Method and system for predicting atmospheric pollutant concentration based on meteorological element correlation analysis

Abstract

The invention provides a method and system for predicting the concentration of atmospheric pollutants based on meteorological element correlation analysis, and the method comprises the steps: carrying out the refined analysis of product data resources based on an atmospheric environment, extracting the multi-source meteorological historical monitoring data of the atmospheric environment, and carrying out the preprocessing of the data, including atmospheric pollutant elements and meteorological elements; establishing an atmospheric pollutant single-element time sequence according to the preprocessed atmospheric environment multi-source meteorological historical monitoring data; estimating a regression coefficient by using a least square method, determining relevance between each meteorological element and each pollutant, and calculating a meteorological element influence factor coefficient; constructing a hybrid model based on the meteorological factor influence factor coefficients; performing atmospheric pollutant index prediction through the mixed model; and receiving current user input, generating atmospheric pollutant concentration prediction information matched with the current user input, and performing visual analysis display. According to the invention, the accuracy and visualization effect of atmospheric pollutant concentration prediction are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of atmospheric environment monitoring and analysis technology, and in particular to a method, system, equipment and medium for predicting atmospheric pollutant concentrations based on meteorological element correlation analysis. Background Art

[0002] With the acceleration of industrialization and the development of urbanization, the problem of air pollution has become increasingly prominent. In order to effectively control and manage air pollution, it is necessary to accurately monitor and predict the concentration trend of air pollutants. Especially in the process of implementing artificial weather modification operations (artificial weather modification operations), how to evaluate the impact of these activities on air quality is particularly important.

[0003] In the related technology, in terms of meteorological data forecasting, the ARIMA model (autoregressive integrated moving average model) can capture the characteristics and trends of time series, thereby predicting future meteorological data. However, for the reprocessing and forecasting of the refined analysis products of meteorological monitoring atmospheric environment in human shadow operations, the meteorological monitoring data in human shadow operations often have complex variability and randomness. When processing such data, the ARIMA model may not be able to accurately handle its changing patterns and characteristics. In addition, the traditional ARIMA model does not consider the impact of meteorological factors on pollutants in forecasting, which limits the accuracy of the forecast results, and thus cannot accurately express the data analysis results through visualization. Summary of the invention

[0004] The present invention provides a method, system, device and medium for predicting the concentration of atmospheric pollutants based on meteorological element correlation analysis, which solves the problem of how to improve the accuracy and visualization of atmospheric pollutant concentration analysis and prediction in the related art.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions:

[0006] In a first aspect, a method for predicting atmospheric pollutant concentrations based on meteorological element correlation analysis is provided, comprising:

[0007] Based on the atmospheric environment refined analysis product data resources, extract and preprocess the atmospheric environment multi-source meteorological historical monitoring data; the atmospheric environment multi-source meteorological historical monitoring data includes atmospheric pollutant elements and meteorological elements;

[0008] Based on the pre-processed atmospheric environment multi-source meteorological historical monitoring data, the single-element time series of atmospheric pollutants is established;

[0009] Use the least squares method to estimate the regression coefficient, determine the correlation between each meteorological element and each pollutant, and calculate the coefficient of the meteorological element influencing factor;

[0010] Based on the coefficients of meteorological element influencing factors, a hybrid model is constructed; and the atmospheric pollutant index is predicted by the hybrid model;

[0011] Receive current user input and generate atmospheric pollutant concentration prediction information and visual analysis display that matches the current user input.

[0012] In a first possible implementation of the first aspect, the multi-source meteorological historical monitoring data of the atmospheric environment includes daily and hourly data of sulfur dioxide, nitrogen dioxide, ozone, carbon monoxide, PM10, PM2.5, atmospheric pressure, temperature, humidity, wind speed, and wind direction.

[0013] Based on the first possible implementation manner of the first aspect, in a second possible implementation manner of the first aspect, the meteorological element impact factor coefficient is the impact factor coefficient of each meteorological element on air pollution at the current time:

[0014] The following expression (1) is used for calculation:

[0015]

[0016] in, is the coefficient of the impact of each meteorological element on air pollution; x i1 、x i2 …,x in are various meteorological elements, including temperature, humidity, wind speed, wind direction and other meteorological elements; b0, b1, b2…, b n The regression coefficients are estimated by the least squares method; the goal of the least squares method is to make the observed value y i With the predicted value The sum of squared errors between minimum, where m is the number of observed sample meteorological elements.

[0017] Based on the second possible implementation of the first aspect, in a third possible implementation of the first aspect, an atmospheric pollutant index is predicted by a hybrid model, specifically including: calculation of trend prediction values ​​of atmospheric environmental elements; calculation of the relationship between data and past noise; and prediction calculation of the atmospheric pollutant index.

[0018] Based on the third possible implementation manner of the first aspect, in a fourth possible implementation manner of the first aspect,

[0019] The following expression (2) is used to calculate the trend forecast value of each atmospheric environmental element at the current time point:

[0020]

[0021] Among them, Y tis the observed value of the single element time series data of the atmospheric environment at time t; Y t-p It is the measured value of each time point p forward from the current time, where p is the p time points in the past; arrive is the relationship coefficient between the current value and the value at the past p time points to the present; δ t is the error term at time point t; c is a constant term;

[0022] The following expression (3) is used to calculate the relationship between the data at the current time point and the past noise:

[0023] P t =μ+∈ t +θ1∈ t-1 +θ2∈ t-2 +θ3∈ t-3 +…+θ q ∈ t-q (3)

[0024] Among them, P t is the time series of the single element of the atmospheric environment related to the past noise, the observed value at time t; μ is the mean of the time series, which is the same for all time points; ∈ t ,∈ t-1 ,…∈ t-q are white noise terms, which are the white noise corresponding to the current time point; θ1, θ2,…,θ q Each one corresponds to a white noise influence degree term, which is the influence degree of the corresponding white noise on the current time point; q is the order, indicating how many past white noise terms are included in the calculation model;

[0025] The air pollutant index prediction and calculation specifically includes:

[0026] Calculate the predicted value of each atmospheric environmental factor at the current time point; use the following expression (4) to calculate the predicted value of each atmospheric environmental factor at the current time point:

[0027]

[0028] Among them, C t Prediction value data for each air pollutant element; is the coefficient of the impact factor of each meteorological element on air pollution;

[0029] The sub-index of each pollutant is calculated according to the predicted value of the atmospheric environmental element; the sub-index of each pollutant is calculated using the following expression (5):

[0030] (I t ):

[0031] Among them, C t is the predicted concentration, S t is the standard concentration;

[0032] The comprehensive index is calculated based on the weighted sub-index of each pollutant; the calculation is performed using the following expression (6):

[0033]

[0034] Among them, I w To predict the comprehensive index of air pollutants; W CO , W PM10 , W PM2.5 is the weight coefficient of each air pollutant, and the sum of the weights is 1; I CO , I PM10 , I PM2.5 It is a sub-index for each pollutant.

[0035] In a fifth possible implementation manner of the first aspect, the visual analysis display includes:

[0036] Correlation diagram between air pollutant concentration and air pressure / temperature / wind speed;

[0037] Relationship between artificial rainfall and the total amount of air pollutants reduced;

[0038] Spatial distribution map of atmospheric pollutant concentrations;

[0039] Predicted trend of atmospheric pollutant concentrations.

[0040] Based on any possible implementation manner of the first aspect, in a fifth possible implementation manner of the first aspect,

[0041] Before using the least squares method to estimate the regression coefficient, determine the correlation between each meteorological element and each pollutant, and calculate the coefficient of the meteorological element influencing factor, perform the following steps:

[0042] Determine whether the single-element time series of atmospheric pollutants is a stationary series; if it is a non-stationary series, perform differential operations on the single element of atmospheric pollutants to convert it into a stationary time series.

[0043] In the second aspect, a system for predicting atmospheric pollutant concentrations based on meteorological element correlation analysis is provided, comprising:

[0044] A data preprocessing module is used to extract and preprocess the atmospheric environment multi-source meteorological historical monitoring data based on the atmospheric environment refined analysis product data resources; the atmospheric environment multi-source meteorological historical monitoring data includes atmospheric pollutant elements and meteorological elements;

[0045] The time series module is used to establish the single-element time series of atmospheric pollutants based on the preprocessed atmospheric environment multi-source meteorological historical monitoring data;

[0046] The meteorological element influencing factor module is used to estimate the regression coefficient using the least square method, determine the correlation between each meteorological element and each pollutant, and calculate the meteorological element influencing factor coefficient;

[0047] A hybrid model prediction module is used to construct a hybrid model based on the coefficients of meteorological element influencing factors; and to predict the atmospheric pollutant index through the hybrid model;

[0048] The visualization analysis module is used to receive the current user input and generate atmospheric pollutant concentration prediction information and visualization analysis display that matches the current user input.

[0049] In a third aspect, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method for predicting atmospheric pollutant concentrations based on correlation analysis of meteorological elements as described in the first aspect.

[0050] In a fourth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method for predicting the concentration of atmospheric pollutants based on correlation analysis of meteorological elements as described in the first aspect are implemented.

[0051] This application introduces the influencing factor coefficients of meteorological elements such as temperature, humidity, and wind speed, so that the model can more accurately reflect the actual impact of these factors on the changes in the concentration of atmospheric pollutants, thereby improving the accuracy of the prediction. The hybrid model combines the autoregressive (AR) and moving average (MA) models, and adds the influencing factors of meteorological elements, making the model more flexible and better able to capture complex patterns in time series data. Each pollutant has a separate sub-index, and the comprehensive index is finally obtained through weighted averaging, making the model results more interpretable, and users can clearly understand which meteorological conditions have a significant impact on pollution. Reduce computing resource requirements: Compared with complex machine learning models, the improved ARIMA model reduces the demand for computing resources and speeds up the calculation while maintaining a high prediction accuracy.

[0052] In addition, this application provides a variety of charts, such as the correlation diagram between atmospheric pollutant concentration and air pressure / temperature / wind speed, the relationship diagram between artificial rainfall and the total reduction of atmospheric pollutants, the spatial distribution diagram of atmospheric pollutant concentration, and the predicted atmospheric pollutant concentration trend diagram, so that users can intuitively understand the data and prediction results. Users can view detailed information for a specific time period or location by moving the mouse, which enhances the user experience and the flexibility of data analysis. The prediction results and visual displays provided provide an important quantitative basis for evaluating the relationship between regional artificial rainfall and atmospheric pollution, which helps environmental management departments make more scientific and reasonable decisions.

[0053] This application effectively provides product development verification and automated visualization of short-term prediction of atmospheric pollutant concentrations, predicts atmospheric pollutant concentrations, and visualizes the prediction process and results, thereby improving the effectiveness and rapidity of atmospheric environmental monitoring data, and can assist in supporting the scientific basis of human shadow operation decision-making. In addition, this application can assist in supporting the feasibility of environmental governance strategies and provide strong technical support for atmospheric pollution monitoring and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic flow chart of a method for predicting atmospheric pollutant concentrations based on meteorological element correlation analysis provided in an embodiment of the present application;

[0055] Figure 2 A schematic flow chart of another method for predicting atmospheric pollutant concentrations based on meteorological element correlation analysis provided in an embodiment of the present application;

[0056] Figure 3 A schematic flow chart of the correlation between atmospheric pollutant concentration and air pressure, temperature and wind speed provided in an embodiment of the present application;

[0057] Figure 4 A schematic diagram of the relationship between the total amount of artificial rainfall in 2017 and the total amount of pollutant reduction provided in an embodiment of the present application;

[0058] Figure 5 A schematic diagram of the spatial distribution of fine particulate matter concentration in a certain area on May 20-21 provided in an embodiment of the present application;

[0059] Figure 6 A schematic diagram of the structure of a system for predicting atmospheric pollutant concentrations based on meteorological element correlation analysis provided in an embodiment of the present application;

[0060] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose, the technical solutions in the embodiments of the present application are clearly described. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present application.

[0062] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0063] The description of the method flow in the specification of the present application and the steps of the flowchart in the drawings of the present specification do not have to be strictly executed according to the step numbers, and the method steps can be executed in a different order. Moreover, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0064] The following is a detailed description of the method, system, device and medium for predicting the concentration of atmospheric pollutants based on meteorological element correlation analysis provided in the embodiments of the present application in combination with the accompanying drawings and preferred embodiments.

[0065] First, the application scenarios of the method for predicting atmospheric pollutant concentrations based on meteorological element correlation analysis in an embodiment of the present application are described in detail.

[0066] At present, based on the refined analysis product of atmospheric environment of the human shadow project, a method and system for predicting atmospheric pollutant concentration and visual display based on meteorological element correlation analysis is provided. The comprehensive index of atmospheric pollutant concentration in the future is predicted based on the historical values ​​of atmospheric environmental elements, which provides an important quantitative basis for evaluating the correlation between regional artificial rainfall influence and atmospheric pollution. Due to the variability and randomness of meteorological processes, it is difficult to accurately predict the atmospheric pollutant index. Currently, the most popular prediction method is to use machine learning models and use genetic algorithm BP neural network technology for prediction, which takes up a lot of time for algorithm developers and users. At the same time, it has slow computing speed and requires high computing resources, which seriously affects work efficiency. The prediction using the traditional ARIMA model does not take into account the impact of meteorological elements on pollutants, cannot fully analyze and predict, and cannot accurately visualize the data analysis results to help users increase their understanding.

[0067] In view of the technical problems in related technologies such as high computing resource requirements and slow calculation speed for short-term prediction of atmospheric pollutants, inability to achieve rapid prediction with high accuracy and multi-dimensional visualization, this application aims to propose a method for predicting atmospheric pollutant concentrations based on correlation analysis of meteorological elements. This method combines historical data and predicted data, uses visualization technology to perform visual analysis and display of predicted atmospheric pollutants, and performs multi-dimensional visualization data display of predicted values ​​and processes, and verifies and compares the predicted information to achieve data standardization, process automation, intelligent prediction, and visualization of process and result analysis.

[0068] See also Figure 1-2 The present application embodiment provides a method for predicting the concentration of atmospheric pollutants based on the correlation analysis of meteorological elements, such as Figure 1-2 As shown, the method of the embodiment of the present application includes:

[0069] Step S1, based on the atmospheric environment refined analysis product data resources, extract and pre-process the atmospheric environment multi-source meteorological historical monitoring data. The atmospheric environment multi-source meteorological historical monitoring data includes atmospheric pollutant elements and meteorological elements.

[0070] This step extracts the concentration data information of various pollutants in a specific area and a uniform height range within a specified historical time period from the refined analysis products of the atmospheric environment monitored by meteorological monitoring. Based on the acquired atmospheric environment multi-source meteorological historical monitoring data, the atmospheric environment multi-source meteorological monitoring data is preprocessed, including but not limited to cleaning data, processing missing values ​​or null values, and standardizing or normalizing data (including format conversion, unit conversion, etc.).

[0071] In some possible implementations, the multi-source meteorological historical monitoring data of the atmospheric environment includes daily and hourly data of sulfur dioxide, nitrogen dioxide, ozone, carbon monoxide, PM10, PM2.5, atmospheric pressure, temperature, humidity, wind speed, and wind direction.

[0072] Exemplarily, the typical pollutant concentration data information includes the location, time period, sulfur dioxide (SO2), nitrogen dioxide (NO2), ozone (O3), carbon monoxide (CO), PM10, PM2.5 of the atmospheric pollutant concentrations in n time periods in a certain year and month; in addition, it also includes corresponding meteorological element data such as atmospheric pressure, temperature, humidity, wind speed, wind direction, etc.

[0073] Step S2, establishing a single-element time series of atmospheric pollutants based on the pre-processed atmospheric environment multi-source meteorological historical monitoring data.

[0074] This step establishes a separate time series for each atmospheric pollutant meteorological data based on the characteristics of multi-source meteorological data of the atmospheric environment.

[0075] Exemplarily, the single-element time series of atmospheric pollutants are established including six atmospheric pollutant elements: SO2, NO2, O3, CO, PM10, and PM2.5.

[0076] In some possible implementations, it is determined whether the single-element time series of air pollutants is a stationary series; if it is a non-stationary series, the single element of the air pollutant is subjected to differential operation and converted into a stationary time series.

[0077] During the specific implementation process, according to the stationarity requirements of the ARIMA model time series, if it is a non-stationary series, the time series of the single-element meteorological data of atmospheric pollutants is differentially operated to continue to verify its stationarity until it meets the stationarity requirements of the time series required by the ARIMA model, forming the single-element meteorological data of atmospheric pollutants for predicting short-term atmospheric pollution and visualization analysis.

[0078] For example, the single-element stationary time series of air pollutants is marked as:

[0079] {N tso2 , N tno2 , N to3 , N tco , N tpm10 , N tpm2.5}.

[0080] Step S3, using the least squares method to estimate the regression coefficient, determine the correlation between each meteorological element and each pollutant, and calculate the meteorological element impact factor coefficient.

[0081] The meteorological element impact factor coefficient is the impact factor coefficient of each meteorological element on air pollution.

[0082] Preprocess the data based on the atmospheric environment multi-source meteorological data, based on the correlation analysis of meteorological elements, see Figure 3-5 , estimate the regression coefficients b0, b1, b2…, b by the least squares method n . Calculate and confirm the coefficient of meteorological element correlation influencing factor Specifically, the following expression (1) is used to calculate the coefficient of the impact factor of each meteorological element on air pollution at the current time:

[0083]

[0084] in, is the coefficient of the impact of each meteorological element on air pollution; x i1 、x i2 …,x in are various meteorological elements, including temperature, humidity, wind speed, wind direction and other meteorological elements; b0, b1, b2…, b nThe regression coefficients are estimated by the least squares method; the goal of the least squares method is to make the observed value y i With the predicted value The sum of squared errors between Minimum, where m is the number of meteorological elements of the observed samples (m is a meteorological element such as atmospheric pressure, temperature, humidity, wind speed, wind direction, etc.).

[0085] Step S4, constructing a hybrid model based on the coefficients of meteorological element influencing factors; and predicting the atmospheric pollutant index through the hybrid model.

[0086] The atmospheric pollutant index is predicted through a hybrid model, including:

[0087] Step S401, calculating the trend prediction value of atmospheric environmental elements;

[0088] Step S402, calculating the relationship between data and past noise,

[0089] Step S403: prediction and calculation of air pollutant index.

[0090] For step S401, the atmospheric environment element trend prediction value calculation is performed by using the following expression (2) to calculate the atmospheric environment element trend prediction value at the current time point:

[0091] Y t =c+φ1Y t-1 +φ2Y t-2 +φ3Y t-3 +…+φ p Y t-p +δ t (2)

[0092] Among them, Y t is the observed value of the single element time series data of the atmospheric environment at time t; Y t-p is the measured value of each time point p forward from the current time, where p is the past p time points; φ1 to φ p is the relationship coefficient between the current value and the value at the past p time points to the present; δ t is the error term at time point t; c is a constant term.

[0093] For the calculation of the relationship between the data and the past noise in step S402, the following expression (3) is used to calculate the relationship between the data at the current time point and the past noise:

[0094] P t =μ+∈ t +θ1∈ t-1 +θ2∈ t-2 +θ3∈ t-3 +…+θ q ∈t-q (3)

[0095] Among them, P t is the time series of the single element of the atmospheric environment related to the past noise, the observed value at time t; μ is the mean of the time series, which is the same for all time points; ∈ t ,∈ t-1 ,…∈ t-q are white noise terms, which are the white noise corresponding to the current time point; θ1, θ2,…,θ q Each one corresponds to a white noise influence degree term, which is the influence degree of the corresponding white noise on the current time point; q is the order, indicating how many past white noise terms are included in the calculation model.

[0096] Step S403 of air pollutant index prediction and calculation specifically includes:

[0097] Step S403a, calculating the predicted value of each atmospheric environmental element at the current time point.

[0098] By using expressions (1), (2) and (3) to perform arithmetic processing, the following expression (4) is used to calculate the predicted value of each atmospheric environmental element at the current time point:

[0099]

[0100] Among them, C t Prediction value data for each air pollutant element; It is the coefficient of the impact factor of each meteorological element on air pollution.

[0101] Step S403b, calculating the sub-index of each pollutant according to the predicted value of the atmospheric environmental element.

[0102] The sub-index of each pollutant is calculated using the following expression (5):

[0103] (I t ):

[0104] Among them, C t is the predicted concentration, S t is the standard concentration.

[0105] For example, for sulfur dioxide, its sub-index in, is the sulfur dioxide concentration, is the standard sulfur dioxide concentration.

[0106] Step S403c, calculating a comprehensive index based on the weighted sub-index of each pollutant.

[0107] For example, the comprehensive index I is calculated using the weighted average method using the following expression (6):

[0108]

[0109] Among them, I w To predict the comprehensive index of air pollutants; W CO , W PM10 , W PM2.5 is the weight coefficient of each air pollutant, and the sum of the weights is 1; I CO , I PM10 , I PM2.5 It is a sub-index for each pollutant.

[0110] In other words, the above steps are based on the single-element time series of atmospheric pollutants, based on the correlation analysis of meteorological elements, improving the ARIMA model by adding meteorological element influencing factors, and performing fusion and hybridization processing on the data to determine the atmospheric pollutant concentration prediction. The modified ARIMA model algorithm includes the following algorithms: autoregressive model (AR), moving average model (MA), influencing factor coefficient calculation, and atmospheric pollutant index prediction calculation.

[0111] Step S5, receiving the current user input, generating air pollutant concentration prediction information and visual analysis display matching the current user input. Specifically, it includes:

[0112] Air pollutant concentration and air pressure / temperature / wind speed correlation diagram: Displays the relationship between air pollutant concentration and air pressure, temperature, and wind speed. Users can move the mouse to view specific values ​​and their changes;

[0113] Relationship between artificial rainfall and total reduction of air pollutants: shows the relationship between artificial rainfall and changes in air pollutant concentrations. Users can view changes in different time periods.

[0114] Spatial distribution map of atmospheric pollutant concentration: showing the spatial distribution of atmospheric pollutant concentration in days;

[0115] Predicted atmospheric pollutant concentration trend chart: shows the changing trend of atmospheric pollutant concentrations over a period of time in the future. Users can view detailed information at a specific moment.

[0116] Based on the above technical solution, this application has the following technical effects and advantages:

[0117] This application introduces the influencing factor coefficients of meteorological elements such as temperature, humidity, and wind speed, so that the model can more accurately reflect the actual impact of these factors on the changes in the concentration of atmospheric pollutants, thereby improving the accuracy of the prediction. The hybrid model combines the autoregressive (AR) and moving average (MA) models, and adds the influencing factors of meteorological elements, making the model more flexible and better able to capture complex patterns in time series data. Each pollutant has a separate sub-index, and the comprehensive index is finally obtained through weighted averaging, making the model results more interpretable, and users can clearly understand which meteorological conditions have a significant impact on pollution. Reduce computing resource requirements: Compared with complex machine learning models, the improved ARIMA model reduces the demand for computing resources and speeds up the calculation while maintaining a high prediction accuracy.

[0118] In addition, this application provides a variety of charts, such as the correlation diagram between atmospheric pollutant concentration and air pressure / temperature / wind speed, the relationship diagram between artificial rainfall and the total reduction of atmospheric pollutants, the spatial distribution diagram of atmospheric pollutant concentration, and the predicted atmospheric pollutant concentration trend diagram, so that users can intuitively understand the data and prediction results. Users can view detailed information for a specific time period or location by moving the mouse, which enhances the user experience and the flexibility of data analysis. The prediction results and visual displays provided provide an important quantitative basis for evaluating the relationship between regional artificial rainfall and atmospheric pollution, which helps environmental management departments make more scientific and reasonable decisions.

[0119] In summary, this application effectively provides product development verification and automated visualization for short-term prediction of atmospheric pollutant concentrations, predicts atmospheric pollutant concentrations, and visualizes the prediction process and results, thereby improving the effectiveness and rapidity of atmospheric environmental monitoring data, and can assist in supporting the scientific basis for decision-making in human shadow operations. In addition, this application can assist in supporting the feasibility of environmental governance strategies and provide strong technical support for atmospheric pollution monitoring and management.

[0120] See also Figure 6 , corresponding to the above-mentioned embodiment of the method for predicting the concentration of atmospheric pollutants based on the correlation analysis of meteorological elements, the embodiment of the present application provides a system for predicting the concentration of atmospheric pollutants based on the correlation analysis of meteorological elements, the system comprising:

[0121] The data preprocessing module 1001 is used to extract and preprocess the atmospheric environment multi-source meteorological historical monitoring data based on the atmospheric environment refined analysis product data resources; the atmospheric environment multi-source meteorological historical monitoring data includes atmospheric pollutant elements and meteorological elements;

[0122] The time series module 1002 is used to establish a single-element time series of atmospheric pollutants based on the pre-processed atmospheric environment multi-source meteorological historical monitoring data;

[0123] The meteorological element impact factor module 1003 is used to estimate the regression coefficient using the least square method, determine the correlation between each meteorological element and each pollutant, and calculate the meteorological element impact factor coefficient;

[0124] The hybrid model prediction module 1004 is used to construct a hybrid model based on the coefficients of the meteorological element influencing factors; and to predict the atmospheric pollutant index through the hybrid model;

[0125] The visualization analysis module 1005 is used to receive current user input and generate atmospheric pollutant concentration prediction information and visualization analysis display matching the current user input.

[0126] The above-mentioned system for predicting the concentration of atmospheric pollutants based on the correlation analysis of meteorological elements implements the steps and various processes of the above-mentioned method embodiment for predicting the concentration of atmospheric pollutants based on the correlation analysis of meteorological elements, and can achieve the same technical effect. To avoid repetition, they will not be repeated here.

[0127] See also Figure 7 Corresponding to the above-mentioned embodiment of the method for predicting the concentration of atmospheric pollutants based on the correlation analysis of meteorological elements, an embodiment of the present application provides an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps and various processes of the above-mentioned embodiment of the method for predicting the concentration of atmospheric pollutants based on the correlation analysis of meteorological elements are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0128] The memory 1009 can be used to store software programs and various data. The memory 1009 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 1009 may include a volatile memory or a non-volatile memory, or the memory 1009 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 1009 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0129] The processor 1010 may include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 1010.

[0130] Corresponding to the above-mentioned embodiment of the method for predicting the concentration of atmospheric pollutants based on the correlation analysis of meteorological elements, the embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by the processor, the steps and various processes of the embodiment of the above-mentioned method for predicting the concentration of atmospheric pollutants based on the correlation analysis of meteorological elements are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0131] The processor is the processor in the electronic device described in the above embodiment of the present application. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0132] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0133] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0134] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for predicting atmospheric pollutant concentrations based on meteorological element correlation analysis, characterized in that: include: Based on the refined analysis product data resources of the atmospheric environment, extract and preprocess the atmospheric environment multi-source meteorological historical monitoring data; The atmospheric environment multi-source meteorological historical monitoring data includes atmospheric pollutant elements and meteorological elements; Based on the pre-processed atmospheric environment multi-source meteorological historical monitoring data, the single-element time series of atmospheric pollutants is established; Use the least squares method to estimate the regression coefficient, determine the correlation between each meteorological element and each pollutant, and calculate the coefficient of the meteorological element influencing factor; Based on the coefficients of meteorological element influencing factors, a hybrid model is constructed; and the atmospheric pollutant index is predicted by the hybrid model; Receive current user input and generate atmospheric pollutant concentration prediction information and visual analysis display that matches the current user input.

2. The method for predicting atmospheric pollutant concentration based on meteorological element correlation analysis according to claim 1 is characterized in that: The atmospheric environment multi-source meteorological historical monitoring data includes daily and hourly data of sulfur dioxide, nitrogen dioxide, ozone, carbon monoxide, PM10, PM2.5, atmospheric pressure, temperature, humidity, wind speed, and wind direction.

3. The method for predicting atmospheric pollutant concentration based on meteorological element correlation analysis according to claim 2 is characterized in that: The meteorological factor impact factor coefficient is the impact factor coefficient of each meteorological factor on air pollution at the current time: The following expression (1) is used for calculation: in, is the coefficient of the impact of each meteorological element on air pollution; x i1 、x i2 …,x in are various meteorological elements, including temperature, humidity, wind speed, wind direction and other meteorological elements; b0, b1, b2…, b n The regression coefficients are estimated by the least squares method; the goal of the least squares method is to make the observed value y i With the predicted value The sum of squared errors between minimum, where m is the number of observed sample meteorological elements.

4. The method for predicting atmospheric pollutant concentration based on meteorological element correlation analysis according to claim 3 is characterized in that: The atmospheric pollutant index is predicted through a hybrid model, including: Calculation of trend prediction values ​​of atmospheric environmental elements; Calculation of the relationship between data and past noise; Prediction and calculation of air pollutant index.

5. The method for predicting atmospheric pollutant concentration based on meteorological element correlation analysis according to claim 4 is characterized in that: The following expression (2) is used to calculate the trend forecast value of each atmospheric environmental element at the current time point: Among them, Y t is the observed value of the single element time series data of the atmospheric environment at time t; Y t-p It is the measured value of each time point p forward from the current time, where p is the p time points in the past; arrive is the relationship coefficient between the current value and the value at the past p time points to the present; δ t is the error term at time point t; c is a constant term; The following expression (3) is used to calculate the relationship between the data at the current time point and the past noise: P t =μ+∈ t +θ1∈ t-1 +θ2∈ t-2 +θ3∈ t-3 +…+θ q ∈ t-q (3) Among them, P t is the time series of the single element of the atmospheric environment related to the past noise, the observed value at time t; μ is the mean of the time series, which is the same for all time points; ∈ t ,∈ t-1 ,…∈ t-q are white noise terms, which are the white noise corresponding to the current time point; θ1, θ2,…,θ q Each one corresponds to a white noise influence degree term, which is the influence degree of the corresponding white noise on the current time point; q is the order, indicating how many past white noise terms are included in the calculation model; The air pollutant index prediction and calculation specifically includes: Calculate the predicted value of each atmospheric environmental factor at the current time point; use the following expression (4) to calculate the predicted value of each atmospheric environmental factor at the current time point: Among them, C t Prediction value data for each air pollutant element; is the coefficient of the impact factor of each meteorological element on air pollution; The sub-index of each pollutant is calculated according to the predicted value of the atmospheric environmental element; the sub-index of each pollutant is calculated using the following expression (5): Among them, C t is the predicted concentration, S t is the standard concentration; The comprehensive index is calculated based on the weighted sub-index of each pollutant; the calculation is performed using the following expression (6): Among them, I w To predict the comprehensive index of air pollutants; W CO , W PM10 , W PM2.5 is the weight coefficient of each air pollutant, and the sum of the weights is 1; I CO , I PM10 , I PM2.5 It is a sub-index for each pollutant.

6. The method for predicting atmospheric pollutant concentrations based on meteorological element correlation analysis according to claim 1, characterized in that: The visual analysis display includes: Correlation diagram between air pollutant concentration and air pressure / temperature / wind speed; Relationship between artificial rainfall and the total reduction of air pollutants; Spatial distribution map of atmospheric pollutant concentrations; Predicted trend of atmospheric pollutant concentrations.

7. The method for predicting atmospheric pollutant concentrations based on meteorological element correlation analysis according to any one of claims 1 to 6, characterized in that: Before using the least squares method to estimate the regression coefficient, determine the correlation between each meteorological element and each pollutant, and calculate the coefficient of the meteorological element influencing factor, perform the following steps: Determine whether the single-element time series of atmospheric pollutants is a stationary series; if it is a non-stationary series, perform differential operations on the single element of atmospheric pollutants to convert it into a stationary time series.

8. A system for predicting atmospheric pollutant concentrations based on meteorological element correlation analysis, characterized in that: include: The data preprocessing module is used to extract and preprocess the atmospheric environment multi-source meteorological historical monitoring data based on the refined analysis product data resources of the atmospheric environment; The atmospheric environment multi-source meteorological historical monitoring data includes atmospheric pollutant elements and meteorological elements; The time series module is used to establish the single-element time series of atmospheric pollutants based on the preprocessed atmospheric environment multi-source meteorological historical monitoring data; The meteorological element influencing factor module is used to estimate the regression coefficient using the least square method, determine the correlation between each meteorological element and each pollutant, and calculate the meteorological element influencing factor coefficient; A hybrid model module is used to construct a hybrid model based on the coefficients of meteorological element influencing factors; and to predict the atmospheric pollutant index through the hybrid model; The visualization analysis module is used to receive the current user input and generate atmospheric pollutant concentration prediction information and visualization analysis display that matches the current user input.

9. An electronic device, characterized in that: The electronic device comprises: a memory, a processor and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the method for predicting the concentration of atmospheric pollutants based on correlation analysis of meteorological elements as claimed in any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the method for predicting the concentration of atmospheric pollutants based on the correlation analysis of meteorological elements as described in any one of claims 1 to 7 are implemented.

Images