Monitoring system for ecological environment and environmental pollution

Abstract

The invention relates to the technical field of environmental monitoring, in particular to an ecological environment and environmental pollution monitoring system and method, and a multi-source heterogeneous data acquisition module comprehensively acquires water quality, weather and space monitoring data. The system comprises a topological mapping data preprocessing module which is used for abnormal data detection and data vacancy filling; the state evolution analysis module is used for constructing an environment state transition network and analyzing an environment state evolution rule; the environment comprehensive evaluation module is used for calculating a water safety level index and a water pollution condition index and generating an environment quality evaluation report; the pollution diffusion prediction module is used for predicting a pollutant diffusion path and concentration distribution and identifying a high-risk area; the intelligent early warning and visualization module is used for generating graded early warning information and visually displaying the environment state and the pollution diffusion condition through multi-dimensional data, so that the coverage and the data integrity of environment monitoring are remarkably improved, the environmental pollution problem can be timely found and dealt with, and the ecological environment safety is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring, and in particular to a system and method for monitoring an ecological environment and environmental pollution, for realizing the collection, processing, analysis, prediction and early warning of environmental monitoring data. Background Art

[0002] With the continuous advancement of industrialization and urbanization, environmental pollution is becoming increasingly serious, posing a major threat to the ecological environment and human health. Traditional environmental monitoring systems typically use single-parameter monitoring, static data analysis, and simple threshold alarm methods, which cannot effectively address complex and changing environmental pollution problems. These systems have the following major shortcomings:

[0003] First, traditional systems usually use a single or a small number of monitoring points with limited monitoring parameters, making it difficult to fully reflect the regional environmental conditions; second, the data processing methods are simple and have limited ability to handle abnormal and missing data, affecting data quality; third, the environmental evaluation indicator system is imperfect and difficult to accurately reflect the environmental quality status; finally, there is a lack of effective pollutant diffusion prediction and intelligent early warning mechanisms, making it impossible to respond to environmental risks in a timely manner.

[0004] In existing technologies, some systems attempt to increase monitoring coverage by adding monitoring points and parameters, but the problem of data silos still exists; some systems introduce methods such as machine learning to improve data analysis capabilities, but lack a grasp of the complex dynamic characteristics of environmental systems; some systems provide simple pollution diffusion simulation functions, but their accuracy and reliability are limited.

[0005] Therefore, there is an urgent need to develop an intelligent environmental monitoring system that can comprehensively collect environmental monitoring data, accurately process abnormal data, scientifically evaluate environmental quality, accurately predict pollution spread and issue early warnings in a timely manner. Summary of the Invention

[0006] The purpose of the present invention is to provide a monitoring system and method for the ecological environment and environmental pollution, aiming to solve the problems existing in the prior art such as incomplete data collection, inaccurate data processing, unscientific environmental evaluation, inaccurate pollution prediction and untimely early warning.

[0007] The present invention proposes a monitoring system for ecological environment and environmental pollution, comprising:

[0008] A multi-source heterogeneous data acquisition module is used to collect water quality monitoring data, meteorological monitoring data, and spatial monitoring data, wherein the water quality monitoring data includes water transparency, temperature, dissolved oxygen, pH, conductivity, turbidity, and pollutant concentration data;

[0009] a topological mapping data preprocessing module, electrically connected to the multi-source heterogeneous data acquisition module, configured to receive environmental monitoring data acquired by the multi-source heterogeneous data acquisition module, map the environmental monitoring data to a topological space, detect abnormal data based on topological distance, and perform data filling using the average value of normal data at both ends of the abnormal data location;

[0010] a state evolution analysis module, electrically connected to the topology mapping data preprocessing module, configured to receive the environmental monitoring data processed by the topology mapping data preprocessing module, construct an environmental state transition network, analyze environmental state evolution laws, and identify key states and critical transition points;

[0011] an environmental comprehensive evaluation module, electrically connected to the state evolution analysis module, configured to receive the environmental state analysis results of the state evolution analysis module, calculate the water safety level index and the water pollution status index, determine the environmental quality level, and generate an environmental quality evaluation report;

[0012] A pollution diffusion prediction module is electrically connected to the environmental comprehensive evaluation module and the state evolution analysis module, and is used to predict the pollutant diffusion path and concentration distribution based on the environmental state evolution law and pollution source characteristics using a multi-scale simulation method to identify high-risk areas;

[0013] The intelligent early warning and visualization module is electrically connected to the pollution diffusion prediction module and the environmental comprehensive evaluation module, and is used to receive the prediction results of the pollution diffusion prediction module and the evaluation results of the environmental comprehensive evaluation module, generate graded early warning information, and display the environmental status and pollution diffusion situation through multi-dimensional data visualization.

[0014] Preferably, the topology mapping data preprocessing module includes:

[0015] A data cleaning unit, used for performing format conversion and standardization processing on the environmental monitoring data;

[0016] Topological mapping unit, used to construct similarity matrix between environmental parameters, generate topological network structure, and map environmental monitoring data into topological space;

[0017] An anomaly detection unit, used to calculate the distance between data points based on a topological distance function and identify abnormal data points that exceed a preset threshold range;

[0018] a data filling unit, configured to determine the position of abnormal data, calculate the average value of normal data at both ends of the abnormal data position, and fill the abnormal data position with the average value;

[0019] The data reconstruction unit is used to rearrange the environmental monitoring data after data filling to form a new data group.

[0020] Preferably, the state evolution analysis module includes:

[0021] The state definition unit is used to integrate environmental monitoring data into environmental state vectors and build an environmental state classification system;

[0022] The transition network construction unit is used to calculate the transition probability between states based on the historical state sequence and construct a state transition network, in which the network nodes represent the environment state and the connections between nodes represent the state transition relationship;

[0023] The key state identification unit is used to calculate the centrality index of nodes in the state transition network, identify high-connectivity nodes as key states of the environment, and identify low-stability nodes as critical points of environmental state changes;

[0024] The evolution law analysis unit is used to analyze the stability and convergence of the state trajectory, identify the periodic and trend changes of the environmental state, and quantify the state change rate.

[0025] Preferably, the comprehensive environmental evaluation module includes:

[0026] Index calculation unit, used to calculate the water safety level index WSS and water pollution index WPC, where:

[0027] The water safety index WSS = dissolved oxygen + temperature + transparency - conductivity - heavy metal concentration;

[0028] The water pollution index WPC = ammonia nitrogen concentration + nitrate nitrogen concentration + nitrite nitrogen concentration + total nitrogen concentration + chemical oxygen demand + permanganate index + total phosphorus concentration + fecal coliform group concentration + total colony count;

[0029] The grading unit is used to grade the environmental quality based on the water safety grade index WSS and the water pollution index WPC, wherein:

[0030] When WSS ≥ 80, the water safety level is "excellent";

[0031] When 80>WSS≥60, the water safety level is "good";

[0032] When 60>WSS≥40, the water safety level is "general";

[0033] When 40>WSS>20, the water safety level is "poor";

[0034] When WSS≤20, the water safety level is "poor";

[0035] The evaluation generation unit is used to generate an environmental quality evaluation report based on the environmental quality level, including an environmental quality level distribution map.

[0036] Preferably, the pollution diffusion prediction module includes:

[0037] Source analysis unit, used to identify the location of pollution sources, characterize emission rates, concentrations and durations, and analyze the physical and chemical characteristics of pollution;

[0038] Environmental conditions analysis unit, used to analyze the impact of meteorological conditions, hydrological conditions and terrain characteristics on the diffusion process;

[0039] Scale decomposition unit, used to decompose the environmental space into three levels: microscale, mesoscale and macroscale;

[0040] Multi-scale simulation unit, used to simulate the pollutant diffusion process at different scales, realize information transfer between scales, and generate comprehensive diffusion prediction results;

[0041] The risk assessment unit is used to identify high-concentration areas and sensitive receptors and assess the pollution risk level based on the diffusion prediction results.

[0042] Preferably, the intelligent early warning and visualization module includes:

[0043] Warning level division unit, used to divide warning levels according to pollution degree and impact range;

[0044] An early warning trigger unit is used to generate early warning information based on monitoring data and prediction results according to preset trigger rules;

[0045] The early warning push unit is used to determine the early warning push area based on the impact range and customize the early warning information content according to the needs of different groups of people;

[0046] Data visualization unit, used to display environmental data through time series graphs, spatial distribution graphs, and association network graphs;

[0047] The interactive decision-making unit is used to provide scenario simulation interaction functions, evaluate the expected effects of different response measures, and support resource optimization allocation.

[0048] Preferably, the multi-source heterogeneous data acquisition module includes:

[0049] Fixed monitoring units, including automatic water quality monitoring stations, weather stations, and air quality monitoring stations, are used to continuously collect environmental parameters at fixed locations;

[0050] Mobile monitoring units, including drones, surface robots, and portable monitors, are used to collect environmental parameters in specific areas or emergency monitoring points;

[0051] Remote sensing monitoring unit, used to collect satellite images and aerial remote sensing data to obtain large-scale environmental information;

[0052] A social sensing unit, which collects public reports and social media environmental information to supplement professional monitoring data;

[0053] The collection strategy management unit is used to dynamically adjust the data collection frequency and sampling point layout according to parameter change characteristics, environmental sensitive areas and abnormal conditions.

[0054] Preferably, the system further comprises:

[0055] A data storage module, electrically connected to the topology mapping data preprocessing module, for storing original environmental monitoring data and preprocessed environmental monitoring data;

[0056] A model management module, electrically connected to the state evolution analysis module and the pollution diffusion prediction module, for managing the environmental state evolution model and the pollution diffusion prediction model, and updating model parameters according to newly added data;

[0057] The system management module is electrically connected to other modules and is used to manage user permissions, system configuration and operating status to ensure safe and stable operation of the system.

[0058] Preferably, the method for the topology mapping data preprocessing module to process abnormal data is:

[0059] Convert the collected environmental monitoring data to a unified format;

[0060] Calculate the distance between monitoring data points based on the topological distance function and detect whether the difference between adjacent data is within the preset data difference range;

[0061] If it is detected that the difference between adjacent data is not within the preset data difference range, the data is marked as abnormal data and the position of the abnormal data is recorded;

[0062] Determine the location of the abnormal data and fill in the abnormal data location based on the average value of the normal data at both ends of the abnormal data location;

[0063] If there is no normal data at both ends of the abnormal data position, calculate the average value of the nearest normal data positions at both ends of the abnormal data position and add it to the abnormal data position;

[0064] The environmental monitoring data after data filling are rearranged to form a new data group.

[0065] A method for monitoring ecological environment and environmental pollution, comprising the following steps:

[0066] Collect environmental monitoring data including water quality monitoring data, meteorological monitoring data and spatial monitoring data;

[0067] Mapping the environmental monitoring data to a topological space, detecting abnormal data based on topological distance, and filling in data gaps using the average value of normal data at both ends of the abnormal data location;

[0068] Based on the processed environmental monitoring data, an environmental state transition network is constructed to analyze the evolution of environmental states and identify key states and critical transition points.

[0069] Based on the results of environmental status analysis, calculate the water safety level index and water pollution status index, determine the environmental quality level, and generate an environmental quality evaluation report;

[0070] Based on the evolution of environmental conditions and the characteristics of pollution sources, multi-scale simulation methods are used to predict pollutant diffusion paths and concentration distributions, and identify high-risk areas;

[0071] Based on the pollution spread prediction results and environmental quality assessment results, graded warning information is generated, and the environmental status and pollution spread situation are displayed through multi-dimensional data visualization.

[0072] By introducing the topological state evolution theory and multi-scale simulation methods, this paper constructs a complete technical solution from data acquisition, processing, analysis to prediction and early warning, which has the following beneficial effects:

[0073] 1. Through the multi-source heterogeneous data acquisition module, comprehensive collection of water quality, meteorological and spatial monitoring data is achieved, significantly improving the coverage and data integrity of environmental monitoring;

[0074] 2. Through topological mapping data preprocessing technology, accurate identification of abnormal data and intelligent gap filling are achieved, improving data quality and reliability;

[0075] 3. Through the state evolution analysis method, the dynamic change law of environmental state is accurately captured, providing a scientific basis for environmental assessment and pollution prediction;

[0076] 4. Through a scientific comprehensive environmental evaluation index system, accurate assessment and classification of environmental quality are achieved;

[0077] 5. The multi-scale pollution diffusion prediction technology improves the prediction accuracy of pollutant diffusion paths and impact ranges;

[0078] 6. Through the intelligent early warning and visualization module, accurate early warning and intuitive display are achieved, providing strong support for environmental management decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 A schematic diagram of the overall architecture of the ecological environment and environmental pollution monitoring system provided by an embodiment of the present invention;

[0080] Figure 2A schematic diagram of the structure of a topology mapping data preprocessing module provided in an embodiment of the present invention;

[0081] Figure 3 A schematic diagram of the structure of a state evolution analysis module provided in an embodiment of the present invention;

[0082] Figure 4 A schematic diagram of the structure of an environmental comprehensive evaluation module provided in an embodiment of the present invention;

[0083] Figure 5 A schematic diagram of the structure of a pollution diffusion prediction module provided by an embodiment of the present invention;

[0084] Figure 6 A schematic diagram of the structure of the intelligent early warning and visualization module provided in an embodiment of the present invention;

[0085] Figure 7 A schematic diagram of the structure of a multi-source heterogeneous data acquisition module provided by an embodiment of the present invention;

[0086] Figure 8 A schematic diagram of a topology mapping data preprocessing process according to an embodiment of the present invention;

[0087] Figure 9 A schematic flow chart of a method for monitoring the ecological environment and environmental pollution provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0088] Please refer to the attached Figure 1-9 The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the scope of the present invention.

[0089] like Figure 1 As shown, the ecological environment and environmental pollution monitoring system provided by the present invention includes a multi-source heterogeneous data acquisition module 1, a topological mapping data preprocessing module 2, a state evolution analysis module 3, an environmental comprehensive evaluation module 4, a pollution diffusion prediction module 5 and an intelligent early warning and visualization module 6. These modules are electrically connected to form a complete data processing chain to realize intelligent monitoring of the entire process from data acquisition to early warning.

[0090] like Figure 7 As shown, the multi-source heterogeneous data acquisition module 1 includes a fixed monitoring unit 11, a mobile monitoring unit 12, a remote sensing monitoring unit 13, a social perception unit 14 and a collection strategy management unit 15.

[0091] The fixed monitoring unit 11 includes an automatic water quality monitoring station, a weather station, and an air quality monitoring station, which are used to continuously collect environmental parameters at fixed points. Preferably, the parameters collected by the automatic water quality monitoring station include water transparency, temperature, dissolved oxygen, pH, conductivity, turbidity, and pollutant concentration data. Among them, the pollutant concentration data include ammonia nitrogen concentration, nitrate nitrogen concentration, nitrite nitrogen concentration, total nitrogen concentration, chemical oxygen demand, permanganate index, total phosphorus concentration, heavy metal concentration, fecal coliform group concentration, and total colony count. The parameters collected by the weather station include temperature, humidity, air pressure, wind speed, wind direction, rainfall, and sunshine duration. The parameters collected by the air quality monitoring station include concentration data of PM2.5, PM10, SO2, NO2, O3, and CO.

[0092] The mobile monitoring unit 12 includes an unmanned aerial vehicle (UAV), a surface robot, and a portable monitoring instrument, which are used to collect environmental parameters for specific areas or emergency monitoring points. In one embodiment of the present invention, the UAV is equipped with a multispectral camera and gas sensors, enabling rapid scanning and monitoring of large areas in a short period of time. The surface robot is equipped with a water quality sensor array, enabling patrol monitoring along a pre-set route within the water. The portable monitoring instrument has the ability to simultaneously detect multiple parameters, making it suitable for rapid testing at emergency sites.

[0093] The remote sensing monitoring unit 13 is used to collect satellite imagery and aerial remote sensing data to obtain large-scale environmental information. Preferably, a multi-source remote sensing data fusion method is used to combine remote sensing data from different bands, such as optical, thermal infrared, and microwave, to extract information on different ground features such as water bodies, vegetation, and cities, thereby achieving large-scale environmental status monitoring.

[0094] The social perception unit 14 is used to collect public reports and social media environmental information to supplement professional monitoring data. In one embodiment of the present invention, public environmental observation data is collected through a mobile application. Natural language processing technology is also used to extract environmental-related information from social media platforms. After information screening and credibility assessment, it is used to supplement professional monitoring data.

[0095] The acquisition strategy management unit 15 is used to dynamically adjust the data acquisition frequency and sampling point layout based on parameter variation characteristics, environmentally sensitive areas, and abnormal conditions. Preferably, high-frequency sampling (e.g., every 5 minutes) is used for rapidly changing parameters such as dissolved oxygen, while low-frequency sampling (e.g., once a day) is used for slowly changing parameters such as heavy metal concentrations. Sampling point density is increased in environmentally sensitive areas such as drinking water source protection areas. When an abnormal environmental parameter is detected, the sampling frequency of the relevant points is automatically increased.

[0096] like Figure 2 As shown, the topology mapping data preprocessing module 2 includes a data cleaning unit 21 , a topology mapping unit 22 , an anomaly detection unit 23 , a data gap filling unit 24 and a data reconstruction unit 25 .

[0097] The data cleaning unit 21 is used to convert and standardize the environmental monitoring data. In one embodiment of the present invention, data from different sources is converted to a standard format, such as JSON or CSV; parameter values ​​are converted to the International System of Units; and data are timestamp-aligned to ensure data time consistency.

[0098] The topology mapping unit 22 is used to construct a similarity matrix between environmental parameters, generate a topological network structure, and map the environmental monitoring data into a topological space. Preferably, the similarity matrix is ​​calculated using an improved cosine similarity method, and the calculation formula is:

[0099] ,

[0100] in: For parameters and similarity between For parameters At the time point The value of For parameters At the time point The value of is the length of the time series; Indicates from arrive The summation operation is used to accumulate the product or square of the parameter values ​​at each time point.

[0101] Based on the similarity matrix, a topological network structure is constructed. When the similarity exceeds a threshold (empirically set at 0.6), a connection is established between the corresponding parameter nodes. The parameter 0.6 was chosen because experiments have shown that this threshold can retain important relationships while filtering out weak correlations, resulting in a network structure that is neither too sparse nor too dense.

[0102] The anomaly detection unit 23 is used to calculate the distance between data points based on the topological distance function and identify abnormal data points that exceed a preset threshold range. Preferably, the topological distance function is defined as:

[0103] ,

[0104] in: For data points and The topological distance between For data points In the parameters The value on For data points In the parameters The value on For parameters The weight reflects the importance of the parameter; is the total number of parameters; Indicates from arrive The summation operation is used to accumulate the weighted sum of the squares of the differences of each parameter; Replace with actual distance value.

[0105] When the topological distance between a data point and its neighbors exceeds a preset threshold (e.g., three standard deviations of the parameter mean), the data point is marked as an outlier. The choice of three standard deviations as the threshold is based on the empirical rule of thumb in statistics. Under the assumption of a normal distribution, the probability of a data point exceeding three standard deviations is only 0.3%, making it a reasonable indicator of an outlier.

[0106] The data filling unit 24 is used to determine the position of the abnormal data, calculate the average value of the normal data at both ends of the abnormal data position, and fill the abnormal data position with the average value. In one embodiment of the present invention, for abnormal data at position p, if the positions p-1 and p+1 on both sides of the abnormal data are normal data, then the average value is calculated. Fill position p; if there is no normal data directly adjacent to the position p, find the nearest normal data point position and , calculate its average value Fill position p.

[0107] The data reconstruction unit 25 is used to rearrange the environmental monitoring data after data filling to form a new data set. Preferably, the time series structure of the data is maintained to ensure that the original time sequence and interval of the data after filling are maintained. At the same time, the data quality label is updated to mark the original data and the filled data, so that they can be treated separately in subsequent analysis.

[0108] Figure 8 This paper demonstrates the complete process of topological mapping data preprocessing. First, the collected environmental monitoring data is formatted to unify all data formats. Then, the distance between monitoring data points is calculated based on the topological distance function, and the difference between adjacent data points is tested to see if it is within a preset data difference range. If the difference between adjacent data points is not within the preset data difference range, the data is marked as abnormal and the location of the abnormal data is recorded. Next, the location of the abnormal data is determined and the abnormal data position is filled in based on the average value of the normal data on both sides of the abnormal data position. If there is no normal data on both sides of the abnormal data position, the average value of the nearest normal data positions on both sides of the abnormal data position is calculated and added to the abnormal data position. Finally, the environmental monitoring data after data filling is rearranged to form a new data group.

[0109] like Figure 3As shown, the state evolution analysis module 3 includes a state definition unit 31 , a transfer network construction unit 32 , a key state identification unit 33 and an evolution law analysis unit 34 .

[0110] The state definition unit 31 is used to integrate the environmental monitoring data into an environmental state vector and construct a classification system for environmental states. In one embodiment of the present invention, the environmental state vector is defined as:

[0111] ,

[0112] in: is the environmental state vector at time point t; to is a set of water quality parameters, including water transparency, temperature, dissolved oxygen and other m parameters; to is a set of meteorological parameters, including n parameters such as temperature, humidity, and wind speed; to is a set of spatial parameters, including p parameters such as geographic location and elevation; m is the number of water quality parameters; n is the number of meteorological parameters; p is the number of spatial parameters; the brackets [] represent vector symbols, indicating that multiple parameters are combined into one vector.

[0113] Based on the environmental state vectors, a clustering approach is used to construct an environmental state classification system. Preferably, a modified K-means clustering algorithm is used, combined with the silhouette coefficient to estimate the optimal number of clusters. Environmental states are typically divided into 5-10 categories, each representing a typical environmental state. The choice of 5-10 categories is based on practical experience and is sufficient to fully reflect the diversity of environmental states without resulting in overly fragmented categories that are difficult to interpret.

[0114] The transition network construction unit 32 is used to calculate the transition probability between states based on the historical state sequence and construct a state transition network, in which the network nodes represent the environment state and the connections between nodes represent the state transition relationship. Preferably, the transition probability calculation formula is:

[0115] ,

[0116] in: From the state Transfer to state probability; To observe from the state Transfer to state The number of times; K is the total number of states; From the state The total number of transitions to any state; Indicates from arrive The summation operation is used to calculate the total number of state transitions.

[0117] Based on the transition probability matrix, a state transition network is constructed, where nodes represent environmental states, connections represent transition relationships between states, and connection weights are corresponding transition probabilities.

[0118] The key state identification unit 33 is used to calculate the centrality index of the nodes in the state transition network, identify high connectivity nodes as key states of the environment, and identify low stability nodes as critical points of environmental state changes. In one embodiment of the present invention, the node centrality calculation adopts the eigenvector centrality method:

[0119] ,

[0120] in: For nodes The centrality value of is the adjacency matrix element, representing the node and The connection weight between them; is the maximum eigenvalue of the adjacency matrix; is the total number of nodes in the network; Indicates from arrive The summation operation is used to accumulate all nodes The weighted centrality values ​​of connected nodes.

[0121] The node stability evaluation adopts the in-and-out degree ratio method:

[0122] ,

[0123] in: For nodes Stability indicators; For nodes The in-degree represents the total probability of entering the state; For nodes The out-degree of , which represents the total probability of transitioning out of the state; A function that takes a smaller value, returning the smaller value of the two parameters; A function that returns the larger of its two arguments.

[0124] When a node's centrality exceeds a threshold (e.g., twice the average network centrality), the node is identified as being in a critical environmental state. When a node's stability falls below a threshold (empirically set at 0.3), the node is identified as a critical point in environmental state change. These thresholds are based on empirical analysis of actual environmental monitoring data and have demonstrated good identification results in multiple environmental monitoring cases.

[0125] The evolution law analysis unit 34 is used to analyze the stability and convergence of the state trajectory, identify the periodic and trend changes of the environmental state, and quantify the state change rate. Preferably, a time series analysis method is used, such as Fourier transform to identify periodic patterns and linear regression analysis to identify trend changes. The state change rate is defined as the number of state transitions per unit time, and the calculation formula is:

[0126] ,

[0127] in: is the state change rate; is the total number of state transitions during the observation period; is the total duration of the observation period, in hours or days.

[0128] like Figure 4 As shown, the comprehensive environmental evaluation module 4 includes an index calculation unit 41 , a level classification unit 42 and an evaluation generation unit 43 .

[0129] The index calculation unit 41 is used to calculate the water safety level index WSS and the water pollution level index WPC. In one embodiment of the present invention, the calculation formula of the water safety level index WSS is:

[0130] ,

[0131] in: is the water safety level index, dimensionless, ranging from 0 to 100; is the dissolved oxygen concentration in mg / L, after normalization; is the water temperature in °C, normalized; is the transparency, the unit is m, after normalization; is the conductivity in μS / cm, after normalization; is the heavy metal concentration, using the comprehensive heavy metal index, dimensionless, after normalization. are the weight coefficients of the corresponding parameters respectively; the sum of all weights satisfies: The weight values ​​can be determined based on expert evaluation, principal component analysis, hierarchical analysis or machine learning methods.

[0132] The calculation formula of the water pollution index WPC is:

[0133] ,

[0134] in: is the water pollution index, dimensionless, ranging from 0 to 500; is the total nitrogen concentration in mg / L, after normalization; is the chemical oxygen demand, in mg / L, after normalization; is the permanganate index, in mg / L, after normalization; is the total phosphorus concentration in mg / L, after normalization; is the fecal coliform concentration, in units of cells / L, normalized after logarithmic processing; is the total number of colonies in cells / L, normalized after logarithmic processing. All parameters have been normalized or logarithmically normalized. is the total (TN) weight, is the weight of chemical oxygen demand (COD), is the weight of the permanganate index (CODm), is the weight of total phosphorus (TP), is the weight of fecal coliforms (FC), is the weight of the total bacterial count (TBC), and the weight satisfies: To ensure the comparability between different parameters, before calculating WSS and WPC, it is necessary to normalize each parameter so that its value range remains consistent.

[0135] The grading unit 42 is used to grade the environmental quality based on the water safety grade index WSS and the water pollution index WPC. Preferably, the water safety grade grading standard is:

[0136] When WSS ≥ 80, the water safety level is "excellent";

[0137] When 80>WSS≥60, the water safety level is "good";

[0138] When 60>WSS≥40, the water safety level is "general";

[0139] When 40>WSS>20, the water safety level is "poor";

[0140] When WSS≤20, the water safety level is "poor";

[0141] The water pollution index WPC is divided into ten levels on a scale of 0-100, with each level being 10 points. Preferably, the water pollution level is divided into the following levels:

[0142] When WPC is 0-10, it is “clean”;

[0143] When WPC is 11-20, it is “cleaner”;

[0144] When WPC is 21-30, it is “lightly polluted”;

[0145] When WPC is 31-40, it is “moderately polluted”;

[0146] When WPC is 41-50, it is “moderately polluted”;

[0147] When WPC is 51-60, it is “heavily polluted”;

[0148] When WPC is 61-70, it is “severely polluted”;

[0149] When WPC is 71-80, it is “very seriously polluted”;

[0150] When WPC is 81-90, it is “extremely polluted”;

[0151] When WPC is 91-100, it is considered “the most seriously polluted water”.

[0152] Evaluation generation unit 43 is configured to generate an environmental quality evaluation report based on the environmental quality level, including an environmental quality level distribution map. Preferably, the environmental quality evaluation report includes the water safety level and water pollution level of each monitoring point, the spatiotemporal distribution characteristics of regional environmental quality, an analysis of environmental quality trend changes, and identification of key pollution factors. The environmental quality level distribution map utilizes GIS technology to color-code monitoring points of different levels on a map, visually displaying the spatial distribution characteristics of environmental quality.

[0153] like Figure 5 As shown, the pollution diffusion prediction module 5 includes a source term analysis unit 51 , an environmental condition analysis unit 52 , a scale decomposition unit 53 , a multi-scale simulation unit 54 and a risk assessment unit 55 .

[0154] The source term analysis unit 51 is used to identify the location of the pollution source, characterize the emission rate, concentration and duration, and analyze the physical and chemical characteristics of the pollution. In one embodiment of the present invention, the characteristics of the pollution source are determined by combining monitoring data inversion and scenario assumptions. The monitoring data inversion adopts the concentration gradient method. Based on the concentration monitoring data of multiple points, the direction of the concentration gradient is analyzed to infer the possible location of the pollution source. The emission characteristic characterization includes parameters such as emission rate (unit: kg / h), concentration (unit: mg / L or mg / m³) and duration (unit: h). The analysis of the physical and chemical characteristics of pollution includes parameters such as solubility, volatility, and degradation rate. These parameters directly affect the migration and transformation behavior of pollutants in the environment.

[0155] Environmental condition analysis unit 52 is used to analyze the impact of meteorological conditions, hydrological conditions, and terrain characteristics on the diffusion process. Preferably, meteorological condition analysis includes parameters such as wind speed, wind direction, atmospheric stability, and turbulence intensity; hydrological condition analysis includes parameters such as flow velocity, flow direction, water depth, and riverbed characteristics; and terrain characteristic analysis includes information such as topographic relief, land cover type, and the distribution of artificial structures. These environmental condition parameters directly influence the diffusion process and path of pollutants.

[0156] The scale decomposition unit 53 is used to decompose the environmental space into three levels: microscale, mesoscale, and macroscale. Preferably, the microscale is defined as the range of 0-100m, suitable for near-field diffusion simulation of pollution sources; the mesoscale is defined as the range of 100m-10km, suitable for regional pollutant transport simulation; and the macroscale is defined as the range of 10km and above, suitable for large-scale pollution impact assessment. Scale decomposition uses a nested grid approach, with different spatial resolutions and time steps at different scales, balancing computational accuracy and efficiency.

[0157] The multi-scale simulation unit 54 is used to simulate pollutant diffusion processes at different scales, enabling inter-scale information transfer and generating comprehensive diffusion prediction results. In one embodiment of the present invention, computational fluid dynamics (CFD) methods are used at the microscale to account for the influence of local terrain and buildings; Gaussian plume models or Lagrangian particle models are used at the mesoscale to simulate regional pollutant transport; and a gridded meteorological-chemical coupled model is used at the macroscale to simulate large-scale pollution diffusion and transformation processes. Inter-scale information transfer utilizes a combination of boundary condition transfer and parameter correction. Coarse-scale simulation results provide boundary conditions for fine-scale simulations, and fine-scale simulation results are used to correct coarse-scale model parameters.

[0158] The risk assessment unit 55 is used to identify high-concentration areas and sensitive receptors based on the diffusion prediction results and assess the pollution risk level. Preferably, the risk assessment adopts the exposure-dose-response chain analysis method to calculate the pollutant exposure level of different regions and populations and assess the health risk and ecological risk. The risk level is divided into low risk (risk value <10⁻ 6 ), medium risk (10⁻ 6 ≤Risk Value<10⁻ 4 ) and high risk (risk value ≥ 10⁻ 4 ) three levels to provide a scientific basis for early warning decisions.

[0159] like Figure 6 As shown, the intelligent warning and visualization module 6 includes a warning level classification unit 61 , a warning triggering unit 62 , a warning pushing unit 63 , a data visualization unit 64 and an interactive decision unit 65 .

[0160] The warning level classification unit 61 is used to classify warning levels based on the degree of pollution and the scope of impact. In one embodiment of the present invention, the warning levels are divided into four levels from low to high: blue warning, yellow warning, orange warning, and red warning. The warning level is determined by comprehensively considering factors such as the multiple of the pollutant concentration exceeding the standard, the area of ​​impact, the duration, and the number of sensitive receptors. For example, when the pollutant concentration exceeds the standard by 1-2 times, the impact area is less than 1 km², the duration does not exceed 24 hours, and fewer than 3 sensitive receptors are affected, a blue warning is determined. When the multiple of the exceedance, the impact area, the duration, or the number of sensitive receptors exceeds the corresponding threshold, the warning level is increased accordingly.

[0161] The early warning trigger unit 62 is used to generate early warning information based on the monitoring data and prediction results according to preset trigger rules. Preferably, the early warning trigger rules include: a trigger rule when the monitoring data exceeds the preset threshold, a trigger rule when the prediction data exceeds the preset threshold, a trigger rule when the state evolution trend exceeds the preset threshold, and a multi-factor comprehensive trigger rule. Among them, the trigger rule when the monitoring data exceeds the preset threshold is the most basic trigger mechanism, triggering an early warning when the monitored pollutant concentration exceeds the environmental quality standard; the trigger rule when the prediction data exceeds the preset threshold is a forward-looking early warning mechanism, triggering an early warning when it is predicted that the pollutant concentration will exceed the environmental quality standard within a certain period of time in the future (such as within 24 hours); the state evolution trend trigger rule is based on the state evolution analysis results and triggers an early warning when the environmental state evolves towards instability or deterioration; the multi-factor comprehensive trigger rule comprehensively considers multiple environmental factors and triggers an early warning when multiple environmental parameters are abnormal at the same time.

[0162] The early warning push unit 63 is used to determine the early warning push area based on the impact range and customize the early warning information content according to the needs of different groups. Preferably, the early warning information push adopts a precise push strategy based on zoning, grading, and classification: zoning push determines the push area based on the pollution impact range and administrative divisions; grading push provides early warning information with different levels of detail based on the type of audience (such as environmental protection departments, emergency management departments, and the general public); and categorized push provides targeted protective advice based on the special needs of different groups (such as the elderly, children, and people with respiratory diseases).

[0163] The data visualization unit 64 is used to display environmental data through time series graphs, spatial distribution graphs, and association network graphs. In one embodiment of the present invention, time dimension visualization uses dynamic time series graphs to display the changing trends of environmental parameters over time; spatial dimension visualization uses GIS maps to display pollution distribution in the form of heat maps and contour maps; and association dimension visualization uses network graphs to display the interrelationships and impact paths between parameters. Multidimensional data visualization technology can transform complex environmental data into intuitive graphics, making it easier for decision makers and the public to understand environmental conditions.

[0164] Interactive decision-making unit 65 is used to provide interactive scenario simulation functions, evaluate the expected effects of different response measures, and support resource optimization. Preferably, through an interactive interface, decision-makers can set different pollution scenarios and response measures. The system automatically simulates and calculates the pollution diffusion path and impact range under different scenarios, and evaluates the effectiveness of different response measures. For example, decision-makers can simulate different pollutant emission control strategies, different emergency resource deployment plans, and different evacuation routes. The system will provide an evaluation of the expected effects of each plan, providing a scientific basis for decision-making.

[0165] like Figure 1 As shown, the system of the present invention further includes a data storage module 7, a model management module 8 and a system management module 9, which provide support for the normal operation of the system.

[0166] The data storage module 7 is electrically connected to the topology mapping data preprocessing module 2 and is used to store raw and preprocessed environmental monitoring data. Preferably, a distributed database system is used, including a relational database (such as PostgreSQL) for storing structured data, a NoSQL database (such as MongoDB) for storing semi-structured and unstructured data, and a time series database (such as InfluxDB) for storing high-frequency time series monitoring data. Data storage adopts a hot-cold tiering strategy, with recent data stored on high-performance storage devices and historical data regularly archived to low-cost storage devices.

[0167] The model management module 8 is electrically connected to the state evolution analysis module 3 and the pollution diffusion prediction module 5, and is used to manage the environmental state evolution model and the pollution diffusion prediction model, and to update the model parameters based on the newly added data. In one embodiment of the present invention, model management includes functions such as model version control, parameter optimization, performance evaluation, and automatic update. Model version control records the evolution history of the model to facilitate tracing and rollback; parameter optimization automatically adjusts model parameters based on newly added data to improve model accuracy; performance evaluation regularly compares the model prediction results with the actual situation to evaluate the model performance; and automatic update determines whether the model needs to be updated based on the performance evaluation results and automatically performs the update operation.

[0168] The system management module 9 is electrically connected to the other modules and is used to manage user permissions, system configuration, and operating status to ensure secure and stable system operation. Preferably, user permission management utilizes a role-based access control (RBAC) approach, assigning different operating permissions based on user roles (e.g., system administrator, data analyst, or general user). System configuration management provides a graphical interface for administrators to adjust system parameters. Operating status monitoring records the operating status of each system module in real time, automatically generates alarms when anomalies are detected, and takes appropriate measures to ensure stable system operation.

[0169] like Figure 9 As shown, the present invention also provides a method for monitoring the ecological environment and environmental pollution, which includes the following steps:

[0170] The first step is to collect environmental monitoring data, including water quality monitoring data, meteorological monitoring data, and spatial monitoring data. Preferably, water quality monitoring data includes water clarity, temperature, dissolved oxygen, pH, conductivity, turbidity, and pollutant concentration data; meteorological monitoring data includes temperature, humidity, air pressure, wind speed, wind direction, rainfall, and sunshine duration; and spatial monitoring data includes geographic location, elevation, and land cover type.

[0171] The second step is to map the environmental monitoring data to a topological space, detect abnormal data based on topological distance, and fill in data gaps using the average value of the normal data at both ends of the abnormal data location. Preferably, the topological mapping adopts the method of the topological mapping unit 22 described above; the abnormality detection adopts the method of the abnormality detection unit 23 described above; and the data gap filling adopts the method of the data gap filling unit 24 described above.

[0172] The third step is to construct an environmental state transition network based on the processed environmental monitoring data, analyze the environmental state evolution patterns, and identify key states and critical transition points. Preferably, the state definition method of the aforementioned state definition unit 31 is used; the transition network construction method of the aforementioned transition network construction unit 32 is used; the key state identification method of the aforementioned key state identification unit 33 is used; and the evolution pattern analysis method of the aforementioned evolution pattern analysis unit 34 is used.

[0173] The fourth step is to calculate the water safety index and water pollution index based on the environmental status analysis results, determine the environmental quality level, and generate an environmental quality evaluation report. Preferably, the index calculation method of the index calculation unit 41 is used; the level classification method of the level classification unit 42 is used; and the evaluation report generation method of the evaluation generation unit 43 is used.

[0174] The fifth step is to use multi-scale simulation methods to predict pollutant diffusion paths and concentration distributions based on the evolution of environmental conditions and the characteristics of pollution sources, and to identify high-risk areas. Preferably, source term analysis uses the methods of the source term analysis unit 51 described above; environmental condition analysis uses the methods of the environmental condition analysis unit 52 described above; scale decomposition uses the methods of the scale decomposition unit 53 described above; multi-scale simulation uses the methods of the multi-scale simulation unit 54 described above; and risk assessment uses the methods of the risk assessment unit 55 described above.

[0175] The sixth step is to generate graded warning information based on the pollution spread prediction results and environmental quality assessment results, and to display the environmental status and pollution spread through multi-dimensional data visualization. Preferably, the warning level classification adopts the method of the warning level classification unit 61 described above; the warning triggering adopts the method of the warning triggering unit 62 described above; the warning push adopts the method of the warning push unit 63 described above; the data visualization adopts the method of the data visualization unit 64 described above; and the interactive decision support adopts the method of the interactive decision unit 65 described above.

[0176] The ecological environment and environmental pollution monitoring system and method provided by the present invention, by introducing topological state evolution theory and multi-scale simulation methods, realize the precise processing of environmental data, accurate analysis of environmental status, scientific evaluation of environmental quality, precise prediction of pollution spread and timely warning of environmental risks, providing strong technical support for environmental monitoring and pollution prevention and control, and has important theoretical innovation value and practical application prospects.

[0177] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A monitoring system for ecological environment and environmental pollution, characterized in that: include: A multi-source heterogeneous data acquisition module is used to collect water quality monitoring data, meteorological monitoring data, and spatial monitoring data, wherein the water quality monitoring data includes water transparency, temperature, dissolved oxygen, pH, conductivity, turbidity, and pollutant concentration data; a topological mapping data preprocessing module, electrically connected to the multi-source heterogeneous data acquisition module, configured to receive environmental monitoring data acquired by the multi-source heterogeneous data acquisition module, map the environmental monitoring data to a topological space, detect abnormal data based on topological distance, and perform data filling using the average value of normal data at both ends of the abnormal data location; a state evolution analysis module, electrically connected to the topology mapping data preprocessing module, configured to receive the environmental monitoring data processed by the topology mapping data preprocessing module, construct an environmental state transition network, analyze environmental state evolution laws, and identify key states and critical transition points; an environmental comprehensive evaluation module, electrically connected to the state evolution analysis module, configured to receive the environmental state analysis results of the state evolution analysis module, calculate the water safety level index and the water pollution status index, determine the environmental quality level, and generate an environmental quality evaluation report; A pollution diffusion prediction module is electrically connected to the environmental comprehensive evaluation module and the state evolution analysis module, and is used to predict the pollutant diffusion path and concentration distribution based on the environmental state evolution law and pollution source characteristics using a multi-scale simulation method to identify high-risk areas; The intelligent early warning and visualization module is electrically connected to the pollution diffusion prediction module and the environmental comprehensive evaluation module, and is used to receive the prediction results of the pollution diffusion prediction module and the evaluation results of the environmental comprehensive evaluation module, generate graded early warning information, and display the environmental status and pollution diffusion situation through multi-dimensional data visualization.

2. The ecological environment and environmental pollution monitoring system according to claim 1, characterized in that: The topology mapping data preprocessing module includes: A data cleaning unit, used for performing format conversion and standardization processing on the environmental monitoring data; Topological mapping unit, used to construct similarity matrix between environmental parameters, generate topological network structure, and map environmental monitoring data into topological space; An anomaly detection unit, used to calculate the distance between data points based on a topological distance function and identify abnormal data points that exceed a preset threshold range; a data filling unit, configured to determine the position of abnormal data, calculate the average value of normal data at both ends of the abnormal data position, and fill the abnormal data position with the average value; The data reconstruction unit is used to rearrange the environmental monitoring data after data filling to form a new data group.

3. The ecological environment and environmental pollution monitoring system according to claim 1, characterized in that: The state evolution analysis module includes: The state definition unit is used to integrate environmental monitoring data into environmental state vectors and build an environmental state classification system; The transition network construction unit is used to calculate the transition probability between states based on the historical state sequence and construct a state transition network, in which the network nodes represent the environment state and the connections between nodes represent the state transition relationship; The key state identification unit is used to calculate the centrality index of nodes in the state transition network, identify high-connectivity nodes as key states of the environment, and identify low-stability nodes as critical points of environmental state changes; The evolution law analysis unit is used to analyze the stability and convergence of the state trajectory, identify the periodic and trend changes of the environmental state, and quantify the state change rate.

4. The ecological environment and environmental pollution monitoring system according to claim 1, characterized in that: The comprehensive environmental evaluation module includes: Index calculation unit, used to calculate the water safety level index WSS and water pollution index WPC, where: The water safety index WSS = dissolved oxygen + temperature + transparency - conductivity - heavy metal concentration; The water pollution index WPC = ammonia nitrogen concentration + nitrate nitrogen concentration + nitrite nitrogen concentration + total nitrogen concentration + chemical oxygen demand + permanganate index + total phosphorus concentration + fecal coliform group concentration + total colony count; The grading unit is used to grade the environmental quality based on the water safety grade index WSS and the water pollution index WPC, wherein: When WSS ≥ 80, the water safety level is "excellent"; When 80>WSS≥60, the water safety level is "good"; When 60>WSS≥40, the water safety level is "general"; When 40>WSS>20, the water safety level is "poor"; When WSS≤20, the water safety level is "poor"; The evaluation generation unit is used to generate an environmental quality evaluation report based on the environmental quality level, including an environmental quality level distribution map.

5. The ecological environment and environmental pollution monitoring system according to claim 1, characterized in that: The pollution diffusion prediction module includes: Source analysis unit, used to identify the location of pollution sources, characterize emission rates, concentrations and durations, and analyze the physical and chemical characteristics of pollution; Environmental conditions analysis unit, used to analyze the impact of meteorological conditions, hydrological conditions and terrain characteristics on the diffusion process; Scale decomposition unit, used to decompose the environmental space into three levels: microscale, mesoscale and macroscale; Multi-scale simulation unit, used to simulate the pollutant diffusion process at different scales, realize information transfer between scales, and generate comprehensive diffusion prediction results; The risk assessment unit is used to identify high-concentration areas and sensitive receptors and assess the pollution risk level based on the diffusion prediction results.

6. The ecological environment and environmental pollution monitoring system according to claim 1, characterized in that: The intelligent early warning and visualization module includes: Warning level division unit, used to divide warning levels according to pollution degree and impact range; An early warning trigger unit is used to generate early warning information based on monitoring data and prediction results according to preset trigger rules; The early warning push unit is used to determine the early warning push area based on the impact range and customize the early warning information content according to the needs of different groups of people; Data visualization unit, used to display environmental data through time series graphs, spatial distribution graphs, and association network graphs; The interactive decision-making unit is used to provide scenario simulation interaction functions, evaluate the expected effects of different response measures, and support resource optimization allocation.

7. The ecological environment and environmental pollution monitoring system according to claim 1, characterized in that: The multi-source heterogeneous data acquisition module includes: Fixed monitoring units, including automatic water quality monitoring stations, weather stations, and air quality monitoring stations, are used to continuously collect environmental parameters at fixed locations; Mobile monitoring units, including drones, surface robots, and portable monitors, are used to collect environmental parameters in specific areas or emergency monitoring points; Remote sensing monitoring unit, used to collect satellite images and aerial remote sensing data to obtain large-scale environmental information; A social sensing unit, which collects public reports and social media environmental information to supplement professional monitoring data; The collection strategy management unit is used to dynamically adjust the data collection frequency and sampling point layout according to parameter change characteristics, environmental sensitive areas and abnormal conditions.

8. The ecological environment and environmental pollution monitoring system according to claim 1, characterized in that: The system further comprises: A data storage module, electrically connected to the topology mapping data preprocessing module, for storing original environmental monitoring data and preprocessed environmental monitoring data; A model management module, electrically connected to the state evolution analysis module and the pollution diffusion prediction module, for managing the environmental state evolution model and the pollution diffusion prediction model, and updating model parameters according to newly added data; The system management module is electrically connected to other modules and is used to manage user permissions, system configuration and operating status to ensure safe and stable operation of the system.

9. The ecological environment and environmental pollution monitoring system according to claim 1, characterized in that: The method for the topology mapping data preprocessing module to process abnormal data is: Convert the collected environmental monitoring data to a unified format; Calculate the distance between monitoring data points based on the topological distance function and detect whether the difference between adjacent data is within the preset data difference range; If it is detected that the difference between adjacent data is not within the preset data difference range, the data is marked as abnormal data and the position of the abnormal data is recorded; Determine the location of the abnormal data and fill in the abnormal data location based on the average value of the normal data at both ends of the abnormal data location; If there is no normal data at both ends of the abnormal data position, calculate the average value of the nearest normal data positions at both ends of the abnormal data position and add it to the abnormal data position; The environmental monitoring data after data filling are rearranged to form a new data group.

10. A method for monitoring ecological environment and environmental pollution, characterized in that: The method comprises the following steps: Collect environmental monitoring data including water quality monitoring data, meteorological monitoring data and spatial monitoring data; Mapping the environmental monitoring data to a topological space, detecting abnormal data based on topological distance, and filling in data gaps using the average value of normal data at both ends of the abnormal data location; Based on the processed environmental monitoring data, an environmental state transition network is constructed to analyze the evolution of environmental states and identify key states and critical transition points. Based on the results of environmental status analysis, calculate the water safety level index and water pollution status index, determine the environmental quality level, and generate an environmental quality evaluation report; Based on the evolution of environmental conditions and the characteristics of pollution sources, multi-scale simulation methods are used to predict pollutant diffusion paths and concentration distributions, and identify high-risk areas; Based on the pollution spread prediction results and environmental quality assessment results, graded warning information is generated, and the environmental status and pollution spread situation are displayed through multi-dimensional data visualization.

Images