A method for tracing the source of water pollution based on multi-factor analysis

Abstract

The present invention discloses a method for tracing the source of water environment pollution based on multi-factor analysis, which relates to the technical field of tracing the source of water environment pollution, and includes the following steps: according to the basic characteristics of the water body and the known variation law of pollutant concentration, the initial pollutant concentration sampling frequency is set, and sampling is performed at different time points to obtain the concentration information of pollutants in the water body, and establish a basic data set for simulating the diffusion and migration path of pollutants; while sampling the pollutant concentration, the underwater environment information is comprehensively collected. The present invention divides the pollutant concentration variation into complex variation type and normal variation type by introducing the pollutant resuspension assessment coefficient and the machine learning model, thereby improving the recognition accuracy and the ability to identify pollution risks in advance, and for complex and changing environments, intelligently adjusts the sampling frequency, dynamically adapts to environmental changes, ensures data accuracy, optimizes resource utilization, and realizes efficient environmental monitoring and management.

Description

Technical Field

[0001] The present invention relates to the technical field of water environment pollution source tracing, and in particular to a water environment pollution source tracing method based on multi-factor analysis. Background Art

[0002] Water pollution source tracing based on multi-factor analysis refers to the use of a variety of different environmental data and analysis techniques to determine the source and cause of water pollution. This method does not only consider a single source of pollution, but also comprehensively considers multiple possible factors, such as industrial emissions, agricultural runoff, urban sewage and natural factors. Through the comprehensive analysis of these different factors, it is possible to more accurately identify the source of pollution and assess its impact on the water environment.

[0003] In specific operations, multi-factor analysis may involve a variety of technical means such as chemical analysis, biological monitoring, geographic information system (GIS) and numerical models. For example, chemical analysis can determine the specific composition of pollutants in water bodies; biological monitoring can assess the impact of pollution on ecosystems; GIS can be used to draw pollution distribution maps; and numerical models can simulate the diffusion and migration paths of pollutants. Combining these data and analysis results can provide a more comprehensive understanding of the sources and dynamic processes of water pollution, thereby providing a scientific basis for pollution prevention and environmental management.

[0004] The prior art has the following deficiencies:

[0005] When simulating the diffusion and migration paths of pollutants, a fixed pollutant concentration sampling frequency is usually used to monitor pollutant concentrations, which is effective under normal circumstances. However, when bottom sediments in water bodies are resuspended into water bodies under specific conditions (such as accelerated water flow or human activities), pollutant concentrations increase rapidly and migration paths become more complicated. A fixed sampling frequency may not be able to capture these rapid changes in a timely manner, causing the model to misjudge the actual migration path of pollutants. If pollutant resuspension cannot be monitored in a timely manner, the response and control of pollution incidents may be delayed, causing pollutants to spread more widely in the water body and affect a larger area.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide a method for tracing the source of water environment pollution based on multi-factor analysis. By introducing a pollutant resuspension assessment coefficient and a machine learning model, the changes in pollutant concentration in the underwater environment are divided into complex change types and normal change types, thereby improving the accuracy of identifying water pollution conditions, timely capturing sediment resuspension events, identifying pollution risks in advance, optimizing sampling frequency and environmental management, and intelligently adjusting the sampling frequency for complex changing environments, dynamically adapting to environmental changes, timely capturing rapid changes in pollutant concentrations, improving data accuracy, optimizing resource utilization, and ensuring efficient environmental monitoring and management to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: a method for tracing the source of water pollution based on multi-factor analysis, comprising the following steps:

[0009] According to the characteristics of the water body and the known variation patterns of pollutant concentrations, the concentration information of pollutants in the water body is obtained by sampling at different time points with the set initial pollutant concentration sampling frequency, and a basic data set is established to simulate the diffusion and migration paths of pollutants.

[0010] While sampling pollutant concentrations, we comprehensively collect underwater environmental information, extract key features that affect pollutant resuspension and diffusion, analyze and process the extracted key features, and input the analyzed and processed key features into a pre-trained machine learning model. Through the analysis of the model, we predict the degree of pollutant resuspension in the current environment.

[0011] Based on the analysis results of the machine learning model, the changes in pollutant concentrations in the current underwater environment are divided into two categories: complex changes and normal changes;

[0012] For situations judged as normal changing environments, data collection will continue at the set initial pollutant concentration sampling frequency. For situations judged as complex changing environments, the actual pollutant sampling frequency will be intelligently regulated based on the initial pollutant concentration sampling frequency to increase the actual pollutant sampling frequency, collect pollutant concentration data at more intensive time intervals, and promptly capture concentration changes after pollutants are re-suspension.

[0013] Preferably, the initial pollutant concentration sampling frequency meets the following conditions:

[0014] First, it is necessary to ensure that the sampling frequency of initial pollutant concentrations is frequent to capture the fluctuations in pollutant concentrations under normal conditions and ensure the continuity and integrity of the data;

[0015] Second, it must be economically feasible, taking into account the limitations of human, material and financial resources, and ensuring sustainable monitoring over a long period of time;

[0016] Third, it must adapt to the characteristics of the water body and be able to representatively reflect the overall condition of the water body.

[0017] Preferably, the key features that are extracted that affect the resuspension and diffusion of pollutants include the scouring force of the water flow on the riverbed and the rate of bubble generation in the sediment. After extraction, the scouring force of the water flow on the riverbed and the rate of bubble generation in the sediment are placed under the detection window for analysis and processing to generate the riverbed bottom shear stress anomaly index and bubble release index respectively.

[0018] Preferably, the analyzed riverbed bottom shear stress anomaly index and bubble release index are input into a pre-trained machine learning model, and a pollutant resuspension assessment coefficient is generated through the model. The degree of pollutant resuspension in the current environment is predicted based on the pollutant resuspension assessment coefficient.

[0019] Preferably, the pollutant resuspension assessment coefficient generated after analyzing and processing the current underwater environmental information under the detection window is compared and analyzed with a preset pollutant resuspension assessment coefficient reference threshold, and the pollutant concentration change of the current underwater environment is divided. The specific division conclusions are as follows:

[0020] If the pollutant resuspension assessment coefficient is greater than the pollutant resuspension assessment coefficient reference threshold, the pollutant concentration change in the current underwater environment is classified as a complex change type;

[0021] If the pollutant resuspension assessment coefficient is less than or equal to the pollutant resuspension assessment coefficient reference threshold, the pollutant concentration change in the current underwater environment is classified as a normal change type.

[0022] Preferably, for the case of a complex changing environment, the actual pollutant sampling frequency is intelligently regulated based on the initial pollutant concentration sampling frequency, and the specific steps for increasing the actual pollutant sampling frequency are as follows:

[0023] The control coefficient is calculated based on the current pollutant resuspension assessment coefficient and the pollutant resuspension assessment coefficient reference threshold to adjust the actual pollutant sampling frequency. The calculation expression is: Among them, Pollutant susp represents the pollutant resuspension assessment coefficient, P threshold Pollutant represents the reference threshold of the pollutant resuspension assessment coefficient. susp >P threshold , K adjust represents the control coefficient, α represents the control parameter, reflecting the control sensitivity, and its value range is 0.1-1.0;

[0024] The actual pollutant sampling frequency is adjusted according to the control coefficient. The adjustment expression is: factual =f initial ·K adjust , where f initial represents the sampling frequency of initial pollutant concentration, f actual Represents the actual pollutant sampling frequency after regulation.

[0025] Preferably, within the detection window, after analyzing and processing the scouring force of the water flow on the riverbed, the steps of generating the abnormal shear stress index of the riverbed bottom are as follows:

[0026] Collect water velocity and water depth data within the detection window as well as particle diameter and density data of riverbed sediments for calculating shear stress;

[0027] Using the water velocity and water depth data, the shear stress of the riverbed is calculated using the following expression: τ = ρ·g·H·S f , where τ represents shear stress, ρ represents water density, g represents gravity acceleration, H represents water depth, and S f Indicates the slope of the riverbed, which is calculated by the water level difference and the length of the river channel. Δh represents the water level difference within the river section, that is, the water level difference between two measuring points, and L represents the horizontal distance between the two measuring points, that is, the length of the river section;

[0028] Calculate the critical shear stress for sediment resuspension and determine the minimum shear stress required for resuspension for comparison with the actual shear stress. The calculation expression is: τ c represents the critical shear stress, ρ s represents the sediment density, d represents the sediment particle diameter, C f represents the drag coefficient;

[0029] Calculate the shear stress anomaly factor, the calculation expression is: E f It represents the shear stress anomaly factor, compares the actual shear stress with the critical shear stress, and evaluates the degree of shear stress anomaly;

[0030] The time weighting factor is introduced to calculate the weighted shear stress within a period of time. The calculation expression is: TWSI stands for time-weighted shear stress, E f (i) represents the shear stress anomaly factor at the i-th moment, T(i) represents the time weight at the i-th moment;

[0031] The time-weighted shear stress is normalized to generate the riverbed bottom shear stress anomaly index, and the formula is as follows: In the formula, BSSI μIt represents the shear stress anomaly index of the riverbed bottom. Max(TWSI) and min(TWSI) represent the maximum and minimum values ​​of the time-weighted shear stress in the detection window, respectively.

[0032] Preferably, after analyzing and processing the bubble generation rate in the sediment, the steps of generating the bubble release index are as follows:

[0033] In the detection window, the basic data of bubble generation rate in the sediment are obtained, including the bubble generation frequency, bubble volume and time point in the sediment. The bubble generation data is expressed as {t k , V k , f k |k=1,2,3,…,n}, n is a positive integer, where t k represents the time of the kth sampling point, V k represents the bubble volume at the kth sampling point, f k Indicates the bubble generation frequency of the kth sampling point;

[0034] Calculate the instantaneous bubble release rate at each time point. The calculation expression is: R k =V k ·f k , where R k Indicates that at time point t k The instantaneous bubble release rate;

[0035] The momentum released by the bubbles is calculated to further quantify the ability of bubbles to disturb the sediment. The expression for the calculation is: P k =V k ·v k ·ρ g , where P k Indicates that at time point t k The bubble release momentum, ρ g represents the gas density, v k Indicates the rising speed of bubbles;

[0036] Taking into account the bubble generation rate and momentum, the cumulative bubble disturbance energy is calculated. The calculation expression is: In the formula, E total Indicates the accumulated bubble disturbance energy within the detection window;

[0037] By detecting the accumulated bubble disturbance energy E in the window total Calculate the bubble release index, the calculation expression is: BRI μ =10·ln(E total +1), where BRI μ Represents the bubble release index.

[0038] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0039] The present invention introduces a pollutant resuspension assessment coefficient and analyzes and processes underwater environmental information based on a machine learning model. It can effectively divide the changes in pollutant concentration in the current underwater environment into two types: complex change type and normal change type. It can significantly improve the accuracy of identifying water pollution conditions and timely capture sediment resuspension events caused by accelerated water flow or human activities. By accurately dividing the types of environmental changes, potential pollution risks can be identified earlier, and preventive and control measures can be taken in advance, thereby avoiding the expansion of the spread of pollutants and reducing the overall impact on the water environment. This division also provides a scientific basis for subsequent sampling frequency adjustments and environmental management, ensuring that the most suitable monitoring strategy can be adopted under different types of changes.

[0040] When a complex changing environment is detected, the present invention intelligently controls the actual sampling frequency based on the initial pollutant concentration sampling frequency, increases the sampling frequency by calculating the control coefficient, and collects pollutant concentration data at more intensive time intervals. This intelligent control method enables the sampling system to dynamically adapt to environmental changes, especially when pollutant resuspension occurs frequently, and can timely capture rapid changes in concentration to ensure the timeliness and accuracy of the data. By adjusting the sampling frequency, more detailed and accurate pollutant concentration change data can be obtained, providing high-quality data support for the simulation of pollutant diffusion and migration paths, which not only improves the responsiveness of the monitoring system, but also optimizes resource utilization, avoids oversampling in normal environments and undersampling in complex environments, thereby achieving efficient environmental monitoring and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0042] Figure 1 The present invention is a method flow chart of a method for tracing the source of water environment pollution based on multi-factor analysis. DETAILED DESCRIPTION

[0043] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0044] The present invention provides Figure 1 A method for tracing the source of water pollution based on multi-factor analysis is shown, comprising the following steps:

[0045] According to the basic characteristics of water bodies and the known variation patterns of pollutant concentrations, the concentration information of pollutants in water bodies is obtained by sampling at different time points with the set initial pollutant concentration sampling frequency, and a basic data set is established to simulate the diffusion and migration paths of pollutants.

[0046] The sampling frequency of initial pollutant concentration should be able to meet the following conditions:

[0047] First, it must be frequent enough to capture typical fluctuations in pollutant concentrations under normal conditions and ensure the continuity and integrity of the data;

[0048] Second, it must be economically feasible, taking into account the limitations of human, material and financial resources to ensure sustainable monitoring over a long period of time.

[0049] Third, it must adapt to the basic characteristics of the water body, such as flow velocity, flow rate and distribution of pollution sources, and be able to representatively reflect the overall condition of the water body.

[0050] By sampling at different time points, the purpose is to systematically collect data on pollutant concentrations in water bodies, which can reflect the dynamic changes of pollutants in water bodies. These sampling points cover different time periods, such as peak, stable and low periods, so as to fully capture the daily fluctuations and abnormal changes in pollutant concentrations. These data establish a detailed basic data set by recording pollutant concentration information at different time points. This data set includes not only the concentration of pollutants, but may also include other relevant environmental parameters such as water temperature, flow rate, pH value, etc. Using this basic data set, further analysis and modeling can be carried out to simulate the diffusion and migration paths of pollutants in water bodies. Through this simulation, the propagation process of pollutants from the source to different locations can be predicted, the scope and impact of pollution can be assessed, and a scientific basis can be provided for pollution control and environmental protection. At the same time, these data can also be used to verify and adjust the model to improve the accuracy and reliability of the simulation. Overall, this process aims to build a comprehensive pollutant diffusion model through detailed data collection and analysis, and provide solid data support for water environment management.

[0051] While sampling pollutant concentrations, we comprehensively collect underwater environmental information, extract key features that affect pollutant resuspension and diffusion, analyze and process the extracted key features, and input the analyzed and processed key features into a pre-trained machine learning model. Through the analysis of the model, we predict the degree of pollutant resuspension in the current environment.

[0052] The key features extracted that affect the resuspension and diffusion of pollutants include the scouring force of water flow on the riverbed and the rate of bubble generation in the sediment (such as methane bubbles). After extraction, the scouring force of water flow on the riverbed and the rate of bubble generation in the sediment are placed under the detection window for analysis and processing, and the shear stress anomaly index and bubble release index of the riverbed bottom are generated respectively. The analyzed and processed shear stress anomaly index and bubble release index of the riverbed bottom are input into the pre-trained machine learning model, and the pollutant resuspension assessment coefficient is generated by the model. The degree of pollutant resuspension in the current environment is predicted based on the pollutant resuspension assessment coefficient.

[0053] When the scouring force of water flow on the riverbed in the water body is large, it will cause the pollutants to be resuspended and diffused. This is because the strong scouring of water flow will increase the kinetic energy of the bottom sediments, so that the particulate matter deposited on the riverbed or lake bottom is resuspended in the water body. Sediments usually contain a large number of pollutants, including heavy metals, organic matter and nutrients. These pollutants are in a relatively stable state in the sediments, but once they are scoured by water flow, the particulate matter carries the pollutants and is resuspended into the water body, thereby increasing the concentration of pollutants in the water body. The resuspended pollutants spread with the water flow, migrate to farther places, and expand the scope of influence. This not only increases the distribution range of pollutants in the water body, but may also affect the health of aquatic organisms and ecosystems. Especially in the case of floods, heavy rains or human activities such as ship navigation, the speed and scouring force of the water flow will be significantly enhanced, resulting in the resuspension and diffusion of pollutants in a larger range and at a higher concentration.

[0054] Within the detection window, after analyzing and processing the scouring force of water flow on the riverbed, the steps to generate the abnormal shear stress index at the bottom of the riverbed are as follows:

[0055] Collect water velocity and water depth data within the detection window as well as particle diameter and density data of riverbed sediments for calculating shear stress;

[0056] It should be noted that water velocity and water depth data can be intelligently acquired through an acoustic Doppler current profiler installed in the river channel, which can measure the velocity and depth distribution of water bodies in real time. The particle diameter and density data of riverbed sediments can be acquired through an automatic sediment sampler and a laser particle size analyzer installed on the riverbed. The automatic sediment sampler collects sediment samples regularly, while the laser particle size analyzer can analyze the particle size and density of these samples online, thereby realizing intelligent data acquisition and providing high-precision data support for subsequent analysis.

[0057] Sediment particle diameter refers to the average size or diameter of particles in the sediment at the bottom of a body of water such as a river, lake, or ocean. It is often used to describe the size of sediment particles to help determine the physical properties and behavior of the sediment. Particle diameter is usually measured in millimeters or microns and can be performed using techniques such as sieve analysis and laser particle size analysis.

[0058] Particle diameter has an important influence on the deposition and resuspension behavior of sediments. Smaller particles (such as clay and fine sand) are more easily disturbed and resuspended by water flow, while larger particles (such as gravel and coarse sand) are more difficult to be transported by water flow. Therefore, understanding the diameter of sediment particles is very important for predicting the dispersion and migration paths of pollutants, because many pollutants are adsorbed on sediment particles and migrate with the movement of particles.

[0059] Using the water velocity and water depth data, the shear stress of the riverbed is calculated using the following expression: τ = ρ·g·H·S f , where τ represents shear stress, ρ represents water density, g represents gravity acceleration, H represents water depth, and S f Indicates the slope of the riverbed, which is calculated by the water level difference and the length of the river channel. Δh represents the water level difference within the river section, that is, the water level difference between two measuring points, and L represents the horizontal distance between the two measuring points, that is, the length of the river section;

[0060] Calculate the critical shear stress for sediment resuspension and determine the minimum shear stress required for resuspension for comparison with the actual shear stress. The calculation expression is: τ c represents the critical shear stress, ρ s represents the sediment density, d represents the sediment particle diameter, C f It represents the drag coefficient, which is determined by the shape and roughness of the sediment particles. The value of the drag coefficient is usually obtained based on experiments and empirical formulas, and depends on the shape, size and fluid dynamics conditions of the sediment particles.

[0061] Calculate the shear stress anomaly factor, the calculation expression is: E f It represents the shear stress anomaly factor, compares the actual shear stress with the critical shear stress, and evaluates the degree of shear stress anomaly;

[0062] The time weighting factor is introduced to calculate the weighted shear stress within a period of time. The calculation expression is: TWSI stands for time-weighted shear stress, E f (i) represents the shear stress anomaly factor at the i-th moment, T(i) represents the time weight at the i-th moment;

[0063] Time weighting refers to the weight values ​​that are assigned to data at different time points in different importance or influence during the analysis or calculation process. It is used to emphasize the importance of data at certain time points relative to data at other time points. For example, in the analysis of riverbed bottom shear stress, if the environmental conditions (such as water velocity, water depth, etc.) at certain time points change dramatically and have a greater impact on the resuspension and diffusion of pollutants, then the data at these time points will be given higher weights to highlight their importance to the overall analysis results. Time weighting helps to more accurately reflect the actual situation, especially when environmental conditions change significantly over time.

[0064] The time-weighted shear stress is normalized to generate the riverbed bottom shear stress anomaly index, and the formula is as follows: In the formula, BSSI μ It represents the shear stress anomaly index of the riverbed bottom. Max(TWSI) and min(TWSI) represent the maximum and minimum values ​​of the time-weighted shear stress in the detection window, respectively.

[0065] It can be seen from the riverbed bottom shear stress anomaly index that, within the detection window, the larger the value of the riverbed bottom shear stress anomaly index generated after the analysis and processing of the water flow's scouring force on the riverbed, the stronger the scouring force of the water flow on the riverbed, resulting in more serious resuspension and diffusion of pollutants in the sediment. On the contrary, if the shear stress anomaly index value is smaller, it indicates that the water flow's scouring force is weaker, and the resuspension and diffusion of pollutants are less serious. Therefore, the riverbed bottom shear stress anomaly index is an important indicator for evaluating and predicting the degree of pollutant resuspension and diffusion.

[0066] The rapid generation rate of bubbles in sediments in water bodies can cause resuspension and diffusion of pollutants. When bubbles are generated and rise in sediments, they carry sediment particles and pollutants attached to them into the water body. When the bubble generation rate is fast, this process is more frequent and intense, causing more sediments and pollutants to be disturbed and suspended. At the same time, the rise of bubbles will also form vertical convection movement in the water body, further promoting the diffusion of pollutants. The rise of bubbles not only drives the physical migration of sediments, but may also change the chemical environment of the water body, such as by increasing the dissolved gas content of the water body or changing the redox conditions, further affecting the morphology and behavior of pollutants. In addition, the rapid generation rate of bubbles may be a manifestation of accelerated decomposition of organic matter at the bottom, which is usually accompanied by enhanced microbial activity, further stirring the sediments and promoting the resuspension and diffusion of pollutants.

[0067] After analyzing the bubble generation rate in the sediment, the steps to generate the bubble release index are as follows:

[0068] In the detection window, the basic data of bubble generation rate in the sediment are obtained, including the bubble generation frequency, bubble volume and time point in the sediment. The bubble generation data is expressed as {t k , V k , f k |k=1,2,3,…,n}, n is a positive integer, where t k represents the time of the kth sampling point, V k represents the bubble volume at the kth sampling point, f k Indicates the bubble generation frequency of the kth sampling point;

[0069] It should be noted that the frequency and volume of bubbles in sediments can be intelligently obtained through an automated sensor network installed in the water body. These sensors can monitor and record the frequency and volume changes of bubbles in real time, and capture the formation and rise of bubbles through technologies such as acoustics, Doppler effect and optical imaging.

[0070] Calculate the instantaneous bubble release rate at each time point. The calculation expression is: R k =V k ·f k , where R k Indicates that at time point t k The instantaneous bubble release rate;

[0071] The momentum released by the bubbles is calculated to further quantify the ability of bubbles to disturb the sediment. The expression for the calculation is: P k =V k ·v k ·ρ g , where P k Indicates that at time point t k The bubble release momentum, ρ g represents the gas density, v k Indicates the rising speed of bubbles;

[0072] Taking into account the bubble generation rate and momentum, the cumulative bubble disturbance energy is calculated. The calculation expression is: In the formula, E total Indicates the accumulated bubble disturbance energy within the detection window;

[0073] By detecting the accumulated bubble disturbance energy E in the window total Calculate the bubble release index, the calculation expression is: BRI μ =10·ln(E total +1), where BRI μ Represents the bubble release index.

[0074] It can be seen from the bubble release index that within the detection window, the larger the value of the bubble release index generated after analyzing the bubble generation rate in the sediment, the higher the frequency and intensity of bubble generation and release, and the more serious the resuspension and diffusion of pollutants. Conversely, the smaller the value of the bubble release index, the lower the frequency and intensity of bubble generation and release, and the less serious the resuspension and diffusion of pollutants. Therefore, the bubble release index can be used as an effective indicator to assess the risk of resuspension and diffusion of pollutants in sediments.

[0075] The machine learning model is not specifically limited here, and can achieve the BSSI of the riverbed bottom shear stress anomaly index μ and bubble release index BRI μ Comprehensive analysis to generate pollutant resuspension assessment coefficient Pollutant susp In order to realize the technical solution of the present invention, the present invention provides a specific implementation method;

[0076] Pollutant resuspension assessment coefficient susp The resulting calculation formula is: Pollutant susp =β1*BSSI μ +β2*BRI μ , where β1 and β2 are the riverbed bottom shear stress anomaly index BSSI μ and bubble release index BRI μ The preset proportional coefficient, and β1 and β2 are both greater than 0.

[0077] It can be seen from the pollutant resuspension assessment coefficient that, under the detection window, the larger the value of the riverbed bottom shear stress anomaly index generated after analyzing and processing the water flow's scouring force on the riverbed, the larger the value of the bubble release index generated after analyzing and processing the bubble generation rate in the sediment, that is, the larger the performance value of the pollutant resuspension assessment coefficient generated after analyzing and processing the current underwater environmental information under the detection window, the more serious the hidden danger of pollutant resuspension and diffusion, and vice versa.

[0078] Based on the analysis results of the machine learning model, the changes in pollutant concentrations in the current underwater environment are divided into two categories: complex changes and normal changes;

[0079] The pollutant resuspension assessment coefficient generated after analyzing and processing the current underwater environmental information under the detection window is compared and analyzed with the pre-set pollutant resuspension assessment coefficient reference threshold, and the changes in pollutant concentrations in the current underwater environment are divided. The specific division conclusions are as follows:

[0080] If the pollutant resuspension assessment coefficient is greater than the pollutant resuspension assessment coefficient reference threshold, the pollutant concentration change in the current underwater environment is classified as a complex change type;

[0081] If the pollutant resuspension assessment coefficient is less than or equal to the pollutant resuspension assessment coefficient reference threshold, the pollutant concentration change in the current underwater environment is classified as a normal change type.

[0082] For situations judged as normal changing environments, data collection will continue at the set initial pollutant concentration sampling frequency. For situations judged as complex changing environments, the actual pollutant sampling frequency will be intelligently regulated based on the initial pollutant concentration sampling frequency, and the actual pollutant sampling frequency will be increased to collect pollutant concentration data at more intensive time intervals, so as to timely capture the concentration changes after the pollutants are re-suspended.

[0083] For situations judged to be normally changing environments, data collection will continue at the set initial pollutant concentration sampling frequency. This means that when the pollutant concentration changes in the underwater environment are assessed to have no significant abnormalities or complex changes, the original sampling frequency will be maintained for monitoring. The initial sampling frequency is set based on the basic characteristics of the water body and the known patterns of changes in pollutant concentrations. It can effectively capture daily fluctuations and trends in pollutant concentrations under normal conditions. By maintaining this frequency, the continuity and integrity of the data are ensured, providing a stable monitoring basis, thereby providing reliable data support for further analysis and long-term environmental assessment.

[0084] For situations where the environment is judged to be complex and changing, the actual pollutant sampling frequency is intelligently regulated based on the initial pollutant concentration sampling frequency. The specific steps to increase the actual pollutant sampling frequency are as follows:

[0085] The control coefficient is calculated based on the current pollutant resuspension assessment coefficient and the pollutant resuspension assessment coefficient reference threshold to adjust the actual pollutant sampling frequency. The calculation expression is: Among them, Pollutant susp represents the pollutant resuspension assessment coefficient, P threshold Pollutant represents the reference threshold of the pollutant resuspension assessment coefficient. susp >P threshold , K adjust represents the control coefficient, α represents the control parameter, reflecting the control sensitivity, and its value range is 0.1-1.0;

[0086] The actual pollutant sampling frequency is adjusted according to the control coefficient. The adjustment expression is: f actual =f initial ·K adjust , where f initialrepresents the sampling frequency of initial pollutant concentration, f actual Indicates the actual pollutant sampling frequency after regulation;

[0087] Implement the adjusted actual pollutant sampling frequency for real-time sampling, dynamically adjust the actual pollutant sampling frequency based on new data, and repeat the above-mentioned control steps to ensure that the actual pollutant sampling frequency always adapts to environmental changes.

[0088] The present invention introduces a pollutant resuspension assessment coefficient and analyzes and processes underwater environmental information based on a machine learning model. It can effectively divide the changes in pollutant concentration in the current underwater environment into two types: complex change type and normal change type. It can significantly improve the accuracy of identifying water pollution conditions and timely capture sediment resuspension events caused by accelerated water flow or human activities. By accurately dividing the types of environmental changes, potential pollution risks can be identified earlier, and preventive and control measures can be taken in advance, thereby avoiding the expansion of the spread of pollutants and reducing the overall impact on the water environment. This division also provides a scientific basis for subsequent sampling frequency adjustments and environmental management, ensuring that the most suitable monitoring strategy can be adopted under different types of changes.

[0089] When a complex changing environment is detected, the present invention intelligently controls the actual sampling frequency based on the initial pollutant concentration sampling frequency, increases the sampling frequency by calculating the control coefficient, and collects pollutant concentration data at more intensive time intervals. This intelligent control method enables the sampling system to dynamically adapt to environmental changes, especially when pollutant resuspension occurs frequently, and can timely capture rapid changes in concentration to ensure the timeliness and accuracy of the data. By adjusting the sampling frequency, more detailed and accurate pollutant concentration change data can be obtained, providing high-quality data support for the simulation of pollutant diffusion and migration paths, which not only improves the responsiveness of the monitoring system, but also optimizes resource utilization, avoids oversampling in normal environments and undersampling in complex environments, thereby achieving efficient environmental monitoring and management.

[0090] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0091] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0092] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0093] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0094] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only one. There may be other division methods in actual implementation. For example, multiple units 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 interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0095] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0096] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0097] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0098] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0099] Finally: The above description is only a preferred embodiment 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 should be included in the protection scope of the present invention.

Claims

1. A method for tracing the source of water pollution based on multi-factor analysis, characterized in that: The following steps are involved: According to the characteristics of the water body and the known variation patterns of pollutant concentrations, the concentration information of pollutants in the water body is obtained by sampling at different time points with the set initial pollutant concentration sampling frequency, and a basic data set is established to simulate the diffusion and migration paths of pollutants. While sampling pollutant concentrations, we comprehensively collect underwater environmental information, extract key features that affect pollutant resuspension and diffusion, analyze and process the extracted key features, and input the analyzed and processed key features into a pre-trained machine learning model. Through the analysis of the model, we predict the degree of pollutant resuspension in the current environment. Based on the analysis results of the machine learning model, the changes in pollutant concentrations in the current underwater environment are divided into two categories: complex changes and normal changes; For situations judged as normal changing environments, data collection will continue at the set initial pollutant concentration sampling frequency. For situations judged as complex changing environments, the actual pollutant sampling frequency will be intelligently regulated based on the initial pollutant concentration sampling frequency, and the actual pollutant sampling frequency will be increased to collect pollutant concentration data at more intensive time intervals, so as to timely capture the concentration changes after the pollutants are re-suspended. The key features that affect the resuspension and diffusion of pollutants include the scouring force of water flow on the riverbed and the bubble generation rate in the sediment. After extraction, the scouring force of water flow on the riverbed and the bubble generation rate in the sediment are placed under the detection window for analysis and processing to generate the riverbed bottom shear stress anomaly index and bubble release index respectively. The analyzed riverbed bottom shear stress anomaly index and bubble release index are input into a pre-trained machine learning model, and the pollutant resuspension assessment coefficient is generated through the model. Based on the pollutant resuspension assessment coefficient, the degree of pollutant resuspension in the current environment is predicted; The pollutant resuspension assessment coefficient generated after analyzing and processing the current underwater environmental information under the monitoring window is compared and analyzed with the pre-set pollutant resuspension assessment coefficient reference threshold, and the changes in pollutant concentrations in the current underwater environment are divided. The specific division conclusions are as follows: If the pollutant resuspension assessment coefficient is greater than the pollutant resuspension assessment coefficient reference threshold, the pollutant concentration change in the current underwater environment is classified as a complex change type; If the pollutant resuspension assessment coefficient is less than or equal to the pollutant resuspension assessment coefficient reference threshold, the pollutant concentration change in the current underwater environment is classified as a normal change type.

2. A method for tracing the source of water pollution based on multi-factor analysis according to claim 1, characterized in that: The sampling frequency of initial pollutant concentration meets the following conditions: First, it is necessary to ensure that the sampling frequency of initial pollutant concentrations is frequent to capture the fluctuations in pollutant concentrations under normal conditions and ensure the continuity and integrity of the data; Second, it must be economically feasible, taking into account the limitations of human, material and financial resources, and ensuring sustainable monitoring over a long period of time; Third, it must adapt to the characteristics of the water body and be able to representatively reflect the overall condition of the water body.

3. The method for tracing the source of water pollution based on multi-factor analysis according to claim 1 is characterized in that: For situations where the environment is judged to be complex and changing, the actual pollutant sampling frequency is intelligently regulated based on the initial pollutant concentration sampling frequency. The specific steps to increase the actual pollutant sampling frequency are as follows: The control coefficient is calculated based on the current pollutant resuspension assessment coefficient and the pollutant resuspension assessment coefficient reference threshold to adjust the actual pollutant sampling frequency. The calculation expression is: Among them, Pollutant susp represents the pollutant resuspension assessment coefficient, P threshold Pollutant represents the reference threshold of the pollutant resuspension assessment coefficient. susp >P threshold , K adjust represents the control coefficient, α represents the control parameter, reflecting the control sensitivity, and its value range is 0.1-1.0; The actual pollutant sampling frequency is adjusted according to the control coefficient. The adjustment expression is: f actual =f initial ·K adjust , where f initial represents the sampling frequency of initial pollutant concentration, f actual Represents the actual pollutant sampling frequency after regulation.

4. The method for tracing the source of water pollution based on multi-factor analysis according to claim 1 is characterized in that: Within the monitoring window, after analyzing and processing the scouring force of water flow on the riverbed, the steps to generate the abnormal shear stress index at the bottom of the riverbed are as follows: Collect water velocity and water depth data within the detection window as well as particle diameter and density data of riverbed sediments for calculating shear stress; Using the water velocity and water depth data, the shear stress of the riverbed is calculated using the following expression: τ = ρ·g·H·S f , where τ represents shear stress, ρ represents water density, g represents gravity acceleration, H represents water depth, and S f Indicates the slope of the riverbed, which is calculated by the water level difference and the length of the river channel. Δh represents the water level difference within the river section, that is, the water level difference between two measuring points, and L represents the horizontal distance between the two measuring points, that is, the length of the river section; Calculate the critical shear stress for sediment resuspension and determine the minimum shear stress required for resuspension for comparison with the actual shear stress. The calculation expression is: τ c represents the critical shear stress, ρ s represents the sediment density, d represents the sediment particle diameter, C f represents the drag coefficient; Calculate the shear stress anomaly factor, the calculation expression is: E f It represents the shear stress anomaly factor, compares the actual shear stress with the critical shear stress, and evaluates the degree of shear stress anomaly; The time weighting factor is introduced to calculate the weighted shear stress within a period of time. The calculation expression is: TSWI stands for time-weighted shear stress, E f (i) represents the shear stress anomaly factor at the i-th moment, T(i) represents the time weight at the i-th moment; The time-weighted shear stress is normalized to generate the riverbed bottom shear stress anomaly index, and the formula is as follows: In the formula, BSSI μ It represents the shear stress anomaly index of the riverbed bottom. Max(TWSI) and min(TWSI) represent the maximum and minimum values ​​of the time-weighted shear stress in the detection window, respectively.

5. The method for tracing the source of water pollution based on multi-factor analysis according to claim 1 is characterized in that: After analyzing the bubble generation rate in the sediment, the steps to generate the bubble release index are as follows: In the detection window, the basic data of bubble generation rate in the sediment are obtained, including the bubble generation frequency, bubble volume and time point in the sediment. The bubble generation data is expressed as {t k , V k , f k |k=1,2,3,…,n}, n is a positive integer, where t k represents the time of the kth sampling point, V k represents the bubble volume at the kth sampling point, f k Indicates the bubble generation frequency of the kth sampling point; Calculate the instantaneous bubble release rate at each time point. The calculation expression is: R k =V k ·f k , where R k Indicates that at time point t k The instantaneous bubble release rate; The momentum released by the bubbles is calculated to further quantify the ability of bubbles to disturb the sediment. The expression for the calculation is: P k =V k ·v k ·ρ g , where P k Indicates that at time point t k The bubble release momentum, ρ g represents the gas density, v k Indicates the rising speed of bubbles; Taking into account the bubble generation rate and momentum, the cumulative bubble disturbance energy is calculated. The calculation expression is: In the formula, E total Indicates the accumulated bubble disturbance energy within the detection window; By detecting the accumulated bubble disturbance energy E in the window total Calculate the bubble release index, the calculation expression is: BRI μ =10·ln(E total +1), where BRI μ Represents the bubble release index.

Images