Water body pollution monitoring and processing system based on multi-dimensional data analysis

Abstract

The invention relates to the technical field of ecological environment monitoring, in particular to a multi-dimensional data analysis-based water body pollution monitoring and processing system, which comprises a dynamic data cube construction module, a pollution event slice extraction module, a multi-dimensional feature fingerprint coupling module, a pollution source reverse traceability module and a self-adaptive early warning trigger module. The method comprises the following steps: receiving water quality parameters of an internet of things sensor, meteorological data of a meteorological hydrological station and satellite remote sensing spectral data, and constructing a dynamic data cube of unified space-time coordinates and feature axes; identifying pollution event slices by using entropy change analysis and a self-adaptive threshold method; carrying out characteristic coupling analysis on the pollution event, and fusing a spectrum fluctuation mode, a physicochemical gradient and toxicity response to generate a pollution characteristic fingerprint; pollution source positioning and contribution weight estimation are realized by adopting a dynamic time warping algorithm, and corresponding disposal equipment is driven to start based on an early warning level, so that intelligent closed-loop control of pollution identification, source tracing and treatment is realized.

Claims

1. A water pollution monitoring and treatment system based on multidimensional data analysis, characterized in that: It includes a dynamic data cube construction module, a pollution event slice extraction module, a multi-dimensional feature fingerprint coupling module, a pollution source reverse tracing module and an adaptive early warning trigger module, among which; The dynamic data cube construction module receives water quality parameters, meteorological data from meteorological and hydrological stations, and satellite remote sensing spectral data uploaded in real time by an IoT sensor array deployed in the monitored water area, and generates a dynamic data cube by aligning the time and space coordinates; The pollution event slice extraction module performs a spatiotemporal sliding window scan on the dynamic data cube, and if the entropy change value of the water quality parameter in the window exceeds the adaptive threshold, the window data is extracted as a pollution event slice; The multi-dimensional feature fingerprint coupling module inputs the pollution event slice into the feature coupling engine, synchronously extracts the spectral reflectance fluctuation pattern, the physical and chemical parameter gradient distribution and the biological toxicity response curve, and fuses them to generate the pollution feature fingerprint; The pollution source reverse tracing module performs dynamic time-warping matching on the pollution feature fingerprint and the pollution source feature database, and outputs the pollution source location coordinates and pollution contribution weight; The adaptive early warning trigger module generates a graded early warning instruction according to the pollution source location coordinates and pollution contribution weights, and drives the aeration equipment or adsorption device in the target water area to start.

2. The water pollution monitoring and treatment system based on multidimensional data analysis according to claim 1 is characterized in that: The dynamic data cube building module includes: Data standardization processing: Receive water quality parameters uploaded in real time by the IoT sensor array deployed in the monitored waters, meteorological data from meteorological and hydrological stations, and satellite remote sensing spectral data, perform normalization processing on the three types of data, and output standardized water quality parameters, standardized meteorological data, and standardized satellite remote sensing spectral data; Time dimension alignment: resampling the standardized water quality parameters, standardized meteorological data, and standardized satellite remote sensing spectral data based on a unified timestamp to generate time-aligned water quality parameters, time-aligned meteorological data, and time-aligned satellite remote sensing spectral data with consistent time resolution; Spatial dimension alignment: mapping the time-aligned water quality parameters, time-aligned meteorological data, and time-aligned satellite remote sensing spectral data to a unified grid coordinate system through a geographic information system spatial interpolation algorithm to generate spatially aligned water quality parameters, spatially aligned meteorological data, and spatially aligned satellite remote sensing spectral data with matching spatial coordinates; Three-dimensional data integration: Integrate the spatially aligned water quality parameters, spatially aligned meteorological data, and spatially aligned satellite remote sensing spectral data along the time axis, horizontal spatial axis, and data feature axis to generate a dynamic data cube containing spatiotemporal attributes and multidimensional features. The data structure satisfies the following requirements: Each grid cell stores a triple of longitude, latitude, and timestamp; The data characteristic axis integrates the water quality parameter subset, meteorological data subset and spectral data subset.

3. The water pollution monitoring and treatment system based on multidimensional data analysis according to claim 2 is characterized in that: The pollution event slice extraction module includes: Initialization of the spatiotemporal sliding window: setting the spatiotemporal sliding window of the initial size, performing sliding scanning along the time axis and horizontal space axis of the dynamic data cube, and extracting the window data set within the current window each time; Calculation of water quality parameter entropy change value: Perform multivariate information entropy analysis on the water quality parameter subset in each window data set, calculate the entropy value difference between the current window and the previous time window, and output the water quality parameter entropy change value; Adaptive threshold generation: Based on the entropy fluctuation range of water quality parameters in the dynamic data cube of the same area over the past 30 days, the adaptive threshold is dynamically calculated using the quantile statistics method; Pollution event slice determination and extraction: If the entropy change value of the water quality parameter exceeds the adaptive threshold corresponding to the current window, the slice extraction mechanism will be triggered to completely intercept the spatiotemporal coordinate range and all data features of the window data set to generate a pollution event slice; If the threshold is not exceeded, the sliding window moves to the next position and repeats the spatiotemporal sliding window initialization, water quality parameter entropy change value calculation and adaptive threshold generation.

4. The water pollution monitoring and treatment system based on multidimensional data analysis according to claim 3 is characterized in that: The multi-dimensional feature fingerprint coupling module includes: Pollution event slice analysis: receiving the pollution event slices generated by the pollution event slice extraction module, inputting them into the feature coupling engine, and separating the satellite remote sensing spectral data and water quality parameters therein; Spectral reflectance fluctuation pattern extraction: In the feature coupling engine, continuous wavelet transform is performed on satellite remote sensing spectral data to extract frequency band energy distribution characteristics and generate spectral reflectance fluctuation patterns; Extraction of gradient distribution of physical and chemical parameters: In the feature coupling engine, spatial Kriging interpolation is performed on water quality parameters, and the rate of change vector field of each parameter in three-dimensional space is calculated to generate the gradient distribution of physical and chemical parameters.

5. The water pollution monitoring and treatment system based on multidimensional data analysis according to claim 4 is characterized in that: The multi-dimensional feature fingerprint coupling module also includes: Biological toxicity response curve generation: In the feature coupling engine, based on the toxic substance concentration data in the water quality parameters, the biological inhibition rate is calculated through the dose-effect function to generate a biological toxicity response curve; Feature fusion and fingerprint generation: The spectral reflectance fluctuation pattern, physical and chemical parameter gradient distribution and biological toxicity response curve are input into the fusion unit of the feature coupling engine, and feature dimension reduction and fusion are performed through principal component analysis to output the pollution feature fingerprint.

6. The water pollution monitoring and treatment system based on multidimensional data analysis according to claim 5 is characterized in that: The pollution source reverse tracing module includes: Pollution feature fingerprint reception: obtaining the pollution feature fingerprint output by the multi-dimensional feature fingerprint coupling module and converting its format into a time series matrix; Pollution source feature database query: Access the pre-built pollution source feature database, retrieve the feature fingerprint time series of all potential pollution sources, and generate a candidate pollution source feature set; Dynamic time warping matching execution: dynamic time warping matching is performed on the pollution feature fingerprint and each feature sequence in the candidate pollution source feature set, the optimal curved path distance between the sequences is calculated, and a matching distance matrix is ​​output.

7. The water pollution monitoring and treatment system based on multidimensional data analysis according to claim 6 is characterized in that: The pollution source reverse tracing module also includes: Determine the pollution source location coordinates: select the top K candidate pollution sources with the smallest distance values ​​in the matching distance matrix, and calculate the pollution source location coordinates based on the weighted average of their geographic coordinates, with the weight being inversely proportional to the matching distance; Pollution contribution weight calculation: Based on the distance values ​​of the matching distance matrix, the pollution contribution weight of each pollution source to the current pollution event is generated through softmax function normalization processing.

8. The water pollution monitoring and treatment system based on multidimensional data analysis according to claim 7 is characterized in that: The adaptive early warning trigger module includes: Pollution source data reception: obtaining the pollution source location coordinates and pollution contribution weights output by the pollution source reverse tracing module; Warning level determination: query the preset warning level mapping table according to the pollution contribution weight: If the pollution contribution weight is greater than 0.6, a red graded warning instruction will be generated; If 0.3≤pollution contribution weight≤0.6, an orange grade warning instruction is generated; If the pollution contribution weight is less than 0.3, a yellow grade warning instruction will be generated.

9. The water pollution monitoring and treatment system based on multidimensional data analysis according to claim 8 is characterized in that: The adaptive early warning trigger module also includes: Disposal equipment matching: Based on the pollution source location coordinates and graded warning instruction levels, the disposal equipment is matched: Red command: activate all aeration equipment and adsorption devices in the target waters; Orange command: Activate the adsorption device within a 500-meter radius of the pollution source's location coordinates; Yellow command: only activate aeration equipment; Device drive signal generation: Convert device activation instructions into IoT control protocol signals, where The aeration device receives oxygenation intensity parameters, and the adsorption device receives adsorbent dosage parameters; Emergency equipment startup: The driving signal is transmitted to the aeration equipment and / or adsorption device in the target area through the water area Internet of Things, triggering them to start operation according to the command parameters.

Images