Water quality monitoring intelligent early warning method and system based on multi-dimensional data analysis

Abstract

The invention discloses a water quality monitoring intelligent early warning method and system based on multi-dimensional data analysis, and belongs to the technical field of water quality monitoring. The method comprises the following steps: processing missing values and noise through a dynamic weighted data filling algorithm to obtain complete water quality data; carrying out multi-parameter collaborative dimensionality reduction by adopting an improved t-SNE algorithm, and mapping high-dimensional water quality parameters to a three-dimensional feature space; constructing a dynamic watershed partition model based on a Delaunay triangulation network and DEM data; calculating a spatial anomaly score through a weighted local outlier factor; performing time anomaly detection in combination with STL (Standard Template Library) decomposition and a Transform model; multi-scale fluctuation detection is realized by using wavelet packet decomposition; fusing space, time and parameter dimensions to construct a three-dimensional judgment matrix, and generating a comprehensive anomaly score; and triggering a multi-level early warning mechanism according to a scoring result. The system can monitor the water quality change in real time, and gives out early warning in time when abnormity occurs, so that the water quality safety is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of water quality monitoring technology, specifically to a smart early warning method and system for water quality monitoring based on multidimensional data analysis. Background Technology

[0002] Water resources are an important foundation for human survival and socio-economic development. The quality of water directly affects the ecological environment, public health, and industrial production. With the acceleration of industrialization and urbanization, water quality monitoring has become an important means of ensuring water resource security. Traditional water quality monitoring methods rely on manual periodic sampling and on-site testing, which have disadvantages such as poor timeliness, high cost, and limited coverage, and are easily affected by the external environment. Existing technologies mostly adopt static analysis methods, which lack comprehensive analysis of the spatiotemporal dynamic changes of water quality data. Specifically, this manifests in the following ways: (1) Data gaps and noise processing are simple and static, making it difficult to adapt to dynamic fluctuations in water quality; (2) Analysis methods are mostly limited to a single dimension, severing the spatiotemporal correlation and having weak ability to capture complex nonlinear patterns and multi-scale cycles; (3) Early warning mechanisms rely on fixed thresholds, have low sensitivity, and are difficult to detect gradual or sudden anomalies caused by multi-parameter coordination in the early stages, and lack refined graded response capabilities. Therefore, how to improve the accuracy, real-time performance, and automation of water quality monitoring systems has become an urgent technical problem to be solved. Summary of the Invention

[0003] The purpose of this invention is to provide a water quality monitoring intelligent early warning method and system based on multidimensional data analysis. By comprehensively considering the spatiotemporal distribution characteristics of the data, dynamically adjusting the data filling method, adopting advanced data dimensionality reduction and analysis algorithms, and combining a multi-level early warning mechanism, it can achieve accurate monitoring and real-time early warning of water quality changes.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] In a first aspect, the present invention provides a water quality monitoring and early warning method based on multidimensional data analysis, comprising:

[0006] S1. Dynamic weighted data filling: Obtain water quality parameter data from each monitoring point, fill in and predict missing values ​​and noise in water quality monitoring to obtain complete water quality parameter data;

[0007] S2. Multi-parameter collaborative dimensionality reduction: Based on the distance between each monitoring point, the improved t-SNE algorithm is used to map the high-dimensional water quality parameter data to a three-dimensional feature space to obtain the three-dimensional feature space coordinates.

[0008] S3. Dynamic watershed zoning: Based on the distance threshold, a Delaunay triangulation network is constructed to obtain the adjacency relationship between monitoring points. Combined with hydrological connectivity constraints, a Voronoi diagram is generated, and the cell weights are dynamically adjusted based on the DEM to obtain a watershed spatial zoning model that reflects the topographic weight.

[0009] S4. Spatial outlier calculation: The alarm threshold for each monitoring point is dynamically set according to the weighted local outlier factor to obtain the spatial anomaly score of each monitoring point.

[0010] S5. Hybrid temporal decomposition: Decompose water quality time series according to STL decomposition method, input into Transformer model, and integrate rainfall periodic function to detect and score time anomalies, and obtain time dimension anomaly score;

[0011] S6: Multi-scale fluctuation detection: Wavelet packet decomposition is performed using the db4 wavelet basis function to calculate the energy entropy of each frequency band. When the energy entropy of the high frequency band suddenly increases, a fluctuation warning is triggered.

[0012] S7: Construction of a three-dimensional judgment matrix: A three-dimensional matrix is ​​constructed by integrating spatial outlier degree, temporal volatility and parameter synergy based on principal component analysis, and a comprehensive anomaly score is obtained by constructing a dynamic threshold surface equation;

[0013] S8: Set warning levels and trigger conditions: Trigger a multi-level response mechanism based on the comprehensive anomaly score and persistence conditions.

[0014] In some embodiments, step S1 of filling in and predicting missing values ​​and noise in water quality monitoring specifically includes:

[0015] By calculating the difference between the water quality parameters at the current moment and the previous moment at each monitoring point, the fluctuation range of historical data can be obtained.

[0016] The noise covariance matrix is ​​dynamically adjusted based on the historical data fluctuation amplitude. The specific adjustment formula is as follows:

[0017]

[0018] Among them, Q t Q is the process noise covariance matrix at time t. t Let be the process noise covariance matrix at time t-1, α be the forgetting factor with a value between 0.85 and 0.95, and ω be the sliding window width. ΔX is the transpose of the state increment at time t, reflecting the change in state at time t relative to previous values. t Let ω be the change vector of historical data, and ω be the width of the sliding window.

[0019] By conducting parameter sensitivity analysis, the sensitivity of each parameter to observation noise is evaluated, and its weights are adjusted to obtain the observation noise matrix.

[0020] The Kalman filter algorithm is used in conjunction with the dynamically adjusted noise covariance matrix and the observation noise matrix to predict and fill in missing water quality data.

[0021] In some embodiments, step S2 specifically includes:

[0022] The water quality parameters of each monitoring point are constructed into a vector, and the distance between each monitoring point is calculated using weighted Mahalanobis distance, replacing the Euclidean distance commonly used in t-SNE. The perplexity parameter is selected as the square root of the number of monitoring points, and dimensionality reduction is performed using the t-SNE algorithm based on weighted Mahalanobis distance. After dimensionality reduction by t-SNE, the water quality data is mapped from high dimension to three-dimensional space.

[0023] In some embodiments, step S3 specifically includes:

[0024] For each monitoring station, the distance between all stations within the watershed is calculated. Based on the watershed area and the number of stations, a distance threshold D is set using the following formula:

[0025]

[0026] Under the calculated distance threshold, the Delaunay triangulation algorithm is used to connect stations, establishing adjacency relationships between them. Hydrological connectivity constraints are introduced to automatically disconnect dams or other barriers within the watershed. Based on the Delaunay triangulation, a Voronoi diagram is generated, and cell weights are adjusted using the watershed's DEM data. The weight formula is as follows:

[0027]

[0028] Among them, h i h is the average elevation of the cell. avg The average elevation of the basin is denoted by , and k is an adjustment coefficient with a value ranging from 0.01 to 0.05.

[0029] In some embodiments, step S5 specifically includes:

[0030] The water quality time series was decomposed according to the STL decomposition method. The decomposition results include: trend term T(t), seasonal term S(t), and residual term R(t).

[0031] The trend term T(t) and residual term R(t) are input into the Transformer model, and anomaly detection is performed on the data using the watershed rainfall periodic function P(t) = sin(2πt / 365) + 0.3sin(2πt / 7). The anomaly score is calculated using the following formula:

[0032] Scoret =λ·|R(t)|+(1-λ)·Attention Weight (t)

[0033] Where λ takes values ​​from 0.6 to 0.8, Attention Weight The anomaly attention weights calculated for the Transformer model.

[0034] In some embodiments, in step S6, when the energy entropy of the high-frequency band >0.5Hz suddenly increases by more than twice the standard deviation of the historical average, a fluctuation warning is triggered.

[0035] Secondly, the present invention provides a water quality monitoring intelligent early warning system based on multidimensional data analysis, comprising:

[0036] Data acquisition and processing module: used to acquire water quality parameter data from each monitoring point in real time, perform dynamic weighted data filling and multi-parameter collaborative dimensionality reduction, and output complete water quality data and three-dimensional feature space coordinates;

[0037] Watershed partitioning module: Constructs a dynamic watershed spatial partitioning model;

[0038] Spatial-temporal analysis module: used to calculate weighted local outlier factors and dynamically set alarm thresholds, and to detect temporal anomalies by decomposing and fusing the Transformer model of the rainfall periodic function using STL, outputting spatial anomaly scores and temporal dimension anomaly scores;

[0039] Fluctuation detection module: used to perform wavelet packet decomposition and frequency band energy entropy analysis, triggering fluctuation warning when the high frequency band energy entropy suddenly increases;

[0040] Comprehensive Judgment Module: Used to construct a three-dimensional judgment matrix and calculate a comprehensive anomaly score using a dynamic threshold surface equation;

[0041] Early warning execution module: Triggers a multi-level response mechanism based on the comprehensive score.

[0042] In some embodiments, the data acquisition and processing module includes:

[0043] Data acquisition module: used to acquire water quality parameter data from each monitoring point in real time;

[0044] Dynamic data filling module: Used to perform dynamic weighted data filling and output complete water quality data;

[0045] Dimensionality reduction module: Used to achieve multi-parameter collaborative dimensionality reduction and generate three-dimensional feature space coordinates.

[0046] Based on the above technical solution, the embodiments of the present invention can produce at least the following technical effects:

[0047] This invention achieves high-precision data preprocessing through dynamic weighted data imputation, improved t-SNE dimensionality reduction, and dynamic watershed partitioning; it constructs a three-dimensional spatial-temporal-parameter judgment matrix by combining weighted local outlier factors, STL-Transformer temporal decomposition, and wavelet packet energy entropy analysis, significantly improving anomaly detection sensitivity; and it achieves a leap from single exceedance alarms to precise risk-based hierarchical management based on a comprehensive scoring triggering multi-level early warning mechanism, enabling real-time monitoring of water quality changes and timely early warning when anomalies occur, providing intelligent protection for water quality safety. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0049] Figure 1 This is a flowchart of an embodiment of the present invention. Detailed Implementation

[0050] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. In addition, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0051] The objective of this invention is achieved through the following technical solution:

[0052] Example 1, as Figure 1 As shown, this embodiment provides a smart early warning method for water quality monitoring based on multidimensional data analysis, which specifically includes the following steps:

[0053] Step 1: Dynamically weighted data imputation

[0054] An adaptive Kalman filter algorithm based on a sliding window is adopted to improve the accuracy and reliability of water quality monitoring data by filling in the data and processing noise.

[0055] (1) Obtain raw water quality monitoring data

[0056] Water quality parameter data are collected from various monitoring stations, including but not limited to pH, COD, and dissolved oxygen. This data may contain missing values ​​or noise, requiring processing.

[0057] (2) Calculate the fluctuation range of historical data

[0058] For each monitoring point, calculate the change vector of historical data, which is the difference between the water quality parameters at the current moment and the previous moment. The formula is:

[0059] ΔX t =X t -X t-1

[0060] Calculate the range of data changes around monitoring point t within a time window, and calculate the variance using the sliding window method.

[0061] (3) Dynamically adjust the noise covariance matrix Q

[0062] Based on the calculated historical data fluctuation range, the noise covariance matrix Q is dynamically adjusted. The specific adjustment formula is as follows:

[0063]

[0064] Among them, Q t Q is the process noise covariance matrix at time t. t This is the process noise covariance matrix at time t-1, α is the forgetting factor (value between 0.85 and 0.95), and ω is the sliding window width (7 to 30 days recommended). It is the transpose of the state increment at time t, which is generally obtained from the state observation and estimation of the actual system, and reflects the change of the state at time t relative to the previous state.

[0065] (4) Setting the differential observation noise matrix R

[0066] Different observation noise matrices R are set for different water quality parameters, such as pH and COD. Through parameter sensitivity analysis, the sensitivity of each parameter to observation noise is evaluated, and its weight is adjusted accordingly.

[0067] (5) Data imputation using Kalman filtering

[0068] The Kalman filter algorithm is used in conjunction with the dynamically adjusted noise covariance matrix Q and the observation noise matrix R to predict and fill in missing water quality data.

[0069] Step 2: Multi-parameter collaborative dimensionality reduction

[0070] (1) Calculate the weighted Mahalanobis distance between monitoring points

[0071] The water quality parameters for each monitoring point are constructed into a vector, and the distance between each monitoring point is calculated using weighted Mahalanobis distance, replacing the Euclidean distance commonly used in t-SNE. The formula for weighted Mahalanobis distance is:

[0072]

[0073] Among them, X i X j Let be the vector of water quality parameters for two monitoring points i and j, and W be the weighted matrix determined according to the water quality standard limits, reflecting the importance of different water quality parameters.

[0074] (2) Set the parameters of t-SNE

[0075] Select the perplexity parameter as the square root of the number of monitoring points (e.g.: To ensure the stability of the dimensionality reduction process, a t-SNE algorithm based on weighted Mahalanobis distance is used for dimensionality reduction.

[0076] (3) Generate a three-dimensional feature space

[0077] After dimensionality reduction using t-SNE, the water quality data is mapped from high dimension to three-dimensional space. This ensures that the dimensionality-reduced data retains more than 90% of the original data variance and provides an effective feature space for subsequent analysis.

[0078] Step 3: Dynamic watershed partitioning

[0079] (1) Calculate the distance threshold

[0080] For each monitoring station, calculate the distance between all stations within the watershed. Based on the watershed area and the number of stations, set a distance threshold D:

[0081]

[0082] (2) Constructing the Delaunay triangulation

[0083] Under the calculated distance threshold, the Delaunay triangulation algorithm is used to connect the sites and establish the adjacency relationship between them.

[0084] (3) Introduce hydrological connectivity constraints

[0085] For dams or other obstructions in the watershed, the connections between them are automatically disconnected to ensure that the connectivity of the watershed conforms to the actual situation.

[0086] (4) Generate Voronoi diagram and adjust weights

[0087] Based on the Delaunay triangulation, a Voronoi diagram is generated. Then, combined with the watershed's digital elevation model (DEM) data, the cell weights are adjusted using the following formula:

[0088]

[0089] Among them, h i h is the average elevation of the cell. avg The average elevation of the basin is denoted by , and k is an adjustment coefficient with a value of 0.01-0.05.

[0090] Step 4: Calculation of Spatial Outlier Degree

[0091] (1) Calculate the weighted local outlier factor

[0092] For each monitoring point, calculate the weighted local outlier factor (WLOF). The formula for calculating WLOF is:

[0093]

[0094] Where, x ij Let ω be the value of parameter j for the i-th station. j μ is the ecological importance weight of parameter j. j and σ j Let N be the mean and standard deviation of parameter j. k This represents the number of neighboring points.

[0095] (2) Calculation of dynamic alarm threshold

[0096] The alarm threshold for each monitoring point is dynamically calculated and set to the larger of the absolute deviation between the 95th percentile value of historical data and three times the median, to ensure timely detection of anomalies.

[0097] Step 5: Hybrid Timing Decomposition

[0098] (1) Temporal decomposition

[0099] The raw water quality time series data were decomposed using the STL (Seasonal, Trend, and Residual) method. The decomposition results include: trend term T(t), seasonal term S(t), and residual term R(t).

[0100] (2) Using Transformer for anomaly detection

[0101] The trend term T(t) and residual term R(t) are input into the Transformer model, and anomaly detection is performed on the data by combining the periodic function of watershed rainfall P(t) = sin(2πt / 365) + 0.3sin(2πt / 7).

[0102] (3) Anomaly score calculation

[0103] The formula for calculating the anomaly score is:

[0104] Score t =λ·|R(t)|+(1-λ)·Attention Weight (t)

[0105] Where λ is the weight coefficient, typically ranging from 0.6 to 0.8, Attention Weight The anomaly attention weights calculated for the Transformer model.

[0106] Step 6: Multi-scale fluctuation detection

[0107] (1) Wavelet packet decomposition

[0108] The water quality signal was decomposed using the db4 wavelet basis function. The number of decomposition layers was determined based on the sampling frequency of the data (5 layers for daily data and 7 layers for hourly data).

[0109] (2) Calculate the frequency band energy entropy

[0110] For each frequency band, calculate its energy entropy using the following formula:

[0111]

[0112] Among them, E b For energy entropy, C b E is the energy component. total This represents the total energy.

[0113] (3) Fluctuation warning trigger

[0114] Calculate the energy entropy for each frequency band. When the energy entropy of the high-frequency band (>0.5Hz) suddenly increases by more than twice the standard deviation of the historical average, a fluctuation warning is triggered.

[0115] Step 7: Construction of the 3D Decision Matrix

[0116] (1) Constructing a three-dimensional matrix

[0117] A three-dimensional matrix is ​​constructed based on spatial outlier, temporal volatility, and parametric coherence. Spatial outlier is calculated using WLOF, temporal volatility is analyzed using the STL-Transformer model, and parametric coherence is calculated using principal component analysis.

[0118] (2) Equation of dynamic threshold surface

[0119] Define the equation for the dynamic threshold surface, and calculate the threshold surface using coefficients a, b, c, d obtained through training with historical data:

[0120] F(x,y,z)=a·x 2 +b·y 2 +c·z 2 +d·x·y·z>T

[0121] Where T is an adjustable threshold, with a default value of 75.

[0122] Step 8: Set the alert level and trigger conditions

[0123] Based on the results of the judgment matrix, the warning level and triggering conditions are set as shown in the table below:

[0124] level Triggering conditions Response Action Level I 70≤Score<80 and lasts for 3 hours Automatically initiate adjacent site verification and detection Level II 80≤Score<90 or a single point of sudden increase of 50% Triggering drone cruise sampling Level III Score ≥ 90 or multiple points in the watershed exhibiting abnormal coordination Activate the emergency tracing model and notify regulatory authorities.

[0125] Example 2

[0126] This embodiment provides a water quality monitoring and early warning system based on multidimensional data analysis, including:

[0127] Data acquisition and processing module: used to acquire water quality parameter data from each monitoring point in real time, perform dynamic weighted data filling and multi-parameter collaborative dimensionality reduction, and output complete water quality data and three-dimensional feature space coordinates;

[0128] Watershed partitioning module: Constructs a dynamic watershed spatial partitioning model;

[0129] Spatial-temporal analysis module: used to calculate weighted local outlier factors and dynamically set alarm thresholds, and to detect temporal anomalies by decomposing and fusing the Transformer model of the rainfall periodic function using STL, outputting spatial anomaly scores and temporal dimension anomaly scores;

[0130] Fluctuation detection module: used to perform wavelet packet decomposition and frequency band energy entropy analysis, triggering fluctuation warning when the high frequency band energy entropy suddenly increases;

[0131] Comprehensive Judgment Module: Used to construct a three-dimensional judgment matrix and calculate a comprehensive anomaly score using a dynamic threshold surface equation;

[0132] Early warning execution module: Triggers a multi-level response mechanism based on the comprehensive score.

[0133] In this embodiment, the data acquisition and processing module includes:

[0134] Data acquisition module: used to acquire water quality parameter data from each monitoring point in real time;

[0135] Dynamic data filling module: Used to perform dynamic weighted data filling and output complete water quality data;

[0136] Dimensionality reduction module: Used to achieve multi-parameter collaborative dimensionality reduction and generate three-dimensional feature space coordinates.

[0137] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A water quality monitoring intelligent early warning method based on multidimensional data analysis, characterized in that, include: S1. Dynamic weighted data filling: Obtain water quality parameter data from each monitoring point, fill in and predict missing values ​​and noise in water quality monitoring to obtain complete water quality parameter data; S2. Multi-parameter collaborative dimensionality reduction: Based on the distance between each monitoring point, the improved t-SNE algorithm is used to map the high-dimensional water quality parameter data to a three-dimensional feature space to obtain the three-dimensional feature space coordinates. S3. Dynamic watershed zoning: Based on the distance threshold, a Delaunay triangulation network is constructed to obtain the adjacency relationship between monitoring points. Combined with hydrological connectivity constraints, a Voronoi diagram is generated, and the cell weights are dynamically adjusted based on the DEM to obtain a watershed spatial zoning model that reflects the topographic weight. S4. Spatial outlier calculation: The alarm threshold for each monitoring point is dynamically set according to the weighted local outlier factor to obtain the spatial anomaly score of each monitoring point. S5. Hybrid temporal decomposition: Decompose water quality time series according to STL decomposition method, input into Transformer model, and integrate rainfall periodic function to detect and score time anomalies, and obtain time dimension anomaly score; S6: Multi-scale fluctuation detection: Wavelet packet decomposition is performed using the db4 wavelet basis function to calculate the energy entropy of each frequency band. When the energy entropy of the high frequency band suddenly increases, a fluctuation warning is triggered. S7: Construction of a three-dimensional judgment matrix: A three-dimensional matrix is ​​constructed by integrating spatial outlier degree, temporal volatility and parameter synergy based on principal component analysis, and a comprehensive anomaly score is obtained by constructing a dynamic threshold surface equation; S8: Set warning levels and trigger conditions: Trigger a multi-level response mechanism based on the comprehensive anomaly score and persistence conditions.

2. The intelligent early warning method for water quality monitoring based on multidimensional data analysis according to claim 1, characterized in that, The step S1 of filling in and predicting missing values ​​and noise in water quality monitoring specifically includes: By calculating the difference between the water quality parameters at the current moment and the previous moment at each monitoring point, the fluctuation range of historical data can be obtained. The noise covariance matrix is ​​dynamically adjusted based on the historical data fluctuation amplitude. The specific adjustment formula is as follows: Where, q t It is the process noise covariance matrix at time t, q t Let be the process noise covariance matrix at time t-1, α be the forgetting factor with a value between 0.85 and 0.95, and ω be the sliding window width. ΔX is the transpose of the state increment at time t, reflecting the change in state at time t relative to previous values. t Let ω be the change vector of historical data, and ω be the width of the sliding window. By conducting parameter sensitivity analysis, the sensitivity of each parameter to observation noise is evaluated, and its weights are adjusted to obtain the observation noise matrix. The Kalman filter algorithm is used in conjunction with the dynamically adjusted noise covariance matrix and the observation noise matrix to predict and fill in missing water quality data.

3. The intelligent early warning method for water quality monitoring based on multidimensional data analysis according to claim 1, characterized in that, Step S2 specifically includes: The water quality parameters of each monitoring point are constructed into a vector, and the distance between each monitoring point is calculated using weighted Mahalanobis distance, replacing the Euclidean distance commonly used in t-SNE. The perplexity parameter is selected as the square root of the number of monitoring points, and dimensionality reduction is performed using the t-SNE algorithm based on weighted Mahalanobis distance. After dimensionality reduction by t-SNE, the water quality data is mapped from high dimension to three-dimensional space.

4. The intelligent early warning method for water quality monitoring based on multidimensional data analysis according to claim 1, characterized in that, Step S3 specifically includes: For each monitoring station, the distance between all stations within the watershed is calculated. Based on the watershed area and the number of stations, a distance threshold D is set using the following formula: Under the calculated distance threshold, the Delaunay triangulation algorithm is used to connect stations, establishing adjacency relationships between them. Hydrological connectivity constraints are introduced to automatically disconnect dams or other barriers within the watershed. Based on the Delaunay triangulation, a Voronoi diagram is generated, and cell weights are adjusted using the watershed's DEM data. The weight formula is as follows: Among them, h i h is the average elevation of the cell. avg The average elevation of the basin is denoted by , and k is an adjustment coefficient with a value ranging from 0.01 to 0.

05.

5. The intelligent early warning method for water quality monitoring based on multidimensional data analysis according to claim 1, characterized in that, Step S5 specifically includes: The water quality time series was decomposed according to the STL decomposition method. The decomposition results include: trend term T(t), seasonal term S(t), and residual term R(t). The trend term T(t) and residual term R(t) are input into the Transformer model, and anomaly detection is performed on the data using the watershed rainfall periodic function P(t) = sin(2πt / 365) + 0.3sin(2πt / 7). The anomaly score is calculated using the following formula: Score t =λ·|R(t)|+(1-λ)·Attention Weight (t) Where λ is the weight coefficient, with a value ranging from 0.6 to 0.8, Attention Weight The anomaly attention weights calculated for the Transformer model.

6. The intelligent early warning method for water quality monitoring based on multidimensional data analysis according to claim 1, characterized in that, In step S6, when the energy entropy of the high-frequency band >0.5Hz suddenly increases by more than twice the standard deviation of the historical average, a fluctuation warning is triggered.

7. A water quality monitoring intelligent early warning system based on multidimensional data analysis, used to implement the method described in any one of claims 1-6, characterized in that, include: Data acquisition and processing module: used to acquire water quality parameter data from each monitoring point in real time, perform dynamic weighted data filling and multi-parameter collaborative dimensionality reduction, and output complete water quality data and three-dimensional feature space coordinates; Watershed partitioning module: Constructs a dynamic watershed spatial partitioning model; Spatial-temporal analysis module: used to calculate weighted local outlier factors and dynamically set alarm thresholds, and to detect temporal anomalies by decomposing and fusing the Transformer model of the rainfall periodic function using STL, outputting spatial anomaly scores and temporal dimension anomaly scores; Fluctuation detection module: used to perform wavelet packet decomposition and frequency band energy entropy analysis, triggering fluctuation warning when the high frequency band energy entropy suddenly increases; Comprehensive Judgment Module: Used to construct a three-dimensional judgment matrix and calculate a comprehensive anomaly score using a dynamic threshold surface equation; Early warning execution module: Triggers a multi-level response mechanism based on the comprehensive score.

8. The intelligent water quality monitoring and early warning system based on multidimensional data analysis according to claim 7, characterized in that, The data acquisition and processing module includes: Data acquisition module: used to acquire water quality parameter data from each monitoring point in real time; Dynamic data filling module: Used to perform dynamic weighted data filling and output complete water quality data; Dimensionality reduction module: Used to achieve multi-parameter collaborative dimensionality reduction and generate three-dimensional feature space coordinates.

Images