Atmospheric pollution monitoring method and device
Through the combination of principal component analysis, wavelet decomposition and Gaussian diffusion model, the problem of traditional air pollution monitoring methods neglecting the correlation and complex changes of pollutants is achieved, and more accurate and reliable air pollution monitoring is achieved.
Patent Information
- Application Number
- CN202510427268.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-07
- Publication Date
- 2025-06-17
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional air pollution monitoring methods ignore the correlation between pollutants and the complexity of pollutant concentrations over time and space, resulting in inaccurate and reliable monitoring results.
The principal component analysis algorithm is used to process the concentration data of atmospheric pollutant and screen out the concentration data of key pollutant; then, the wavelet decomposition algorithm is used to analyze the time characteristics, and the Gaussian diffusion model analyzes the spatial characteristics to fully reflect the situation of atmospheric pollution.
Through the dual consideration of time characteristics and spatial characteristics, the accuracy and reliability of air pollution monitoring are improved, and the overall situation of air pollution can be fully reflected.
Smart Images
Figure CN120161171A_ABST
Abstract
Description
Technical Field
[0001] This disclosure belongs to the technical field of atmospheric monitoring, and more specifically, relates to a method and device for monitoring air pollution. Background Art
[0002] Traditional air pollution monitoring methods often rely on the monitoring of the concentration of a single pollutant, ignoring the possible correlations between pollutants and the complexity of the variation of pollutant concentrations over time and space.
[0003] Therefore, accurately and reliably monitoring the air pollution situation has become one of the important contents in the field of environmental protection. Summary of the Invention
[0004] The purpose of this disclosure is to provide a method and device for monitoring air pollution to improve the accuracy and reliability of air pollution monitoring.
[0005] In the first aspect of the embodiments of this disclosure, a method for monitoring air pollution is provided, including: Processing the atmospheric pollutant concentration data based on the principal component analysis algorithm to obtain the target pollutant concentration data; Analyzing the target pollutant concentration data based on the wavelet decomposition algorithm to determine the time characteristics of the target pollutant concentration data; Determining the spatial characteristics of the target pollutant concentration data based on the Gaussian diffusion model; wherein both the time characteristics and the spatial characteristics of the target pollutant concentration data are the monitoring results of air pollution.
[0006] In the second aspect of the embodiments of this disclosure, a device for monitoring air pollution is provided, including: A target data acquisition module for processing the atmospheric pollutant concentration data based on the principal component analysis algorithm to obtain the target pollutant concentration data; A time characteristic determination module for analyzing the target pollutant concentration data based on the wavelet decomposition algorithm to determine the time characteristics of the target pollutant concentration data; A spatial characteristic determination module for determining the spatial characteristics of the target pollutant concentration data based on the Gaussian diffusion model; wherein both the time characteristics and the spatial characteristics of the target pollutant concentration data are the monitoring results of air pollution.
[0007] In the third aspect of the embodiments of this disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned method for monitoring air pollution are implemented.
[0008] In a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned air pollution monitoring method are implemented.
[0009] The beneficial effects of the air pollution monitoring method and device provided by the embodiments of the present disclosure are as follows: The present disclosure uses the principal component analysis algorithm to effectively screen out the key pollutant concentration data and remove redundant information. Subsequently, the wavelet decomposition algorithm enables the time characteristics of the monitoring data to be clearly presented, and both the change trend and periodic pattern of the pollutants can be accurately captured. At the same time, the introduction of the Gaussian diffusion model provides a scientific prediction for the diffusion of pollutants in space, making the monitoring results not limited to a certain time point or location, but able to comprehensively reflect the overall situation of air pollution. Therefore, by considering both the time characteristics and space characteristics, the present disclosure can improve the accuracy and reliability of air pollution monitoring. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.
[0011] Figure 1 It is a schematic flowchart of an air pollution monitoring method provided by an embodiment of the present disclosure; Figure 2 It is a structural block diagram of an air pollution monitoring device provided by an embodiment of the present disclosure; Figure 3 It is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0012] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present disclosure. However, those skilled in the art should clearly understand that the present disclosure can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present disclosure.
[0013] To make the objectives, technical solutions, and advantages of the present disclosure clearer, the following will be described through specific embodiments with reference to the drawings.
[0014] Please refer toFigure 1 , Figure 1 is a schematic flowchart of an air pollution monitoring method provided by an embodiment of the present disclosure. The method includes: S101: Process the air pollutant concentration data based on the principal component analysis algorithm to obtain the target pollutant concentration data.
[0015] In this embodiment, the principal component analysis (PCA) algorithm is a linear transformation method that converts the original air pollutant concentration data (i.e., multiple variables) into new variables (i.e., principal components / target pollutant concentration data) through linear combination. Considering the correlation between multiple air pollutant concentrations and the fact that not all of these variables play an equally important role in air pollution monitoring, processing the air pollutant concentration data through the PCA algorithm can obtain target pollutant concentration data that are independent of each other and retain as much original data information as possible.
[0016] The air pollutant concentration data are the concentration values of different pollutants obtained by setting up monitoring stations and other means in air environmental monitoring. Air pollutants can include sulfur dioxide (SO2), nitrogen dioxide (NO2), carbon monoxide (CO), ozone (O3), inhalable particulate matter (PM 10 ), and fine particulate matter (PM 2.5 ), etc. They can come from different monitoring stations and different time points, forming a multi-dimensional data set. At the same time, the sources of air pollutant concentration data are diverse and can include industrial emissions, vehicle exhaust, natural sources (such as vegetation emissions), and other human activities (such as agricultural activities, construction, etc.). Pollutants from different sources are mixed with each other, making the air pollutant concentration data show complex change patterns.
[0017] There is a correlation between air pollutants, and the correlation indicates the existence of redundant information in the data. The PCA algorithm can remove redundant information and determine the pollutants that truly make important contributions to air pollution, that is, the target pollutants.
[0018] The target pollutant concentration data are the concentration information of the pollutants that make the main contributions to air pollution screened out by the PCA algorithm. At the same time, after determining the target pollutant concentration data, the data dimension is simplified, and the analysis efficiency can be improved when analyzing air pollution subsequently.
[0019] S102: Analyze the target pollutant concentration data based on the wavelet decomposition algorithm to determine the time characteristics of the target pollutant concentration data.
[0020] In this embodiment, the wavelet decomposition algorithm is a signal processing technique that can decompose a complex signal into sub-signals of different scales and frequencies. By selecting an appropriate wavelet basis function, local analysis of the signal can be performed in both the time and frequency dimensions.
[0021] Let the target pollutant concentration data be a time series , where is the number of data points.
[0022] Wavelet decomposition is to select a wavelet basis function and a scaling function , and perform a layer of wavelet decomposition on the target pollutant concentration data
[0023] The time characteristics are the laws and characteristics presented by the target pollutant concentration data with the change of time. For example, periodic changes, trend changes, etc.
[0024] In this embodiment, the wavelet analysis algorithm decomposes the target pollutant concentration data into components of different frequencies, and then analyzes the changes of these components with time to determine the time characteristics such as periodicity and trend in the target pollutant concentration data.
[0025] S103: Determine the spatial characteristics of the target pollutant concentration data based on the Gaussian diffusion model; among them, the time characteristics of the target pollutant concentration data and the spatial characteristics of the target pollutant concentration data are both monitoring results of air pollution.
[0026] In this embodiment, the Gaussian diffusion model is a mathematical model used to describe the diffusion law of pollutants in the atmosphere, assuming that the concentration distribution of pollutants in the atmosphere conforms to the Gaussian distribution. This model considers the influence of the emission situation of the pollution source, meteorological conditions, etc. on the diffusion of pollutants, and calculates the concentration distribution of pollutants at different positions in space through corresponding formulas.
[0027] The spatial characteristics are the distribution characteristics and laws of the target pollutants in space, including the spatial distribution range of pollutant concentration, the position of high-concentration areas, and the gradient change of concentration, etc. For example, the concentration of pollutants is higher near the pollution source and gradually decreases with the increase of distance.
[0028] The monitoring results of air pollution are information about the air pollution situation obtained by integrating the time characteristics and spatial characteristics of the target pollutant concentration data, which is helpful to understand the degree, scope, change trend and possible influencing factors of air pollution, and provide a scientific basis for formulating subsequent air pollution prevention and control measures.
[0029] Specifically, in this embodiment, the Gaussian diffusion model is utilized to calculate the concentration distribution of the target pollutant in space by combining the emission information and meteorological information of the target pollutant, thereby determining its spatial characteristics. Meanwhile, by integrating the temporal characteristics of the target pollutant concentration data obtained from the previous analysis, the characteristics in the above two aspects are used as the final result of air pollution monitoring, comprehensively reflecting the status of air pollution.
[0030] As can be seen from the above, the present disclosure can effectively screen out the key pollutant concentration data and remove redundant information by using the principal component analysis algorithm. Subsequently, the wavelet decomposition algorithm enables the temporal characteristics of the monitoring data to be clearly presented, and both the change trend and periodic pattern of the pollutant can be accurately captured. Meanwhile, the introduction of the Gaussian diffusion model provides a scientific prediction for the diffusion of pollutants in space, making the monitoring results not limited to a certain time point or location, but able to comprehensively reflect the overall situation of air pollution. Therefore, by considering both the temporal characteristics and spatial characteristics, the present disclosure can improve the accuracy and reliability of air pollution monitoring.
[0031] In an embodiment of the present disclosure, the air pollutant concentration data includes concentration data of multiple types of pollutants; Based on the principal component analysis algorithm, the air pollutant concentration data is processed to obtain the target pollutant concentration data, including: Each type of pollutant concentration data is standardized to obtain multiple types of standard pollutant concentration data; Based on the multiple types of standard pollutant concentration data, a covariance matrix is determined; Based on the covariance matrix, multiple eigenvalues are determined; Based on the multiple eigenvalues, the target pollutant concentration data is determined.
[0032] In an embodiment of the present disclosure, each eigenvalue corresponds to a pollutant concentration data; Based on the multiple eigenvalues, determining the target pollutant concentration data includes: Based on each eigenvalue, a ranking is performed to determine the contribution rate of the multiple eigenvalues; Based on the contribution rate of each eigenvalue, a cumulative contribution rate is determined; If the cumulative contribution rate is greater than or equal to a preset contribution rate threshold, the target pollutant concentration data is determined based on the eigenvalue corresponding to the cumulative contribution rate.
[0033] In this embodiment, by setting multiple monitoring stations in the target area, the air pollutant concentration data of this area is obtained. The air pollutant concentration data includes multiple types of pollutant concentration data, which can include sulfur dioxide (SO2), nitrogen dioxide (NO2), carbon monoxide (CO), ozone (O3), inhalable particulate matter (PM 10 ) and fine particulate matter (PM 2.5) etc.
[0034] Specifically, the steps of processing the atmospheric pollutant concentration data based on the principal component analysis algorithm to obtain the target pollutant concentration data can be as follows: First, perform a standardization operation on the concentration data of each type of pollutant to convert it into standard data with the same scale and distribution, which can avoid the excessive amplification or reduction of the influence of certain variables in subsequent analyses due to the large differences in the dimensions and numerical ranges of the concentration data of different pollutants.
[0035] Suppose the atmospheric pollutant concentration data includes types of pollutants and is observed at different times (or monitoring points). Use the matrix to represent the atmospheric pollutant concentration data, where represents the concentration of the th observation time (or monitoring point) and the th type of pollutant, , .
[0036] Considering that recent data can better reflect the current atmospheric pollution situation than long-term data, let the weight of the th observation time be , and , then the calculation formulas for the weighted mean and the weighted standard deviation are as follows: The weighted mean is: ; The weighted standard deviation is:
[0037] The weighted standardization formula is: ; The concentration data of multiple types of standard pollutants can be the matrix .
[0038] Second, calculate the covariance between the concentration data of various types of standard pollutants to obtain the covariance matrix. The covariance matrix reflects the linear correlation between the concentrations of different pollutants, and the mutual relationship between various types of pollutants can be understood by analyzing the covariance matrix.
[0039] The covariance matrix is a matrix, and its element represents the covariance between the concentration data of the th and the th types of standard pollutants, and the calculation formula is: ; Then the covariance matrix 。
[0040] Third, perform eigenvalue decomposition on the covariance matrix, and multiple eigenvalues can be obtained. The magnitude of the eigenvalue represents the amount of original data information contained in each principal component. The larger the eigenvalue, the more important the corresponding principal component is.
[0041] Solve the covariance matrix of the characteristic equation:
[0042] where is the eigenvalue to be solved, is the identity matrix of. The above equation is a -th degree polynomial equation about . Solving this equation can obtain eigenvalues , arrange them in descending order, that is .
[0043] Fourth, calculate the contribution rate of each eigenvalue .
[0044] .
[0045] Fifth, calculate the cumulative contribution rate .
[0046] , .
[0047] Determine the preset contribution rate threshold, and find the smallest such that the preset contribution rate threshold, and select the first eigenvalues corresponding principal components. The pollutant concentration data corresponding to this principal component is the target pollutant concentration data.
[0048] Specifically, determining the preset contribution rate threshold includes: If the correlation of the atmospheric pollutant concentration data is less than the first correlation threshold, then select any cumulative contribution rate greater than or equal to the first cumulative contribution rate as the preset contribution rate threshold; If the correlation of the atmospheric pollutant concentration data is greater than or equal to the first correlation threshold, then select any cumulative contribution rate less than the first cumulative contribution rate and greater than or equal to the second cumulative contribution rate as the preset contribution rate threshold; where the first cumulative contribution rate is greater than the second cumulative contribution rate.
[0049] The first correlation threshold can be set according to the complexity of the source of atmospheric pollutant concentration data. Considering the correlation of atmospheric pollutant concentration data, that is, when the degree of mutual correlation of multi-category pollutant concentration data is less than the first correlation threshold, a relatively high preset contribution rate threshold needs to be set to ensure that enough principal components are extracted to accurately describe the atmospheric pollution situation.
[0050] The first cumulative contribution rate and the second cumulative contribution rate can be dynamically adjusted according to the actual situation.
[0051] Considering that the cumulative contribution rate cannot be too low, otherwise it will not play the role of principal component screening, so it is necessary to set the second cumulative contribution rate as the lowest reference. For example, the first cumulative contribution rate can be 90%, and the second cumulative contribution rate can be 80%.
[0052] Or, determining the preset contribution rate threshold includes: If the data volume of the atmospheric pollutant concentration data is less than the first quantity, then select any cumulative contribution rate greater than or equal to the third cumulative contribution rate as the preset contribution rate threshold; If the data volume of the atmospheric pollutant concentration data is greater than or equal to the first quantity, then select any cumulative contribution rate less than the third cumulative contribution rate and greater than or equal to the fourth cumulative contribution rate as the preset contribution rate threshold; Wherein, the third cumulative contribution rate is greater than the fourth cumulative contribution rate.
[0053] Considering that in the case of a small data volume, each data point is relatively more important, and losing a part of the principal components can have a greater impact on the result. At this time, a relatively large cumulative contribution rate needs to be selected as the preset contribution rate threshold.
[0054] It can be concluded from the above that in this embodiment, through the principal component analysis algorithm, first, the concentration data of various pollutants are standardized to ensure the comparability between data. Then, by constructing the covariance matrix and solving the eigenvalues, the main components in the data can be identified. Based on the contribution rate of the eigenvalues for sorting and accumulation, when the cumulative contribution rate reaches the preset threshold, the most representative target pollutant concentration data can be screened out. This embodiment not only simplifies the complex atmospheric pollution data, but also improves the accuracy and efficiency of data analysis.
[0055] In an embodiment of the present disclosure, based on the wavelet decomposition algorithm, the target pollutant concentration data is analyzed to determine the time characteristics of the target pollutant concentration data; Based on the periodic fluctuation characteristics of the target pollutant concentration data, the wavelet basis function is determined; Based on the frequency characteristics of the target pollutant concentration data, the decomposition level is determined; Based on the wavelet basis function and the decomposition level, the target pollutant concentration data is wavelet decomposed to obtain wavelet coefficients; Determine the time characteristics of the target pollutant concentration data based on wavelet coefficients.
[0056] In an embodiment of the present disclosure, determining the time characteristics of the target pollutant concentration data based on wavelet coefficients includes: Perform threshold processing on the wavelet coefficients to determine the target wavelet coefficients; Extract features from the target wavelet coefficients to determine the distribution under multiple scales; Analyze the distribution under multiple scales to determine the time characteristics of the target pollutant concentration data.
[0057] In this embodiment, the periodic fluctuation characteristic means that the target pollutant concentration data has a certain regularity over time. The wavelet basis function is the function used to transform the signal in wavelet decomposition. Different wavelet basis functions have different characteristics, and it is necessary to select a suitable wavelet basis function according to the data characteristics to better analyze the signal. The frequency characteristic is the distribution characteristic of the data on different frequency components, which reflects the speed of data change. The high-frequency part corresponds to the rapid change of the data, and the low-frequency part corresponds to the slow change of the data. The decomposition level is the number of times the signal is decomposed into multiple levels in the wavelet decomposition process. The decomposition level determines the fineness of the analysis. The more levels, the deeper the detailed analysis of the signal, but the greater the computational amount.
[0058] Threshold processing is used to remove noise or unimportant information and highlight key features. The target wavelet coefficients are the wavelet coefficients retained after threshold processing. Feature extraction is to extract information from the target wavelet coefficients that can reflect the data characteristics, such as the mean, variance, energy, etc. of the coefficients at different scales, so as to describe the distribution of the data at different scales. The distribution under multiple scales is the distribution state of the characteristics of the target pollutant concentration data at different scales after wavelet decomposition. Different scales correspond to different time scales or frequency ranges, which helps to comprehensively understand the change law of the data at different levels.
[0059] Specifically, the steps of this embodiment can be as follows: First, according to the periodic fluctuation law presented by the target pollutant concentration data, select a matching wavelet basis function. For example, if the data has obvious short-period fluctuations, a wavelet basis function with good localization characteristics can be selected to more accurately capture these periodic features.
[0060] Second, determine the wavelet decomposition level according to the complexity of different frequency components in the target pollutant concentration data and the analysis requirements.
[0061] Determining the decomposition level based on the frequency characteristics of the target pollutant concentration data includes: If the complexity of the data frequency components is greater than or equal to a preset complexity, select the second number of layers as the number of layers for wavelet decomposition; If the complexity of the data frequency components is less than the preset complexity, select the third number of layers as the number of layers for wavelet decomposition; Among them, the second number is greater than the third number.
[0062] If the data frequency components are complex, more layers are needed to analyze each frequency component in detail; if the simple features of the low-frequency or high-frequency part are mainly concerned, fewer layers can be selected.
[0063] Third, use the selected wavelet basis function and the number of decomposition layers to perform wavelet decomposition operations on the target pollutant concentration data, and convert the data into wavelet coefficients at different scales and frequencies. The above coefficients contain the information of the data at each scale and frequency.
[0064] Fourth, set an appropriate threshold to screen the wavelet coefficients, remove those coefficients below the threshold, and the remaining ones are the target wavelet coefficients, which are more critical for subsequent analysis of time characteristics.
[0065] Considering the characteristic differences of wavelet coefficients at different scales, the threshold can be dynamically adjusted in an iterative manner, and the continuity of the coefficients can be maintained during the threshold processing to reduce the deviation.
[0066] Let the threshold of the th iteration be , the initial threshold be , the th wavelet coefficient of the th layer be ; The expression of the adaptive weight function is:
[0067] Among them, is the total number of wavelet coefficients of the th layer, and is the summation index variable. This weight function reflects the magnitude relationship of the current coefficient relative to other coefficients in this layer; Then, iteratively update the threshold:
[0068] Among them, is a parameter that controls the iteration step size, and its value range is between ; Finally, the calculation formula of the processed wavelet coefficients (i.e., the target wavelet coefficients) is:
[0069] Among them, is the sign function, is a very small positive number, for example , which is used to avoid the case where the denominator is zero.
[0070] Fifth, extract features such as mean, variance, and energy from the target wavelet coefficients to describe the distribution characteristics of the data at different scales, and understand the variation laws of the data at different time scales or frequency ranges.
[0071] Sixth, comprehensively analyze the distribution characteristics at different scales, and find out the time characteristics such as periodicity, trend, and mutation points of the data. For example, by observing the distribution of the coefficient energy at different scales, judge at which time scales there are significant changes in the data, so as to determine the time characteristics.
[0072] Periodicity analysis can be carried out by observing the energy distribution of the target wavelet coefficients at different scales. If the energy is concentrated at specific periodic positions at a certain scale, it indicates that the data has corresponding periodicity. At the same time, the period can be further determined by calculating the autocorrelation function of the wavelet coefficients at this scale.
[0073] Trend analysis can be carried out by analyzing the change trend of the approximation coefficients. If the approximation coefficients increase or decrease monotonically with time, it indicates that the data has an upward or downward trend.
[0074] Mutation point detection is to find points with large amplitudes in the detail coefficients, and these points can correspond to the mutation points of the target pollutant concentration data. If the absolute value of the detail coefficient is greater than or equal to the first threshold, the corresponding point is taken as the mutation point, where the first threshold is set according to experience.
[0075] It can be concluded from the above that in this embodiment, by identifying the periodic fluctuations of the data, selecting the matching wavelet basis function, and reasonably determining the decomposition level in combination with the frequency characteristics, the accuracy of the analysis is effectively improved. The wavelet coefficients obtained after wavelet decomposition, through threshold processing and feature extraction, clearly show the distribution of the data at multiple scales, and further reveal the time characteristics of the target pollutant concentration data.
[0076] In an embodiment of the present disclosure, determining the spatial characteristics of the target pollutant concentration data based on the Gaussian diffusion model includes: Determine the pollution source information data and meteorological data of the target pollutant concentration data; Determine the diffusion coefficients of the Gaussian diffusion model, and the diffusion coefficients include horizontal diffusion coefficients and vertical diffusion coefficients; Input the pollution source information data, meteorological data and diffusion coefficients into the Gaussian diffusion model to obtain the spatial characteristics of the target pollutant concentration data.
[0077] In this embodiment, the pollution source information data is various information about the pollution source, such as the location of the pollution source (such as longitude and latitude coordinates), the emission rate of pollutants (i.e., the mass of pollutants emitted per unit time), and the emission height (such as the vertical height at which the pollution source emits pollutants), etc. The above data is the key to determining the initial conditions of pollutant diffusion.
[0078] The meteorological data is meteorological-related information that has an important impact on pollutant diffusion, and may include wind speed, wind direction, atmospheric stability, and mixing layer height, etc. Different meteorological conditions will significantly change the diffusion mode of pollutants. Among them, atmospheric stability can characterize the strength of vertical movement of the atmosphere and affect the vertical diffusion of pollutants.
[0079] The diffusion coefficient is a parameter for the diffusion ability of pollutants in the atmosphere, and is divided into a horizontal diffusion coefficient and a vertical diffusion coefficient. The horizontal diffusion coefficient is the degree of diffusion of pollutants in the horizontal direction (i.e., perpendicular to the wind direction); the vertical diffusion coefficient is the diffusion ability of pollutants in the vertical direction.
[0080] Let the concentration of the target pollutant be , where , , are spatial coordinates respectively.
[0081] The pollution source information data may include: The pollution source location is , where , are horizontal coordinates, is the emission height; The pollutant emission rate is .
[0082] The meteorological data may include: The average wind speed is , and the wind direction is denoted as the angle with the axis; The atmospheric stability parameter is denoted as F; The mixing layer height is E.
[0083] The horizontal diffusion coefficient and the vertical diffusion coefficient are functions of the downwind distance , where is the distance along the wind direction from the pollution source to the calculation point.
[0084] For the horizontal diffusion coefficient : If the wind direction distance is less than or equal to the first preset distance threshold, the horizontal diffusion coefficient is calculated by the first formula; If the wind direction distance is greater than the first preset distance threshold, the lateral diffusion coefficient is calculated using the second formula; Among them, the parameters of the first formula and the second formula are different. The first formula can be a linear equation with one variable, and the second formula can be a power function equation.
[0085] For the vertical diffusion coefficient : If the wind direction distance is less than or equal to the second preset distance threshold, the lateral diffusion coefficient is calculated using the third formula; If the wind direction distance is greater than the second preset distance threshold, the lateral diffusion coefficient is calculated using the fourth formula; Among them, the parameters of the third formula and the fourth formula are different. The third formula can be a linear equation with one variable, and the fourth formula can be a power function equation. At the same time, the parameters of the first formula and the third formula are also different, and the parameters of the second formula and the fourth formula are also different.
[0086] Considering the change of pollution source emissions, the time factor is introduced to reflect the dynamic change of pollution source emissions; Considering the influence of wind shear, in the atmosphere, the wind speed and direction change with height, that is, there is wind shear. In order to consider the influence of wind shear, the average wind speed is changed to a function of the wind speed changing with height . , where is the wind speed at the reference height , is an index related to the surface roughness.
[0087] The formula of the Gaussian diffusion model is:
[0088] The above formula considers the emission rate of the pollution source, the wind speed, the lateral diffusion coefficient, the vertical diffusion coefficient, as well as the spatial coordinates and the pollution source emission height. By substituting the pollution source information data, meteorological data, and diffusion coefficient determined previously, the concentration of the target pollutant at any position in space can be calculated , so as to obtain the spatial characteristics of the target pollutant concentration data.
[0089] It can be concluded from the above that this embodiment is based on the pollution source information data and the implemented meteorological data, and determines the lateral diffusion coefficient and the vertical diffusion coefficient, enabling the model to accurately predict the diffusion path and concentration distribution of pollutants. At the same time, the spatial characteristics of the target pollutant concentration data visually display the diffusion trend and influence range of pollutants, providing strong data support for environmental protection and pollution control.
[0090] In one embodiment of the present disclosure, the spatial characteristics of the target pollutant concentration data include the concentration distribution of the target pollutant concentration data in space; An air pollution monitoring method includes: Determine the concentration mean value of the target pollutant concentration data based on the concentration distribution of the target pollutant concentration data in space; If the concentration mean value is greater than or equal to a preset concentration threshold, the area corresponding to the concentration mean value is regarded as a polluted area; If the concentration mean value is less than the preset concentration threshold, the area corresponding to the concentration mean value is regarded as a non-polluted area.
[0091] In this embodiment, the concentration distribution of the target pollutant concentration data in space is the concentration change state of the target pollutant within the entire spatial range. For example, within a certain area, where the concentration is high and where it is low, and whether the change in concentration is gentle or drastic, etc.
[0092] The concentration mean value is a numerical value obtained by averaging the concentration values of the target pollutant concentration data within a certain area, reflecting the overall average level of the target pollutant concentration in this area. The preset concentration threshold is a concentration critical value preset for judging the pollution degree.
[0093] When the calculated concentration mean value is greater than or equal to the preset concentration threshold, it indicates that the average concentration of the target pollutant in this area is relatively high and has reached a level that may have an adverse impact on the environment and human health. Therefore, this area is designated as a polluted area.
[0094] If the concentration mean value is less than the preset concentration threshold, it means that the average concentration of the target pollutant in this area is relatively low and meets the environmental quality requirements. Therefore, it is determined as a non-polluted area.
[0095] It can be concluded from the above that in this embodiment, by analyzing the concentration distribution of the target pollutant concentration data in space, a comprehensive view of the pollutant concentration can be obtained. Then, the concentration mean value is calculated and compared with the preset concentration threshold. If the concentration mean value reaches or exceeds the threshold, this area is determined as a polluted area and needs to be closely monitored and corresponding treatment measures are taken; if the concentration mean value is lower than the threshold, this area is regarded as a non-polluted area and the environmental condition is relatively good. This embodiment not only improves the monitoring efficiency but also provides a scientific basis for environmental protection decision-making.
[0096] Corresponding to the air pollution monitoring method in the above embodiment, Figure 2 This is a structural block diagram of an air pollution monitoring device provided by an embodiment of the present disclosure. For the sake of convenience of description, only the parts related to the embodiments of the present disclosure are shown. Refer to Figure 2, the air pollution monitoring device 20 includes: a target data acquisition module 21, a time feature determination module 22, and a space feature determination module 23.
[0097] Among them, the target data acquisition module 21 is used to process the air pollutant concentration data based on the principal component analysis algorithm to obtain the target pollutant concentration data; The time feature determination module 22 is used to analyze the target pollutant concentration data based on the wavelet decomposition algorithm to determine the time feature of the target pollutant concentration data; The space feature determination module 23 is used to determine the space feature of the target pollutant concentration data based on the Gaussian diffusion model; Among them, both the time feature of the target pollutant concentration data and the space feature of the target pollutant concentration data are the monitoring results of air pollution.
[0098] In an embodiment of the present disclosure, the air pollutant concentration data includes multiple types of pollutant concentration data; The target data acquisition module 21 is specifically used to perform standardization processing on each type of pollutant concentration data to obtain multiple types of standard pollutant concentration data; Determine the covariance matrix based on the multiple types of standard pollutant concentration data; Determine multiple eigenvalues based on the covariance matrix; Determine the target pollutant concentration data based on the multiple eigenvalues.
[0099] In an embodiment of the present disclosure, each eigenvalue corresponds to a pollutant concentration data; The target data acquisition module 21 is specifically further used to sort based on each eigenvalue to determine the contribution rate of the multiple eigenvalues; Determine the cumulative contribution rate based on the contribution rate of each eigenvalue; If the cumulative contribution rate is greater than or equal to a preset contribution rate threshold, then determine the target pollutant concentration data based on the eigenvalue corresponding to the cumulative contribution rate.
[0100] In an embodiment of the present disclosure, the time feature determination module 22 is specifically used to determine the wavelet basis function based on the periodic fluctuation feature of the target pollutant concentration data; Determine the decomposition level based on the frequency feature of the target pollutant concentration data; Perform wavelet decomposition on the target pollutant concentration data based on the wavelet basis function and the decomposition level to obtain wavelet coefficients; Determine the time feature of the target pollutant concentration data based on the wavelet coefficients.
[0101] In an embodiment of the present disclosure, the time feature determination module 22 is specifically further used to perform threshold processing on the wavelet coefficients to determine the target wavelet coefficients; Extract features from the target wavelet coefficients to determine the distribution at multiple scales; Analyze the distribution at multiple scales to determine the time characteristics of the target pollutant concentration data.
[0102] In an embodiment of the present disclosure, the spatial feature determination module 23 is specifically configured to determine the pollution source information data and meteorological data of the target pollutant concentration data; Determine the diffusion coefficients of the Gaussian diffusion model, where the diffusion coefficients include the lateral diffusion coefficient and the vertical diffusion coefficient; Input the pollution source information data, meteorological data, and diffusion coefficients into the Gaussian diffusion model to obtain the spatial features of the target pollutant concentration data.
[0103] In an embodiment of the present disclosure, the spatial features of the target pollutant concentration data include the concentration distribution of the target pollutant concentration data in space; An air pollution monitoring device 20 further includes: a pollution area determination module; The pollution area determination module is configured to determine the concentration mean of the target pollutant concentration data based on the concentration distribution of the target pollutant concentration data in space; If the concentration mean is greater than or equal to the preset concentration threshold, the area corresponding to the concentration mean is used as the pollution area; If the concentration mean is less than the preset concentration threshold, the area corresponding to the concentration mean is used as the non-pollution area.
[0104] See Figure 3 , Figure 3 is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. As Figure 3 shown, the electronic device 300 in this embodiment may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The above-mentioned processors 301, input devices 302, output devices 303, and memories 304 communicate with each other through a communication bus 305. The memory 304 is used to store computer programs, and the computer programs include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. Among them, the processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above device embodiments, such as Figure 2 the functions of the modules 21 to 23 shown.
[0105] It should be understood that in the embodiments of the present disclosure, the so-called processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0106] The input device 302 may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the direction information of the fingerprint of the user), a microphone, etc., and the output device 303 may include a display (such as an LCD), a speaker, etc.
[0107] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A part of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.
[0108] In specific implementation, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present disclosure may implement the implementation manners described in the first embodiment and the second embodiment of an air pollution monitoring method provided by the embodiments of the present disclosure, and may also implement the implementation manner of the electronic device described in the embodiments of the present disclosure, which will not be elaborated herein.
[0109] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, all or part of the processes in the methods of the above embodiments are implemented. It can also be completed by instructing relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.
[0110] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as the hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk equipped on the electronic device, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer-readable storage medium can also include both the internal storage unit and the external storage device of the electronic device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store the data that has been output or will be output.
[0111] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.
[0112] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described electronic devices and units can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0113] In several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection to each other can be an indirect coupling or communication connection through some interfaces or units, or can also be an electrical, mechanical or other form of connection.
[0114] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can also be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present disclosure.
[0115] In addition, each functional unit in various embodiments of the present disclosure can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.
[0116] The above is only the specific implementation manner of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of various equivalent modifications or replacements, and these modifications or replacements should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.
Claims
1. A method for monitoring air pollution, characterized in that: include: The atmospheric pollutant concentration data is processed based on the principal component analysis algorithm to obtain the target pollutant concentration data; Analyzing the target pollutant concentration data based on a wavelet decomposition algorithm to determine the time characteristics of the target pollutant concentration data; Determine the spatial characteristics of the target pollutant concentration data based on a Gaussian diffusion model; Among them, the time characteristics of the target pollutant concentration data and the spatial characteristics of the target pollutant concentration data are both monitoring results of air pollution.
2. The air pollution monitoring method according to claim 1, characterized in that: The atmospheric pollutant concentration data includes multiple types of pollutant concentration data; The method of processing the atmospheric pollutant concentration data based on the principal component analysis algorithm to obtain the target pollutant concentration data includes: Standardize the concentration data of each type of pollutant to obtain multiple types of standard pollutant concentration data; Determining a covariance matrix based on the multiple types of standard pollutant concentration data; determining a plurality of eigenvalues based on the covariance matrix; The target pollutant concentration data is determined based on the plurality of characteristic values.
3. A method for monitoring air pollution according to claim 2, characterized in that: Each characteristic value corresponds to a pollutant concentration data; The determining the target pollutant concentration data based on the multiple characteristic values comprises: Sorting is performed based on each eigenvalue to determine the contribution rate of multiple eigenvalues; Determine the cumulative contribution rate based on the contribution rate of each eigenvalue; If the cumulative contribution rate is greater than or equal to a preset contribution rate threshold, the target pollutant concentration data is determined based on the characteristic value corresponding to the cumulative contribution rate.
4. The air pollution monitoring method according to claim 1, characterized in that: The target pollutant concentration data is analyzed based on a wavelet decomposition algorithm to determine the time characteristics of the target pollutant concentration data; Determining a wavelet basis function based on the periodic fluctuation characteristics of the target pollutant concentration data; Determining the number of decomposition layers based on the frequency characteristics of the target pollutant concentration data; Performing wavelet decomposition on the target pollutant concentration data based on the wavelet basis function and the decomposition layer number to obtain wavelet coefficients; The temporal characteristics of the target pollutant concentration data are determined based on the wavelet coefficients.
5. An air pollution monitoring method as claimed in claim 4, characterized in that: The determining the time characteristics of the target pollutant concentration data based on the wavelet coefficients includes: Performing threshold processing based on the wavelet coefficients to determine target wavelet coefficients; Extracting features of the target wavelet coefficients to determine their distribution at multiple scales; The distribution conditions at the multiple scales are analyzed to determine the temporal characteristics of the target pollutant concentration data.
6. The air pollution monitoring method according to claim 1, characterized in that: The determining of the spatial characteristics of the target pollutant concentration data based on the Gaussian diffusion model includes: Determine the pollution source information data and meteorological data of the target pollutant concentration data; Determining a diffusion coefficient of the Gaussian diffusion model, wherein the diffusion coefficient includes a lateral diffusion coefficient and a vertical diffusion coefficient; The pollution source information data, the meteorological data and the diffusion coefficient are input into the Gaussian diffusion model to obtain the spatial characteristics of the target pollutant concentration data.
7. An air pollution monitoring method as claimed in claim 6, characterized in that: The spatial characteristics of the target pollutant concentration data include the concentration distribution of the target pollutant concentration data in space; The air pollution monitoring method comprises: Determining a concentration mean of the target pollutant concentration data based on the concentration distribution of the target pollutant concentration data in space; If the concentration mean is greater than or equal to a preset concentration threshold, the area corresponding to the concentration mean is regarded as a contaminated area; If the concentration mean is less than a preset concentration threshold, the area corresponding to the concentration mean is regarded as a non-polluted area.
8. An air pollution monitoring device, characterized in that: include: A target data acquisition module is used to process the atmospheric pollutant concentration data based on the principal component analysis algorithm to obtain target pollutant concentration data; A time characteristic determination module, used to analyze the target pollutant concentration data based on a wavelet decomposition algorithm to determine the time characteristics of the target pollutant concentration data; A spatial feature determination module, used to determine the spatial features of the target pollutant concentration data based on a Gaussian diffusion model; Among them, the time characteristics of the target pollutant concentration data and the spatial characteristics of the target pollutant concentration data are both monitoring results of air pollution.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.