The emission data refers to the concentration of each pollutant of each pollution source over a period of time, and the emission data and toxicological parameters are data collected at each statistical interval within the historical time;

[0069] The pollutants include those directly discharged from pollution sources and new pollutants generated by metabolism among pollutants.

[0070] The specific method for collecting the pollutant emission data and toxicological parameters of N pollution sources, calculating the partial correlation coefficients among pollutants, and constructing a pollutant causal relationship diagram based on the toxicological parameters and partial correlation coefficients is as follows:

[0071] Step S110: Set a statistical interval t1. Collect the emission data of pollutants from N pollution sources within n1 statistical intervals. For each statistical interval, form an emission data matrix X, where the emission data of the j-th pollutant from the a-th pollution source is x aj ;

[0072] Step S120: For each statistical interval, collect the toxicological parameters of the pollution sources;

[0073] Step S130: For the statistical interval closest to the current time, subtract the mean of all elements in each column from each element in each column of the emission data matrix of this statistical interval to obtain a centered matrix. Calculate the covariance matrix of the centered matrix, perform an inverse operation on the covariance matrix to obtain a precision matrix, and calculate the partial correlation coefficient of pollutant pair (i, j) based on the precision matrix;

[0074] The calculation formula for the centered matrix is: where μ represents the mean of all elements in each column, and T represents the transpose symbol;

[0075] The calculation formula for the covariance matrix is:

[0076] The calculation formula for the precision matrix is:

[0077] The calculation formula for the partial correlation coefficient of pollutant pair (i, j) is: where p ij is the element in the i-th row and j-th column of the precision matrix, p ii is the element in the i-th row and i-th column of the precision matrix, p jj is the element in the j-th row and j-th column of the precision matrix;

[0078] The partial correlation coefficient is used to describe the correlation among pollutants after controlling the influence of other pollutants;

[0079] Taking the statistical interval closest to the current time as the statistical interval for calculating the partial correlation coefficient is because this statistical interval is closest to the real-time pollution situation and toxicity effect.

[0080] Step S140: Set the partial correlation coefficient threshold. Pollutant pairs with a partial correlation coefficient greater than the partial correlation coefficient threshold are determined to have a significant partial correlation coefficient, and the causal relationship of this pollutant pair is discriminated according to the toxicological parameters;

[0081] The partial correlation coefficient threshold is set by those skilled in the art according to actual needs;

[0082] The specific method for discriminating the causal relationship of this pollutant pair according to the toxicological parameters is as follows:

[0083] Step S141: Obtain the first emission time of pollutant i and pollutant j. When the first emission time of pollutant i is earlier than that of pollutant j, and the difference in the first emission time between pollutant i and pollutant j |T j -T i | is greater than the time threshold Δt, then it is determined that pollutant i is the cause of pollutant j, and a directed edge i→j is added; where, T i represents the first emission time of pollutant i, and T j represents the first emission time of pollutant j;

[0084] The time threshold Δt is set by those skilled in the art according to actual needs;

[0085] Step S142: If pollutant j is a metabolite of pollutant i, then pollutant i is the cause of pollutant j, and a directed edge i→j is added;

[0086] Step S143: If pollutant i and pollutant j come from the same pollution source, then there is a common cause relationship between pollutant i and pollutant j, and an undirected edge i—j is added;

[0087] When there is a two-way causal relationship between pollutant i and pollutant j, then a two-way edge is used When pollutant i and pollutant j satisfy both the causal relationship in Step S141 and Step S142 and the common cause relationship in Step S143, then the directed edge of the causal relationship is added first, and an undirected edge is added on the basis of the directed edge.

[0088] Step S150: Based on the directed edges and undirected edges between pollutants, construct a pollutant causal relationship graph. The nodes in the pollutant causal relationship graph represent pollutants, the edges represent causal relationships, and the weights of the edges are the partial correlation coefficients between pollutants.

[0089] The above steps collect the emission data and toxicological parameters of pollution sources, providing a data basis for subsequent analysis, calculating the partial correlation coefficients between pollutants to quantify the correlation between pollutants, and constructing a causal relationship graph of pollutants based on the toxicological parameters and partial correlation coefficients to reveal the causal relationship between pollutants, providing a framework for adding toxicity effect nodes, extracting sub-causal relationship graphs, and constructing Bayesian networks.

[0090] Step S200: For the pollutant combination S to be studied in the nth pollution source, divide the pollutants into samples by combining the emission data and toxicological parameters, add toxicity effect nodes to the pollutant causal relationship graph, extract the sub-causal relationship graph, and determine the pollutant parent node set and toxicity effect parent node set according to the sub-causal relationship graph;

[0091] The toxicity effect node refers to the node of the combined toxicity effect caused by the pollutant combination;

[0092] The specific method for dividing the pollutants into samples by combining the emission data and toxicological parameters for the pollutant combination S to be studied in the nth pollution source, adding toxicity effect nodes to the pollutant causal relationship graph, extracting the sub-causal relationship graph, and determining the pollutant parent node set and toxicity effect parent node set according to the sub-causal relationship graph is as follows:

[0093] Step S210: Determine the pollutant combination S to be studied in the nth pollution source, where the pollutant combination includes pollutants S 1 、S 2 、...、S k , and k is the number of pollutants in the pollutant combination; determine the pollutants that appear in each statistical interval according to the emission data, and take all the pollutants that appear in each statistical interval and the corresponding emission data and toxicological parameters as a sample, and sort them in chronological order to obtain n1 samples; among them, the emission data includes the emission concentration, and when the emission concentration of the pollutant is greater than 0, it means that the pollutant appears;

[0094] Since the total number of statistical intervals is n1 and the samples are divided according to the statistical intervals, the total number of samples obtained is also n1;

[0095] Step S220: Add a toxicity effect node Toxicity to the pollutant causal relationship graph. For each sample, when the toxicological parameter of the sample is greater than the toxicity threshold, it means that the sample has a combined toxicity effect. Draw directed edges from pollutants S 1 、S 2 、...、S k to point to the toxicity effect node, and a sub-causal relationship graph is formed by the pollutant nodes and the toxicity effect nodes;

[0096] Optionally, if there are other pollutants in the pollutant causal relationship diagram that affect the toxicity effect of the pollutant, add the other pollutant nodes to the sub-causal relationship diagram;

[0097] Step S230: Determine the set of parent nodes of the toxicity effect pa(Toxicity) and the set of parent nodes of the pollutant pa(S i ) in each sample according to the sub-causal relationship diagram.

[0098] The above steps divide the pollutants into different samples according to the pollutant combinations to be studied, in combination with emission data and toxicological parameters, add toxicity effect nodes in the pollutant causal relationship diagram, connect the pollutant nodes with the toxicity effect nodes, extract the sub-causal relationship diagram containing the pollutant nodes and the toxicity effect nodes, and determine the set of pollutant parent nodes and the set of parent nodes of the toxicity effect according to the sub-causal relationship diagram. Dividing the samples can analyze the effects of different pollutant combinations targeted; adding toxicity effect nodes can associate the pollutants with the toxicity effects; extracting the sub-causal relationship diagram can simplify the analysis scope; determining the set of parent nodes provides a basis for calculating the conditional probability.

[0099] Step S300: Calculate the first conditional probability of the pollutant nodes according to the samples, calculate the second conditional probability and the third conditional probability of the toxicity effect nodes, and obtain the conditional probability table of each pollutant node and the conditional probability table of the toxicity effect nodes in the pollutant combination S;

[0100] The specific method for calculating the first conditional probability of the pollutant nodes according to the samples, calculating the second conditional probability and the third conditional probability of the toxicity effect nodes, and obtaining the conditional probability table of each pollutant node and the conditional probability table of the toxicity effect nodes in the pollutant combination S is as follows:

[0101] Step S310: In each statistical interval, if the pollutant node S in the pollutant combination i appears simultaneously with the given set of parent nodes of the pollutant pa(S i ), record the state of the pollutant node S i in this statistical interval as 1, otherwise record it as 0. Count the frequency N(S i , pa(S i )) of the state being 1 in all statistical intervals, count the frequency N(pa(S i )) of the appearance of the set of parent nodes of the pollutant pa(S i ) in all statistical intervals, and divide the frequency of the state being 1 in all statistical intervals by the frequency of the appearance of the set of parent nodes of the pollutant pa(S i ) to obtain the first conditional probability of the pollutant node S i under the given set of parent nodes of the pollutant pa(S i );

[0102] The pollutant node S i The calculation formula for the first conditional probability under a given set of pollutant parent nodes pa(S i ) is as follows:

[0103] Step S320: Obtain the conditional probability table of the pollutant node S from the first conditional probabilities of the pollutant node S i under different sets of pollutant parent nodes; i ;

[0104] Step S330: Count the frequency of the set of parent nodes of the toxicity effect node that satisfies the given set of toxicity effect parent nodes pa(Toxicity) in all statistical intervals, denoted as N(pa(Toxicity)). In the statistical intervals that satisfy the given set of toxicity effect parent nodes, count the frequency of the occurrence of the toxicity effect, denoted as N(Toxicity, pa(Toxicity)). Divide the frequency of the occurrence of the toxicity effect by the frequency of the set of parent nodes that satisfies the given set of toxicity effect parent nodes to obtain the second conditional probability of the toxicity effect node under the given set of toxicity effect parent nodes;

[0105] The calculation formula for the second conditional probability of the toxicity effect node under the given set of toxicity effect parent nodes is:

[0106] Step S340: Set the states of the toxicity effect node as {State 1, State 2,..., State y}, with a total of y states. Count the frequency of each state that occurs in the statistical intervals that satisfy the given set of toxicity effect parent nodes, denoted as N(state, pa(Toxicity));

[0107] Preferably, the states of the toxicity effect node are divided into four states: 4, 3, 2, and 1, corresponding to severe, moderate, mild, and non-toxic, respectively;

[0108] Step S350: Divide the frequency of each state that occurs by the frequency of the set of parent nodes that satisfies the given set of toxicity effect parent nodes to obtain the third conditional probability of each state of the toxicity effect node under the given set of toxicity effect parent nodes;

[0109] The calculation formula for the third conditional probability is:

[0110] Step S360: Construct a complete conditional probability table of the toxicity effect node from the second conditional probabilities of the toxicity effect node under different sets of toxicity effect parent nodes and the third conditional probabilities of each state of the toxicity effect node under different sets of toxicity effect parent nodes.

[0111] The above steps are used to calculate the conditional probability table, which quantifies the probability distributions of pollutant nodes and toxicity effect nodes under different conditions and is an important parameter for constructing a Bayesian network.

[0112] Exemplarily, as Figure 2 shown, it is a sub-causal relationship diagram of the combined toxicity effect provided by this application. To study the probability of the combined toxicity effect of pollutant combinations A, B, and C, a toxicity effect node Toxicity is added to the pollutant causal relationship diagram, and directed edges are drawn from the pollutant combinations A, B, and C to point to the toxicity effect node. From the pollutant causal relationship diagram, it is known that pollutant D is produced due to the metabolism between pollutants B and C. Then, pollutant D, pollutant combinations A, B, and C, and the toxicity effect node Toxicity form a sub-causal relationship diagram;

[0113] According to the chain rule of the Bayesian network, P(Toxicity,A,B,C,D) = P(Toxicity|D) × P(D|B,C) × P(B|A) × P(C|A) × P(A). Given the values of the parent nodes, the child node is independent of its non-descendant nodes.

[0114] Step S400: Construct a Bayesian network based on the conditional probability tables of pollutant nodes and toxicity effect nodes, obtain the joint probability distribution of pollutant combinations according to the Bayesian network, acquire the current emission concentration of the pollutant combination to form an evidence vector, and calculate the posterior probability distribution based on the evidence vector;

[0115] The specific method for constructing a Bayesian network based on the conditional probability tables of pollutant nodes and toxicity effect nodes, obtaining the joint probability distribution of pollutant combinations according to the Bayesian network, acquiring the current emission concentration of the pollutant combination to form an evidence vector, and calculating the posterior probability distribution is as follows:

[0116] Step S410: Corresponding the pollutant nodes and toxicity effect nodes in the sub-causal relationship diagram to each node in the Bayesian network, adding corresponding directed edges in the Bayesian network according to the directed edges in the sub-causal relationship diagram, and using the conditional probability tables of each pollutant node and the conditional probability table of the toxicity effect node as the parameters of the corresponding nodes in the Bayesian network;

[0117] The nodes in the Bayesian network are the pollutant nodes and toxicity effect nodes in the sub-causal relationship diagram;

[0118] Step S420: Combine the conditional probability tables of each pollutant node according to the Bayesian network to obtain the joint probability distribution P(Toxicity,S 1 ,S 2 ,...,S k ) of the pollutant combination;

[0119] The combined conditional probability tables of each pollutant node according to the Bayesian network to obtain the calculation formula for the joint probability distribution of the pollutant combination S is: P(Toxicity,S 1 ,S 2 ,...,S k ) = P(Toxicity|S 1 ,S 2 ,...,S k ) × ∏ i P(S i |pa(S i ))), where P(Toxicity|S 1 ,S 2 ,...,S k ) represents the conditional probability of the toxicity effect node, and P(S i |pa(S i )) is the first conditional probability of the pollutant node S i , and pa(S i ) represents the set of pollutant parent nodes;

[0120] The conditional probability of the toxicity effect node is the second conditional probability when the set of toxicity effect parent nodes pa(Toxicity) is (S 1 ,S 2 ,...,S k );

[0121] The joint probability distribution can be decomposed into the product of the conditional probabilities of each node, obtained from the conditional probability tables of the pollutant nodes and toxicity effect nodes calculated in step S300;

[0122] The Bayesian network outputs the values of the conditional probabilities of each pollutant node decomposed in the joint probability distribution, and substitutes them into the calculation formula of the joint probability distribution to calculate the value of the joint probability distribution of the pollutant combination S.

[0123] Step S430: Obtain the emission concentration of each pollutant in the current statistical interval, and form the evidence vector E = (e 1 ,e 2 ,...,e m ), and substitute it into the joint probability distribution to calculate the probability of the evidence vector E; where e m represents the emission concentration of the m-th pollutant observed in the current statistical interval, and m is the number of types of pollutants observed in the current statistical interval;

[0124] The calculation formula for the probability of the evidence vector E is:

[0125] The evidence vector refers to the emission concentration of each pollutant in the current statistical interval;

[0126] Step S440: Calculate the posterior probability distribution P(Toxicity|E) of the pollutant combination S under the given evidence vector E based on Bayesian network inference;

[0127] The calculation formula for the posterior probability distribution is as follows: where P(Toxicity, E) represents the joint probability of the simultaneous occurrence of the toxicity effect node and the evidence vector;

[0128] The posterior probability distribution represents the state distribution of the toxicity effect node under the condition of the known evidence vector E.

[0129] Figure 3 It is the flowchart of the calculation method for the posterior probability distribution provided by this application.

[0130] The Bayesian network in the above steps can comprehensively consider the causal relationship and conditional probability between pollutants and calculate the joint probability distribution; the posterior probability distribution can update the state probability of the toxicity effect node according to the current evidence vector, providing a basis for evaluating the severity of the toxicity effect.

[0131] Step S500: Obtain the probabilities of the toxicity effect node in different states according to the posterior probability distribution, and take the state corresponding to the maximum probability as the current severity of the toxicity effect. When the state is greater than the state threshold, select the pollutant node with the highest pollution weight in the pollutant combination S for priority treatment;

[0132] The specific method of obtaining the probabilities of the toxicity effect node in different states according to the posterior probability distribution, taking the state corresponding to the maximum probability as the current severity of the toxicity effect, and selecting the pollutant node with the highest pollution weight in the pollutant combination S for priority treatment when the state is greater than the state threshold is as follows:

[0133] Step S510: Obtain the probabilities of the toxicity effect node in each state according to the posterior probability distribution;

[0134] Step S520: Find the state with the maximum probability, and take the value of this state as the current severity of the toxicity effect. When the severity of the toxicity effect is greater than the state threshold, it indicates that the current toxicity effect requires pollutant treatment;

[0135] The state threshold is set by those skilled in the art according to actual needs;

[0136] Step S530: Obtain the sum of the weights of the edges of the shortest path between each pollutant node and the toxicity effect node, and combine the current emission concentration of the pollutant to calculate the pollution weight of each pollutant node in the pollutant combination;

[0137] The calculation formula for the pollution weight of each pollutant node is: where θ, β, and γ are adjustment parameters, sumRi represents the sum of the weights of the edges of the shortest path between the pollutant node S i and the toxicity effect node, and V i represents the current emission concentration of the pollutant node S i ;

[0138] The adjustment parameters are set to appropriate values according to the experience of domain experts and the results of data analysis;

[0139] Step S540: Take the pollutant node with the highest pollution weight as the pollutant to be treated preferentially.

[0140] Through the above steps of comparing the posterior probabilities, the severity of the current toxicity effect can be judged; combined with the pollution weight, the pollutant that has the greatest impact on the toxicity effect can be determined, and a treatment plan can be formulated accordingly.

[0141] Embodiment 2

[0142] As Figure 4 shown, the soil and groundwater pollutant toxicity effect risk diagnosis and control system provided by the present application includes:

[0143] A pollution data collection module, which is used to collect the pollutant emission data and toxicological parameters of N pollution sources, calculate the partial correlation coefficient between pollutants, and construct a pollutant causal relationship diagram according to the toxicological parameters and the partial correlation coefficient;

[0144] A parent node determination module, which is used for the pollutant combination S to be studied in the nth pollution source, divides the pollutants into samples by combining the emission data and toxicological parameters, adds a toxicity effect node in the pollutant causal relationship diagram, extracts a sub-causal relationship diagram, and determines a pollutant parent node set and a toxicity effect parent node set according to the sub-causal relationship diagram;

[0145] A conditional probability table determination module, which is used to calculate the first conditional probability of the pollutant node according to the sample, calculate the second conditional probability and the third conditional probability of the toxicity effect node, and obtain the conditional probability table of each pollutant node and the conditional probability table of the toxicity effect node in the pollutant combination S;

[0146] The posterior probability calculation module is used to construct a Bayesian network based on the conditional probability table of the pollutant nodes and the conditional probability table of the toxicity effect nodes, obtain the joint probability distribution of the pollutant combinations according to the Bayesian network, acquire the current emission concentration of the pollutant combinations to form an evidence vector, and calculate the posterior probability distribution based on the evidence vector;

[0147] The pollution weight calculation module is used to obtain the probabilities of the toxicity effect nodes in different states according to the posterior probability distribution, take the state corresponding to the maximum probability as the current severity of the toxicity effect, and when the state is greater than the state threshold, select the pollutant node with the highest pollution weight in the pollutant combination S for priority treatment.

[0148] Embodiment 3

[0149] According to another aspect of the present application, an electronic device is also provided. The electronic device may include one or more processors and one or more memories. Among them, computer-readable code is stored in the memory, and when the computer-readable code is run by one or more processors, it can execute the soil and groundwater pollutant toxicity effect risk diagnosis and control method as described above.

[0150] The method or system according to an embodiment of the present application can also be implemented by means of the architecture of an electronic device. The electronic device may include a bus, one or more CPUs, a read-only memory (ROM), a random access memory (RAM), a communication port connected to a network, input / output components, a hard disk, etc. The storage device in the electronic device, such as the ROM or the hard disk, can store the method for diagnosing and controlling the toxic effects of soil and groundwater pollutants provided by the present application. The method for diagnosing and controlling the toxic effects of soil and groundwater pollutants may, for example, include: collecting pollutant emission data and toxicological parameters of N pollution sources, calculating the partial correlation coefficients between pollutants, and constructing a pollutant causal relationship diagram based on the toxicological parameters and the partial correlation coefficients; for the pollutant combination S to be studied in the nth pollution source, dividing the pollutants into samples in combination with the emission data and the toxicological parameters, adding a toxic effect node in the pollutant causal relationship diagram, and extracting a sub-causal relationship diagram, and determining a pollutant parent node set and a toxic effect parent node set according to the sub-causal relationship diagram; calculating the first conditional probability of the pollutant node according to the sample, calculating the second conditional probability and the third conditional probability of the toxic effect node, and obtaining a conditional probability table of each pollutant node and a conditional probability table of the toxic effect node in the pollutant combination S; constructing a Bayesian network based on the conditional probability table of the pollutant node and the conditional probability table of the toxic effect node, obtaining the joint probability distribution of the pollutant combination according to the Bayesian network, obtaining the current emission concentration of the pollutant combination to form an evidence vector, and calculating the posterior probability distribution based on the evidence vector; obtaining the probabilities when the toxic effect node is in different states according to the posterior probability distribution, taking the state corresponding to the maximum probability as the current severity of the toxic effect, and when the state is greater than the state threshold, selecting the pollutant node with the highest pollution weight in the pollutant combination S for priority treatment. Further, the electronic device may also include a user interface. Of course, when implementing different devices, one or more components in the electronic device may be omitted according to actual needs.

[0151] Example 4

[0152] According to an embodiment of the present application, a readable storage medium is provided. A computer-readable instruction is stored on the computer-readable storage medium. When the computer-readable instruction is run by a processor, it can execute the method for diagnosing and controlling the toxic effects of soil and groundwater pollutants according to the embodiment of the present application described with reference to the above drawings. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and cache, etc. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc.

[0153] In addition, according to the embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the present application provides a non-transitory machine-readable storage medium storing machine-readable instructions that can be run by a processor to execute instructions corresponding to the method steps provided by the present application. For example: collecting pollutant emission data and toxicology parameters of N pollution sources, calculating the partial correlation coefficients between pollutants, constructing a pollutant causal relationship graph based on the toxicology parameters and partial correlation coefficients; for the pollutant combination S to be studied in the nth pollution source, dividing the pollutants into samples by combining the emission data and toxicology parameters, adding a toxicity effect node in the pollutant causal relationship graph, and extracting a sub-causal relationship graph, and determining the pollutant parent node set and the toxicity effect parent node set according to the sub-causal relationship graph; calculating the first conditional probability of the pollutant nodes according to the samples, calculating the second conditional probability and the third conditional probability of the toxicity effect nodes, obtaining the conditional probability table of each pollutant node and the conditional probability table of the toxicity effect node in the pollutant combination S; constructing a Bayesian network based on the conditional probability table of the pollutant nodes and the conditional probability table of the toxicity effect nodes, obtaining the joint probability distribution of the pollutant combination according to the Bayesian network, obtaining the current emission concentration of the pollutant combination to form an evidence vector, and calculating the posterior probability distribution based on the evidence vector; obtaining the probabilities of the toxicity effect nodes in different states according to the posterior probability distribution, taking the state corresponding to the maximum probability as the current severity of the toxicity effect, and when the state is greater than the state threshold, selecting the pollutant node with the highest pollution weight in the pollutant combination S for priority treatment. When this computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0154] The methods, apparatuses, and devices of the present application can be implemented in many ways. For example, the methods, apparatuses, and devices of the present application can be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of the steps for the method is only for illustration, and the steps of the method of the present application are not limited to the specific order described above unless otherwise specifically stated. In addition, in some embodiments, the present application can also be implemented as a program recorded in a recording medium, and these programs include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers a recording medium storing a program for executing the method according to the present application.

[0155] In addition, parts of the above technical solutions provided in the embodiments of the present application that are consistent with the corresponding technical solutions in the prior art in terms of implementation principles are not described in detail to avoid excessive elaboration.

[0156] The specific embodiments described above further elaborate in detail the objectives, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only the specific embodiments of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for risk diagnosis and control of toxic effects of soil and groundwater pollutants, characterized in that: include: Collect pollutant emission data and toxicological parameters of N pollution sources, calculate the partial correlation coefficients between pollutants, and construct a pollutant causal relationship diagram based on toxicological parameters and partial correlation coefficients; For the pollutant combination S to be studied in the nth pollution source, the pollutants are divided into samples in combination with emission data and toxicological parameters, toxic effect nodes are added to the pollutant causal relationship graph, and the sub-causal relationship graph is extracted. The pollutant parent node set and the toxic effect parent node set are determined according to the sub-causal relationship graph; Calculate the first conditional probability of the pollutant node according to the sample, calculate the second conditional probability and the third conditional probability of the toxic effect node, and obtain the conditional probability table of each pollutant node and the conditional probability table of the toxic effect node in the pollutant combination S; A Bayesian network is constructed based on the conditional probability table of pollutant nodes and the conditional probability table of toxic effect nodes. The joint probability distribution of pollutant combinations is obtained based on the Bayesian network. The current emission concentration of the pollutant combination is obtained to form an evidence vector. The posterior probability distribution is calculated based on the evidence vector. According to the posterior probability distribution, the probability of the toxic effect node being in different states is obtained, and the state corresponding to the maximum probability is taken as the current severity of the toxic effect. When the state is greater than the state threshold, the pollutant node with the highest pollution weight in the pollutant combination S is selected for priority treatment.

2. The method for diagnosing and controlling the toxic effects of soil and groundwater pollutants according to claim 1, characterized in that: The specific method of collecting pollutant emission data and toxicological parameters of N pollution sources, calculating the partial correlation coefficients between pollutants, and constructing a pollutant causal relationship diagram according to the toxicological parameters and partial correlation coefficients is as follows: Set the statistical interval t1, collect the emission data of pollutants from N pollution sources within n1 statistical intervals, and construct the emission data matrix X for each statistical interval, where the emission data of the jth pollutant from the ath pollution source is x aj ; For each statistical interval, toxicological parameters of the pollution sources were collected; For the statistical interval closest to the current time, subtract the mean of all elements in each column from each element in the emission data matrix of the statistical interval to obtain the central matrix X c , calculate the covariance matrix X of the centered matrix f , perform the inverse operation on the covariance matrix to obtain the precision matrix X p , calculate the partial correlation coefficient r of pollutant pair (i, j) according to the precision matrix ij ; A partial correlation coefficient threshold is set, and the pollutant pairs with partial correlation coefficients greater than the partial correlation coefficient threshold are judged to have significant partial correlation coefficients, and the causal relationship of the pollutant pairs is judged based on toxicological parameters; Based on the directed and undirected edges between pollutants, a pollutant causal relationship graph is constructed. The nodes in the pollutant causal relationship graph represent pollutants, the edges represent causal relationships, and the weights of the edges are the partial correlation coefficients between pollutants.

3. The method for diagnosing and controlling the toxic effects of soil and groundwater pollutants according to claim 2, characterized in that: The specific method for determining the causal relationship between the pollutants based on toxicological parameters is as follows: Get the first emission time of pollutant i and pollutant j. When the first emission time of pollutant i is earlier than that of pollutant j, and the first emission time difference between pollutant i and pollutant j is |T j -T i | is greater than the time threshold Δt, then pollutant i is determined to be the cause of pollutant j, and a directed edge i→j is added; where T i represents the first emission time of pollutant i, T j represents the first emission time of pollutant j; If pollutant j is a metabolite of pollutant i, then pollutant i is the cause of pollutant j, and a directed edge i→j is added; If pollutant i and pollutant j come from the same pollution source, there is a common cause relationship between pollutant i and pollutant j, and an undirected edge i—j is added.

4. The method for diagnosing and controlling the toxic effects of soil and groundwater pollutants according to claim 3, characterized in that: For the pollutant combination S to be studied in the nth pollution source, the pollutants are divided into samples in combination with emission data and toxicological parameters, toxic effect nodes are added to the pollutant causal relationship graph, and the sub-causal relationship graph is extracted. The specific method for determining the pollutant parent node set and the toxic effect parent node set according to the sub-causal relationship graph is: Determine the pollutant combination S to be studied in the nth pollution source, wherein the pollutant combination includes pollutants S1, S2, ..., S k , k is the number of pollutants in the pollutant combination; the pollutants appearing in each statistical interval are determined according to the emission data, all pollutants appearing in each statistical interval and the corresponding emission data and toxicological parameters are taken as a sample, and are sorted in chronological order to obtain n1 samples; wherein, the emission data includes emission concentration, and when the emission concentration of a pollutant is greater than 0, it indicates that the pollutant appears; Add a toxic effect node Toxicity in the pollutant causal relationship diagram. For each sample, when the toxicological parameter of the sample is greater than the toxicity threshold, it means that the sample has a synergistic toxic effect. k Directed edges are drawn to the toxic effect nodes, and a sub-causal relationship graph is formed by the pollutant nodes and the toxic effect nodes; According to the child causal relationship diagram, the toxic effect parent node set pa (Toxicity) and the pollutant parent node set pa (S i ).

5. The method for diagnosing and controlling the toxic effects of soil and groundwater pollutants according to claim 4, characterized in that: The specific method of calculating the first conditional probability of the pollutant node according to the sample, calculating the second conditional probability and the third conditional probability of the toxic effect node, and obtaining the conditional probability table of each pollutant node and the conditional probability table of the toxic effect node in the pollutant combination S is: In each statistical interval, if the pollutant node S in the pollutant combination i With the given pollutant parent node set pa(S i ) appear at the same time, the pollutant node S i The state in the statistical interval is recorded as 1, otherwise it is recorded as 0, and the frequency N (S) of the state being 1 in all statistical intervals is counted. i ,pa(S i )), count the pollutant parent node set pa(S i ) appears N(pa(S i )), divide the frequency of state 1 in all statistical intervals by the pollutant parent node set pa(S i ) appears, and the pollutant node S is obtained i In a given pollutant parent node set pa(S i ) under the first conditional probability P(S i |pa(S i )); By pollutant node S i The first conditional probability under different pollutant parent node sets obtains the pollutant node S i The conditional probability table of ; Count the frequency of the parent node set of the toxic effect node satisfying the given toxic effect parent node set pa(Toxicity) in all statistical intervals, recorded as N(pa(Toxicity)), and the frequency of the occurrence of the toxic effect in the statistical interval satisfying the given toxic effect parent node set, recorded as N(Toxicity, pa(Toxicity)), and divide the frequency of the occurrence of the toxic effect by the frequency of satisfying the given toxic effect parent node set to obtain the second conditional probability P(Toxicity|pa(Toxicity)) of the toxic effect node under the given toxic effect parent node set; Set the state of the toxic effect node to {State 1, State 2, ..., State y}, with a total of y states. Count the frequency of each state in the statistical interval that satisfies the given set of toxic effect parent nodes, recorded as N(state, pa(Toxicity)); Divide the frequency of each state by the frequency of satisfying a given set of toxic effect parent nodes to obtain the third conditional probability P(state|pa(Toxicity)) of each state of the toxic effect node under the given set of toxic effect parent nodes; The complete conditional probability table of the toxic effect node is composed of the second conditional probability of the toxic effect node under different toxic effect parent node sets and the third conditional probability of each state of the toxic effect node under different toxic effect parent node sets.

6. The method for diagnosing and controlling the toxic effects of soil and groundwater pollutants according to claim 5, characterized in that: The conditional probability table based on the pollutant node and the conditional probability table of the toxic effect node is used to construct a Bayesian network, the joint probability distribution of the pollutant combination is obtained according to the Bayesian network, the current emission concentration of the pollutant combination is obtained to form an evidence vector, and the specific method for calculating the posterior probability distribution based on the evidence vector is as follows: The pollutant nodes and toxic effect nodes in the sub-causal relationship graph correspond to each node in the Bayesian network, and the corresponding directed edges are added to the Bayesian network according to the directed edges of the sub-causal relationship graph. The conditional probability table of each pollutant node and the conditional probability table of the toxic effect node are used as parameters of the corresponding nodes in the Bayesian network. The conditional probability tables of each pollutant node are combined according to the Bayesian network to obtain the joint probability distribution P (Toxicity, S1, S2, ..., S k ); Obtain the emission concentration of each pollutant in the current statistical interval, and form the evidence vector E = (e1, e2, ..., e m ), substitute into the joint probability distribution, and calculate the probability P(E) of the evidence vector E; where e m It represents the emission concentration of the mth pollutant observed in the current statistical interval, where m is the number of pollutant types observed in the current statistical interval; The posterior probability distribution P(Toxicity|E) of the pollutant combination S under a given evidence vector E is calculated based on Bayesian network reasoning.

7. The method for diagnosing and controlling the toxic effects of soil and groundwater pollutants according to claim 6, characterized in that: The specific method of obtaining the probability of the toxic effect node being in different states according to the posterior probability distribution, taking the state corresponding to the maximum probability as the current severity of the toxic effect, and selecting the pollutant node with the highest pollution weight in the pollutant combination S for priority treatment when the state is greater than the state threshold is: The probability of the toxic effect node being in each state is obtained according to the posterior probability distribution; Find the state with the highest probability and use the value of this state as the current severity of the toxic effect. When the severity of the toxic effect is greater than the state threshold, it means that the current toxic effect requires pollutant control. Obtain the sum of the weights of the edges of the shortest path from each pollutant node to the toxic effect node, and calculate the pollution weight of each pollutant node in the pollutant combination in combination with the current emission concentration of the pollutant; The pollutant nodes with the highest pollution weights are selected as the pollutants to be treated first.

8. A soil and groundwater pollutant toxic effect risk diagnosis and control system, which is used to implement the soil and groundwater pollutant toxic effect risk diagnosis and control method according to any one of claims 1 to 7, characterized in that: include: The pollution data collection module is used to collect the pollutant emission data and toxicological parameters of N pollution sources, calculate the partial correlation coefficients between pollutants, and construct a pollutant causal relationship diagram based on the toxicological parameters and partial correlation coefficients; The parent node determination module is used to divide the pollutants into samples according to the emission data and toxicological parameters for the pollutant combination S to be studied in the nth pollution source, add toxic effect nodes to the pollutant causal relationship graph, extract the sub-causal relationship graph, and determine the pollutant parent node set and the toxic effect parent node set according to the sub-causal relationship graph; A conditional probability table determination module is used to calculate the first conditional probability of the pollutant node according to the sample, calculate the second conditional probability and the third conditional probability of the toxic effect node, and obtain the conditional probability table of each pollutant node and the conditional probability table of the toxic effect node in the pollutant combination S; The posterior probability calculation module is used to construct a Bayesian network based on the conditional probability table of the pollutant node and the conditional probability table of the toxic effect node, obtain the joint probability distribution of the pollutant combination according to the Bayesian network, obtain the current emission concentration of the pollutant combination to form an evidence vector, and calculate the posterior probability distribution based on the evidence vector; The pollution weight calculation module is used to obtain the probability of the toxic effect node being in different states according to the posterior probability distribution, and take the state corresponding to the maximum probability as the current severity of the toxic effect. When the state is greater than the state threshold, the pollutant node with the highest pollution weight in the pollutant combination S is selected for priority treatment.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the method for diagnosing and controlling the risk of toxic effects of pollutants in soil and groundwater are implemented as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which is suitable for loading by a processor to execute the steps in the soil and groundwater pollutant toxic effect risk diagnosis and control method as described in any one of claims 1-7.

Images