CN116776073B

CN116776073B - Pollutant concentration evaluation method and device

Info

Publication number: CN116776073B
Application number: CN202311015531.3A
Authority: CN
Inventors: 文质彬; 亢思静; 肖林鸿; 张稳定; 王文丁; 王倩; 陈焕盛; 吴剑斌; 秦东明
Original assignee: 3Clear Technology Co Ltd
Current assignee: 3Clear Technology Co Ltd
Priority date: 2023-08-14
Filing date: 2023-08-14
Publication date: 2023-11-21
Anticipated expiration: 2043-08-14
Also published as: CN116776073A

Abstract

The application provides a method and a device for evaluating pollutant concentration, and belongs to the field of atmospheric physics. The method comprises the following steps: determining a first meteorological integrated diagnostic index and a first measured contaminant concentration of the target area within a fitting period; determining a target fitting function of the target area based on the first weather integrated diagnostic index and the first measured pollutant concentration in the fitting period, wherein the target fitting function is used for indicating a mapping relationship between the weather integrated diagnostic index and the pollutant concentration; determining a second weather integrated diagnostic index for the target area within the target period; determining a fitting pollutant concentration of the target area in the target period based on the target fitting function and a second weather comprehensive diagnostic index in the target period; based on the fitted pollutant concentrations over the target period, the pollutant concentration effect of the weather on the target area is evaluated, and/or the pollutant concentration effect of the emissions on the target area is evaluated. By adopting the application, the consumption of computing resources is small.

Description

Pollutant concentration evaluation method and device

Technical Field

The application relates to the field of atmospheric physics, in particular to a method and a device for evaluating pollutant concentration.

Background

The atmospheric pollution source and the atmospheric condition change are two major determinants influencing the pollutant change, the two determinants are mutually interweaved and interacted, and the influence degree of the weather condition on the pollutant change is very great. Meteorological conditions affect the concentration of contaminants by affecting the dilution, diffusion, accumulation and removal processes of the contaminants, e.g., by causing the transport of contaminants between regions under the influence of an atmospheric air flow field, rapidly forming PM at high concentrations in high humidity, steady weather conditions _2.5 An atmospheric pollution process that is a feature; and the high temperature, low humidity and low wind speed in summer and autumn are favorable for the local generation of ozone. When being affected by adverse weather conditions, the air quality of the area is extremely easy to rapidly deteriorate, and the air quality control effect is also weakened. The analysis of the impact of meteorological conditions on the production of pollutants, particularly particulate matter and ozone, and how to quantitatively evaluate the impact of meteorological conditions and pollution source emission changes on the production of particulate matter and ozone is a problem faced by the environmental sector in the management decision service. Therefore, the construction of a method for quantitatively evaluating the meteorological and emission influences of pollutants has important significance for determining pollution causes and making pollution prevention and control plans.

The current mainstream scheme for quantitatively evaluating the influence of weather and emission is to utilize a third-generation air quality model for scene simulation, namely, to formulate different weather and emission scenes by a control variable method (keeping the weather input unchanged, changing an emission list or fixing an emission source unchanged and changing the weather input) to respectively perform numerical simulation, and quantitatively evaluate the influence of the weather and the emission on the concentration of pollutants according to the concentration differences simulated under different scenes. The physical and chemical processes related to the weather and emission influence considered by the scheme are particularly comprehensive, but the scheme has the defects of large consumption of computing resources, complicated required input variables and parameters, influence by uncertainty of a chemical mechanism in an emission source list and a mode and the like.

Therefore, there is a need for an evaluation method for contaminant concentration that is less computationally expensive.

Disclosure of Invention

In order to solve the problems in the prior art, the embodiment of the application provides a method and a device for estimating the concentration of pollutants, which can reduce the consumption of computing resources. The technical proposal is as follows:

according to an aspect of the present application, there is provided a method of assessing a concentration of a contaminant, the method comprising:

determining a fitting period, and determining a first meteorological comprehensive diagnostic index and a first measured pollutant concentration of a target area in the fitting period;

Determining a target fitting function of the target area based on the first weather integrated diagnostic index and the first measured pollutant concentration in the fitting period, wherein the target fitting function is used for indicating a mapping relation between the weather integrated diagnostic index and the pollutant concentration;

determining a target period to be evaluated, and determining a second weather comprehensive diagnosis index of the target region in the target period;

determining a fitting contaminant concentration of the target region within the target period based on the target fitting function and a second weather integrated diagnostic index within the target period;

based on the fitted pollutant concentrations over the target period, estimating a pollutant concentration effect of weather on the target region, and/or estimating a pollutant concentration effect of emissions on the target region.

Optionally, the determining the first weather integrated diagnostic index of the target region in the fitting period includes:

acquiring historical meteorological data and corresponding historical pollutant concentrations of a target area;

based on the historical meteorological data and the corresponding historical pollutant concentration, carrying out statistics, and constructing a meteorological comprehensive diagnosis index model of the target area;

Acquiring first meteorological data of the target area in the fitting period;

substituting the first meteorological data into the meteorological comprehensive diagnosis index model to determine a first meteorological comprehensive diagnosis index of the target area in the fitting period.

Optionally, the determining the second weather integrated diagnostic index of the target area in the target period includes:

acquiring second meteorological data of the target area in the target period;

substituting the second meteorological data into the meteorological comprehensive diagnostic index model to determine a second meteorological comprehensive diagnostic index of the target area in the fitting period.

Optionally, the determining the target fitting function of the target region based on the first meteorological comprehensive diagnostic index and the first measured contaminant concentration in the fitting period includes:

taking the first meteorological comprehensive diagnostic index in the fitting period as an independent variable sample, and taking the first measured pollutant concentration in the fitting period as the independent variable sample;

and performing polynomial fitting on the independent variable samples and the dependent variable samples based on a polynomial fitting algorithm to construct a target fitting function of the target region.

Optionally, when the target period is a period of emission control, and the fitting period is a period of normal emission before and after emission control:

estimating the effect of emissions on the pollutant concentration of the target zone based on the fitted pollutant concentrations over the target period of time, comprising:

acquiring a second measured contaminant concentration within the target period;

and subtracting the fitted pollutant concentration from the second measured pollutant concentration in the target period to determine the pollutant concentration change value under the control of the emission pipe.

Optionally, when the fitting period is a period satisfying a preset long term condition:

estimating a contaminant concentration effect of weather on the target area based on the fitted contaminant concentrations over the target period, comprising:

determining a third weather integrated diagnostic index for the target area within a comparison period;

determining a fitted contaminant concentration of the target region within the contrast period based on the target fitting function and a third weather integrated diagnostic index within the contrast period;

estimating a weather-affected rate of change of the target period relative to the contrast period based on the fitted contaminant concentration within the target period and the fitted contaminant concentration within the contrast period;

determining a weather-emission impact rate of change of the target period relative to the contrast period based on a second measured contaminant concentration within the target period and a third measured contaminant concentration within the contrast period;

based on the weather-induced change rate and the weather-emissions-induced change rate, an emissions-induced change rate of the target period relative to the comparison period is estimated.

determining a fitting pollutant concentration under a weather average state condition;

subtracting the fitting pollutant concentration in the target period from the fitting pollutant concentration under the weather average state condition, and determining the pollutant concentration change value under the weather influence in the target period;

Subtracting the second measured pollutant concentration in the target period from the fourth measured pollutant concentration value in the historical long-term period to determine a pollutant concentration change value under the influence of weather-emission in the target period;

and subtracting the pollutant concentration change value under the influence of weather-emission in the target period from the pollutant concentration change value under the influence of weather, and determining the pollutant concentration change value under the influence of emission in the target period.

Optionally, the determining the fitting pollutant concentration under the weather mean state condition includes:

substituting the historical long-term meteorological data into the target fitting function, and determining the fitting pollutant concentration under the condition of the average climate state.

Optionally, the method further comprises:

and subtracting the pollutant concentration change value under the influence of the second actually measured pollutant concentration and the meteorological influence in the target period to determine the meteorological correction concentration.

According to another aspect of the present application, there is provided an apparatus for estimating a concentration of a contaminant, the apparatus comprising:

the first determining module is used for determining a fitting period and determining a first weather comprehensive diagnosis index and a first measured pollutant concentration of the target area in the fitting period;

A fitting module, configured to determine a target fitting function of the target area based on the first weather integrated diagnostic index and the first measured contaminant concentration in the fitting period, where the target fitting function is used to indicate a mapping relationship between the weather integrated diagnostic index and the contaminant concentration;

the second determining module is used for determining a target period to be evaluated and determining a second weather comprehensive diagnosis index of the target area in the target period;

a third determining module for determining a fitting contaminant concentration of the target area within the target period based on the target fitting function and a second weather integrated diagnostic index within the target period;

an evaluation module for evaluating a pollutant concentration effect of weather on the target area and/or evaluating a pollutant concentration effect of emissions on the target area based on the fitted pollutant concentrations over the target period.

Optionally, the first determining module is configured to:

Acquiring first meteorological data of the target area in the fitting period;

Optionally, the second determining module is configured to:

acquiring second meteorological data of the target area in the target period;

Optionally, the fitting module is configured to:

the evaluation module is used for:

Acquiring a second measured contaminant concentration within the target period;

the evaluation module is used for:

and subtracting the pollutant concentration under the influence of the weather-emission and the pollutant concentration under the influence of the weather in the target period to determine the pollutant concentration change value under the influence of the emission in the target period.

Optionally, the evaluation module is configured to:

Optionally, the evaluation module is further configured to:

and subtracting the second measured pollutant concentration in the target period from the pollutant concentration under the influence of the meteorological influence to determine the meteorological correction concentration.

According to another aspect of the present application, there is provided an electronic apparatus including:

a processor; and

a memory in which a program is stored,

wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the above-described method of estimating the concentration of contaminants.

According to another aspect of the present application, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the above-described method of estimating a contaminant concentration.

The application has the following beneficial effects:

(1) Fitting the first weather comprehensive diagnosis index and the first actually measured pollutant concentration in a fitting period to construct a mapping relation between the weather comprehensive diagnosis index and the pollutant concentration, so as to obtain a target fitting function; during the evaluation, the second weather integrated diagnostic index for the target period is substituted into the target fitting function to determine the fitting contaminant concentration within the target period. The fitting pollutant concentration can be used for respectively and quantitatively evaluating the influence of weather and emission on the pollutant concentration under different scenes. Because the fitting function between the meteorological comprehensive diagnosis index and the pollutant concentration is constructed, compared with a numerical model and a filtering statistical model, the method can flexibly discuss long-term and short-term meteorological and emission contributions, and has the advantages of small calculation resource consumption, clear physical meaning of the model and the like.

(2) And a polynomial fitting method is used for fitting the mapping relation between the weather comprehensive diagnosis index and the pollutant concentration, and compared with a linear regression method, the polynomial fitting method can better capture nonlinear characteristics in the correlation relation. And the optimal order of polynomial fitting is automatically judged based on algorithms such as a k-fold cross validation method and the like, so that the phenomenon of overfitting can be prevented.

Drawings

Further details, features and advantages of the application are disclosed in the following description of exemplary embodiments with reference to the following drawings, in which:

FIG. 1 illustrates a flow chart of a method of estimating contaminant concentration provided in accordance with an exemplary embodiment of the present application;

FIG. 2 illustrates a schematic technical route for constructing a weather integrated diagnostic index provided in accordance with an exemplary embodiment of the present application;

FIG. 3 illustrates a technical route schematic for short-term emissions management control performance assessment provided in accordance with an exemplary embodiment of the present application;

FIG. 4 illustrates a technical route diagram of a comparative evaluation of a target period with other periods provided in accordance with an exemplary embodiment of the present application;

FIG. 5 illustrates a technical route schematic for long term weather effect correction provided in accordance with an exemplary embodiment of the present application;

FIG. 6 shows a schematic block diagram of an apparatus for estimating contaminant concentration provided in accordance with an exemplary embodiment of the present application;

fig. 7 shows a block diagram of an exemplary electronic device that can be used to implement an embodiment of the application.

Detailed Description

Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While the application is susceptible of embodiment in the drawings, it is to be understood that the application may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided to provide a more thorough and complete understanding of the application. It should be understood that the drawings and embodiments of the application are for illustration purposes only and are not intended to limit the scope of the present application.

It should be understood that the various steps recited in the method embodiments of the present application may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the application is not limited in this respect.

The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below. It should be noted that the terms "first," "second," and the like herein are merely used for distinguishing between different devices, modules, or units and not for limiting the order or interdependence of the functions performed by such devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those skilled in the art will appreciate that "one or more" is intended to be construed as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the devices in the embodiments of the present application are for illustrative purposes only and are not intended to limit the scope of such messages or information.

The current mainstream scheme for quantitatively evaluating the influence of weather and emission is to utilize a third-generation air quality model for scene simulation, namely, to formulate different weather and emission scenes by a control variable method (keeping the weather input unchanged, changing an emission list or fixing an emission source unchanged and changing the weather input) to respectively perform numerical simulation, and quantitatively evaluate the influence of the weather and the emission on the concentration of pollutants according to the concentration differences simulated under different scenes. The physical and chemical processes related to the weather and emission influence considered by the scheme are particularly comprehensive, but the scheme has the defects of large consumption of computing resources, complicated required input variables and parameters, influence by uncertainty of a chemical mechanism in an emission source list and a mode and the like. Compared with the defects of a numerical dynamic model, the statistical model has small calculation resource consumption and flexible configuration, can meet the requirements of short-term weather and quantitative evaluation of emission (such as investigation of contribution of emission management and control before and after major activity guarantee, evaluation of contemporaneous weather influence in a month and the like), and can also realize exploration of weather and emission contribution difference of a certain target period relative to a history long term (climate state), and numerical simulation is difficult to realize the latter related to the history long-term simulation due to calculation resource limitation.

The method comprises the steps of establishing a mapping relation between a meteorological factor and a pollutant concentration by using a statistical model, wherein a currently mainstream statistical analysis method is a time sequence filtering method, namely, a time sequence of a meteorological variable and the pollutant concentration is filtered, the time sequence of the meteorological variable and the pollutant concentration is divided into a short-term component and a long-term component (namely, a baseline component, the baseline component comprises the long-term component and a seasonal component under certain subdivision conditions), modeling is conducted on the long-term component, and the difference (residual) between a concentration sequence fitted by the model and an actual concentration is considered to comprise long-term trend contribution and short-term component (meteorological+emission) of emission, and then the residual is filtered, so that the influence of long-term meteorological and emission change trend on the pollutant concentration can be discussed respectively. However, the filtering method (including wavelet analysis, KZ filtering, moving average and other filtering methods) cannot divide the contribution of short-term weather and emissions to pollutants. The calculation mode is not flexible enough, and the method is mainly applied to weather modification (namely, discussing weather and emission contribution on a longer time scale), and the calculation thought cannot be applied to short-term management and control influence evaluation, contemporaneous weather influence evaluation and the like.

Based on the method, the method for evaluating the concentration of the pollutants can flexibly discuss long-term and short-term weather and emission contributions, and has the advantages of low consumption of computing resources, clear physical meaning of a model and the like. The method may be performed by a terminal, a server, and/or other processing-capable device. The method provided by the embodiment of the application can be completed by any device or can be completed by a plurality of devices together.

The method will be described with reference to a flowchart of the method of estimating the concentration of the contaminant shown in fig. 1.

Step 101, determining a fitting period, and determining a first weather integrated diagnostic index and a first measured pollutant concentration of the target area in the fitting period.

In one possible embodiment, the effect of the concentration of the contaminant may be evaluated for a short-term or long-term target period of time in the determination of the cause of the contaminant and the assignment of a pollution control plan, etc. Wherein the contaminant may refer to any one of a variety of contaminants, such as PM _2.5 、PM ₁₀ 、O ₃ 、NO ₂ And waiting for atmospheric pollutants. Assessment of the effect of the concentration of the contaminant, e.g. on the PM under meteorological or emission influence, respectively _2.5 The concentration was estimated.

For the contaminant concentration evaluation for the short term period, two periods of a preset duration before and after the target period may be taken as the fitting period. As an example, when a large-scale activity is held at 2023, 4, 1, 5 days, and emission control is required to be performed (the period is a target period), the effect of emission control is required to be evaluated after the activity, and two periods of half a month before and after the target period can be taken as fitting periods. The fitting period at this time satisfies the short term condition.

For the contaminant concentration evaluation of the long term period, the historical long term period of the target period may be taken as the fitting period. As an example, where the effect of the contaminant concentration needs to be assessed for 2023 years (i.e., the target period), then 5 years of history, 2018-2022, may be taken as the fit period. The fitting period at this time satisfies the long term condition.

It should be noted that the short-term and long-term division indicated in the present embodiment follows the division rule in the art.

Of course, the fitting period for which the short term condition or the long term condition is satisfied may also be determined according to specific evaluation requirements.

After determining the fitting period, a weather integrated diagnostic index of the target area within the fitting period may be calculated, which is referred to as a first weather integrated diagnostic index in this embodiment; and the measured contaminant concentration of the target area during the fit period is obtained, which is referred to as the first measured contaminant concentration in this embodiment. The measured contaminant concentration typically includes, among other things, a contaminant concentration under meteorological influences and a contaminant concentration under emission influences.

Specifically, the process of determining the first weather integrated diagnostic index for the target region over the fit period may be as follows:

based on historical meteorological data and corresponding historical pollutant concentrations, statistics is carried out, and a meteorological comprehensive diagnosis index model of a target area is built;

acquiring first meteorological data of a target area in a fitting period;

substituting the first meteorological data into a meteorological comprehensive diagnosis index model to determine a first meteorological comprehensive diagnosis index of the target area in a fitting period.

The specific process of determining the weather integrated diagnostic index will be described with reference to the technical route diagram for constructing the weather integrated diagnostic index shown in fig. 2.

In one possible embodiment, historical weather data and corresponding historical contaminant concentrations for the target area over the past years, such as weather data and contaminant concentrations for 5 years in history, are obtained and the corresponding years are taken as statistical years.

N weather factors to be selected in the historical weather data are input, wherein N is an integer greater than 1. Alternatively, the weather factors to be selected may include ground elements and high altitude elements, the ground elements having a 24 hour time varying (°c), a 24 hour varying pressure (hPa), a 2m relative humidity (%), a sea level air pressure (hPa), a 10m horizontal wind speed (m/s), a 10m wind direction (°), and the like; the altitude factor is selected to be 1000/925/850/700/500hPa, and comprises relative humidity (%), horizontal wind component U, V (m/s), horizontal wind speed (m/s), vertical speed (Pa/s) and divergence(s) ^-1 ) Mixed layer height (boundary layer height), etc.

Sequencing all meteorological data samples of the same meteorological factor according to the numerical value, and eliminating the extremely high value and the extremely low value of 5% (the percentage is not limited in the embodiment) before and after the removal; the remaining samples are uniformly divided into M intervals according to the percentile (the number of the specific intervals is not limited in this embodiment, for example, may be 10), so that the number of the weather data samples in each interval is substantially the same. On this basis, meteorological data samples for n×m intervals can be obtained. As one example, the meteorological data samples are composed of 02, 08, 14, 20 hour meteorological observations.

And respectively acquiring the pollutant concentrations of the meteorological data samples in each interval at corresponding moments, sequencing the pollutant concentrations of the pollutants (namely the pollutant concentrations P in the figure 2) according to the ascending order of the pollutant concentrations, and counting the number of samples of high-concentration events and low-concentration events in each interval. The high concentration event in practical application can be that the concentration of the pollutant corresponding to the current day is the concentration of the first 25% of the local emission in the statistical period, and the rest is the low concentration event. In practice, the separation of different contaminant species can be defined, e.g. for PM _2.5 Concentration division high concentration events, low concentration events can be targeted to PM _2.5 The weather comprehensive diagnostic index for ozone can be obtained by dividing high concentration events and low concentration events for the ozone concentration.

For the pollutant, the interval index of each meteorological factor is calculated, and the calculation formula is as follows:

（1）

wherein K is _in Representing the index of the meteorological factor i corresponding to the nth interval, i epsilon N and N epsilon M; a, a _in Representing the number of samples of high concentration events in interval n in which meteorological factor i is distributed in a statistical year; b _in Representing the number of samples of low concentration events in interval n in which meteorological factor i is distributed in a statistical year; a represents the total number of samples of high concentration events in a statistical year; b represents the total number of samples of low concentration events over the statistical year.

Calculating the difference between the maximum value and the minimum value of the sub-indexes of each meteorological factor, sorting the meteorological factors according to the difference from large to small, removing autocorrelation factors of which the correlation passes the significance test, finally selecting the front preset number of meteorological factors (for example, the front 10 meteorological factors), recording the selected meteorological factor types, the meteorological critical values and the sub-indexes of each interval, and constructing a corresponding meteorological comprehensive diagnosis index model according to the records.

When the method is applied, first meteorological data in a fitting period are obtained, the meteorological comprehensive diagnosis index model is input, the intervals which are met by the first meteorological data are searched according to the types of meteorological factors in the model and the meteorological critical values of all the intervals, and corresponding index division is added to obtain the first meteorological comprehensive diagnosis index of the target area in the fitting period.

Step 102, determining a target fitting function of the target region based on the first meteorological integrated diagnostic index and the first measured contaminant concentration during the fitting period.

Wherein the objective fitting function may be used to indicate a mapping between the weather integrated diagnostic index and the contaminant concentration.

In one possible embodiment, studies have shown that there is a correlation between meteorological factors and contaminant concentrations. Therefore, the mapping relation between the meteorological comprehensive diagnosis index and the pollutant concentration can be constructed to form a corresponding target fitting function, so that the correlation between the meteorological factors and the pollutant concentration is captured.

Alternatively, since not all weather factors are linearly related to the pollutant concentration, the embodiment adopts a polynomial fitting mode to construct a mapping relationship between the weather comprehensive diagnostic index and the pollutant concentration, thereby better capturing the nonlinear relationship between the weather factors and the pollutant concentration. The corresponding process may be as follows:

In one possible embodiment, if the weather integrated diagnostic index is used as an independent variable and the pollutant concentration is used as a dependent variable, the independent variable is unique, and the calculation efficiency is improved compared with the fitting of a plurality of independent variables.

The polynomial fitting may be a first order polynomial, a second order polynomial, a third order polynomial, etc., in theory, the higher the order of the polynomial fitting, the smaller the difference between the fitting value and the measured value will be, but the phenomenon of "over fitting" will occur when the order is too high, i.e. the fitting relation is too complex or even distorted. Therefore, an algorithm of polynomial fitting can be used to determine the optimal order. Alternatively, the algorithm of the polynomial fitting may include a k-fold cross-validation method, a leave-one-out cross-validation method, a ridge regression method, etc., and the embodiment is not limited to a specific algorithm.

As an example, the optimum order determination process based on the k-fold cross validation method will be described below.

The basic idea of the k-fold cross validation method is to randomly divide the independent variable samples and the corresponding dependent variable samples into non-overlapping k subsets (the k value can be selected as any integer greater than or equal to 2, and the proper k value can be selected according to the number of samples). Model training and validation is then performed k times, training on k-1 subsets at a time, and validation on the remaining one subset (the subset not used for training in the round). Finally, training and validation errors are estimated by averaging the results of k experiments.

The method comprises the following specific steps:

1. the first weather integrated diagnostic index sample (independent variable) and the first measured contaminant concentration sample (dependent variable) are randomly divided into non-overlapping k subsets.

2. From which one subset is chosen as the validation set, the remaining k-1 subsets are used to train a polynomial regression model of the form below equation (2). In the middle ofFor the concentration of the contaminant to be fitted,Ifor the corresponding weather integrated diagnostic index,dis the highest order of polynomial regression model, +.>Is of the order ofiCorresponding coefficients. For the scattered distribution of the meteorological comprehensive diagnosis index and the pollutant concentration, the highest possible order is set for obtaining higher calculation efficiency dmax is 5 (without limitation).

(2)

Will bed=1，2，……，dmax are respectively substituted to build different ordersdThe polynomial regression model below.

3. Substituting the first meteorological comprehensive diagnostic index in the verification set (namely the subset which does not participate in training the polynomial regression model in the step 2) into the step 2 to obtain different ordersdThe fitted pollutant concentration is calculated by using a polynomial regression model, the fitted pollutant concentration is substituted into the following formula (3) to calculate the root mean square error between the fitted pollutant concentration and the first measured pollutant concentration in the verification set, and different orders are recordeddCorresponding root mean square error values. Where rmse is root mean square error, J is the number of samples in the validation set (J independent variables, J dependent variables), C _j For the contaminant concentration of the jth sample,the contaminant concentration was fitted to the j-th sample.

(3)

4. Repeating steps 2, 3 and k times (i.e. traversing all subsets as verification set), recording k different ordersdCorresponding root mean square error and averaging, wherein the average value of the root mean square error is the polynomial order corresponding to the minimumdIs the optimal order. And selecting a polynomial fitting function corresponding to the optimal order as a mapping relation between the final weather comprehensive diagnosis index and the pollutant concentration, and obtaining the target fitting function.

Of course, other evaluation criteria may be used to determine the optimal order, such as minimum absolute error, maximum correlation coefficient, etc., which is not limited in this embodiment.

Step 103, determining a target period to be evaluated, and determining a second weather comprehensive diagnosis index of the target area in the target period.

The specific process may be as follows:

acquiring second meteorological data of a target area in a target period;

substituting the second meteorological data into a meteorological comprehensive diagnosis index model to determine a second meteorological comprehensive diagnosis index of the target area in the fitting period.

The specific embodiment is the same as the above manner of determining the first integrated diagnostic index of the meteorological apparatus in step 101, and will not be described herein.

Step 104, determining the fitting pollutant concentration of the target area in the target period based on the target fitting function and the second weather comprehensive diagnosis index in the target period.

In one possible implementation, the second weather integrated diagnostic index may be substituted into the target fitting function determined in step 102 to calculate the corresponding fitting contaminant concentration.

Because the construction basis of the fitting function is the weather comprehensive diagnosis index and the pollutant concentration of the fitting period, and the pollutant concentration is the pollutant concentration under the joint influence of weather and emission, the fitting pollutant concentration obtained through calculation of the fitting function can be regarded as the pollutant concentration corresponding to the weather comprehensive diagnosis index under the emission level of the fitting period.

On this basis, when the duration of the fitting period satisfies a preset short-term condition, the fitting contaminant concentration within the target period calculated based on the fitting function determined by the fitting period may include the contaminant concentration under the influence of the short-term emission level and the contaminant concentration under the influence of the weather together.

When the length of the fitting period satisfies the preset long term condition, the emission level of the fitting period may be regarded as an average emission level (for example, an average emission level of 5 years in history) due to the longer length of the fitting period, and the fitting pollutant concentration in the target period calculated based on the fitting function determined by the fitting period may include the pollutant concentration under the combined influence of the average emission level and weather.

Step 105, estimating a pollutant concentration effect of the weather on the target area based on the fitted pollutant concentrations over the target period, and/or estimating a pollutant concentration effect of the emissions on the target area.

In a possible implementation manner, according to selection of the fitting period, the fitting pollutant concentration corresponding to the fitting function of the short-term fitting period and the fitting pollutant concentration corresponding to the fitting function of the long-term fitting period can be calculated for the target period, and in combination with the second actually measured pollutant concentration in the target period and the pollutant concentration under the weather average state condition of the target area, the influence of weather and emission can be quantitatively evaluated respectively.

The concentration of contaminants under climatic mean state conditions may be referred to herein as a concentration of contaminants that does not include meteorological and emission effects. Alternatively, a fitting function corresponding to a fitting period satisfying the long term condition may be used to determine the concentration of the contaminant under the weather-averaged condition, and the specific process may be as follows: substituting the historical long-term meteorological data into a target fitting function to determine the fitting pollutant concentration under the condition of the average climate state.

In the actual evaluation process, the fitting pollutant concentration corresponding to the fitting function of the short-term fitting period and/or the fitting pollutant corresponding to the fitting function of the long-term fitting period can be flexibly adopted, long-term and short-term weather and emission influences are discussed, and the method has the advantages of small calculation resource consumption, clear model physical significance and the like. Three specific application scenarios will be described in this embodiment.

Application scenario 1: short term emission control performance assessment

The corresponding process of assessing the effect of emissions on the concentration of pollutants in a target zone may be as follows:

acquiring a second measured pollutant concentration in a target period, wherein the second measured pollutant concentration is the pollutant concentration under the control of the emission pipe;

In one possible implementation, referring to the technical route schematic of short-term emission control performance evaluation shown in fig. 3, in application scenario 1, the target period may be an emission control period, and the fitting period may be a period of normal emission before and after emission control. At this time, in the case where the fitting pollutant concentration calculated by the objective fitting function determined by the above steps may be the normal emission, the pollutant concentration under the combined influence of the weather and the normal emission in this period is included. The second measured pollutant concentration is the pollutant concentration under the control of the emission control, namely the pollutant concentration under the combined influence of the meteorological emission in the period and the emission after the emission control in the period. If the fitted pollutant concentration and the second measured pollutant concentration within the target period are subtracted, a pollutant concentration variation value under the control of the exhaust pipe can be obtained.

For example, when a large-scale activity is held for 1 to 5 days of 4 months of 2023 in a certain place, the emission control is required to be implemented (the period is the target period), the emission control effect is required to be evaluated after the activity, the weather comprehensive diagnostic index and the pollutant concentration of the target period are used for establishing a fitting relation, and the corresponding fitting pollutant concentration C under the normal emission condition can be obtained after substituting the weather comprehensive diagnostic index of the target period _f And the actual observed concentration after the control is C, C _f -C can represent the concentration variation due to the exhaust control.

Application scenario 2: comparison of target time period with other time periods

The corresponding process of assessing the effect of weather on the concentration of contaminants in a target area may be as follows:

determining a third weather integrated diagnostic index of the target area in the comparison period;

determining a fitting pollutant concentration of the target area in the comparison period based on the target fitting function and a third weather comprehensive diagnosis index in the comparison period;

the rate of change of the weather effect of the target period relative to the contrast period is estimated based on the fitted contaminant concentration within the target period and the fitted contaminant concentration within the contrast period.

determining a weather-emission impact rate of change of the target period relative to the comparison period based on the second measured contaminant concentration in the target period and the third measured contaminant concentration in the comparison period;

based on the weather-induced change rate and the weather-induced change rate described above, the emission-induced change rate of the target period relative to the comparative period is evaluated.

The target time period and the comparison time period can be any time period and can be flexibly selected according to the evaluation requirement. For example, the target period may be 2023 year 4 month, the contrast period may be 2022 year 4 month, the contrast period may be 2023 year 3 month, or 2023 year 1 month-3 month, or the like.

In one possible implementation, referring to the technical route schematic of the comparative evaluation of the target period and the other periods shown in fig. 4, in the application scenario 2, the fitting period may be a period that satisfies the long-term condition, for example, may be a historical long-term period. At this time, the fitted contaminant concentration calculated by the objective fitting function determined by the above steps may include the contaminant concentration under the combined influence of the average emission level and weather.

Using the target period (t ₁ ) The weather data of (2) can calculate the weather comprehensive diagnosis index day by day, and the weather comprehensive diagnosis index is substituted into the target fitting function to obtain the fitting pollutant concentration day by day, and the average concentration C of the fitting pollutant in the period is further calculated ₁ . Similarly, a comparison period (t ₂ ) The weather data of (2) can calculate the weather comprehensive diagnosis index day by day, and the weather comprehensive diagnosis index is substituted into the target fitting function to obtain the fitting pollutant concentration day by day, and the average concentration C of the fitting pollutant in the period is further calculated ₂ . Calculation (C) ₁ -C ₂ )/C ₂ *100 percent, the change rate of the concentration of the pollutant in the target period compared with the weather condition difference in the comparison period can be obtained.

Obtaining an average value by using the daily measured pollutant concentration in the target period to obtain the measured pollutant Average concentration of dye C ₃ . Similarly, the average concentration C of the measured pollutant is obtained by calculating the average value of the measured pollutant concentration every day in the comparison period ₄ . Calculation (C) ₃ -C ₄ )/C ₄ *100%, the actual pollutant concentration change rate of the target period compared with the comparison period, namely the weather-emission influence change rate, can be obtained, and the pollutant concentration change rate caused by the weather condition difference and the emission difference is included. Subtracting the weather-emission impact rate of change from the weather-impact rate of change may evaluate the emission impact rate of change of the target period relative to the comparison period.

Application scenario 3: long term weather modification

and subtracting the fitting pollutant concentration in the target period from the fitting pollutant concentration under the weather average state condition, and determining the pollutant concentration change value under the weather influence in the target period.

And subtracting the pollutant concentration under the influence of the weather-emission and the pollutant concentration under the influence of the weather in the target period, and determining the pollutant concentration change value under the influence of the emission in the target period.

Further, the process of determining the weather modification concentration may be as follows:

and subtracting the change value of the concentration of the second actually measured pollutant in the target period from the change value of the concentration of the pollutant under the influence of the meteorological influence to determine the meteorological correction concentration.

As an example, with reference to the long term weather effect correction schematic of FIG. 5, the pollutant concentration of a year (target period: e.g., 2023) is measuredValue ofThe measured mean value of the contaminant concentration (++A) over many years (comparative history long term period: e.g. 2018-2022, 5 years)>)，/>Representative is the effect of the combined weather and emissions for the target period on the concentration of the contaminant, i.e., the change in concentration of the contaminant under the weather-emissions effect:

（4）

fitting a weather comprehensive diagnosis index for years (2018-2022) to the pollutant concentration day by day, and calculating the pollutant concentration under the weather average state condition based on a function obtained by fitting) The method comprises the steps of carrying out a first treatment on the surface of the Calculating a weather integrated diagnostic index for a target period (e.g., 2023), calculating a target period contaminant fitting concentration based on a fitted function >；/>Representative is the effect of the meteorological conditions after filtering out emissions effects on the concentration of contaminants, i.e. the change in concentration of contaminants under the meteorological effects:

（5）

representative are the effects of emissions on pollutants (i.e. the change in concentration of pollutants under the influence of emissions) after filtering out the influence of meteorological conditions, +.>Represents the concentration of the contaminant after filtering out the effect of the weather conditions (i.e., the weather corrected concentration):

（6）

（7）

the embodiment of the application has the following beneficial effects:

The embodiment of the application provides a pollutant concentration evaluation device which is used for realizing the pollutant concentration evaluation method. As shown in a schematic block diagram of an apparatus for estimating a concentration of a contaminant shown in fig. 6, an apparatus 600 for estimating a concentration of a contaminant includes: a first determination module 601, a fitting module 602, a second determination module 603, a third determination module 604, and an evaluation module 605.

A first determining module 601, configured to determine a fitting period, and determine a first integrated diagnostic index of an meteorological and a first measured contaminant concentration of a target area in the fitting period;

a fitting module 602, configured to determine a target fitting function of the target area based on the first weather integrated diagnostic index and the first measured contaminant concentration during the fitting period, where the target fitting function is configured to indicate a mapping relationship between the weather integrated diagnostic index and the contaminant concentration;

A second determining module 603, configured to determine a target period to be evaluated, and determine a second weather comprehensive diagnostic index of the target area within the target period;

a third determination module 604 for determining a fitted contaminant concentration of the target area within the target period based on the target fitting function and a second weather integrated diagnostic index within the target period;

an evaluation module 605 for evaluating a pollutant concentration effect of weather on the target area and/or evaluating a pollutant concentration effect of emissions on the target area based on the fitted pollutant concentrations over the target period.

Optionally, the first determining module 601 is configured to:

acquiring first meteorological data of the target area in the fitting period;

Optionally, the second determining module 603 is configured to:

acquiring second meteorological data of the target area in the target period;

Optionally, the fitting module 602 is configured to:

the evaluation module 605 is configured to:

acquiring a second measured contaminant concentration within the target period;

The evaluation module 605 is configured to:

the evaluation module 605 is configured to:

The evaluation module 605 is configured to:

Optionally, the evaluation module 605 is configured to:

Optionally, the evaluation module 605 is further configured to:

In the embodiment of the application, a mapping relation between a weather comprehensive diagnostic index and a pollutant concentration is constructed by fitting a first weather comprehensive diagnostic index and a first actually measured pollutant concentration in a fitting period to obtain a target fitting function; during the evaluation, the second weather integrated diagnostic index for the target period is substituted into the target fitting function to determine the fitting contaminant concentration within the target period. The fitting pollutant concentration can be used for respectively and quantitatively evaluating the influence of weather and emission on the pollutant concentration under different scenes. Because the fitting function between the meteorological comprehensive diagnosis index and the pollutant concentration is constructed, compared with a numerical model and a filtering statistical model, the method can flexibly discuss long-term and short-term meteorological and emission contributions, and has the advantages of small calculation resource consumption, clear physical meaning of the model and the like.

The exemplary embodiment of the application also provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor. The memory stores a computer program executable by the at least one processor for causing the electronic device to perform a method according to an embodiment of the application when executed by the at least one processor.

The exemplary embodiments of the present application also provide a non-transitory computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is for causing the computer to perform a method according to an embodiment of the present application.

The exemplary embodiments of the application also provide a computer program product comprising a computer program, wherein the computer program, when being executed by a processor of a computer, is for causing the computer to perform a method according to an embodiment of the application.

Referring to fig. 7, a block diagram of an electronic device 700 that may be a server or a client of the present application will now be described, which is an example of a hardware device that may be applied to aspects of the present application. Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the applications described and/or claimed herein.

As shown in fig. 7, the electronic device 700 includes a computing unit 701 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 may also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

Various components in the electronic device 700 are connected to the I/O interface 705, including: an input unit 706, an output unit 707, a storage unit 708, and a communication unit 709. The input unit 706 may be any type of device capable of inputting information to the electronic device 700, and the input unit 706 may receive input numeric or character information and generate key signal inputs related to user settings and/or function controls of the electronic device. The output unit 707 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, video/audio output terminals, vibrators, and/or printers. Storage unit 708 may include, but is not limited to, magnetic disks, optical disks. The communication unit 709 allows the electronic device 700 to exchange information/data with other devices through computer networks, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and/or chipsets, such as bluetooth devices, wiFi devices, wiMax devices, cellular communication devices, and/or the like.

The computing unit 701 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above. For example, in some embodiments, the method of assessing contaminant concentration may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 700 via the ROM 702 and/or the communication unit 709. In some embodiments, the computing unit 701 may be configured to perform the method of estimating the contaminant concentration by any other suitable means (e.g., by means of firmware).

Program code for carrying out methods of the present application may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present application, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

Claims

1. A method of assessing a concentration of a contaminant, the method comprising:

estimating a contaminant concentration effect of weather on the target area, and/or estimating a contaminant concentration effect of emissions on the target area, based on the fitted contaminant concentrations over the target period;

When the target period is a period of emission control, and the fitting period is a period of normal emission before and after emission control:

the estimating the effect of emissions on the pollutant concentration of the target zone based on the fitted pollutant concentrations over the target period of time comprises:

acquiring a second measured contaminant concentration within the target period;

subtracting the fitted pollutant concentration from the second measured pollutant concentration in the target period to determine a pollutant concentration variation value under the control of the emission pipe;

wherein, when the fitting period is a period satisfying a preset long-term condition:

estimating an emission-impact rate of change of the target period relative to the contrast period based on the weather-impact rate of change and the weather-emission-impact rate of change;

2. The method of claim 1, wherein said determining a first meteorological synthetic diagnostic index for the target region over the fit period comprises:

acquiring first meteorological data of the target area in the fitting period;

3. The method of claim 2, wherein the determining a second weather integrated diagnostic index for the target area over the target period comprises:

Acquiring second meteorological data of the target area in the target period;

4. The method of claim 1, wherein the determining the target fitting function for the target region based on the first weather integrated diagnostic index and the first measured contaminant concentration over the fitting period comprises:

5. The method of claim 1, wherein said determining the fit contaminant concentration under climatically averaged state conditions comprises:

6. The method of claim 5, wherein the method further comprises:

7. An apparatus for estimating a concentration of a contaminant, the apparatus comprising:

8. An electronic device, comprising:

a processor; and

a memory in which a program is stored,

wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the method according to any of claims 1-6.

9. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-6.