Method and System for Tracing the Diffusion Path of Air Pollution Based on Meteorological Data

Abstract

The present invention discloses a method and system for tracing the diffusion path of air pollution based on meteorological data, which relates to the technical field of pollution path tracing. The method includes: establishing a high-density monitoring network; obtaining the time-series point monitoring data set of the high-density monitoring network and distributing pollution hotspots; configuring high-precision sensors and monitoring drones in the pollution hotspots, establishing three-dimensional data of the pollution field, and synchronously obtaining the wind force data set; establishing state variables; using an atmospheric diffusion model to perform prediction fitting of a set of initial parameters based on the observed variable wind force data set to generate the pollutant distribution and establish candidate solutions; performing a global particle search on the candidate solutions to establish the tracing result of the pollution diffusion path. The present invention solves the technical problems in the prior art that it is difficult to accurately identify pollution hotspots and the accuracy and reliability of tracing the diffusion path of air pollution are low, and achieves the technical effect of improving the accuracy and reliability of tracing the diffusion path of air pollution.

Description

Technical Field

[0001] The present invention relates to the technical field of pollution path tracing, and specifically relates to a method and system for tracing the diffusion path of air pollution based on meteorological data. Background Art

[0002] With the acceleration of industrialization and urbanization, the problem of air pollution has become increasingly severe, and it is crucial to accurately trace the diffusion path of air pollution. In the existing technologies, there are many difficulties in air pollution monitoring. On the one hand, the monitoring range of traditional monitoring means is limited and the monitoring points are sparsely distributed, making it difficult to obtain comprehensive and accurate pollution data. For example, relying only on a few fixed monitoring stations, it is impossible to timely grasp the detailed spatial distribution and dynamic changes of pollution, and it is easy to miss areas with serious local pollution. On the other hand, the existing methods for tracing the diffusion path of pollution have poor accuracy. Due to the lack of in-depth fusion analysis of meteorological data and pollution data, when considering key parameters such as the location of pollution sources, emission intensity, and emission time, it is not comprehensive and accurate enough, resulting in difficulty in accurately determining the source and diffusion trajectory of pollution.

[0003] There are technical problems in the prior art that it is difficult to accurately identify pollution hotspots, and the accuracy and reliability of tracing the diffusion path of air pollution are low. Summary of the Invention

[0004] The present application provides a method and system for tracing the diffusion path of air pollution based on meteorological data, which are used to solve the technical problems in the prior art that it is difficult to accurately identify pollution hotspots, and the accuracy and reliability of tracing the diffusion path of air pollution are low.

[0005] In view of the above problems, the present application provides a method and system for tracing the diffusion path of air pollution based on meteorological data.

[0006] In the first aspect of the present application, a method for tracing the diffusion path of air pollution based on meteorological data is provided, and the method includes:

[0007] Connect small air quality sensors using NB-IoT and LoRa to establish a high-density monitoring network; obtain the time-series point monitoring data set of the high-density monitoring network, screen for anomalies in the time-series point monitoring data set through fixed thresholds, and distribute pollution hotspots based on spatial interpolation and point anomaly recognition results; configure high-precision sensors and monitoring drones in the pollution hotspots to perform pollution-focused collection, establish three-dimensional pollution field data, and synchronously obtain wind data sets; establish state variables, and construct observation variables using the wind data sets and the three-dimensional pollution field data; use an atmospheric diffusion model to perform prediction fitting of the wind data sets based on a set of initial parameters for the observation variables to generate pollutant distributions, and perform inverse fitting by minimizing the error function between the pollutant distributions and the three-dimensional pollution field data to establish candidate solutions, where the initial parameters are parameters set according to the state variables; perform global particle search on the candidate solutions, and perform two-layer optimization of local inverse fitting based on the global particle search results to establish pollution diffusion path tracing results.

[0008] In the second aspect of the present application, an atmospheric pollution diffusion path tracing system based on meteorological data is provided. The system includes:

[0009] A high-density monitoring network establishment module for connecting small air quality sensors using NB-IoT and LoRa to establish a high-density monitoring network; a pollution hotspot area distribution module for obtaining the time-series point monitoring data set of the high-density monitoring network, screening for anomalies in the time-series point monitoring data set through fixed thresholds, and distributing pollution hotspots based on spatial interpolation and point anomaly recognition results; a three-dimensional pollution field data establishment module for configuring high-precision sensors and monitoring drones in the pollution hotspots to perform pollution-focused collection, establish three-dimensional pollution field data, and synchronously obtain wind data sets; a state variable establishment module for establishing state variables and constructing observation variables using the wind data sets and the three-dimensional pollution field data; a candidate solution establishment module for using an atmospheric diffusion model to perform prediction fitting of the wind data sets based on a set of initial parameters for the observation variables to generate pollutant distributions, and performing inverse fitting by minimizing the error function between the pollutant distributions and the three-dimensional pollution field data to establish candidate solutions, where the initial parameters are parameters set according to the state variables; a pollution diffusion path tracing result establishment module for performing global particle search on the candidate solutions and performing two-layer optimization of local inverse fitting based on the global particle search results to establish pollution diffusion path tracing results.

[0010] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0011] Connect small air quality sensors using NB-IoT and LoRa to establish a high-density monitoring network; obtain the time-series point monitoring data set of the high-density monitoring network, and based on spatial interpolation and point anomaly recognition results, distribute pollution hotspots; configure high-precision sensors and monitoring drones in the pollution hotspots to perform pollution collection of concern, establish three-dimensional data of the pollution field, and synchronously obtain the wind force data set; establish state variables; use the atmospheric diffusion model to predict and fit a set of initial parameters based on the observed variable wind force data set to generate the pollutant distribution and establish candidate solutions; perform a global particle search on the candidate solutions, and perform a two-layer optimization of local inversion fitting according to the global particle search results to establish the pollution diffusion path tracing results. It achieves the technical effect of improving the accuracy and reliability of atmospheric pollution diffusion path tracing. Brief Description of the Drawings

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0013] Figure 1 Schematic flowchart of the method for tracing the atmospheric pollution diffusion path based on meteorological data provided by the embodiments of the present application;

[0014] Figure 2 Schematic structural diagram of the system for tracing the atmospheric pollution diffusion path based on meteorological data provided by the embodiments of the present application.

[0015] Explanation of reference numerals: High-density monitoring network establishment module 10, pollution hotspot area distribution module 20, three-dimensional data establishment module 30 of the pollution field, state variable establishment module 40, candidate solution establishment module 50, pollution diffusion path tracing result establishment module 60. Detailed Embodiments

[0016] The present application provides a method and system for tracing the atmospheric pollution diffusion path based on meteorological data, which are used to solve the technical problems in the prior art that it is difficult to accurately identify pollution hotspots and the accuracy and reliability of atmospheric pollution diffusion path tracing are low.

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0018] Example 1, as Figure 1 shown, this application provides a method for tracing the diffusion path of air pollution based on meteorological data, and the method includes:

[0019] Step S100: Connect small air quality sensors using NB-IoT and LoRa to establish a high-density monitoring network.

[0020] Specifically, first of all, a wide and detailed monitoring network needs to be constructed. Two low-power wide-area network communication technologies, NB-IoT (Narrow Band Internet of Things) and LoRa (Long Range Radio), are applied therein, which have the advantages of wide coverage, strong penetration ability, low power consumption, etc. Small air quality sensors, due to their small size and easy deployment characteristics, become the basic units of the monitoring network. With the help of NB-IoT and LoRa technologies, a large number of small air quality sensors are interconnected. These sensors are scattered and deployed in the target monitoring area, and they are distributed according to a certain density and layout, forming a high-density monitoring network. In this way, it is possible to comprehensively and real-time collect air quality data at different positions in the monitoring area, providing rich and reliable data support for subsequent accurate analysis of the air pollution situation, determination of pollution hotspots, and tracing of pollution diffusion paths.

[0021] Step S200: Obtain the time-series point monitoring data set of the high-density monitoring network, screen the anomalies in the time-series point monitoring data set through a fixed threshold, and distribute pollution hotspots based on spatial interpolation and point anomaly recognition results.

[0022] Specifically, after establishing the high-density monitoring network, obtain the time-series point monitoring data set from the established high-density monitoring network. This data set records the air quality data collected by the monitoring network at different time points, covering various pollution index information of many monitoring points. Use a pre-set fixed threshold to screen these data, and determine the data points that exceed or are lower than the threshold as abnormal data. These abnormal data may imply the occurrence or change of pollution conditions. Then, use spatial interpolation technology to infer the air quality data at other unmonitored positions in the monitoring area based on the data of known monitoring points, so as to have a more comprehensive estimate of the pollution distribution in the entire area. At the same time, combined with the point anomaly recognition results, comprehensively analyze the areas where abnormal data frequently appear and the areas where high pollution concentrations are found through spatial interpolation, and finally determine and mark the pollution hotspots. These areas are where air pollution is relatively serious and need to be focused on, providing key basis for subsequent more accurate monitoring and analysis.

[0023] Step S300: Configure high-precision sensors and monitoring drones in the pollution hotspots, perform focused pollution collection, establish three-dimensional data of the pollution field, and synchronously obtain the wind force data set.

[0024] Specifically, in order to obtain more accurate and comprehensive pollution information, high-precision sensors such as FTIR spectrometers and GC-MS gas analyzers are deployed in these pollution hotspots. At the same time, monitoring drones are arranged to work in coordination. An independent acquisition attention degree is established using the pollution hotspots. Based on factors such as the severity and scope of pollution in the hotspots, the key points and frequencies of acquisition are determined to ensure that key pollution data can be effectively captured. Then, an adjacent association compensation for the independent acquisition attention degree is carried out, considering possible pollution transfer or influencing factors around the hotspots to optimize the acquisition strategy. After that, the high-precision sensors and monitoring drones start to perform the acquisition work on the concerned pollution. The high-precision sensors collect detailed data of different pollutants from the ground, and the monitoring drones collect data from multiple angles and heights in the air. The combination of the two constructs three-dimensional data of the pollution field containing pollution information at different heights and positions. During the process of collecting pollution data, wind force data sets of the area, including information such as wind speed and wind direction, are obtained synchronously through meteorological monitoring equipment or relevant data interfaces. These data provide key basis for subsequent analysis of the diffusion of air pollution and help to more accurately understand the diffusion trend of pollutants under different meteorological conditions.

[0025] Step S400: Establish state variables and construct observation variables using the wind force data set and the three-dimensional pollution field data.

[0026] Specifically, state variables are defined and established. These variables are quantitative representations of the sources and initial conditions of air pollution diffusion, specifically covering the location of pollution sources, emission intensity, and emission time. The location of the pollution source is accurately marked by determining its precise spatial coordinates (such as longitude, latitude, and altitude). The emission intensity is measured by the mass of pollutants released per unit time, and the emission time is accurate to a specific time point. These three variables together construct the basic framework for describing the initial state of pollution. Then, observation variables are constructed based on the obtained wind force data set and three-dimensional pollution field data as the core basis. The wind force data set contains dynamic information such as wind speed and wind direction, which directly affect the diffusion direction and speed of pollutants; the three-dimensional pollution field data details the distribution of pollutant concentrations at different spatial positions and heights. When constructing, the two are deeply integrated. For example, the wind speed at a certain area at a specific moment is combined with the pollutant concentration at the corresponding position to form a wind speed-pollutant concentration correlation variable to reflect the immediate impact of wind force on pollutant concentration; according to the change of wind direction, the change of pollutant concentrations at different positions is correlated to construct a wind direction-pollutant concentration change variable to show the diffusion trend of pollutants when the wind direction changes. By integrating these data in various ways, observation variables that can comprehensively reflect the real-time dynamics of air pollution diffusion are constructed, providing strong support for subsequent accurate analysis using the air diffusion model.

[0027] Step S500: Use an atmospheric diffusion model to perform prediction fitting on a set of initial parameters based on the wind force data set of the observed variables, generate the pollutant distribution, and perform inverse fitting by minimizing the error function between the pollutant distribution and the three-dimensional data of the pollution field to establish candidate solutions. The initial parameters are the parameters set according to the state variables.

[0028] Specifically, a set of initial parameters is set according to the previously established state variables. These initial parameters contain key information such as the location of the pollution source, emission intensity, and emission time, which initially depict the starting conditions of atmospheric pollution diffusion. Subsequently, the atmospheric diffusion model is used to perform prediction fitting based on the wind force data set in the observed variables. The atmospheric diffusion model will simulate the diffusion process of pollutants in the atmosphere according to these initial parameters and wind force data, and then generate the distribution of pollutants at different spatial positions. Since there may be differences between the pollutant distribution generated by the model and the actual three-dimensional data of the pollution field, it is necessary to optimize the model by minimizing the error function between the two. Calculate the difference in pollutant concentration at each corresponding position between the generated pollutant distribution and the three-dimensional data of the pollution field, construct the error function, and then use an optimization algorithm to continuously adjust the initial parameters to gradually reduce the value of the error function. This process is inverse fitting. After multiple iterative calculations, a set of parameter combinations that minimize the error function is obtained, and these parameter combinations constitute the candidate solutions. These candidate solutions represent possible pollution source parameter settings, providing multiple potential choices for determining the pollution diffusion path that best conforms to the actual situation.

[0029] Step S600: Perform a global particle search on the candidate solutions and conduct a two-layer optimization of local inverse fitting based on the global particle search results to establish the pollution diffusion path tracing results.

[0030] Specifically, with the candidate solution as the center, particles are evenly distributed around it. These particles form a candidate particle set, and each particle represents a pollution source parameter containing information such as the location of the pollution source, emission intensity, and emission time. Then, global particle search begins. During the search process, it is continuously determined whether the update stage of the particle meets the preset stage threshold. If it meets, the positions of the particles in the candidate particle set are updated according to the distance constraint. Before updating the position, the pollutant distribution of each particle needs to be predicted first. According to the prediction result, the particle weight is calculated, and the particle weight is used as the particle fitness value. Combining the particle contraction factor, random perturbation amplitude, and update interval to complete the position update, and record the update result in the regional exploration window. When the update stage of the particle does not meet the preset stage threshold, the exploration result of the regional exploration window is called to perform regional elimination identification, and the particles that do not meet the requirements are eliminated from the candidate particle set. The remaining particles are used to continue the update search, and finally the global particle search result is obtained. Based on the global particle search result, a two-layer optimization of local inversion fitting is carried out. Through the fitness value of the particles in the global particle search result, the candidate solution is updated and tracked to identify the particles or combinations of particles that are most likely to reflect the real pollution situation, and the update tracking identification result is established. Then, using this result to optimize the position of the candidate solution, further adjusting the pollution source parameters to complete the two-layer optimization of local inversion fitting. After this series of operations, considering the global and local optimization information comprehensively, the pollution diffusion path tracing result that best conforms to the actual situation is finally determined, clearly presenting key information such as the diffusion trajectory of the pollutant starting from the source, the diffusion time, and the diffusion degree at different stages.

[0031] In a possible implementation manner, step S600 further includes:

[0032] Step S610: With the candidate solution as the center, particles are evenly distributed to establish a candidate particle set, where each particle in the candidate particle set represents a pollution source parameter, and the pollution source parameter includes the location of the pollution source, emission intensity, and emission time.

[0033] Step S620: Determine whether the update stage of the particle meets the preset stage threshold.

[0034] Step S630: If the update stage of the particle meets the preset stage threshold, update the position of the candidate particle set through distance constraint and record it in the regional exploration window.

[0035] Step S640: After the update stage of the particle does not meet the preset stage threshold, call the exploration result of the regional exploration window to perform regional elimination identification, use the regional elimination identification result to eliminate the corresponding particles of the candidate particle set, and continue the update search according to the remaining particles to establish the global particle search result.

[0036] Specifically, after a series of preliminary operations are completed to obtain candidate solutions, with the candidate solution as the center, particles are evenly distributed in a multi-dimensional space. Assume that the pollution source location represented by the candidate solution is a specific spatial coordinate point, and there are corresponding values for the emission intensity and emission time. Based on these values, within a certain range around the candidate solution, the attributes of each particle are determined according to specific rules. For the pollution source location, in three-dimensional space, by making small offsets along each coordinate axis direction at equal intervals or in a specific distribution pattern based on the candidate solution location, the position coordinates of different particles are generated; similar operations are performed on the emission intensity and emission time. Around the corresponding values of the candidate solution, a series of different values are generated at certain intervals or according to a distribution law and assigned to each particle. Each particle is assigned a unique set of pollution source parameters, which include the precise pollution source location, the specific emission intensity, and the accurate emission time. In this way, the constructed candidate particle set covers numerous potential pollution source parameter combinations around the candidate solution.

[0037] During the search and optimization process of particles, each particle has its specific update stage, which records the number of updates or the iteration process experienced by the particle from the initial state to the current state. The preset stage threshold is a standard value set in advance based on various factors such as research experience on air pollution diffusion problems, computing resources, and the desired computing accuracy. The current update stage value of each particle is obtained in real-time and compared with the preset stage threshold. Through this judgment operation, it is determined whether the particle has reached the stage node where specific operations need to be performed.

[0038] When the update stage of the particle reaches the preset stage threshold, the positions of the candidate particle set are updated according to the distance constraint. The distance constraint, as a restrictive rule, ensures that the positions of the particles after update conform to the actual physical laws and logic of air pollution diffusion, and avoids unreasonable large jumps of the particles. During the update process, each particle in the candidate particle set is calculated one by one, comprehensively considering the current position of the particle, surrounding environmental factors, and the interaction relationship with other particles, etc., to determine its new position. After the update is completed, the new position information of these particles will be recorded in the regional exploration window, which stores the phased results of the particles during the exploration process and provides data support for subsequent analysis.

[0039] When the update stage of the particles does not meet the preset stage threshold, at this time, the exploration results stored in the regional exploration window are called to perform regional elimination recognition. Regional elimination recognition is a screening process. By analyzing factors such as the position changes of particles in the previous exploration process, their associations with other particles, and their impacts on the overall pollution diffusion model, it is determined which particles deviate from the possible optimal solutions and which particles have lower exploration direction values. Based on the results of regional elimination recognition, the low-value particles corresponding in the candidate particle set are eliminated, and only those particles that are more likely to approach the true pollution source parameters are retained. Then, these remaining particles are used to continue the update search, continuously adjusting the positions of the particles and the pollution source parameters they represent, and continuously exploring better solutions. After multiple such iterative operations, a global particle search result is finally established, providing a key basis for accurately tracing the atmospheric pollution diffusion path.

[0040] In a possible implementation manner, step S630 further includes:

[0041] Step S631: Predict the pollutant distribution for each particle in the candidate particle set to establish a prediction result.

[0042] Step S632: Calculate the weight of each particle according to the prediction result as follows:

[0043] ;

[0044] Wherein, represents the weight of particle , represents the actual observed pollutant concentration data obtained from the three-dimensional data of the pollution field, represents particle 's simulated pollutant concentration, represents the standard deviation of the observation noise.

[0045] Step S633: Use the weight of the particle as the particle fitness value to perform position update of the candidate particle set.

[0046] Specifically, to predict the pollutant distribution for each particle in the candidate particle set and establish the prediction results, the following specific implementation means are adopted: First, extract the pollution source parameters represented by each particle, including the precise location of the pollution source (such as longitude, latitude, and altitude determined based on the geographical coordinate system), emission intensity (pollutant emission amount per unit time), and emission time (accurate to a specific time point). Then, combine the meteorological data collected in the early stage, especially the wind speed dataset, to obtain wind speed and wind direction information. At the same time, use other meteorological monitoring devices to obtain data such as atmospheric temperature, humidity, and air pressure to determine the atmospheric stability. Based on this information, select a suitable atmospheric diffusion model, such as the AERMOD model. In the model, take the pollution source location of the particle as the starting point, and determine the initial pollutant emission flux according to the emission intensity. Set the dominant direction of pollutant diffusion according to the wind direction, and calculate the transmission speed of the pollutant in this direction using the wind speed. Combine the atmospheric stability to determine the parameters used in the model to describe the diffusion degree of pollutants in the horizontal and vertical directions. For example, when the stability is high, the pollutant diffusion is relatively restricted, corresponding to smaller diffusion parameters; on the contrary, when it is unstable, the diffusion parameters are larger. Use these parameters to calculate the pollutant concentrations at each spatial point within a certain range centered on the pollution source at different times through the model. Integrate the calculated pollutant concentration data at different times and different spatial points to form the pollutant distribution prediction results for each particle. These results are presented in the form of three-dimensional data, covering spatial positions (x, y, z coordinates) and the time dimension, intuitively showing the diffusion of pollutants in space over time, providing key data support for subsequent calculation of particle weights and updating of particle positions, and facilitating the accurate tracing of the atmospheric pollution diffusion path.

[0047] Then, calculate the weight of each particle according to the prediction results. The calculation formula is In this formula, represents the weight of particle , and its numerical value directly reflects the degree of fit between the combination of pollution source parameters represented by this particle and the actual pollution situation. is the actual observed pollutant concentration data obtained from the three-dimensional data of the pollution field, which is an intuitive manifestation of the real pollution situation; represents particle The pollutant concentration simulated by the model; represents the standard deviation of the observation noise, which measures the uncertainty of the observation data. In terms of the principle of the formula, the smaller the difference between the actual observed concentration and the simulated concentration, the larger the value of the exponential part, and the higher the weight of the particle, indicating that the combination of pollution source parameters represented by this particle is closer to the real situation.

[0048] Take the weight of the particle as the particle fitness value, and perform the position update operation of the candidate particle set based on this as the core basis. The particle fitness value represents the degree of fit between the combination of pollution source parameters represented by the particle and the actual air pollution situation. The greater the weight, that is, the higher the fitness value, the closer the parameter combination represented by the particle is to the real pollution source situation. First, determine the particle contraction factor according to the particle fitness value. For particles with a high fitness value, the contraction factor is set relatively small, aiming to make the particle move less during position update to maintain exploration in the area close to the real solution; while for particles with a low fitness value, the contraction factor is relatively large, giving it a larger movement range to explore new areas and increasing the possibility of finding a better solution. Create an update interval based on the current particle position and distance constraint. The distance constraint is set according to the actual physical laws and relevant experience of air pollution diffusion to ensure that the position of the particle after update is within a reasonable range and avoid unrealistic jumps. This update interval defines the boundary of the range within which the particle position can change during update. At the same time, configure the random perturbation amplitude. The random perturbation amplitude introduces a certain degree of randomness to the particle position update to prevent the particle from falling into a local optimal solution. When performing position update, comprehensively consider the three elements of the particle contraction factor, random perturbation amplitude, and update interval. For each particle, adjust the movement step size according to its own contraction factor, and then randomly select a direction within the update interval in combination with the random perturbation amplitude to move, thus completing the position update of the candidate particle set. In this way, the particles continuously adjust their positions in the search space, gradually approaching the real pollution source parameters, laying a foundation for accurately tracing the air pollution diffusion path.

[0049] In a possible implementation manner, step S633 further includes:

[0050] Step S6331: Configure the particle contraction factor according to the particle fitness value.

[0051] Step S6332: Create an update interval based on the current particle position and the distance constraint.

[0052] Step S6333: Configure the random perturbation amplitude, and perform the position update of the candidate particle set according to the random perturbation amplitude, the particle contraction factor, and the update interval.

[0053] Specifically, the particle fitness value is determined based on the previously calculated particle weights, which reflects the matching degree between the combination of pollution source parameters represented by the particle and the actual air pollution situation. The particle contraction factor is configured according to this fitness value. For particles with a higher fitness value, it means that the combination of pollution source parameters they represent is closer to the real situation. To avoid the particles deviating from this possible correct area in subsequent searches, a smaller particle contraction factor is set, so that the particles move relatively less during position update and can explore better solutions more finely near the current area. On the contrary, for particles with a lower fitness value, it means that the current combination of pollution source parameters deviates greatly from the actual situation. At this time, a larger particle contraction factor is configured to allow the particles to move within a larger range and increase the chance of finding a better solution.

[0054] Obtain the specific position information of each particle in space. These position information precisely identify the coordinates of the particle in the current search space. For example, in a three-dimensional space model, it is the coordinate values composed of longitude, latitude, and altitude. The distance constraint is set according to the actual physical laws of air pollution diffusion, past research experience, and the specific requirements of this task. It stipulates the maximum distance that the particle can move when updating its position. For example, considering factors such as the diffusion speed and range limit of pollutants in the atmosphere, and the fact that pollution sources do not appear instantaneously in distant areas in the real scenario, a reasonable distance threshold is set. Taking the current particle position as the reference point, range boundaries are defined in each direction according to the distance constraint. On a two-dimensional plane, a circular or square (depending on the specific setting method) area is expanded around the particle's position as the center and with the distance constraint value as the radius; in three-dimensional space, a sphere is constructed with the particle position as the center of the sphere and the distance constraint value as the radius, or a cuboid-shaped area is formed by expanding in the three coordinate axis directions respectively according to the distance constraint value. This area is the update interval created for particle position update, which limits the range that the particle can reach in the subsequent position update process, ensuring that the movement of the particle is both exploratory and in line with the actual situation, avoiding large jumps of the particle that do not conform to physical laws, and laying a foundation for more accurately determining the particle position and tracing the pollution diffusion path in the future.

[0055] Configure the random perturbation amplitude. The random perturbation amplitude introduces a certain degree of randomness to the position update of the particles, preventing the particles from falling into local optimal solutions during the search process. In actual operation, according to the particle contraction factor and the update interval, combined with the configured random perturbation amplitude, the position of the candidate particle set is updated. For each particle, first adjust its movement step according to the particle contraction factor, and then randomly select a direction within the update interval to move according to the random perturbation amplitude. In this way, the particles continuously adjust their positions in the search space, continuously explore more realistic pollution source parameters, gradually approach the true pollution diffusion path, and provide strong support for accurately tracing the atmospheric pollution diffusion path.

[0056] In a possible implementation manner, step S640 further includes:

[0057] Step S641: Obtain the flight trajectory of the monitoring UAV, and calibrate the particle with the maximum fitness value in the retained particles as the standard particle.

[0058] Step S642: Establish a trajectory influence compensation according to the flight trajectory and the standard particle.

[0059] Step S643: Perform an update search constraint on the retained particles through the trajectory influence compensation.

[0060] Specifically, obtain the flight trajectory of the monitoring UAV. The monitoring UAV will record its own flight path during the mission. This trajectory contains the spatial position information of the UAV at different time points, reflecting its activity range and path changes over the polluted area. At the same time, evaluate the retained particles, find the particle with the maximum fitness value among them, and calibrate it as the standard particle. This standard particle represents the particle that is most likely to be close to the true pollution source parameters determined during the current search process. A high fitness value means that the combination of parameters such as the pollution source location, emission intensity, and emission time represented by it has a relatively optimal matching degree with the actual pollution situation.

[0061] First, extract the spatial position information of the monitoring UAV at each time point from its flight trajectory data. These information accurately record the movement path of the UAV over the polluted area. At the same time, clarify the key parameters such as the pollution source location, emission intensity, and emission time represented by the standard particles. Based on the atmospheric diffusion model, combined with the currently obtained meteorological data, such as wind speed, wind direction, temperature, humidity, etc., starting from the pollution source parameters of the standard particles, simulate the diffusion process of pollutants in the atmosphere from the emission time, so as to obtain the concentration distribution of pollutants at different time and space points. For each point on the UAV flight trajectory, calculate the distance between it and the pollution source location, judge its relative position in the pollution diffusion direction, and obtain the simulated pollutant concentration corresponding to this point. According to these data, assign an influence factor to each point. The closer the point is to the pollution source, the more it is located in the main direction of pollution diffusion and the higher the simulated pollutant concentration, the greater its influence factor. Integrate the influence factors of all points on the flight trajectory, and through data analysis and processing, construct a model describing the influence of the flight trajectory on particle search, which is the trajectory influence compensation. When performing an updated search on the remaining particles later, use this trajectory influence compensation mechanism to adjust parameters such as the search direction and step size of the particles according to the spatial position and time of the particles, so that the search process of the particles is more in line with the actual pollution diffusion situation, thereby improving the accuracy and efficiency of tracing the atmospheric pollution diffusion path.

[0062] When the remaining particles are ready for an updated search, first perform a matching query in the trajectory influence compensation model based on the current spatial position and time information of each remaining particle to obtain the corresponding influence parameters. These influence parameters reflect the degree to which the area where the particle is located is affected by the UAV flight trajectory and the standard particles (representing the current optimal pollution source parameter combination). If the particle is in an area of the UAV flight trajectory that is greatly affected by pollution, and the trajectory influence compensation shows that this area is of great significance for finding the true pollution source, then during the updated search, the movement direction of the particle will be more inclined to approach the pollution source location represented by the standard particles, and at the same time, the movement step size may be appropriately reduced to explore this area more finely and increase the probability of finding a better solution. On the contrary, if the particle is in an area with less influence, the adjustment range of its movement direction and step size is relatively small, maintaining a certain exploration range to avoid deviating too much from the possible optimal solution area. In this way, the trajectory influence compensation sets reasonable rules and restrictions for the updated search of the remaining particles, guides the particles to explore more efficiently in the search space, avoids blind search, makes the updated search of the particles more in line with the actual pollution diffusion situation, helps to determine the pollution source parameters faster and more accurately, and realizes the accurate tracing of the atmospheric pollution diffusion path.

[0063] In a possible implementation manner, step S200 further includes:

[0064] Step S210: Obtain the spatial data of the space covered by the high-density monitoring network and read the retrospective wind data.

[0065] Step S220: Conduct spatial correlation analysis based on the spatial data and the retrospective wind data.

[0066] Step S230: Perform anomaly clustering on the point anomaly recognition results to establish the anomaly clustering results.

[0067] Step S240: Use the anomaly clustering results and the spatial correlation analysis results for spatial interpolation to distribute the pollution hotspots.

[0068] Specifically, obtain the detailed spatial data of the space covered by the high-density monitoring network. These data include information such as the geographical coordinates and topographic and geomorphic features of the area covered by the monitoring network, accurately depicting the spatial form of the monitoring area. At the same time, read the retrospective wind data, which records the wind speed, wind direction changes, etc. in the monitoring area over a past period, providing meteorological basic data for subsequent analysis.

[0069] Correspond the geographical location information in the spatial data with each time node in the retrospective wind data. Using longitude and latitude as the coordinate reference, study the wind conditions at different geographical locations at each moment. For example, compare the wind speed changes in mountainous areas and urban plain areas during the same time period to analyze the influence of terrain on wind speed. For wind direction, through visualization means such as drawing a wind rose diagram, observe the differences in the dominant wind directions in different regions and the variation law of wind direction with geographical location. Use statistical analysis methods to calculate the correlation coefficient between the spatial position and wind force elements to quantify the degree of association between the two. For example, calculate the Pearson correlation coefficient between wind speed and altitude to judge the change trend of wind speed with altitude. At the same time, with the help of the spatial analysis function of the Geographic Information System (GIS), analyze the spatial distribution characteristics of wind force and the possible impact of wind force on pollutant diffusion. By synthesizing the analysis results from multiple aspects, sort out the internal relationship between the spatial data and the retrospective wind data, providing important data support and analysis basis for subsequent determination of pollution hotspots.

[0070] Process the early-stage point anomaly recognition results to establish anomaly clustering results. In the early stage, a series of point anomaly data have been identified by screening the time-series point monitoring dataset of the high-density monitoring network using a fixed threshold. In this step, a clustering algorithm such as the density-based spatial clustering algorithm DBSCAN is adopted. This algorithm scans all the point anomaly recognition results and clusters them based on the distribution density of data points in space and their distance relationships. First, a core point is determined, that is, a point with a density reaching a certain threshold. Around the core point, other points within a specific distance range are grouped into the same class. If a point is not a core point but its distance from a core point is within the specified range, it will also be assigned to the corresponding class. In this way, the clustering range is continuously expanded, and anomaly points with similar spatial positions and characteristics are grouped together. For example, in the monitoring area, if multiple anomaly points are concentrated geographically and the trends of pollutant concentration changes they reflect are similar, they will be clustered into one class. Finally, after the algorithm's processing, the originally scattered point anomaly recognition results are summarized into multiple different clusters. These clustering results clearly show the aggregation pattern of anomaly data in space, providing key clues for subsequent determination of pollution hotspots and helping to more accurately locate and analyze areas with severe air pollution.

[0071] Spatial interpolation is performed using the abnormal clustering results and spatial correlation analysis results obtained in the early stage to determine the distribution of pollution hotspots. The abnormal clustering results show the spatial aggregation of abnormal data, identifying which areas have concentrated abnormal phenomena, and these areas are likely to be the key pollution areas. The spatial correlation analysis results reveal the internal relationship between spatial location and factors such as wind force. For example, the impact of wind force in different areas on pollutant diffusion is different. When performing spatial interpolation, first, according to the spatial correlation analysis results and combined with wind force data, the diffusion trend and speed of pollutants in different areas are determined. For example, if the spatial correlation analysis shows that the wind direction and speed in a certain area will cause pollutants to diffuse in a specific direction, then this factor will be considered when performing spatial interpolation. Then, taking the abnormal aggregation areas in the abnormal clustering results as the core, using spatial interpolation algorithms (such as inverse distance weighted interpolation method, Kriging interpolation method, etc.), and based on the known monitoring point data and spatial correlation information, the areas in the monitoring area where data is not directly monitored are estimated. According to factors such as the distance between the surrounding monitoring points and the target area, and the strength of the correlation, a reasonable pollution value is assigned to the target area. The areas closer to the abnormal clustering center and with stronger correlation with the surrounding monitoring points are more affected by the abnormal clustering results, and the estimated pollution value is higher; otherwise, it is lower. In this way, the discrete monitoring data and abnormal clustering information are extended to the entire monitoring area to form a continuous pollution distribution model, so as to clearly distribute the pollution hotspots. These pollution hotspots are areas with relatively serious air pollution that require key attention and treatment, providing a key basis for subsequent tracing of air pollution diffusion paths and pollution prevention and control.

[0072] In a possible implementation manner, step S300 further includes:

[0073] Step S310: The high-precision sensor includes an FTIR spectrometer and a GC-MS gas analyzer.

[0074] Specifically, the high-precision sensors configured in pollution hotspots include FTIR spectrometers and GC-MS gas analyzers. FTIR spectrometer, or Fourier transform infrared spectrometer, analyzes the composition of substances by measuring the absorption of infrared rays of different wavelengths. In the atmospheric pollution monitoring scenario, qualitative and quantitative analysis of various organic and inorganic pollutants in the air of pollution hotspots can be performed, the types of pollutants can be identified based on the characteristic absorption peaks of different pollutants, and the concentration of pollutants can be determined by the intensity of the absorption peaks. GC-MS gas analyzer, or gas chromatography-mass spectrometry, first uses gas chromatography to separate the different components in the mixed gas, and then uses a mass spectrometer to accurately qualitatively and quantitatively detect the separated components. It has extremely high detection sensitivity for volatile organic pollutants and can effectively detect trace amounts of organic pollutants in the atmosphere. These two high-precision sensors play a key role in pollution hotspots, helping to obtain more accurate pollutant information.

[0075] In a possible implementation, step S300 further includes:

[0076] Step S310: Using pollution hotspots to establish independent collection attention.

[0077] Step S320: After the attention degree adjacent association compensation is performed on the independent collection attention degree, attention contamination collection is performed.

[0078] Specifically, first, based on the pollution hotspots identified by the previous operations of fixed threshold screening of time-series point monitoring data set anomalies, spatial interpolation, and point anomaly identification, the independent collection attention is constructed. Since the pollution status of these pollution hotspots is crucial for accurate tracing paths, when establishing independent collection attention, the severity of pollution in different parts of the pollution hotspots, pollution change trends, and spatial locations will be comprehensively considered. For areas with high pollution concentrations and large fluctuations, a higher collection attention is given, which means that the monitoring frequency and detail of the area will be increased in the future, and more abundant data will be obtained to accurately analyze the pollution situation; while for areas with relatively light pollution and relatively stable changes, a relatively low collection attention is given, but a certain monitoring intensity is still maintained. In this way, an independent collection attention system is established for pollution hotspots, making subsequent monitoring and collection work more targeted and efficient, and laying a solid foundation for accurately obtaining pollution data and accurately establishing three-dimensional data of pollution sites.

[0079] Due to the spatial diffusivity of pollution, the pollution situation in one area is closely related to adjacent areas. Therefore, it is necessary to consider the relationship between each monitoring area and its surrounding adjacent areas to perform adjacent correlation compensation for the independent collection attention. For example, if the independent collection attention of a certain area is originally high and there are also pollution signs in its adjacent areas, then based on the continuity of pollutant diffusion, the attention of this area should be further increased; conversely, if the pollution level in the adjacent area is low and the possibility of its pollution impact is small, then the adjustment range of the attention of this area is appropriately reduced. After completing the adjacent correlation compensation of attention, the attention pollution collection work begins. At this time, according to the adjusted attention, the monitoring resources are allocated targeted. For areas with high attention, increase the monitoring frequency and accuracy, use high-precision sensors for more detailed monitoring, such as using FTIR spectrometers and GC-MS gas analyzers to accurately analyze the pollutant components, and at the same time use monitoring drones to obtain data from different angles and heights; for areas with relatively low attention, maintain a certain monitoring intensity to ensure that potential pollution changes can be detected in a timely manner. Through this attention pollution collection method based on adjacent correlation compensation of attention, it is possible to obtain more comprehensive and accurate pollution data in pollution hotspots, provide strong support for establishing accurate three-dimensional pollution field data, and thus assist in the accurate tracing of subsequent atmospheric pollution diffusion paths.

[0080] In a possible implementation manner, step S600 further includes:

[0081] Step S650: Update and track the identification of candidate solutions through the particle fitness values of the global particle search results, and establish an update tracking identification result.

[0082] Step S660: Use the update tracking identification result to optimize the position of the candidate solution to complete the double-layer optimization of local inversion fitting.

[0083] Specifically, after completing the global particle search, a series of particle fitness values will be obtained. Based on these particle fitness values, the work aims to update and track the identification of candidate solutions and establish corresponding results. The particle fitness value reflects the degree of fit between the combination of pollution source parameters (such as pollution source location, emission intensity, emission time) represented by each particle and the actual pollution situation. Based on these fitness values, pay attention to the particles with higher fitness values because the candidate solutions corresponding to them are more likely to be close to the true pollution source parameters. By comparing the change trends of different particle fitness values, observe which candidate solutions show better adaptability changes during the search process, such as the fitness value gradually increasing or remaining at a high level within a certain range. Record these candidate solutions with good trends in detail, including information such as their parameter changes and spatial positions at different search stages, so as to establish an update tracking identification result.

[0084] The genetic algorithm is used to optimize the position of the candidate solution by utilizing the updated tracking recognition result, and complete the double-layer optimization of local inversion fitting. First, the candidate solutions in the updated tracking recognition result are regarded as individuals in the genetic algorithm, and the parameters such as the pollution source location, emission intensity, and emission time of each candidate solution are the genes of the individual. Then, population initialization is carried out, and a certain number of candidate solutions are selected from the updated tracking recognition result to form the initial population. In the evolutionary process of each generation, according to the fitness value of the individual (which can be determined by comparing the difference between the simulated pollutant distribution and the three-dimensional data of the pollution field, and the smaller the difference, the higher the fitness value), the selection operator is used to select better individuals. For example, the roulette wheel selection method is used, and the individuals with higher fitness are more likely to be selected. Then, crossover operation is performed on the selected individuals. Two individuals are randomly selected and part of their genes are exchanged to generate new candidate solutions, so as to simulate gene recombination in biological evolution and increase the diversity of the population. At the same time, mutation operation is performed on the individuals with a certain probability, and some genes of the individuals are randomly changed to avoid the algorithm falling into the local optimal solution. After multiple generations of evolution, the individuals in the population gradually develop in a better direction, that is, the positions of the candidate solutions are continuously optimized. When the preset termination conditions are met, such as the number of generations of evolution reaches the set value or the fitness value of the population no longer increases significantly, the optimal individual obtained at this time is the optimized candidate solution, and the double-layer optimization of local inversion fitting is successfully completed, providing a more accurate basis for accurately tracing the atmospheric pollution diffusion path.

[0085] Embodiment 2, based on the same inventive concept as the method for tracing the atmospheric pollution diffusion path based on meteorological data in the foregoing embodiment, as Figure 2 shown, the present application provides a system for tracing the atmospheric pollution diffusion path based on meteorological data. The system in the embodiments of the present application and the method embodiments are based on the same inventive concept. Among them, the system includes:

[0086] The high-density monitoring network establishment module 10 is used to establish a high-density monitoring network by connecting small air quality sensors using NB-IoT and LoRa.

[0087] The pollution hot spot area distribution module 20 is used to obtain the time-series point monitoring data set of the high-density monitoring network, screen the anomalies of the time-series point monitoring data set through a fixed threshold, and distribute the pollution hot spot areas based on spatial interpolation and point anomaly recognition results.

[0088] The three-dimensional pollution field data establishment module 30 is used to configure high-precision sensors and monitoring drones in the pollution hot spot area, perform pollution collection of interest, establish three-dimensional pollution field data, and synchronously obtain the wind force data set.

[0089] The state variable establishment module 40 is used to establish state variables and construct observation variables with the wind force data set and the three-dimensional pollution field data.

[0090] The candidate solution establishment module 50 is used to predict and fit a set of initial parameters based on an observation variable wind power data set by using an atmospheric diffusion model, generate a pollutant distribution, and perform inverse fitting by minimizing an error function between the pollutant distribution and three-dimensional data of a pollution field to establish a candidate solution, where the initial parameters are parameters set according to state variables.

[0091] The pollution diffusion path tracing result establishment module 60 is used to perform a global particle search on the candidate solution and perform a two-layer optimization of local inverse fitting according to the global particle search result to establish a pollution diffusion path tracing result.

[0092] Furthermore, the system is also used to implement the following functions:

[0093] Taking the candidate solution as the center, particles are evenly distributed to establish a candidate particle set, where each particle in the candidate particle set represents a pollution source parameter, and the pollution source parameter includes a pollution source location, an emission intensity, and an emission time; determining whether the update stage of the particle meets a preset stage threshold; if the update stage of the particle meets the preset stage threshold, updating the position of the candidate particle set through distance constraint and recording it in a regional exploration window; when the update stage of the particle does not meet the preset stage threshold, calling the exploration result of the regional exploration window to perform regional elimination identification, eliminating the corresponding particles of the candidate particle set by using the regional elimination identification result, and performing continuous update search according to the remaining particles to establish a global particle search result.

[0094] Furthermore, the system is also used to implement the following functions:

[0095] Predicting the pollutant distribution for each particle in the candidate particle set to establish a prediction result; calculating the weight of each particle according to the prediction result as follows: ; where represents the weight of particle , represents the actual observed pollutant concentration data obtained according to the three-dimensional data of the pollution field, represents particle 's simulated pollutant concentration, represents the standard deviation of the observation noise; taking the weight of the particle as the particle fitness value to perform position update of the candidate particle set.

[0096] Furthermore, the system is also used to implement the following functions:

[0097] Configuring a particle contraction factor according to the particle fitness value; creating an update interval based on the current particle position and the distance constraint; configuring a random perturbation amplitude, and performing position update of the candidate particle set according to the random perturbation amplitude, the particle contraction factor, and the update interval.

[0098] Furthermore, the system is also used to implement the following functions:

[0099] Obtain the flight trajectory of the monitoring drone, and calibrate the particle with the maximum fitness value in the retained particles as the standard particle; establish a trajectory influence compensation based on the flight trajectory and the standard particle; perform an update search constraint on the retained particles through the trajectory influence compensation.

[0100] Furthermore, the system is also used to implement the following functions:

[0101] Obtain the spatial data of the space covered by the high-density monitoring network, and read the retrospective wind force data; perform a spatial correlation analysis based on the spatial data and the retrospective wind force data; perform anomaly clustering on the point anomaly recognition results to establish an anomaly clustering result; use the anomaly clustering result and the spatial correlation analysis result for spatial interpolation to distribute the pollution hot spot areas.

[0102] Furthermore, the system is also used to implement the following functions:

[0103] The high-precision sensors include an FTIR spectrometer and a GC-MS gas analyzer.

[0104] Furthermore, the system is also used to implement the following functions:

[0105] Use the pollution hot spot areas to establish an independent collection attention; after performing an attention adjacent association compensation on the independent collection attention, perform a concerned pollution collection.

[0106] Furthermore, the system is also used to implement the following functions:

[0107] Perform an update tracking identification of the candidate solution through the particle fitness value of the global particle search result, and establish an update tracking identification result; use the update tracking identification result to optimize the position of the candidate solution to complete the double-layer optimization of local inversion fitting.

[0108] It should be noted that the above sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above describes specific embodiments of this specification. Additionally, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0109] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0110] This specification and the drawings are merely illustrative of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A method for tracing the diffusion path of atmospheric pollution based on meteorological data, characterized in that: The method comprises: Use NB-IoT and LoRa to connect small air quality sensors and establish a high-density monitoring network; Acquire the time-series point monitoring data set of the high-density monitoring network, filter the anomalies of the time-series point monitoring data set by a fixed threshold, and distribute the pollution hotspot areas based on the spatial interpolation and point anomaly identification results; High-precision sensors and monitoring drones are deployed in pollution hotspots to collect pollution data, establish three-dimensional data of pollution sites, and simultaneously obtain wind data sets; Establishing state variables, and constructing observation variables with the wind data set and the three-dimensional data of the pollution field; An atmospheric diffusion model is used to predict and fit a set of initial parameters to a wind data set based on observed variables to generate pollutant distribution, and an inversion fit is performed by minimizing the error function between the pollutant distribution and the three-dimensional data of the pollution field to establish a candidate solution. The initial parameters are parameters set according to the state variables, and the initial parameters include: pollution source location, emission intensity, and emission time; Performing a global particle search on the candidate solution, and performing a double-layer optimization of local inversion fitting based on the global particle search results to establish a pollution diffusion path tracing result; The performing a global particle search on the candidate solution comprises: Taking the candidate solution as the center, uniformly distributing particles to establish a candidate particle set, wherein each particle in the candidate particle set represents a pollution source parameter, and the pollution source parameter includes a pollution source location, emission intensity, and emission time; Determine whether the particle's update phase meets a preset phase threshold; If the update stage of the particle meets the preset stage threshold, the position of the candidate particle set is updated through the distance constraint and recorded in the area exploration window; When the update stage of the particle does not meet the preset stage threshold, the exploration result of the regional exploration window is called to perform regional elimination identification, the corresponding particles of the candidate particle set are eliminated using the regional elimination identification result, and the update search is continued based on the retained particles to establish a global particle search result.

2. The method for tracing the diffusion path of atmospheric pollution based on meteorological data according to claim 1, characterized in that: The updating of the position of the candidate particle set by the distance constraint also includes: Predict pollutant distribution for each particle in the candidate particle set and establish prediction results; The weight of each particle is calculated according to the prediction results, as follows: ； in, Characterizing particles The weight of Characterize the actual observed pollutant concentration data obtained from the three-dimensional data of the pollution site, Characterizing particles The simulated pollutant concentration is Characterizes the standard deviation of the observation noise; The weight of the particle is used as the particle fitness value to perform the position update of the candidate particle set.

3. The method for tracing the diffusion path of air pollution based on meteorological data according to claim 2, characterized in that: The method of using the particle weight as the particle fitness value to perform position update of the candidate particle set includes: configuring a particle shrinkage factor according to the particle fitness value; Creating an update interval based on the current particle position and the distance constraint; The random disturbance amplitude is configured, and the position of the candidate particle set is updated according to the random disturbance amplitude, the particle shrinkage factor, and the update interval.

4. The method for tracing the diffusion path of air pollution based on meteorological data according to claim 1, characterized in that: The continuing updating search according to the retained particles includes: Obtain the flight trajectory of the monitoring drone, and calibrate the particle with the maximum fitness value among the retained particles as the standard particle; Establishing trajectory impact compensation according to the flight trajectory and the standard particles; The updated search constraints for the retained particles are performed by the trajectory impact compensation.

5. The method for tracing the diffusion path of air pollution based on meteorological data according to claim 1, characterized in that: The distribution of pollution hotspot areas based on spatial interpolation and point anomaly identification results includes: Obtain spatial data of the space covered by the high-density monitoring network and read backtracking wind data; Performing spatial correlation analysis based on the spatial data and the retrospective wind data; Performing abnormality clustering on the point abnormality recognition results to establish abnormality clustering results; The abnormal clustering results and spatial correlation analysis results are used to perform spatial interpolation to distribute pollution hot spots.

6. The method for tracing the diffusion path of air pollution based on meteorological data according to claim 1, characterized in that: The high-precision sensors include a FTIR spectrometer and a GC-MS gas analyzer.

7. The method for tracing the diffusion path of air pollution based on meteorological data according to claim 1, characterized in that: The execution focuses on pollution collection and establishes three-dimensional data of the pollution field, including: Use pollution hotspots to establish independent collection attention; After the independent collection attention is compensated for the adjacent association of attention, attention contamination collection is performed.

8. The method for tracing the diffusion path of air pollution based on meteorological data according to claim 1, characterized in that: The double-layer optimization of performing local inversion fitting according to the global particle search results includes: Performing update tracking and identification of candidate solutions through the particle fitness values ​​of the global particle search results, and establishing an update tracking and identification result; The update tracking identification result is used to optimize the position of the candidate solution to complete the double-layer optimization of the local inversion fitting.

9. The atmospheric pollution diffusion path tracing system based on meteorological data is characterized by: The system is used to implement the atmospheric pollution diffusion path tracing method based on meteorological data according to any one of claims 1 to 8, and the system comprises: High-density monitoring network establishment module, used to connect small air quality sensors using NB-IoT and LoRa to establish a high-density monitoring network; A pollution hotspot area distribution module is used to obtain the time-series point monitoring data set of the high-density monitoring network, filter the anomalies of the time-series point monitoring data set through a fixed threshold, and distribute the pollution hotspot areas based on spatial interpolation and point anomaly identification results; The pollution site 3D data establishment module is used to configure high-precision sensors and monitoring drones in pollution hotspots, perform pollution collection, establish pollution site 3D data, and simultaneously obtain wind data sets; A state variable establishment module, used to establish state variables and construct observation variables with the wind data set and the pollution field three-dimensional data; A candidate solution establishment module is used to use an atmospheric diffusion model to perform a prediction fit of a set of initial parameters based on a wind data set of observed variables to generate a pollutant distribution, and to perform inversion fitting by minimizing an error function between the pollutant distribution and the three-dimensional data of the pollution field to establish a candidate solution, wherein the initial parameters are parameters set according to the state variables; The pollution diffusion path tracing result establishing module is used to perform a global particle search on the candidate solution, and perform a double-layer optimization of local inversion fitting based on the global particle search results to establish the pollution diffusion path tracing result.

Images