Water environment pollution monitoring management method and system based on big data

Abstract

The invention discloses a water environment pollution monitoring management method and system based on big data, and particularly relates to the technical field of water environment monitoring. A drainage basin is divided into a pollution influence main control area, a pollution diffusion boundary area and a pollution interaction transition area; extracting high-frequency pollution factors by using a big data clustering algorithm, constructing a high-frequency pollution factor incidence matrix, establishing a pollution diffusion path prediction model in combination with historical flow direction data and a time sequence analysis technology, and outputting a potential pollution propagation area and intensity; the current pollution diffusion state is analyzed through dynamic matching of real-time monitoring data and the prediction model, and a pollution diffusion real-time prediction result is generated; according to the method, the pollution risk level of each area in the drainage basin is evaluated based on the prediction result, the partition pollution early warning information is generated, the historical treatment case data is combined, pollution prevention and control and treatment suggestions are provided, precision and intelligence of water environment pollution monitoring are achieved, support is provided for water pollution treatment, and the method has remarkable environmental protection benefits and practical application value.

Description

Technical Field

[0001] The present invention relates to the field of water environment monitoring technology, and more specifically, to a water environment pollution monitoring and management method and system based on big data. Background Art

[0002] Traditional water environment monitoring methods mainly rely on fixed-point monitoring and manual sampling and analysis. Not only do they have a long monitoring cycle and limited coverage, but they also make it difficult to accurately predict the diffusion dynamics of pollution and regional impacts. In addition, faced with complex basin hydrological conditions and the diversity of pollutant types, traditional monitoring technologies lack pertinence and systematicness, and are difficult to meet the current needs for efficient decision-making in water environment pollution control. Against the backdrop of the rapid development of big data and intelligent technologies, combining multi-source monitoring data with intelligent analysis algorithms has become an important direction for solving the problem of water environment pollution monitoring.

[0003] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a water environment pollution monitoring and management method and system based on big data to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The water environment pollution monitoring and management method based on big data includes the following steps:

[0007] Obtain multi-source historical water environment monitoring data for the target basin, and divide the target basin into pollution-affected main control areas, pollution diffusion boundary areas, and pollution interaction transition areas based on hydrological and geomorphological characteristics, pollution source distribution, and water body fluidity;

[0008] In the main pollution control area, high-frequency pollution factors are extracted based on the big data clustering algorithm, and the correlation strength between high-frequency pollution factors and water quality indicators in the surrounding pollution diffusion boundary area is analyzed to generate a high-frequency pollution factor correlation matrix;

[0009] Based on the correlation matrix of high-frequency pollution factors and the historical flow change data of pollution interaction transition zones, combined with time series analysis technology, a pollution diffusion path prediction model is constructed to output potential pollution propagation areas and pollution intensity;

[0010] Dynamically match the multi-source water environment real-time monitoring data of the target basin with the pollution diffusion path prediction model, analyze the current pollution diffusion status of the target basin, and obtain the real-time prediction results of pollution diffusion;

[0011] Based on the real-time prediction results of pollution diffusion, the pollution risk level of each area in the target river basin is evaluated, regional pollution warning information is generated, and pollution prevention and control and governance recommendations are provided in combination with historical governance case data.

[0012] In a preferred embodiment, multi-source historical water environment monitoring data of the target basin is obtained, and based on the hydrological and geomorphological characteristics, the distribution of pollution sources and the fluidity of water bodies, the target basin is divided into the pollution impact main control area, the pollution diffusion boundary area and the pollution interaction transition area, specifically:

[0013] Based on the geographic information data of the target watershed, determine the main hydrological flow direction, flow rate and regional water volume in the watershed, and preliminarily identify the pollutant accumulation area;

[0014] Extract the source distribution information of industrial emissions, agricultural non-point source pollution and domestic sewage in the target watershed, and calibrate the pollution source distribution intensive area based on the pollutant emissions and water inlet channels;

[0015] Divide the pollution impact control area according to the water flow direction and the distribution of pollutant accumulation areas;

[0016] Extract water quality monitoring data of water bodies at the edge of the target basin, determine the diffusion law of pollutants, and delineate the pollution diffusion boundary area;

[0017] Between the main pollution control area and the pollution diffusion boundary area, the pollution interaction transition zone is determined based on the basin topography and water flow diffusion characteristics.

[0018] In a preferred embodiment, in the pollution-affected main control area, high-frequency pollution factors are extracted based on a big data clustering algorithm, and the correlation strength between the high-frequency pollution factors and the water quality indicators in the surrounding pollution diffusion boundary area is analyzed to generate a pollution factor correlation matrix, specifically:

[0019] Extract historical water environment monitoring data of the main control area affected by pollution, conduct time series analysis on pollution indicators, identify indicator factors with pollution frequency higher than the preset threshold, and obtain a set of high-frequency pollution factors;

[0020] Based on the high-frequency pollution factor set, determine the temporal impact range and spatial coverage of each high-frequency pollution factor in the pollution diffusion boundary area;

[0021] The big data clustering algorithm is used to group the impact characteristics of high-frequency pollution factors in different sections to form an associated distribution model;

[0022] Based on the correlation distribution model, the correlation strength between high-frequency pollution factors and water quality indicators in the diffusion boundary area is evaluated, and the correlation matrix of high-frequency pollution factors is generated.

[0023] In a preferred embodiment, based on the high-frequency pollution factor correlation matrix and the historical flow change data of the pollution interaction transition zone, combined with the time series analysis technology, a pollution diffusion path prediction model is constructed to output the potential pollution propagation area and pollution intensity, specifically:

[0024] According to the correlation matrix of high-frequency pollution factors, the potential path of the pollution diffusion starting point and the pollution diffusion direction is determined;

[0025] Extract historical flow direction change data in the pollution interaction transition zone, determine the dynamic characteristics of water flow velocity, direction and key nodes, and generate a preliminary model of pollution migration path;

[0026] Based on the time series concentration variation trend of high-frequency pollution factors and combined with the water flow diffusion characteristics, a dynamic prediction model for pollution diffusion path is established;

[0027] Regional hydrological and geomorphological constraint parameters are added to the dynamic prediction model of pollution diffusion path, the pollution diffusion path is optimized and adjusted, the pollution diffusion path prediction results are generated, and the potential pollution propagation area and pollution intensity are determined.

[0028] In a preferred embodiment, regional hydrological and geomorphic constraint parameters are added to the dynamic prediction model of pollution diffusion path, the pollution diffusion path is optimized and adjusted, the pollution diffusion path prediction result is generated, and the potential pollution propagation area and pollution intensity are determined, specifically:

[0029] Extract hydrological and geomorphological characteristics data of the target watershed, including river morphology, watershed slope, water body depth and surface permeability;

[0030] Based on the hydrological and geomorphological characteristics, a set of constraint parameters is established to define the flow resistance coefficient, diffusion boundary adjustment factor and pollutant deposition probability;

[0031] The hydrological and geomorphic constraint parameters are embedded in the dynamic prediction model of pollution diffusion path to correct the dynamic change trend of pollution diffusion direction and key nodes;

[0032] According to the constraint parameters, the abnormal diffusion area in the diffusion path is optimized, the diffusion range and propagation speed are adjusted, the optimized pollution diffusion path prediction results are generated, and the potential pollution propagation area and pollution intensity are determined.

[0033] In a preferred embodiment, the real-time monitoring data of the multi-source water environment of the target basin is dynamically matched with the pollution diffusion path prediction model, the current pollution diffusion state of the target basin is analyzed, and the real-time prediction result of pollution diffusion is obtained, specifically:

[0034] Obtain real-time monitoring data of multi-source water environment in the target basin, including water quality indicators, flow velocity and direction data, and dynamic change data of pollutant concentration;

[0035] Input the multi-source water environment real-time monitoring data of the target basin into the pollution diffusion path prediction model, combine the diffusion direction, path nodes and pollution intensity parameters in the pollution diffusion path prediction model, and match the dynamic change trend of the multi-source water environment real-time monitoring data with the pollution diffusion path prediction model;

[0036] Evaluate the diffusion impact range and peak changes of abnormal water quality indicators in multi-source water environment real-time monitoring data, and update the pollution diffusion path prediction model;

[0037] According to the updated pollution diffusion path prediction model, the current pollution diffusion status of the target basin is generated, including the diffusion range, pollution concentration distribution and pollution diffusion speed, and the real-time prediction results of pollution diffusion are obtained.

[0038] In a preferred embodiment, based on the real-time prediction results of pollution diffusion, the pollution risk level of each area in the target basin is evaluated, regional pollution warning information is generated, and pollution prevention and control and governance suggestions are provided in combination with historical governance case data, specifically:

[0039] Based on the diffusion range, pollution concentration distribution and diffusion speed data in the real-time prediction results of pollution diffusion, combined with the regional water quality benchmark threshold and pollutant category, the pollution risk score of the target watershed is obtained;

[0040] Based on the pollution risk score, the target watershed is divided into high-risk, medium-risk and low-risk areas, and a regional pollution risk level map is generated;

[0041] Based on the diffusion dynamics and pollution concentration peaks in high-risk areas, the direction and impact range of possible further spread of pollution are predicted, and regional pollution warning information is generated;

[0042] Extract historical governance case data, combine the pollution diffusion trend and regional characteristics of high-risk areas, and recommend suitable pollution prevention and control and governance plans.

[0043] On the other hand, the present invention provides a water environment pollution monitoring and management system based on big data, including a watershed division module, a correlation strength analysis module, a pollution diffusion prediction module, a pollution diffusion state analysis module and an evaluation and early warning module;

[0044] The watershed division module is used to obtain multi-source historical water environment monitoring data of the target watershed, and divide the target watershed into the pollution impact main control area, pollution diffusion boundary area and pollution interaction transition area based on the hydrological and geomorphological characteristics, pollution source distribution and water body fluidity;

[0045] The correlation strength analysis module is used to extract high-frequency pollution factors in the pollution-affected main control area based on the big data clustering algorithm, and analyze the correlation strength between the high-frequency pollution factors and the water quality indicators in the surrounding pollution diffusion boundary area to generate a high-frequency pollution factor correlation matrix;

[0046] The pollution diffusion prediction module is used to build a pollution diffusion path prediction model based on the high-frequency pollution factor correlation matrix and the historical flow change data of the pollution interaction transition zone, combined with time series analysis technology, and output the potential pollution propagation area and propagation intensity;

[0047] The pollution diffusion state analysis module is used to dynamically match the real-time monitoring data of the multi-source water environment in the target basin with the pollution diffusion path prediction model, analyze the current pollution diffusion state of the target basin, and obtain the real-time prediction results of pollution diffusion;

[0048] The assessment and early warning module is used to evaluate the pollution risk level of each area in the target river basin based on real-time prediction results of pollution diffusion, generate regional pollution warning information, and provide pollution prevention and control and governance recommendations in combination with historical governance case data.

[0049] The technical effects and advantages of the water environment pollution monitoring and management method and system based on big data of the present invention are as follows:

[0050] By dividing the pollution impact main control area, pollution diffusion boundary area and pollution interaction transition area, the pollution core area and diffusion law in the basin can be accurately identified, providing a scientific basis for pollution source tracking; based on the big data clustering algorithm, high-frequency pollution factors are extracted and the correlation matrix is ​​constructed, which effectively improves the analysis accuracy of pollution factors and avoids the problem of information isolation in traditional monitoring methods; thirdly, the pollution diffusion path prediction model constructed by combining time series analysis technology and hydrological and geomorphological characteristics can dynamically predict the potential pollution propagation area and intensity, and realize high-precision simulation of pollution diffusion; through real-time monitoring data and dynamic matching of the model, the pollution diffusion status is updated in time, which greatly improves the timeliness of monitoring; regional pollution warning and prevention and control suggestions based on historical governance cases can provide managers with targeted decision-making support, realize the intelligent, precise and efficient monitoring of basin pollution, and have important environmental protection significance and broad practical application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A schematic diagram of a water environment pollution monitoring and management method based on big data of the present invention;

[0052] Figure 2 It is a structural schematic diagram of the water environment pollution monitoring and management system based on big data of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Example 1

[0055] Figure 1 The present invention provides a water environment pollution monitoring and management method based on big data, which includes the following steps:

[0056] Obtain multi-source historical water environment monitoring data for the target basin, and divide the target basin into pollution-affected main control areas, pollution diffusion boundary areas, and pollution interaction transition areas based on hydrological and geomorphological characteristics, pollution source distribution, and water body fluidity;

[0057] In the main pollution control area, high-frequency pollution factors are extracted based on the big data clustering algorithm, and the correlation strength between high-frequency pollution factors and water quality indicators in the surrounding pollution diffusion boundary area is analyzed to generate a high-frequency pollution factor correlation matrix;

[0058] Based on the correlation matrix of high-frequency pollution factors and the historical flow change data of pollution interaction transition zones, combined with time series analysis technology, a pollution diffusion path prediction model is constructed to output potential pollution propagation areas and pollution intensity;

[0059] Dynamically match the multi-source water environment real-time monitoring data of the target basin with the pollution diffusion path prediction model, analyze the current pollution diffusion status of the target basin, and obtain the real-time prediction results of pollution diffusion;

[0060] Based on the real-time prediction results of pollution diffusion, the pollution risk level of each area in the target river basin is evaluated, regional pollution warning information is generated, and pollution prevention and control and governance recommendations are provided in combination with historical governance case data.

[0061] Specifically, the multi-source historical water environment monitoring data of the target basin is obtained, and based on the hydrological and geomorphological characteristics, the distribution of pollution sources and the fluidity of water bodies, the target basin is divided into the pollution impact main control area, the pollution diffusion boundary area and the pollution interaction transition area, including:

[0062] Based on the geographic information data of the target river basin, determine the main hydrological flow direction, flow rate and regional water body capacity in the river basin, and preliminarily identify the pollutant accumulation area; specifically, the geographic information data of the target river basin includes river morphology, river basin boundaries, water body area, surface elevation and other geographic information, usually obtained by satellite remote sensing, drone aerial photography or geographic information system; these data are used to accurately describe the spatial distribution of the river basin. Hydrological flow direction: refers to the natural flow path of water in the river basin, such as flowing from upstream to downstream, which may pass through confluence points, branch streams, etc.; flow rate: the speed of water flow, which is related to the river channel morphology, slope and water volume; water body capacity: the water storage capacity of each water body section determines whether pollutants are easy to accumulate; pollutant accumulation areas refer to areas where water flows slowly and the probability of pollutant deposition is higher; by combining flow rate, water body capacity and flow direction analysis, find out where pollutants are prone to accumulate;

[0063] Extract the source distribution information of industrial emissions, agricultural non-point source pollution and domestic sewage in the target watershed, combine the pollutant emissions and water inlet channels, and calibrate the pollution source distribution intensive areas; specifically, industrial emissions: pollutants discharged by industrial facilities enter the river through pipes or direct outlets, such as phosphorus-containing wastewater discharged by chemical plants; agricultural non-point source pollution: fertilizers and pesticides in farmland are washed into the river by rainwater, and are often distributed downstream of agricultural irrigation areas; domestic sewage: sewage generated by the daily life of urban or rural residents, which may enter the basin through sewage pipes or rivers. Pollutants include nitrogen, phosphorus and organic matter etc.; Water inlet channel: the way pollutants enter the water body, including drainage pipes, surface runoff formed by rainwater erosion, etc.; Marking the dense distribution area of ​​pollution sources: According to the distribution information and emission volume of various pollution sources, find out the areas where pollution sources are relatively concentrated, which are called dense distribution areas of pollution sources; For example, there are 3 industrial parks distributed in the upstream area of ​​the basin, which discharge about 2,000 tons of heavy metal-containing sewage every day; the midstream area is a large area of ​​farmland, and runoff brings pesticides and fertilizers into the water body during the rainy season; the downstream area is a living community, and the imperfect sewage pipe network causes domestic sewage to be discharged directly into the river without treatment. Combining this information, the upstream can be marked as an industrial pollution-intensive area, the midstream as an agricultural non-point source pollution-intensive area, and the downstream as a domestic sewage-intensive area;

[0064] According to the direction of water flow and the distribution of pollutant accumulation areas, the main pollution control areas are divided; specifically, the direction of water flow: combined with geographic information and hydrological flow data, the propagation route of pollutants in the basin is determined; for example, pollution in the upstream may have a direct impact on the middle and lower reaches; distribution of pollutant accumulation areas: using data such as flow velocity and water body capacity, locate which areas are the main deposition points of pollutants; the main pollution control areas are divided: refers to the areas with the highest pollutant concentration and the most significant impact on the overall water quality of the basin; for example, in the basin, the river section near the upstream chemical plant forms high-concentration pollution deposits due to large emissions and slow water flow; through analysis, it is found that this area has a significant impact on the water quality of the downstream water body, so it is divided into the main pollution control area;

[0065] Extract water quality monitoring data of water bodies at the edge of the target basin, determine the diffusion law of pollutants, and delineate pollution diffusion boundary areas; specifically, water bodies at the edge of the basin: refers to water bodies close to the boundary or periphery of the basin, these areas are usually the farthest end of pollutant diffusion or the critical point of natural purification; Pollutant diffusion law: analyze the concentration changes and diffusion speed of pollutants in edge water bodies to determine the diffusion range and direction of pollutants; Pollution diffusion boundary area: refers to the outermost area of ​​the pollutant diffusion range, usually the area with the lowest pollutant concentration but still exceeding the water quality benchmark; illustratively, in the downstream boundary area of ​​the river, water quality monitoring data shows that the pollutant concentration is gradually decreasing, but it is still exceeding the standard. According to data analysis, it was found that the pollutant concentration in this area was affected by upstream emissions, but due to the slow flow rate, a diffusion boundary area was formed;

[0066] Between the pollution-affected main control area and the pollution diffusion boundary area, the pollution interaction transition zone is determined based on the basin landform and water flow diffusion characteristics; specifically, the basin landform characteristics: such as the influence of changes in the width and slope of the river channel on pollution diffusion. Wide river sections may reduce flow velocity and promote pollutant deposition; narrow river sections may accelerate pollution diffusion; water flow diffusion characteristics include the speed, range and flow direction of water flow diffusion; illustratively, in the basin, high-concentration pollutants in the main control area diffuse to the downstream through water flow, and the pollution concentration in the river section before diffusion to the boundary area is significantly reduced. Combined with the landform characteristics, it is found that the transition zone includes a tributary confluence point and a slow-flow area, and these sections are determined to be pollution interaction transition zones.

[0067] Specifically, in the pollution-affected main control area, high-frequency pollution factors are extracted based on the big data clustering algorithm, and the correlation strength between high-frequency pollution factors and water quality indicators in the surrounding pollution diffusion boundary area is analyzed to generate a high-frequency pollution factor correlation matrix, including:

[0068] Extract historical water environment monitoring data of the pollution control area, conduct time series analysis on pollution indicators, identify indicator factors with pollution frequency higher than the preset threshold, and obtain a set of high-frequency pollution factors; specifically, historical water environment monitoring data of the pollution control area refers to long-term accumulated water quality monitoring data, including physical indicators (such as turbidity), chemical indicators (such as nitrogen and phosphorus concentrations) and biological indicators (such as plankton density); time series analysis: conduct trend analysis of monitoring data in the time dimension to identify periodicity, seasonal changes or emergencies of pollution indicators; high-frequency pollution factor set: contains major pollutants that appear continuously or repeatedly during the monitoring period, reflecting the typical pollution characteristics of the pollution control area;

[0069] Based on the set of high-frequency pollution factors, determine the temporal influence range and spatial coverage range of each high-frequency pollution factor in the pollution diffusion boundary area; specifically, the temporal influence range: analyze the propagation time law of high-frequency pollution factors in the pollution diffusion boundary area, such as the time required for a certain pollutant to diffuse from the main control area to the boundary area and its concentration change trend; spatial coverage range: determine the spatial distribution of high-frequency pollution factors, such as its maximum diffusion radius and concentration distribution gradient in the diffusion boundary area;

[0070] The big data clustering algorithm is used to group the impact characteristics of high-frequency pollution factors in different sections to form an associated distribution model; specifically, the big data clustering algorithm: use algorithms (such as K-Means) to cluster the spatiotemporal characteristics of high-frequency pollution factors, and classify pollution factors with similar diffusion laws into the same group; clustering can be calculated based on multidimensional data such as pollutant concentration, diffusion rate, and regional impact; the impact characteristics of different sections refer to the concentration changes, propagation speed, and impact range of pollution factors in the main control area, diffusion boundary area, and interactive transition area; associated distribution model: describes the spatial distribution characteristics of high-frequency pollution factors and their correlation. For example, some high-frequency pollution factors may have a superposition effect in the same area;

[0071] Based on the correlation distribution model, the correlation strength between high-frequency pollution factors and water quality indicators in the diffusion boundary area is evaluated to generate a correlation matrix of high-frequency pollution factors; specifically, the relationship between high-frequency pollution factors and water quality indicators in the diffusion boundary area (such as dissolved oxygen, pH value, turbidity) is measured; the degree of correlation of factors is quantified through correlation analysis (such as Pearson correlation coefficient or mutual information method). For example, changes in nitrogen concentration may significantly affect the level of dissolved oxygen; high-frequency pollution factor correlation matrix: a two-dimensional matrix, where rows represent high-frequency pollution factors, columns represent water quality indicators in the diffusion boundary area, and the values ​​in the matrix represent the correlation strength (such as positive correlation, negative correlation, or no correlation).

[0072] Specifically, based on the correlation matrix of high-frequency pollution factors and the historical flow change data of pollution interaction transition zones, combined with time series analysis technology, a pollution diffusion path prediction model is constructed to output potential pollution propagation areas and pollution intensity, including:

[0073] According to the correlation matrix of high-frequency pollution factors, the starting point of pollution diffusion and the potential path of pollution diffusion direction are determined; specifically, the starting point of pollution diffusion: the point with high pollutant concentration and obvious correlation strength is determined through the correlation matrix as the starting area of ​​pollution diffusion; for example, a certain discharge outlet upstream may be identified as the starting point of pollution due to excessive high-frequency factors; the potential path of pollution diffusion direction: combined with the hydrological flow data of the basin and the correlation law of high-frequency pollution factors, the path of pollutant diffusion from the starting point to the downstream is inferred;

[0074] Extract historical flow direction change data in the pollution interaction transition zone, determine the dynamic characteristics of water flow velocity, direction and key nodes, and generate a preliminary model of pollution migration path; specifically, historical flow direction change data include hydrodynamic characteristics such as flow velocity, seasonal changes in flow direction, and tributary confluence points;

[0075] Based on the time series concentration change trend of high-frequency pollution factors and the water flow diffusion characteristics, a dynamic prediction model of pollution diffusion path is established; specifically, the time series concentration change trend of pollution factors: according to the monitoring data, the concentration change pattern of high-frequency pollution factors over time (such as seasonal increase or sudden exceeding of the standard) is analyzed to provide a basis for dynamic prediction; water flow diffusion characteristics: including hydrodynamic factors such as diffusion speed and diffusion radius, which directly affect the diffusion range and concentration distribution of pollutants;

[0076] Regional hydrological and geomorphological constraint parameters are added to the dynamic prediction model of pollution diffusion path, the pollution diffusion path is optimized and adjusted, the pollution diffusion path prediction results are generated, and the potential pollution propagation area and pollution intensity are determined.

[0077] Specifically, regional hydrological and geomorphological constraint parameters are added to the dynamic prediction model of pollution diffusion path, the pollution diffusion path is optimized and adjusted, the pollution diffusion path prediction results are generated, and the potential pollution propagation area and pollution intensity are determined, including:

[0078] Extract the hydrological and geomorphological characteristic data of the target basin, including river morphology, basin slope, water body depth and surface permeability; specifically, hydrological and geomorphological data include core information describing river morphology and basin characteristics; river morphology: such as the width, tortuosity and location of bifurcation points of the river, these characteristics will affect the flow rate and diffusion direction of the water flow; basin slope: determines the gravity-driven intensity of the water flow, steep slopes will cause the water flow to accelerate, while gentle slopes may cause water accumulation or deposit pollutants; water body depth: deep water areas diffuse more slowly, and pollutants may be deposited at the bottom; shallow water areas diffuse faster, but are easily disturbed by the external environment; surface permeability: areas with high permeability may cause pollutants to diffuse underground, reducing the concentration of pollutants in the water body, but may pollute groundwater;

[0079] Based on the hydrological and geomorphological characteristics, a set of constraint parameters is established to define the water flow resistance coefficient, the diffusion boundary adjustment factor and the probability of pollutant deposition. Specifically, the constraint parameter set is a set of key parameters used to describe the impact of hydrological and geomorphological features on pollution diffusion, including water flow resistance, pollutant diffusion boundary and deposition characteristics. Water flow resistance coefficient: describes the degree of friction or obstacles that the water body is subject to. For example, the roughness of the riverbed (such as rocks, silt, etc.) will increase resistance, slow down the flow of water and the diffusion of pollution. Diffusion boundary adjustment factor: used to correct the pollution diffusion range. For example, when the river channel becomes narrower, the diffusion radius may need to be reduced; when the river channel width increases, the diffusion range may expand. Pollutant deposition probability: used to quantify the possibility of pollutant deposition under different hydrological conditions; the probability of deposition is higher in deep water areas or slow flow areas, while the probability of deposition is lower in fast-flowing shallow water areas.

[0080] Embed the hydro-geomorphological constraint parameters into the dynamic prediction model of pollution diffusion path to correct the dynamic change trend of pollution diffusion direction and key nodes; specifically, embed the hydro-geomorphological constraint parameters: use parameters such as river morphology, slope, flow rate, etc. as input variables to adjust the path and rate of pollution diffusion in the model to ensure that the diffusion direction meets the actual geomorphological conditions; correct the diffusion direction: adjust the offset of the diffusion direction according to the geomorphological data, for example, the pollution diffusion path may deviate from the original prediction result at a sharp turn; correct the dynamic change trend of key nodes: dynamically adjust the changes in pollutant concentrations at important nodes in the basin (such as confluence points and tributary intersections); for example, there is a tributary converging in the middle reaches of the river. According to the geomorphological data, the flow rate near the tributary entrance is low, and pollutants are expected to form a high-concentration accumulation area at this node. After embedding this geomorphological feature into the model, the correction result shows that the peak concentration point of the pollutant is offset from the original predicted main river channel to the tributary entrance;

[0081] According to the constraint parameters, the abnormal diffusion area in the diffusion path is optimized, the diffusion range and propagation speed are adjusted, the optimized pollution diffusion path prediction results are generated, and the potential pollution propagation area and pollution intensity are determined. For example, the initial pollution diffusion path dynamic prediction model of the basin predicts that pollutants will form a 20-kilometer-long diffusion range in the downstream. After optimization, the diffusion range is reduced to 15 kilometers, and the peak pollution concentration is increased to 3.5 mg / L.

[0082] Specifically, the real-time monitoring data of multi-source water environment in the target basin is dynamically matched with the pollution diffusion path prediction model, the current pollution diffusion status of the target basin is analyzed, and the real-time prediction results of pollution diffusion are obtained, including:

[0083] Obtain real-time monitoring data of multi-source water environment in the target basin, including water quality indicators, flow velocity and direction data, and dynamic change data of pollutant concentration;

[0084] Input the multi-source water environment real-time monitoring data of the target basin into the pollution diffusion path prediction model, and combine the diffusion direction, path nodes and pollution intensity parameters in the pollution diffusion path prediction model to match the dynamic change trend of the multi-source water environment real-time monitoring data with the pollution diffusion path prediction model; specifically, diffusion direction: the main direction of pollutant propagation, such as diffusion along the main river channel or tributaries; path nodes: important points on the diffusion path, such as pollutant turning points, diversion ports or confluence points; pollution intensity parameters: concentration distribution, concentration peak and diffusion speed of pollutants; dynamic change trend matching: compare the diffusion path, concentration distribution and propagation rate of real-time data with the prediction model to identify whether the actual diffusion deviates from the model prediction;

[0085] Evaluate the diffusion impact range and peak changes of abnormal water quality indicators in multi-source water environment real-time monitoring data, and update the pollution diffusion path prediction model; specifically, evaluate the diffusion range: analyze the spatial area affected by abnormal indicators (such as upstream, downstream or tributaries), and predict its possible propagation direction; peak changes in pollution concentration: determine the peak position of pollutant concentration and its time change trend, such as whether the pollutant concentration reaches a peak quickly at a certain point or accumulates slowly;

[0086] Based on the updated pollution diffusion path prediction model, the current pollution diffusion status of the target watershed is generated, including the diffusion range, pollution concentration distribution and pollution diffusion speed, and the real-time prediction results of pollution diffusion are obtained; specifically, the diffusion range: the area where pollutants have currently reached, usually presented as a spatial distribution map; pollution concentration distribution: the spatial distribution and changing trend of pollutant concentration within the diffusion range; pollution diffusion speed: the speed at which pollutants propagate on different paths, which is used to assess the urgency of downstream impacts.

[0087] Specifically, based on the real-time prediction results of pollution diffusion, the pollution risk level of each area in the target basin is evaluated, regional pollution warning information is generated, and pollution prevention and control and governance suggestions are provided in combination with historical governance case data, including:

[0088] Based on the diffusion range, pollution concentration distribution and diffusion speed data in the real-time prediction results of pollution diffusion, combined with the regional water quality benchmark threshold and pollutant category, the pollution risk score of the target watershed is obtained;

[0089] Based on the pollution risk score, the target watershed is divided into high-risk, medium-risk and low-risk areas, and a regional pollution risk level map is generated;

[0090] Based on the diffusion dynamics and pollution concentration peaks in high-risk areas, the direction and impact range of possible further spread of pollution are predicted, and regional pollution warning information is generated;

[0091] Extract historical governance case data, combine the pollution diffusion trend and regional characteristics of high-risk areas, and recommend suitable pollution prevention and control and governance plans.

[0092] Example 2

[0093] The difference between Example 2 of the present invention and Example 1 is that this example introduces a water environment pollution monitoring and management system based on big data.

[0094] Figure 2 The present invention provides a schematic diagram of the structure of a water environment pollution monitoring and management system based on big data, which includes a watershed division module, a correlation strength analysis module, a pollution diffusion prediction module, a pollution diffusion state analysis module, and an evaluation and early warning module;

[0095] The watershed division module is used to obtain multi-source historical water environment monitoring data of the target watershed, and divide the target watershed into the pollution impact main control area, pollution diffusion boundary area and pollution interaction transition area based on the hydrological and geomorphological characteristics, pollution source distribution and water body fluidity;

[0096] The correlation strength analysis module is used to extract high-frequency pollution factors in the pollution-affected main control area based on the big data clustering algorithm, and analyze the correlation strength between the high-frequency pollution factors and the water quality indicators in the surrounding pollution diffusion boundary area to generate a high-frequency pollution factor correlation matrix;

[0097] The pollution diffusion prediction module is used to build a pollution diffusion path prediction model based on the high-frequency pollution factor correlation matrix and the historical flow change data of the pollution interaction transition zone, combined with time series analysis technology, and output the potential pollution propagation area and pollution intensity;

[0098] The pollution diffusion state analysis module is used to dynamically match the real-time monitoring data of the multi-source water environment in the target basin with the pollution diffusion path prediction model, analyze the current pollution diffusion state of the target basin, and obtain the real-time prediction results of pollution diffusion;

[0099] The assessment and early warning module is used to evaluate the pollution risk level of each area in the target river basin based on real-time prediction results of pollution diffusion, generate regional pollution warning information, and provide pollution prevention and control and governance recommendations in combination with historical governance case data.

[0100] 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.

[0101] 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.

[0102] Those of ordinary skill in the art will appreciate that the modules 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.

[0103] 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 modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0104] 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 modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0105] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0106] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0107] If the functions are implemented in the form of software function modules 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 each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0108] 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.

[0109] 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 water environment pollution monitoring and management method based on big data, characterized in that: The steps include: Obtain multi-source historical water environment monitoring data for the target basin, and divide the target basin into pollution-affected main control areas, pollution diffusion boundary areas, and pollution interaction transition areas based on hydrological and geomorphological characteristics, pollution source distribution, and water body fluidity; In the main pollution control area, high-frequency pollution factors are extracted based on the big data clustering algorithm, and the correlation strength between high-frequency pollution factors and water quality indicators in the surrounding pollution diffusion boundary area is analyzed to generate a high-frequency pollution factor correlation matrix; Based on the correlation matrix of high-frequency pollution factors and the historical flow change data of pollution interaction transition zones, combined with time series analysis technology, a pollution diffusion path prediction model is constructed to output potential pollution propagation areas and pollution intensity; Dynamically match the multi-source water environment real-time monitoring data of the target basin with the pollution diffusion path prediction model, analyze the current pollution diffusion status of the target basin, and obtain the real-time prediction results of pollution diffusion; Based on the real-time prediction results of pollution diffusion, the pollution risk level of each area in the target river basin is evaluated, regional pollution warning information is generated, and pollution prevention and control and governance recommendations are provided in combination with historical governance case data.

2. The water environment pollution monitoring and management method based on big data according to claim 1 is characterized in that: Obtain multi-source historical water environment monitoring data for the target basin, and divide the target basin into the pollution impact main control area, pollution diffusion boundary area and pollution interaction transition area based on hydrological and geomorphological characteristics, pollution source distribution and water body fluidity. Specifically: Based on the geographic information data of the target watershed, determine the main hydrological flow direction, flow rate and regional water volume in the watershed, and preliminarily identify the pollutant accumulation area; Extract the source distribution information of industrial emissions, agricultural non-point source pollution and domestic sewage in the target watershed, and calibrate the pollution source distribution intensive area based on the pollutant emissions and water inlet channels; Divide the pollution impact control area according to the water flow direction and the distribution of pollutant accumulation areas; Extract water quality monitoring data of water bodies at the edge of the target basin, determine the diffusion law of pollutants, and delineate the pollution diffusion boundary area; Between the main pollution control area and the pollution diffusion boundary area, the pollution interaction transition zone is determined based on the basin topography and water flow diffusion characteristics.

3. The water environment pollution monitoring and management method based on big data according to claim 1 is characterized in that: In the main pollution control area, high-frequency pollution factors are extracted based on the big data clustering algorithm, and the correlation strength between high-frequency pollution factors and water quality indicators in the surrounding pollution diffusion boundary area is analyzed to generate a pollution factor correlation matrix, which is as follows: Extract historical water environment monitoring data of the main control area affected by pollution, conduct time series analysis on pollution indicators, identify indicator factors with pollution frequency higher than the preset threshold, and obtain a set of high-frequency pollution factors; Based on the high-frequency pollution factor set, determine the temporal impact range and spatial coverage of each high-frequency pollution factor in the pollution diffusion boundary area; The big data clustering algorithm is used to group the impact characteristics of high-frequency pollution factors in different sections to form an associated distribution model; Based on the correlation distribution model, the correlation strength between high-frequency pollution factors and water quality indicators in the diffusion boundary area is evaluated, and the correlation matrix of high-frequency pollution factors is generated.

4. The water environment pollution monitoring and management method based on big data according to claim 1 is characterized in that: Based on the correlation matrix of high-frequency pollution factors and the historical flow change data of pollution interaction transition zones, combined with time series analysis technology, a pollution diffusion path prediction model is constructed to output potential pollution propagation areas and pollution intensity, specifically: According to the correlation matrix of high-frequency pollution factors, the potential path of the pollution diffusion starting point and the pollution diffusion direction is determined; Extract historical flow direction change data in the pollution interaction transition zone, determine the dynamic characteristics of water flow velocity, direction and key nodes, and generate a preliminary model of pollution migration path; Based on the time series concentration variation trend of high-frequency pollution factors and combined with the water flow diffusion characteristics, a dynamic prediction model for pollution diffusion path is established; Regional hydrological and geomorphological constraint parameters are added to the dynamic prediction model of pollution diffusion path, the pollution diffusion path is optimized and adjusted, the pollution diffusion path prediction results are generated, and the potential pollution propagation area and pollution intensity are determined.

5. The water environment pollution monitoring and management method based on big data according to claim 4 is characterized in that: Regional hydrological and geomorphological constraint parameters are added to the dynamic prediction model of pollution diffusion path to optimize and adjust the pollution diffusion path, generate pollution diffusion path prediction results, and determine the potential pollution propagation area and pollution intensity, specifically: Extract hydrological and geomorphological characteristics data of the target watershed, including river morphology, watershed slope, water body depth and surface permeability; Based on the hydrological and geomorphological characteristics, a set of constraint parameters is established to define the flow resistance coefficient, diffusion boundary adjustment factor and pollutant deposition probability; The hydrological and geomorphic constraint parameters are embedded in the dynamic prediction model of pollution diffusion path to correct the dynamic change trend of pollution diffusion direction and key nodes; According to the constraint parameters, the abnormal diffusion area in the diffusion path is optimized, the diffusion range and propagation speed are adjusted, the optimized pollution diffusion path prediction results are generated, and the potential pollution propagation area and pollution intensity are determined.

6. The water environment pollution monitoring and management method based on big data according to claim 1 is characterized in that: Dynamically match the multi-source water environment real-time monitoring data of the target basin with the pollution diffusion path prediction model, analyze the current pollution diffusion status of the target basin, and obtain the real-time prediction results of pollution diffusion, specifically: Obtain real-time monitoring data of multi-source water environment in the target basin, including water quality indicators, flow velocity and direction data, and dynamic change data of pollutant concentration; Input the multi-source water environment real-time monitoring data of the target basin into the pollution diffusion path prediction model, combine the diffusion direction, path nodes and pollution intensity parameters in the pollution diffusion path prediction model, and match the dynamic change trend of the multi-source water environment real-time monitoring data with the pollution diffusion path prediction model; Evaluate the diffusion impact range and peak changes of abnormal water quality indicators in multi-source water environment real-time monitoring data, and update the pollution diffusion path prediction model; According to the updated pollution diffusion path prediction model, the current pollution diffusion status of the target basin is generated, including the diffusion range, pollution concentration distribution and pollution diffusion speed, and the real-time prediction results of pollution diffusion are obtained.

7. The water environment pollution monitoring and management method based on big data according to claim 1 is characterized in that: Based on the real-time prediction results of pollution diffusion, the pollution risk level of each area in the target basin is evaluated, and regional pollution warning information is generated. In combination with historical governance case data, pollution prevention and control and governance suggestions are provided, specifically: Based on the diffusion range, pollution concentration distribution and diffusion speed data in the real-time prediction results of pollution diffusion, combined with the regional water quality benchmark threshold and pollutant category, the pollution risk score of the target watershed is obtained; Based on the pollution risk score, the target watershed is divided into high-risk, medium-risk and low-risk areas, and a regional pollution risk level map is generated; Based on the diffusion dynamics and pollution concentration peaks in high-risk areas, the direction and impact range of possible further spread of pollution are predicted, and regional pollution warning information is generated; Extract historical governance case data, combine the pollution diffusion trend and regional characteristics of high-risk areas, and recommend suitable pollution prevention and control and governance plans.

8. A water environment pollution monitoring and management system based on big data, used to implement the water environment pollution monitoring and management method based on big data according to any one of claims 1 to 7, characterized in that: It includes watershed division module, correlation strength analysis module, pollution diffusion prediction module, pollution diffusion state analysis module and assessment and early warning module; The watershed division module is used to obtain multi-source historical water environment monitoring data of the target watershed, and divide the target watershed into the pollution impact main control area, pollution diffusion boundary area and pollution interaction transition area based on the hydrological and geomorphological characteristics, pollution source distribution and water body fluidity; The correlation strength analysis module is used to extract high-frequency pollution factors in the pollution-affected main control area based on the big data clustering algorithm, and analyze the correlation strength between the high-frequency pollution factors and the water quality indicators in the surrounding pollution diffusion boundary area to generate a high-frequency pollution factor correlation matrix; The pollution diffusion prediction module is used to build a pollution diffusion path prediction model based on the high-frequency pollution factor correlation matrix and the historical flow change data of the pollution interaction transition zone, combined with time series analysis technology, and output the potential pollution propagation area and pollution intensity; The pollution diffusion state analysis module is used to dynamically match the real-time monitoring data of the multi-source water environment in the target basin with the pollution diffusion path prediction model, analyze the current pollution diffusion state of the target basin, and obtain the real-time prediction results of pollution diffusion; The assessment and early warning module is used to evaluate the pollution risk level of each area in the target river basin based on real-time prediction results of pollution diffusion, generate regional pollution warning information, and provide pollution prevention and control and governance recommendations in combination with historical governance case data.

Images