An urban fine particulate matter tracing system and method based on multiple atmospheric super stations

Abstract

The present invention provides an urban fine particulate matter source tracing system and method based on multiple atmospheric super stations, which relates to the technical field of air pollution monitoring and source tracing. The system includes a data acquisition module for collecting observation data in real time through multiple atmospheric super stations; a data preprocessing module for preprocessing the observation data; a source tracing model construction module for constructing a source tracing model based on the positive definite matrix factorization receptor model and the random forest algorithm; a real-time collaborative source tracing module for inputting the preprocessed data into the source tracing model and outputting the source contribution ratio and regional emission weight through parallel computing, and introducing an atmospheric diffusion model to dynamically correct the source tracing result; and a result display and analysis module for an interactive visualization tool based on WebGL to display the source tracing result through dynamic pie charts and 3D bar charts. The present invention solves the deficiencies of traditional methods and provides efficient decision-making support for urban pollution control.

Description

Technical Field

[0001] The present invention relates to the technical field of air pollution monitoring and source tracing, and particularly to an urban fine particulate matter source tracing system and method based on multiple air super stations. Background Art

[0002] In the current context of the accelerating urbanization process, the problem of air pollution is becoming increasingly serious, and fine particulate matter (PM 2.5 ) has become a key pollutant endangering human health and the ecological environment. It can penetrate deep into the human respiratory system, causing various diseases, and at the same time have a negative impact on climate, visibility, etc. Therefore, accurately and quickly determining the source of PM 2.5 has become the core of formulating effective pollution control strategies.

[0003] Early air pollution source tracing technologies mainly relied on the analysis of pollutant chemical components, and inferred pollution sources by comparing the characteristics of pollutants from different sources. However, the information obtained by this method is limited, and it is impossible to accurately quantify the contribution degree of each pollution source, making it difficult to meet the actual needs.

[0004] With the development of computer technology, receptor models have become the main tools for urban air pollution source tracing, among which positive matrix factorization and chemical mass balance models are widely used. However, these traditional models have many limitations:

[0005] Insufficient spatial representativeness: Traditional models mostly rely on the observation data of a single urban air super station or manual off-line observation data. The monitoring range of a single air super station is limited and can only cover the surrounding area, making it difficult to represent the air pollution situation of the entire city or region. The sources of urban air pollution are extensive and complex, including industrial emissions, vehicle exhaust, biomass burning, dust, etc. Scattered pollution sources may not be effectively identified and traced, resulting in the lack of comprehensiveness and pertinence of governance measures.

[0006] Limited vertical detection ability: Conventional air super stations mainly monitor near-surface air pollutants and have insufficient vertical distribution detection ability for high-altitude pollutants. In fact, the distribution of pollutants in the vertical direction is not uniform, and high-altitude pollutants can affect near-surface air quality through vertical atmospheric exchange. The fixed monitoring points of a single air super station are difficult to capture these dynamic changes, making the source tracing results lagging and uncertain, and unable to timely and accurately reflect the impact of the vertical structure of air pollution on ground pollution.

[0007] Limited time resolution: The update frequency of manual off-line monitoring data is low, usually sampling once a day or several days. In the urban environment where air quality changes rapidly, this low-frequency monitoring cannot reflect the changes, diffusion, and migration processes of air quality in real time. In the face of sudden pollution events, traditional models are difficult to quickly trace the source, resulting in the inability to take effective response measures in a timely manner and delaying the treatment opportunity.

[0008] These deficiencies in the existing technology for tracing the sources of urban fine particulate matter seriously restrict the implementation of air pollution control work. Therefore, it is urgent to develop a new method for efficiently and accurately tracing the sources of fine particulate matter, which can not only make up for the deficiencies of traditional technologies but also provide strong technical support for urban air pollution control, and has important practical significance. Summary of the Invention

[0009] To this end, the present invention provides a system and method for tracing the sources of urban fine particulate matter based on multiple atmospheric superstations, which are used to solve the problems in the existing technology that traditional tracing methods rely on single-station or manual off-line observation data, have insufficient spatial representativeness, limited vertical detection capabilities, limited time resolution, and are difficult to meet the requirements for quickly and accurately tracing the sources of fine particulate matter in complex urban environments.

[0010] To solve the above problems, an embodiment of the present invention provides a system for tracing the sources of urban fine particulate matter based on multiple atmospheric superstations, the system comprising:

[0011] A data acquisition module, configured to collect observation data in real time through multiple atmospheric superstations, the observation data including fine particulate matter concentration, chemical composition, and meteorological parameter data, and the atmospheric superstations including urban stations, suburban stations, and regional stations, which are arranged according to a weighted scoring model of urban scale, pollution source distribution, population density, and topography;

[0012] A data preprocessing module, configured to preprocess the observation data;

[0013] A source tracing model construction module, configured to construct a source tracing model based on a positive definite matrix factorization receptor model and a random forest algorithm;

[0014] A real-time collaborative source tracing module, configured to input the preprocessed data into the source tracing model, and output the contribution ratio of pollution sources and the regional emission weight through parallel computing, and at the same time introduce an atmospheric diffusion model to dynamically correct the source tracing results;

[0015] A result display and analysis module, configured to use an interactive visualization tool based on WebGL to display the source tracing results through dynamic pie charts and 3D bar charts.

[0016] Preferably, constructing the source tracing model based on the positive definite matrix factorization receptor model and the random forest algorithm includes:

[0017] Using the positive definite matrix factorization receptor model to decompose the concentration matrix of each chemical component in the observed fine particulate matter into , where is the number of pollution source factors, m is the number of samples, n is the type of chemical components, is the factor contribution matrix, is the factor spectrum matrix;

[0018] Iteratively optimize the positive definite matrix factorization receptor model through the Bootstrap resampling technique;

[0019] Select the optimal number of pollution source factors through cross-validation , so that the model explained variance is maximized and the sum of squared residuals is minimized, satisfying ;

[0020] Utilize the random forest algorithm combined with the knowledge graph technology to fuse the prior knowledge of the spatio-temporal distribution of pollution sources, the emission characteristics of pollution sources, and meteorological conditions, optimize the model input features, and jointly evaluate the model performance through the leave-one-out method and K-fold cross-validation. The objective function is:

[0021] ;

[0022] wherein, is the total number of samples, is the true label of the th sample, is the predicted label of the th sample, is the regularization coefficient, is the total number of feature dimensions, is the th weight coefficient of the feature.

[0023] Preferably, the iterative optimization of the positive definite matrix factorization receptor model through the Bootstrap resampling technique includes:

[0024] Randomly draw subsamples from the original data and generate a Bootstrap dataset by repeating a set number of times;

[0025] Perform positive definite matrix factorization on each sub-dataset, and calculate the mean and confidence interval of the factor contribution matrix;

[0026] Constrain all elements of the factor contribution matrix and the factor spectrum matrix to be non-negative values to ensure the physical rationality of the pollution source contribution.

[0027] Preferably, the calculation formula for the sum of squared residuals is:

[0028] ;

[0029] wherein, is the sum of squared residuals; m represents the number of samples; n represents the types of chemical components; p represents the number of pollution source factors; is an element in the original data matrix, indicating the th sample and the The concentration value of a chemical component; is an element in the factor contribution matrix G, representing the contribution of the th sample to the total concentration by the th pollution source; is an element in the factor spectrum matrix F, representing the concentration ratio of the th chemical component in the th pollution source; is an element in the uncertainty matrix U, representing the measurement uncertainty of the th sample for the th chemical component.

[0030] Preferably, the formula of the weighted scoring model is:

[0031] ;

[0032] where is the weight of the th atmospheric superstation, is the representativeness score of the th atmospheric superstation, is the coverage score of the th atmospheric superstation, is the data quality score of the th atmospheric superstation, and n is the number of atmospheric superstations.

[0033] Preferably, the introduction of the atmospheric diffusion model to dynamically correct the tracing result includes:

[0034] ;

[0035] where is the pollutant concentration at the horizontal coordinate , vertical height z and time [[ID=6)]], is the total number of pollution sources, is the horizontal position coordinate of the th pollution source, is the emission intensity of the th pollution source, and are diffusion parameters, is the wind speed, is the emission height of the th pollution source.

[0036] Preferably, in the result display and analysis module, the pollution source contribution ratio and regional emission weight are displayed by overlaying a dynamic pie chart and a 3D heat map, supporting users to interactively screen the spatial and temporal ranges, and calculating the regional pollution contribution difference through the following formula:

[0037] ;

[0038] Among them, and are the pollution source contribution rates of the urban station, suburban station or regional station respectively, is the regional pollution contribution difference value.

[0039] The data preprocessing module includes a data cleaning unit, a standardization processing unit and a feature extraction unit. The data cleaning unit uses the 3 principle combined with an adaptive low-pass filter to eliminate outliers; the standardization processing unit uses the dynamic threshold Z-score standardization method for concentration data and the Min-Max standardization method for chemical composition data; the feature extraction unit extracts key features through a deep neural network combined with principal component analysis and linear discriminant analysis.

[0040] Preferably, the formula of the dynamic threshold Z-score standardization method is:

[0041] ;

[0042] Among them, represents the standardized concentration value, represents the real-time concentration information of the current monitoring station, represents the dynamically calculated real-time mean value, represents the dynamically calculated real-time standard.

[0043] An embodiment of the present invention also provides a method for tracing the source of urban fine particulate matter based on multiple atmospheric superstations. The method uses the above-mentioned system for tracing the source of urban fine particulate matter based on multiple atmospheric superstations, and includes the following steps:

[0044] Collect observation data in real time through multiple atmospheric superstations. The observation data includes fine particulate matter concentration, chemical composition and meteorological parameter data. The atmospheric superstations include urban stations, suburban stations and regional stations, and are arranged according to a weighted scoring model of urban scale, pollution source distribution, population density and topography;

[0045] Preprocess the observation data;

[0046] Construct a source tracing model based on the positive definite matrix factorization receptor model and the random forest algorithm;

[0047] Input the preprocessed data into the source tracing model, and output the pollution source contribution ratio and regional emission weight through parallel computing, and at the same time introduce an atmospheric diffusion model to dynamically correct the source tracing result;

[0048] An interactive visualization tool based on WebGL displays the traceability results through dynamic pie charts and 3D bar charts.

[0049] As can be seen from the above technical solutions, the present invention application has the following beneficial effects:

[0050] First, multi-dimensional data fusion and high-precision processing. By scientifically arranging urban stations, suburban stations, and regional stations, combining a dynamic weighted scoring model to optimize the site weights, and adopting dynamic threshold Z-score normalization and Min-Max normalization methods, the representativeness and comparability of the data are effectively improved. The deep neural network combines principal component analysis (PCA) and linear discriminant analysis (LDA) to automatically extract key features, significantly reducing redundant information and providing a high-quality data basis for the model.

[0051] Second, intelligent model and fast response ability. Innovatively integrating the positive definite matrix factorization receptor model (PMF) and the random forest algorithm, through Bootstrap resampling iterative optimization and cross-validation techniques, ensuring the physical rationality of the pollution source contribution and the high interpretability of the model. Combining with a parallel computing architecture, the single-site traceability analysis can be completed within 5 minutes, with an accuracy rate of over 90%, significantly superior to the timeliness and accuracy of traditional methods.

[0052] Third, dynamic visualization and scientific decision-making support. The WebGL-based interactive tool realizes multi-dimensional visualizations such as 3D heat maps and dynamic pie charts, supporting users to screen the spatio-temporal range in real-time and calculate the differences in regional pollution contributions. Combining the dynamically corrected results of the atmospheric diffusion model and the intelligent early warning algorithm, it provides accurate pollution source distributions, contribution ratios, and trend predictions for environmental management departments, helping to formulate efficient governance strategies. Description of the Drawings

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly describe the drawings required to be used in the embodiments. By referring to the drawings, the features and advantages of the present invention will be more clearly understood. The drawings are schematic and should not be construed as limiting the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. Among them:

[0054] Figure 1 It is a block diagram of a system for tracing fine particulate matter in a city based on multiple atmospheric super stations provided by the present invention;

[0055] Figure 2 It is a flowchart of a method for tracing fine particulate matter in a city based on multiple atmospheric super stations provided by the present invention. Detailed Embodiments

[0056] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0057] Embodiment 1:

[0058] To solve the problem in the prior art that traditional traceability methods rely on single-station or manual off-line observation data, which have insufficient spatial representativeness, limited vertical detection capabilities, and limited time resolution, and are difficult to meet the requirements for rapid and accurate traceability of fine particulate matter in complex urban environments. As Figure 1 shown, the present invention proposes an urban fine particulate matter traceability system based on multiple atmospheric superstations. The system includes:

[0059] A data acquisition module 100 for real-time collecting observation data through multiple atmospheric superstations. The observation data includes fine particulate matter concentration, chemical composition, and meteorological parameter data. The atmospheric superstations include urban stations, suburban stations, and regional stations, and are arranged according to a weighted scoring model of urban scale, pollution source distribution, population density, and topography.

[0060] A data preprocessing module 200 for preprocessing the observation data.

[0061] A traceability model construction module 300 for constructing a traceability model based on the positive definite matrix factorization receptor model and the random forest algorithm.

[0062] A real-time collaborative traceability module 400 for inputting the preprocessed data into the traceability model and outputting the contribution ratio of pollution sources and the regional emission weight through parallel computing. At the same time, an atmospheric diffusion model is introduced to dynamically correct the traceability results.

[0063] A result display and analysis module 500 for an interactive visualization tool based on WebGL to display the traceability results through dynamic pie charts and 3D bar charts.

[0064] As can be seen from the above technical solutions, the present invention proposes an urban fine particulate matter traceability system based on multiple atmospheric super stations. By using a weighted scoring model to layout urban stations, suburban stations and regional stations (covering multi-dimensional pollution sources and terrain), and combining dynamic threshold Z-score and Min-Max normalization (to improve data comparability) with a deep neural network and PCA / LDA (to extract key features) to efficiently preprocess multi-source data; constructing a PMF-random forest fusion model (physical rationality and high interpretability) to analyze the contribution of pollution sources, combining parallel computing with an atmospheric diffusion model (5-minute rapid response, dynamically correcting errors), and through WebGL interactive visualization (3D heat map, dynamic pie chart) to display the traceability results in real time, realizing rapid and accurate traceability of fine particulate matter, and providing dynamic and visual scientific decision-making support for pollution control.

[0065] In the data acquisition module 100, first, according to factors such as urban scale, pollution source distribution, population density, and topography and landforms, a weighted scoring model is used to determine the layout of atmospheric super stations. The formula of the weighted scoring model is:

[0066] ;

[0067] Among them, is the weight of the th atmospheric super station, is the representative score of the th atmospheric super station, is the coverage score of the th atmospheric super station, is the data quality score of the th atmospheric super station, and n is the number of atmospheric super stations.

[0068] According to the calculation results, at least 3 atmospheric super stations are reasonably layout in different regions of the city, including urban stations, suburban stations and regional stations. The urban station is set at the center of the urban built-up area, responsible for monitoring the overall air quality status and change trend of the city; the suburban station is located in the surrounding suburbs of the city, used to compare the air quality differences between the city and the suburbs, and monitor the city's pollution diffusion; the regional station is set outside the city, monitoring the air quality status and pollutant transmission law in a large area.

[0069] The present invention comprehensively layouts stations considering multiple factors, enabling the monitoring network to cover different functional areas, enhancing the representativeness and comprehensiveness of the monitoring data, accurately reflecting the air quality status of different regions and the whole city, and providing a more reliable data basis for subsequent traceability analysis.

[0070] The construction of each atmospheric super station strictly follows relevant standards and specifications, equipped with professional monitoring instruments and equipment, such as fine particulate matter concentration monitors, chemical composition analyzers, meteorological parameter monitors, etc., and a perfect quality control and quality assurance system is established. The instruments and equipment are calibrated and maintained regularly to ensure their stable operation and guarantee the accuracy and reliability of the monitoring data.

[0071] The present invention uses professional instruments to ensure accurate data collection, and the quality control system guarantees the stable operation of the instruments, improves the accuracy and reliability of the data, provides high-quality data for the traceability model, and avoids deviations in the traceability results caused by data errors.

[0072] In this embodiment, each atmospheric super station is equipped with professional monitoring instruments, including:

[0073] Fine particulate matter concentration monitor: The measurement range is 0 - 1000 μg / m³, and the detection limit is not less than 1 μg / m³, which is used to accurately measure the concentration of fine particulate matter.

[0074] Chemical composition analyzer: including on-line automatic monitors for water-soluble ions chromatography in the particle group, on-line automatic monitors for inorganic elements, and on-line automatic monitors for organic carbon and inorganic carbon. It can accurately detect the main chemical components in PM 2.5 such as 8 water-soluble components including sulfate, nitrate, etc., nearly 20 inorganic elements such as Fe, Zn, Cu, etc., as well as organic carbon and elemental carbon, etc., and the detection limit is lower than 1.0 ng / m³.

[0075] Meteorological parameter monitor: It can accurately measure meteorological parameters such as temperature, humidity, wind speed, and wind direction in real time, and the measurement accuracy is better than ±5%.

[0076] Furthermore, the monitoring instruments of each atmospheric super station collect data such as fine particulate matter concentration, chemical composition, and meteorological parameters in real time at regular time intervals (such as every 60 minutes), and transmit the data to the data processing center through a high-speed and stable wireless transmission network. Encryption and other measures are taken during the transmission process to ensure the integrity and security of the data, and prevent data loss or tampering.

[0077] The real-time collection and efficient transmission of the present invention enable the data processing center to obtain the latest monitoring data, provide support for rapid traceability, timely reflect the changes in air quality, and contribute to a rapid response in the event of a pollution incident.

[0078] In the data preprocessing module 200, after receiving the data, the data processing center uses the 3σ principle combined with an adaptive low-pass filter to clean the data by the data cleaning unit. Through this method, outliers are identified and removed, noise is filtered, and combined with the relevant monitoring data of multiple super stations, the parameter settings are adjusted according to the real-time monitoring data of each station to achieve more accurate data cleaning.

[0079] Further, for the concentration data, the normalization processing unit adopts the Z-score normalization method with a dynamic threshold, and the formula is . Among them, represents the normalized concentration value, represents the real-time concentration information of the current monitoring site, represents the dynamically calculated real-time mean value, represents the dynamically calculated real-time standard. Using the Z-score normalization based on the dynamic threshold can adjust the mean value and standard deviation according to the real-time distribution of the data, making the normalized data more comparable.

[0080] For the chemical composition data, the Min-Max normalization method is used, fully considering the actual physical meaning of the data to avoid information loss during the normalization process.

[0081] Further, the feature extraction unit uses a method that combines a deep neural network with principal component analysis (PCA) and linear discriminant analysis (LDA) to extract key features. In this way, the features hidden in the data that are closely related to the sources of fine particulate matter are automatically mined, reducing data redundancy, retaining real and effective information, and improving the efficiency and accuracy of the source tracing model. The processed data is stored in a dedicated database to provide a high-quality data basis for the subsequent construction of the source tracing model.

[0082] In the source tracing model construction module 300, the present invention uses the positive definite matrix factorization receptor model (PMF) to decompose the concentration matrix of each chemical component in the observed atmospheric particulate matter into a factor contribution matrix and a factor spectrum matrix. At the same time, combined with the random forest algorithm, prior knowledge such as the spatio-temporal distribution of pollution sources, emission characteristics, and meteorological conditions is integrated. PMF can effectively analyze the contribution of pollution sources and the chemical composition spectrum, and the random forest algorithm integrates prior knowledge to optimize the model, improving the adaptability and accuracy of the model and more accurately identifying pollution sources.

[0083] Specifically, using the positive definite matrix factorization receptor model to decompose the concentration matrix of each chemical component in the observed fine particulate matter into , where is the number of pollution source factors, m is the number of samples, n is the type of chemical components, is the factor contribution matrix, is the factor spectrum matrix.

[0084] Furthermore, the Bootstrap resampling technique is used to iteratively optimize the positive definite matrix factor receptor model. Sub-samples are randomly drawn from the original data, and Bootstrap data sets are generated by repeating a set number of times (1000 times); positive definite matrix factorization is performed on each sub-data set, and the mean and confidence intervals of the factor contribution matrix are calculated; all elements of the factor contribution matrix and the factor spectrum matrix are constrained to be non-negative values to ensure the physical reasonableness of the pollution source contributions.

[0085] Furthermore, the optimal number of pollution source factors is selected through cross-validation , to maximize the model's explained variance and minimize the sum of squared residuals , satisfying . The formula for the sum of squared residuals is:

[0086] ;

[0087] where is the sum of squared residuals; m represents the number of samples; n represents the types of chemical components; p represents the number of pollution source factors; is the element in the original data matrix, representing the concentration value of the th chemical component in the th sample; is the element in the factor contribution matrix G, representing the contribution of the th pollution source to the total concentration in the th sample; is the element in the factor spectrum matrix F, representing the concentration ratio of the th chemical component in the th pollution source; is the element in the uncertainty matrix U, representing the measurement uncertainty of the th chemical component in the th sample.

[0088] Furthermore, the random forest algorithm is used in combination with knowledge graph technology to fuse the prior knowledge of the spatio-temporal distribution of pollution sources, the emission characteristics of pollution sources, and meteorological conditions, optimize the model input features, and jointly evaluate the model performance through the leave-one-out method and K-fold cross-validation. The objective function is:

[0089] ;

[0090] where is the total number of samples, is the true label of the th sample, is the predicted label of the th sample, is the regularization coefficient, is the total number of feature dimensions, is the weight coefficient of the

[0091] In the real-time collaborative traceability module 400, the preprocessed data is input into the constructed traceability model, and parallel computing architecture is used for rapid calculation to output the source contribution ratio of fine particulate matter and the regional emission weight. The present invention can complete the single-site traceability analysis within 5 minutes, with an accuracy of over 90%, significantly superior to the timeliness and accuracy of traditional methods.

[0092] Furthermore, the present invention introduces an atmospheric diffusion model to dynamically correct the traceability result. The formula of the atmospheric diffusion model is:

[0093] ;

[0094] where is the pollutant concentration at the horizontal coordinate , vertical height z and time , is the total number of pollution sources, is the horizontal position coordinate of the is the emission intensity of the and are diffusion parameters, is the wind speed, is the emission height of the

[0095] Furthermore, the traceability result of the present invention is updated in real time and stored in the result database for subsequent query and analysis.

[0096] In the result display and analysis module 500, through the WebGL-based interactive visualization tool, the traceability result is displayed in various intuitive forms such as dynamic pie charts, 3D bar charts, 3D heat maps, etc. These visualization charts support users to freely zoom, rotate and filter the spatio-temporal range, facilitating users to deeply analyze the traceability result from different perspectives.

[0097] The present invention provides rich data analysis tools, including trend prediction analysis based on time series, pollution source correlation analysis based on association rule mining, pollution type classification analysis based on cluster analysis, etc. At the same time, the regional pollution contribution difference is calculated through the formula , where and are the pollution source contribution rates of urban stations, suburban stations or regional stations respectively, It is the contribution difference value of regional pollution, which helps environmental management departments deeply understand the laws behind the data and provides comprehensive data support for formulating scientific and reasonable pollution control strategies.

[0098] Embodiment 2:

[0099] As Figure 2 shown, the present invention provides a method for tracing the source of fine particulate matter in a city based on multiple atmospheric super stations. This method uses the system for tracing the source of fine particulate matter in a city based on multiple atmospheric super stations in the above Embodiment 1, and includes the following steps:

[0100] S1: Real-time collect observation data through multiple atmospheric super stations. The observation data includes fine particulate matter concentration, chemical composition, and meteorological parameter data. The atmospheric super stations include urban stations, suburban stations, and regional stations, and are arranged according to a weighted scoring model of urban scale, pollution source distribution, population density, and topography and geomorphology;

[0101] S2: Preprocess the observation data;

[0102] S3: Construct a source tracing model based on the positive definite matrix factorization receptor model and the random forest algorithm;

[0103] S4: Input the preprocessed data into the source tracing model, and output the contribution ratio of pollution sources and the regional emission weight through parallel computing. At the same time, introduce an atmospheric diffusion model to dynamically correct the source tracing results;

[0104] S5: Based on a WebGL-based interactive visualization tool, display the source tracing results through dynamic pie charts and 3D bar charts.

[0105] A method for tracing the source of fine particulate matter in a city based on multiple atmospheric super stations in this embodiment uses the aforementioned system for tracing the source of fine particulate matter in a city based on multiple atmospheric super stations. Therefore, the specific implementation methods in the method for tracing the source of fine particulate matter in a city based on multiple atmospheric super stations can be seen in the embodiment part of the aforementioned system for tracing the source of fine particulate matter in a city based on multiple atmospheric super stations. For example, steps S1, S2, S3, S4, and S5 respectively use the data acquisition module 100, data preprocessing module 200, source tracing model construction module 300, real-time collaborative source tracing module 400, and result display and analysis module 500 in the aforementioned system for tracing the source of fine particulate matter in a city based on multiple atmospheric super stations. Therefore, its specific implementation methods can refer to the descriptions of the corresponding various part embodiments. To avoid redundancy, they will not be elaborated here.

[0106] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0107] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0108] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks. These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0109] Obviously, the above embodiments are only examples for clear illustration and are not limitations on the implementation manners. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all the implementation manners here. And the obvious changes or modifications derived therefrom are still within the protection scope of the present invention.

Claims

1. An urban fine particulate matter traceability system based on multiple atmospheric super stations, characterized in that, include: A data acquisition module is used to collect observation data in real time through multiple atmospheric super stations, including fine particulate matter concentration, chemical composition, and meteorological parameter data. The atmospheric super stations include urban stations, suburban stations, and regional stations, and are arranged according to a weighted scoring model based on city size, pollution source distribution, population density, and topography; Data preprocessing module, used to preprocess the observation data; The traceability model construction module is used to build a traceability model based on the positive definite matrix factor receptor model and the random forest algorithm, including: Using the positive definite matrix factorization receptor model, the concentration matrix X of each chemical component in the observed fine particulate matter m×n is decomposed into G m×p ·F p×n , where p is the number of pollution source factors, m is the number of samples, n is the type of chemical components, G m×p is the factor contribution matrix, and F p×n is the factor spectrum matrix; The positive definite matrix factor receptor model was iteratively optimized using the Bootstrap resampling technique; Select the optimal number of pollution source factors p through cross-validation to maximize the model's explained variance R 2 and minimize the sum of squared residuals Q, satisfying |R 2 - Q| ≤ 0.05; The random forest algorithm is combined with knowledge graph technology to integrate the prior knowledge of the spatiotemporal distribution of pollution sources, pollution source emission characteristics, and meteorological conditions to optimize the model input features. The model performance is jointly evaluated by the leave-one-out method and K-fold cross-validation. The objective function is: Among them, T is the total number of samples, y t is the true label of the t-th sample, is the predicted label of the t-th sample, λ is the regularization coefficient, l is the total number of feature dimensions, and β j is the weight coefficient of the j-th feature; A real-time collaborative tracing module is used to input pre-processed data into the tracing model and output the pollution source contribution ratio and regional emission weight through parallel calculation. At the same time, an atmospheric diffusion model is introduced to dynamically correct the tracing results. The result display and analysis module is an interactive visualization tool based on WebGL, which displays the traceability results through dynamic pie charts and 3D bar charts.

2. The urban fine particulate matter traceability system based on multiple atmospheric super stations according to claim 1, characterized in that The method of iteratively optimizing the positive definite matrix factor receptor model by using the Bootstrap resampling technique comprises: Randomly extract subsamples from the original data and repeat a set number of times to generate the Bootstrap dataset; Perform positive definite matrix factorization on each sub-dataset and calculate the mean and confidence interval of the factor contribution matrix; All elements of the constraint factor contribution matrix and factor spectrum matrix are non-negative to ensure the physical rationality of the pollution source contribution.

3. The urban fine particulate matter tracing system based on multiple atmospheric super stations according to claim 1, characterized in that, The calculation formula of the residual sum of squares is: where Q is the sum of squared residuals; m represents the number of samples; n represents the number of chemical component types; p represents the number of pollution source factors; x ij is an element in the original data matrix, representing the concentration value of the j-th chemical component in the i-th sample; g ik is an element in the factor contribution matrix G, representing the contribution of the k-th pollution source to the total concentration in the i-th sample; f kj is an element in the factor spectrum matrix F, representing the concentration ratio of the j-th chemical component in the k-th pollution source; u ij is an element in the uncertainty matrix U, representing the measurement uncertainty of the j-th chemical component in the i-th sample.

4. The urban fine particulate matter traceability system based on multiple atmospheric super stations according to claim 1, wherein The formula of the weighted scoring model is: Among them, W i is the weight of the i-th atmospheric super station, R i , R j are the representativeness scores of the i-th and j-th atmospheric super stations, C i , C j are the coverage scores of the i-th and j-th atmospheric super stations, Q i , Q j are the data quality scores of the i-th and j-th atmospheric super stations, and n is the number of atmospheric super stations.

5. The urban fine particulate matter traceability system based on multiple atmospheric super stations according to claim 1, characterized in that, The introduction of the atmospheric diffusion model to dynamically correct the tracing results includes: Among them, C(x, y, t) is the pollutant concentration at the horizontal coordinates (x, y), vertical height z, and time t. S is the total number of pollution sources, and y s is the horizontal position coordinate of the sth pollution source, and Q s is the emission intensity of the sth pollution source, and σ y and σ z are diffusion parameters, u is the wind speed, and H s is the emission height of the sth pollution source.

6. The urban fine particulate matter traceability system based on multiple atmospheric super stations according to claim 1, characterized in that, In the results display and analysis module, the pollution source contribution ratio and regional emission weight are displayed through the superposition of dynamic pie charts and 3D heat maps, allowing users to interactively filter the time and space ranges and calculate the regional pollution contribution differences using the following formula: Among them, S i and S j are the pollution source contribution rates of the urban station, suburban station or regional station respectively, and ΔS ij is the regional pollution contribution difference value.

7. The urban fine particulate matter traceability system based on multiple atmospheric super stations according to claim 1, characterized in that, The data preprocessing module includes a data cleaning unit, a standardization processing unit and a feature extraction unit. The data cleaning unit adopts the 3σ principle combined with an adaptive low-pass filter to eliminate outliers; the standardization processing unit adopts a dynamic threshold Z-score standardization method for concentration data and a Min-Max standardization method for chemical composition data; the feature extraction unit extracts key features through a deep neural network combined with principal component analysis and linear discriminant analysis.

8. The urban fine particulate matter traceability system based on multiple atmospheric super stations according to claim 7, characterized in that, The formula for the Z-score normalization method of the dynamic threshold is: Among them, Z 动态 represents the standardized concentration value, x i represents the real-time concentration information of the current monitoring site, μ 实时 represents the real-time mean value calculated dynamically, σ 实时 represents the real-time standard calculated dynamically.

9. A method for tracing the sources of urban fine particulate matter based on multiple atmospheric super stations, characterized in that, The method uses the urban fine particulate matter tracing system based on multiple atmospheric super stations according to any one of claims 1 to 8, comprising the following steps: Collect observation data in real time through multiple atmospheric super stations. The observation data includes fine particulate matter concentration, chemical composition, and meteorological parameter data. The atmospheric super stations include urban stations, suburban stations, and regional stations, and are arranged according to a weighted scoring model of urban scale, pollution source distribution, population density, and topography and geomorphology; Preprocess the observation data; Construct a source tracing model based on the positive definite matrix factorization receptor model and the random forest algorithm; Input the preprocessed data into the source tracing model, and output the source contribution ratio and regional emission weight through parallel computing. At the same time, introduce an atmospheric diffusion model to dynamically correct the source tracing results; Based on the WebGL-based interactive visualization tool, display the source tracing results through dynamic pie charts and 3D bar charts.

Images