CN115840793A - Meteorological space normalization method and system based on random forest - Google Patents
Meteorological space normalization method and system based on random forest Download PDFInfo
- Publication number
- CN115840793A CN115840793A CN202211591261.6A CN202211591261A CN115840793A CN 115840793 A CN115840793 A CN 115840793A CN 202211591261 A CN202211591261 A CN 202211591261A CN 115840793 A CN115840793 A CN 115840793A
- Authority
- CN
- China
- Prior art keywords
- meteorological
- city
- cities
- data
- concentration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000007637 random forest analysis Methods 0.000 title claims abstract description 45
- 238000010606 normalization Methods 0.000 title claims abstract description 44
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 64
- 231100000719 pollutant Toxicity 0.000 claims abstract description 64
- 238000009792 diffusion process Methods 0.000 claims abstract description 57
- 230000008859 change Effects 0.000 claims abstract description 53
- 238000003915 air pollution Methods 0.000 claims abstract description 51
- 238000000034 method Methods 0.000 claims abstract description 45
- 230000001419 dependent effect Effects 0.000 claims description 11
- 238000011156 evaluation Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 5
- 230000009286 beneficial effect Effects 0.000 abstract description 7
- 238000010835 comparative analysis Methods 0.000 abstract description 5
- 238000001303 quality assessment method Methods 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000002349 favourable effect Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000012512 characterization method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 239000000443 aerosol Substances 0.000 description 1
- 239000000809 air pollutant Substances 0.000 description 1
- 231100001243 air pollutant Toxicity 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007865 diluting Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000006552 photochemical reaction Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a meteorological space normalization method and system based on random forests, and relates to the technical field of air quality assessment. The method comprises the following steps: acquiring meteorological conditions and atmospheric pollutant concentration data of a plurality of target cities; constructing a random forest model for each target city; sequentially replacing meteorological data in the city independent variable data set with meteorological data of other cities; inputting each replaced independent variable data set into the constructed random forest model to obtain a plurality of groups of predicted values of the concentration of the atmospheric pollutants; and calculating the change rate of each group of concentration predicted values relative to the observation values, and comparing and evaluating the air pollution meteorological diffusion conditions of each city, wherein the greater the relative change rate is, the more optimal the meteorological diffusion conditions are. The method can be used for evaluating the difference of the atmospheric pollutant concentration of a plurality of cities under the normalized meteorological conditions and the real meteorological conditions, and is beneficial to the comparative evaluation of the advantages and disadvantages of meteorological diffusion conditions of different cities.
Description
Technical Field
The invention relates to the technical field of air quality assessment, in particular to a meteorological space normalization method and system based on a random forest.
Background
The air pollution meteorological diffusion condition refers to the meteorological evaluation of the capability of meteorological conditions for diluting, diffusing and removing air pollutants. Under the increasing influence of human activities, the population, traffic, urban planning and energy consumption of areas are significantly changed, resulting in increasingly prominent air pollution problems. In terms of air quality, the influence of the weather diffusion condition is important in addition to the comprehensive influence of the emission of local pollutants, the influence of external pollution sources, the generation of secondary pollutants in chemical reaction and the like. Research shows that in relatively clean areas, the contribution rate of meteorological conditions to the influence of air quality can reach 80-90% within the allowable range of atmospheric environment capacity. In different cities, the meteorological conditions of the cities are different due to different factors such as geographical positions, terrain conditions and the like, so that the air pollution meteorological diffusion conditions are obviously different. With comparable emission levels and regulatory levels, air quality in different cities may have significant gaps. Therefore, the assessment of the air pollution meteorological diffusion conditions of each city is helpful to enhance the understanding of the air pollution cause and the atmospheric pollutant holding capacity of each city, and the establishment of a corresponding control scheme according to the specific conditions of each city is facilitated, so that certain reference is provided for the establishment of an environmental management policy.
For the assessment of the air pollution meteorological diffusion conditions of the urban population, a scholars designs two methods for respectively assessing the environmental meteorological condition index (EMI) and the meteorological integrated index (MSI) of the urban. The EMI index refers to the rate of change in aerosol concentration caused by the weather conditions under constant emissions when compared to one another in the same month between different years. The MSI index is a comprehensive index considering Photochemical Reaction Conditions (PRC) and Physical Diffusion Capacity (PDC). Both indexes are used for comprehensively evaluating the air pollution meteorological diffusion conditions of cities, and can be used for comparison among different cities. EMI index mainly for PM 2.5 Pollution meteorological condition evaluation, and MSI meteorological index takes temperature, solar radiation and wind speed into consideration, so that the method is suitable for evaluating city pair O 3 Polluted weather conditionsHowever, due to the complexity of meteorological effects, the uncertainty of these exponential assessment results is large.
The meteorological space normalization method comprises the steps of calculating the atmospheric pollutant concentration of each city under the normalized meteorological condition, calculating the change rate of the normalized atmospheric pollutant concentration relative to an observation value, and reflecting the difference of air pollution meteorological diffusion conditions among different cities. The larger the change rate is, the better the meteorological diffusion condition is; and vice versa. The analysis result of the weather normalization method has certain reference significance for formulation of relevant policies, and the method only needs conventional weather and air quality monitoring data, and the calculated amount is small.
Disclosure of Invention
The invention provides a meteorological space normalization method and a meteorological space normalization system based on a random forest, which are used for evaluating whether meteorological conditions of different cities are favorable for dissipation of atmospheric pollutants and comparing and evaluating air pollution meteorological diffusion conditions of various cities.
The embodiment of the invention is realized by the following steps:
in a first aspect, the invention provides a meteorological space normalization method based on a random forest, which comprises the following steps:
acquiring meteorological conditions and atmospheric pollutant concentration data of a plurality of target cities;
taking the time indication variable and the meteorological variable of each target city as independent variables, taking the concentration of atmospheric pollutants as dependent variables, and constructing a random forest model for each city;
sequentially replacing meteorological data in the independent variable data set of each target city with meteorological data of other cities to obtain a plurality of groups of replaced independent variable data sets;
respectively inputting the independent variable data sets after the target cities are replaced into random forest models of corresponding cities to obtain a plurality of groups of predicted values of the concentration of the atmospheric pollutants;
calculating the average value of all predicted values of the concentration of the atmospheric pollutants, namely a meteorological space normalization result, calculating the change rate of the atmospheric pollutants relative to the observation value, and evaluating and comparing the air pollution meteorological diffusion conditions of various cities according to the relative change rate, wherein the greater the relative change rate is, the more optimal the air pollution meteorological diffusion conditions are;
XV＝(AP P -AP T )/AP T
wherein XV is the change rate of the meteorological space normalized predicted value relative to the observation value of the atmospheric pollutant concentration, AP P Normalized prediction value of meteorological space, AP, for atmospheric pollutant concentration T Is an observed value of the concentration of the atmospheric pollutants.
The invention provides a meteorological space normalization method and a meteorological space normalization system based on a random forest, which are used for comparing and evaluating air pollution meteorological diffusion conditions among different cities, namely the greater the relative change rate is, the better the air pollution meteorological diffusion conditions are. The method fully considers the influence of various meteorological factors on the urban air quality, adopts a meteorological space normalization method, takes a time indicator variable and a meteorological variable as independent variables, takes the concentration of atmospheric pollutants as dependent variables, and constructs a random forest model. And sequentially replacing the meteorological data in the independent variable data set of the city with meteorological data of other cities aiming at each target city to obtain a plurality of groups of replaced independent variable data sets. And inputting the obtained multiple groups of replaced autovariate data sets into the established random forest model to obtain multiple groups of predicted values of the concentration of the atmospheric pollutants. And calculating the mean value of each group to be used as a meteorological space normalization predicted value, and calculating the change rate of the meteorological space normalization predicted value relative to the observation value, wherein the change rate is used for evaluating and comparing the air pollution meteorological diffusion conditions of each city. The method can be used for calculating the change rate of the atmospheric pollutant concentration relative to the observation value of each city under the normalized meteorological condition, and is beneficial to comparative evaluation of the air pollution meteorological diffusion conditions of different cities.
Based on the first aspect, in some embodiments of the present invention, for each target city, sequentially replacing the meteorological data in the independent variable data set with meteorological data of other cities to obtain multiple sets of replaced independent variable data sets, including the following steps:
and aiming at each target city, sequentially replacing meteorological data in the independent variable data set with meteorological data of other cities to obtain a plurality of groups of replaced independent variable data sets of the city.
Based on the first aspect, in some embodiments of the present invention, the expression of the random forest model of the target city is:
Y＝f(W 1 ,W 2 ,…,W m ,T 1 ,T 2 ,…,T n )
(4)
wherein Y is an atmospheric pollutant (e.g., NO) of the city 2 ) Concentration, W 1 ,W 2 ,…W m Is a meteorological variable (Table 1), T 1 ,T 2 ,…T n Is a time indicator variable (table 1).
TABLE 1 time indicating variable and meteorological variable table
In some embodiments of the invention according to the first aspect, the independent variables comprise a meteorological variable and a time indicator variable.
In a second aspect, the invention provides a meteorological space normalization system based on a random forest, which comprises a data acquisition module, a model construction module, a data replacement module, a prediction analysis module and an evaluation module, wherein:
the data acquisition module is used for acquiring meteorological conditions and atmospheric pollutant concentration data of a plurality of target cities;
the model building module is used for building a random forest model for each city by taking the time indication variable and the meteorological variable of each target city as independent variables and taking the concentration of atmospheric pollutants as dependent variables;
the data replacement module is used for sequentially replacing meteorological data in the independent variable data set of each target city with meteorological data of other cities to obtain a plurality of groups of replaced independent variable data sets;
the prediction analysis module is used for inputting the independent variable data sets after the target cities are replaced into random forest models of corresponding cities to obtain a plurality of groups of atmospheric pollutant concentration predicted values;
the evaluation module is used for calculating the average value of all predicted values of the concentration of the atmospheric pollutants, namely the meteorological space normalized predicted value, calculating the change rate of the meteorological space normalized predicted value relative to the observation value, and evaluating and comparing the air pollution diffusion meteorological conditions of the atmospheric pollutants of various cities according to the relative change rate (namely, the larger the relative change rate is, the better the air pollution diffusion meteorological conditions are);
XV＝(AP P -AP T )/AP T
wherein XV is the change rate of the meteorological space normalized predicted value relative to the observation value of the atmospheric pollutant concentration, AP P Normalized prediction value of meteorological space, AP, for atmospheric pollutant concentration T An atmospheric pollutant concentration observation is taken.
The system fully considers the influence of various meteorological factors on the urban air pollution meteorological diffusion condition through the cooperation of a plurality of modules such as a data acquisition module, a model construction module, a data replacement module, a prediction analysis module and an evaluation module, adopts a meteorological space normalization method, takes a time indicator variable and a meteorological variable as independent variables, takes the concentration of atmospheric pollutants as dependent variables, and constructs a random forest model. Sequentially replacing meteorological data in the independent variable data set of each target city with meteorological data of other cities aiming at each target city; and inputting the obtained multiple groups of replaced independent variable data into the established random forest model to obtain multiple groups of predicted values of the concentration of the atmospheric pollutants, calculating the mean value of the predicted values as a meteorological space normalization result, calculating the change rate of the predicted values relative to the observation value, and evaluating and comparing the meteorological diffusion conditions of the air pollution of each city. The method can be used for calculating the change rate of the atmospheric pollutant concentration value under the normalized meteorological condition relative to the real meteorological condition of different cities, and is beneficial to comparatively evaluating the air pollution meteorological diffusion conditions of different cities.
The invention has at least the following advantages or beneficial effects:
the invention discloses a meteorological space normalization method and a meteorological space normalization system based on a random forest. The method and the system comprehensively consider the influence of a plurality of meteorological conditions on the urban air quality, and construct the response relation of the meteorological conditions by a machine learning method. Sequentially taking meteorological data of other cities as a group of replaced meteorological data of the city to obtain a plurality of groups of replaced autovariate data sets; and then, inputting the obtained multiple groups of replaced independent variable data sets into the established random forest model for calculation to obtain multiple groups of predicted values of the concentration of the atmospheric pollutants. And calculating the mean value of each group to be used as a meteorological space normalized predicted value, and calculating the change rate of the meteorological space normalized predicted value relative to the observation value, wherein the change rate is used for evaluating and comparing the air pollution meteorological diffusion conditions of a plurality of cities. The method can be used for calculating the change rate of the atmospheric pollutant concentration relative to the observation value of each city under the normalized meteorological condition, and is beneficial to comparative evaluation of air pollution meteorological diffusion conditions among different cities. The data required by the method are conventional meteorological and air quality monitoring data, and the calculation amount is small.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to these drawings without inventive effort.
FIG. 1 is a flow chart of a method for meteorological space normalization based on random forests according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of weather normalization in a method for weather space normalization based on random forests according to an embodiment of the present invention;
FIG. 3 is a schematic block diagram of a meteorological space normalization system based on random forests according to an embodiment of the present invention.
Icon: 100. a data acquisition module; 200. a model building module; 300. a data replacement module; 400. a predictive analysis module; 500. and an evaluation module.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
Examples
As shown in fig. 1-2, in a first aspect, an embodiment of the present invention provides a method for meteorological space normalization based on a random forest, including the following steps:
s1, acquiring meteorological data and NO of 6 main cities (Beijing, shanghai, chengdu, wuhan, xian and Shenzhen) 2 Concentration data;
s2, independent variable (meteorological variable and time variable) and dependent variable (NO) based on each city 2 Concentration) data, a random forest model is established for each city.
With time-indicating variables and meteorological variables as arguments, NO 2 The concentration is used as a dependent variable, and a random forest model of the target city is constructed; the time indicating variables include trend term, year, month, day, week, hour and day from new year; meteorological variables include air temperature, relative humidity, wind speed, wind direction, and air pressure.
And S3, respectively replacing the meteorological variables on the spatial scale for multiple times to obtain multiple groups of replaced meteorological data on the spatial scale. Specifically, for each city, the meteorological data of other 5 cities are entirely replaced to the city to serve as 5 groups of replaced meteorological data of the city;
and S4, each city uses the established model, 5 groups of replaced meteorological data are used, each group of meteorological data and time variables are led into the model together to obtain a group of predicted values, and finally 5 groups of predicted values are obtained, and the 5 groups of predicted values calculate the average value according to time grouping to obtain the meteorological normalized concentration in the city space. The meteorological normalization on the space scale among cities is based on the calculation of NO of the cities under a normalized meteorological condition under the condition that the emission conditions of the cities are not changed 2 The concentration and the obtained weather normalization result can reflect whether the weather conditions of the city are better than those of other cities at the same time, namely the city air pollution weather diffusion conditions between different cities can be indirectly compared.
S5, calculating and combining NO of each group 2 The average value of the predicted concentration values is used as the normalization result of the meteorological space, the relative change rate of the predicted normalization value of the meteorological space relative to the observed value is calculated, and the relative change rate is calculated according to the phaseEvaluation of the rate of change and comparison of NO in various cities 2 Air pollution diffusion weather conditions (the greater the relative rate of change, NO) 2 The more optimal the air pollution diffusion meteorological conditions).
The invention discloses a meteorological space normalization method and system based on a random forest. The method and the system comprehensively consider the influence of a plurality of meteorological conditions on the air quality of the city, and construct the response relation of the method through a machine learning method. Most of the existing methods for evaluating the urban air pollution meteorological diffusion conditions are directed at a specific pollutant, and the method and the system provided by the invention are suitable for various atmospheric pollutants. The method and the system adopt a meteorological space normalization method, a time variable and a meteorological variable are used as independent variables, the concentration of atmospheric pollutants is used as a dependent variable to construct a random forest model, a spatial data replacement method is adopted to process meteorological data, and for each target city, the meteorological data of other cities are sequentially used as a group of replaced meteorological data of the city to obtain a plurality of groups of replaced independent variable data sets; and then, importing the obtained multiple groups of meteorological data into the replaced autovariate data set, and inputting the autovariate data set into the established random forest model for calculation to obtain multiple groups of predicted values of the atmospheric pollutant concentration. And calculating the mean value of each group to be used as a meteorological space normalization predicted value, and calculating the change rate of the meteorological space normalization predicted value relative to the observation value, wherein the change rate is used for evaluating and comparing the air pollution meteorological diffusion conditions of each city. The method can be used for calculating the change rate of the atmospheric pollutant concentration relative to the observation value of each city under the normalized meteorological condition, and is beneficial to comparative evaluation of the air pollution meteorological diffusion conditions of different cities. The data required by the method are conventional meteorological and air quality monitoring data, and the calculation amount is small.
Based on the first aspect, in some embodiments of the present invention, the expression of the target random forest model is: y = f (X) 1 ,X 2 ,…,X n ) Wherein: y is urban NO 2 Concentration, X 1 ,X 2 ,…X n For each predictor variable of the city. The predictive variables include meteorological variables and time variables. The independent variables are shown in table 1.
Based on the first aspect, in some embodiments of the present invention, the method for meteorological space normalization based on random forest further comprises the following steps:
and S5, displaying the result.
The results of the meteorological space normalization indicate that NO is present in different cities under respective emission conditions under a normalized meteorological condition 2 And (4) concentration. The relative change of the weather space normalized predicted value relative to the observed value in four seasons of spring, summer, autumn and winter represents whether the weather conditions of different cities are favorable for pollutant diffusion in different seasons, the larger the numerical value is, the better the weather conditions of the city are, the more favorable the pollutant diffusion is, namely, the more optimal the air pollution diffusion weather conditions are, and vice versa. It can thus be seen that in the six cities listed, NO 2 The air pollution diffusion meteorological condition of the Shenzhen is better than that of other cities every month. And except that the city with the worst air pollution diffusion weather conditions in summer is Beijing city, the other three seasons are the worst air pollution diffusion weather conditions in the Western-An city. Overall, six cities are expressed as NO 2 The air pollution diffusion meteorological conditions are ranked from good to bad as follows: shenzhen city>Shanghai city>Wuhan City>Beijing City>Adult city>Xi' an city.
TABLE 2 spatial weather normalized NO of six cities in each season 2 Rate of change (%) a
a NO normalized by space meteorology 2 Rate of change characterization of NO for each city 2 The greater the change rate value is, the more optimal the air pollution diffusion meteorological condition is
According to the relative change result of the space weather normalized predicted value relative to the observed value from 2019 to 2021, the larger the numerical value is, the better the weather condition of the city is, the more favorable the diffusion of pollutants is, namely, the air pollution diffusion weather stripThe more preferred the member and vice versa. No in Shenzhen city from 2019 to 2021 2 The air pollution diffusion meteorological conditions are the best (the change rates of 2019-2021 are 11.32%,18.31% and 11.69%, respectively); NO of Xian City 2 The air pollution diffusion meteorological conditions are the worst (the change rates of 2019-2021 are-6.24%, -4.37%, -5.91%, respectively). NO of each city 2 Sequencing of air pollution diffusion meteorological conditions and seasonal NO 2 The air pollution diffusion meteorological conditions are consistent and are as follows: shenzhen city>Shanghai city>Wuhan City>Beijing City>Adult city>Xi' an city. NO of each city 2 The air pollution diffusion weather conditions accord with the integral trend that the south is superior to the north and the east is superior to the west.
TABLE 3 spatial weather normalized NO of six major cities 2 Rate of change (%) a
| City | 2019 | 2020 | 2021 |
| Beijing City | 3.22 | 9.03 | 4.96 |
| Shanghai city | 5.65 | 7.61 | 9.03 |
| Adult city | -3.08 | -1.03 | -0.16 |
| Wuhan City | 4.65 | 5.96 | 6.60 |
| Shenzhen city | 11.32 | 18.31 | 11.69 |
| Xi' an city | -6.24 | -4.37 | -5.91 |
a NO normalized by space meteorology 2 Rate of change characterization of NO in various cities 2 The greater the change rate value is, the more optimal the air pollution diffusion meteorological condition is
As shown in fig. 3, in a second aspect, an embodiment of the present invention provides a system for meteorological space normalization based on a random forest, including a data obtaining module 100, a model building module 200, a data replacing module 300, a prediction analysis module 400, and an evaluation module 500, where:
a data acquisition module 100 for acquiring meteorological data and NO of a target city 2 Concentration data;
a model construction module 200 for using the time variable and the meteorological variable of the target city as independent variables, NO 2 Constructing a target random forest model by taking the concentration as a dependent variable;
the data replacement module 300 is configured to, for each target city, sequentially replace the meteorological data of the target city with meteorological data of other cities to obtain multiple sets of replaced meteorological data;
a prediction analysis module 400, configured to import each set of replaced meteorological variables and corresponding time data in the spatial scale into the target random forest model as a plurality of sets of prediction sets, and generate a plurality of sets of NOs 2 A concentration predicted value;
an evaluation module 500 for calculating and comparing NO for each group 2 The average value of the predicted concentration values is used as a meteorological normalization result, the relative change rate of the spatial meteorological normalization predicted value relative to the observed value is calculated, and NO of each city is evaluated and compared according to the relative change rate 2 The air pollution diffusion meteorological conditions (the relative change rate is also large, and the air pollution diffusion meteorological conditions are better).
The system comprehensively considers the influence of a plurality of meteorological conditions on the urban air quality through the cooperation of a plurality of modules such as a data acquisition module, a model construction module, a data replacement module, a prediction analysis module and an evaluation module, and constructs the response relation of the system through a machine learning method. Most of the existing methods for evaluating the urban air pollution meteorological diffusion conditions aim at a specific atmospheric pollutant, and the method and the system provided by the invention are suitable for various atmospheric pollutants. The system takes a time variable and a meteorological variable as independent variables, takes the concentration of atmospheric pollutants as a dependent variable to construct a random forest model, adopts a spatial data replacement method to process meteorological data, and sequentially takes the meteorological data of other cities as a group of replaced meteorological data of the city aiming at each target city so as to obtain a plurality of groups of replaced independent variable data sets; and then, importing the obtained multiple groups of meteorological data into the replaced autovariate data set, and inputting the autovariate data set into the established random forest model for calculation to obtain multiple groups of predicted values of the atmospheric pollutant concentration. And calculating the mean value of each group to be used as a meteorological space normalization predicted value, and calculating the change rate of the meteorological space normalization predicted value relative to the observation value, wherein the change rate is used for evaluating and comparing the air pollution meteorological diffusion conditions of each city. The method can be used for calculating the change rate of the atmospheric pollutant concentration relative to the observation value of each city under the normalized meteorological condition, and is beneficial to comparative evaluation of the air pollution meteorological diffusion conditions of different cities. The data required by the method are conventional meteorological and air quality monitoring data, and the calculation amount is small.
In the embodiments provided in the present application, it should be understood that the disclosed method and system and method can be implemented in other ways. The method and system embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (5)
1. A meteorological space normalization method based on a random forest is characterized by comprising the following steps:
acquiring meteorological conditions and atmospheric pollutant concentration data of a plurality of target cities;
taking the time indication variable and the meteorological variable of each target city as independent variables, taking the concentration of atmospheric pollutants as dependent variables, and constructing a random forest model for each city;
sequentially replacing meteorological data in the independent variable data set of each target city with meteorological data of other cities to obtain a plurality of groups of replaced independent variable data sets;
respectively inputting the independent variable data sets after the target cities are replaced into random forest models of corresponding cities to obtain a plurality of groups of predicted values of the concentration of the atmospheric pollutants;
calculating the average value of all predicted values of the concentration of the atmospheric pollutants, namely a meteorological space normalization result, calculating the change rate of the atmospheric pollutants relative to the observation value, and evaluating and comparing the air pollution meteorological diffusion conditions of various cities according to the relative change rate, wherein the greater the relative change rate is, the more optimal the air pollution meteorological diffusion conditions are;
XV＝(AP P -AP T )/AP T
wherein XV is the change rate of the meteorological space normalized predicted value relative to the observation value of the atmospheric pollutant concentration, AP P Normalized prediction value of meteorological space, AP, for atmospheric pollutant concentration T Is an observed value of the concentration of the atmospheric pollutants.
2. The method as claimed in claim 1, wherein for each target city, sequentially replacing meteorological data in the independent variable data set with meteorological data of other cities to obtain a plurality of replaced independent variable data sets, the method comprises the following steps:
and sequentially replacing the meteorological data in the city independent variable data set with meteorological data of other cities aiming at each target city to obtain a plurality of groups of replaced independent variable data sets of the target city.
3. The method as claimed in claim 1, wherein the expression of the random forest model of the target city is as follows:
Y＝f(W 1 ,W 2 ,…,W m ，T 1 ,T 2 ,…,T n )
wherein Y is an atmospheric pollutant (e.g., NO) of the city 2 ) Concentration, W 1 ,W 2 ,…W m As meteorological independent variables, T 1 ,T 2 ,…T n A variable is indicated for time.
4. A method for meteorological space normalization based on random forests, according to claim 1, wherein the independent variables comprise meteorological variables, time indicating variables and the like.
5. The random forest based meteorological space normalization system is characterized by comprising a data acquisition module, a model construction module, a data replacement module, a prediction analysis module and an evaluation module, wherein:
the data acquisition module is used for acquiring meteorological conditions and atmospheric pollutant concentration data of a plurality of target cities;
the model building module is used for building a random forest model for each city by taking the time indication variable and the meteorological variable of each target city as independent variables and taking the concentration of atmospheric pollutants as dependent variables;
the data replacement module is used for sequentially replacing meteorological data in the independent variable data set of each target city with meteorological data of other cities to obtain a plurality of groups of replaced independent variable data sets;
the prediction analysis module is used for inputting the independent variable data sets after the target cities are replaced into random forest models of corresponding cities to obtain a plurality of groups of atmospheric pollutant concentration predicted values;
the evaluation module is used for calculating the average value of all predicted values of the concentration of the atmospheric pollutants, namely the meteorological space normalized predicted value, calculating the change rate of the meteorological space normalized predicted value relative to the observation value, and evaluating and comparing the air pollution diffusion meteorological conditions of the atmospheric pollutants of various cities according to the relative change rate (namely, the larger the relative change rate is, the better the air pollution diffusion meteorological conditions are);
XV＝(AP P -AP T )/AP T
wherein XV is the change rate of the meteorological space normalized predicted value relative to the observation value of the atmospheric pollutant concentration, AP P Weather space normalized prediction value, AP, for atmospheric pollutant concentration T An atmospheric pollutant concentration observation is taken.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211591261.6A CN115840793B (en) | 2022-12-12 | 2022-12-12 | Meteorological space normalization method and system based on random forest |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211591261.6A CN115840793B (en) | 2022-12-12 | 2022-12-12 | Meteorological space normalization method and system based on random forest |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115840793A true CN115840793A (en) | 2023-03-24 |
| CN115840793B CN115840793B (en) | 2024-05-07 |
Family
ID=85578442
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211591261.6A Active CN115840793B (en) | 2022-12-12 | 2022-12-12 | Meteorological space normalization method and system based on random forest |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115840793B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2161321C2 (en) * | 1998-07-14 | 2000-12-27 | Государственный ракетный центр "КБ им. акад. В.П. Макеева" | Process of control over effluent of polluting substances from sources polluting city atmosphere |
| KR20050004316A (en) * | 2003-06-27 | 2005-01-12 | 재단법인 포항산업과학연구원 | Prediction method of polluted air dispersion using multiple meteorological data |
| CN106250666A (en) * | 2016-06-22 | 2016-12-21 | 中国水利水电科学研究院 | A kind of irrigation system ecumene lake nitrogen and phosphorus loading analogy method |
| CN110288138A (en) * | 2019-06-12 | 2019-09-27 | 淮阴工学院 | A method of the air quality index prediction divided based on community |
| CN110531030A (en) * | 2019-08-16 | 2019-12-03 | 北京慧辰资道资讯股份有限公司 | A kind of method and device based on the analysis of Internet of Things big data atmosphere pollution |
| CN110673229A (en) * | 2019-10-23 | 2020-01-10 | 新亚优华科技有限公司 | Atmospheric pollutant diffusion track tracking method based on hotspot grid technology |
| CN111461439A (en) * | 2020-04-02 | 2020-07-28 | 浙江大学 | Urban atmospheric diffusion process-based simulation prediction multi-heat-source heat supply system load scheduling distribution method and system |
| CN111489015A (en) * | 2020-03-20 | 2020-08-04 | 天津大学 | Atmosphere O based on multiple model comparison and optimization3Concentration prediction method |
| US20210080614A1 (en) * | 2018-02-05 | 2021-03-18 | Hitachi, Ltd. | Weather Prediction Correction Method and Weather Prediction System |
| CN112798013A (en) * | 2019-11-13 | 2021-05-14 | 中国科学院光电研究院 | Method for verifying on-orbit absolute radiation calibration result of optical load |
| CN114266200A (en) * | 2022-02-24 | 2022-04-01 | 山东大学 | Nitrogen dioxide concentration prediction method and system |
| CN114912343A (en) * | 2022-03-30 | 2022-08-16 | 南通大学 | LSTM neural network-based air quality secondary prediction model construction method |
| CN115033809A (en) * | 2022-05-20 | 2022-09-09 | 浙江工业大学 | Urban particulate matter space-time management and control method |
| CN115146537A (en) * | 2022-07-12 | 2022-10-04 | 四川大学 | Atmospheric pollutant emission estimation model construction method and system based on power consumption |
| CN115293360A (en) * | 2022-07-12 | 2022-11-04 | 中国环境科学研究院 | Atmospheric pollutant concentration analysis method and device and storage medium |
-
2022
- 2022-12-12 CN CN202211591261.6A patent/CN115840793B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2161321C2 (en) * | 1998-07-14 | 2000-12-27 | Государственный ракетный центр "КБ им. акад. В.П. Макеева" | Process of control over effluent of polluting substances from sources polluting city atmosphere |
| KR20050004316A (en) * | 2003-06-27 | 2005-01-12 | 재단법인 포항산업과학연구원 | Prediction method of polluted air dispersion using multiple meteorological data |
| CN106250666A (en) * | 2016-06-22 | 2016-12-21 | 中国水利水电科学研究院 | A kind of irrigation system ecumene lake nitrogen and phosphorus loading analogy method |
| US20210080614A1 (en) * | 2018-02-05 | 2021-03-18 | Hitachi, Ltd. | Weather Prediction Correction Method and Weather Prediction System |
| CN110288138A (en) * | 2019-06-12 | 2019-09-27 | 淮阴工学院 | A method of the air quality index prediction divided based on community |
| CN110531030A (en) * | 2019-08-16 | 2019-12-03 | 北京慧辰资道资讯股份有限公司 | A kind of method and device based on the analysis of Internet of Things big data atmosphere pollution |
| CN110673229A (en) * | 2019-10-23 | 2020-01-10 | 新亚优华科技有限公司 | Atmospheric pollutant diffusion track tracking method based on hotspot grid technology |
| CN112798013A (en) * | 2019-11-13 | 2021-05-14 | 中国科学院光电研究院 | Method for verifying on-orbit absolute radiation calibration result of optical load |
| CN111489015A (en) * | 2020-03-20 | 2020-08-04 | 天津大学 | Atmosphere O based on multiple model comparison and optimization3Concentration prediction method |
| CN111461439A (en) * | 2020-04-02 | 2020-07-28 | 浙江大学 | Urban atmospheric diffusion process-based simulation prediction multi-heat-source heat supply system load scheduling distribution method and system |
| CN114266200A (en) * | 2022-02-24 | 2022-04-01 | 山东大学 | Nitrogen dioxide concentration prediction method and system |
| CN114912343A (en) * | 2022-03-30 | 2022-08-16 | 南通大学 | LSTM neural network-based air quality secondary prediction model construction method |
| CN115033809A (en) * | 2022-05-20 | 2022-09-09 | 浙江工业大学 | Urban particulate matter space-time management and control method |
| CN115146537A (en) * | 2022-07-12 | 2022-10-04 | 四川大学 | Atmospheric pollutant emission estimation model construction method and system based on power consumption |
| CN115293360A (en) * | 2022-07-12 | 2022-11-04 | 中国环境科学研究院 | Atmospheric pollutant concentration analysis method and device and storage medium |
Non-Patent Citations (5)
| Title |
|---|
| SHAH 等: "Balluino:High Altitude Balloon/Drone Based Air Pollution and PM 2.5 Monitoring System", 2019 IEEE LONG ISLAND SYSTEMS, APPLICATIONS AND TECHNOLOGY CONFERENCE(LISAT), 3 March 2019 (2019-03-03), pages 1 - 5 * |
| 夏豫齐: "大气稀释扩散能力与污染物(SO_2)浓度变化规律(初步分析)", 环境科学与技术, no. 03, 18 August 1980 (1980-08-18), pages 43 - 53 * |
| 李莹 等: "基于GIS的陕西省大气污染物的时空分布研究", 《新型工业化》, vol. 11, no. 6, pages 33 - 35 * |
| 王戎骁 等: "基于源项估计的污染气体扩散数据驱动仿真", 《系统仿真学报》, vol. 29, no. 9, 8 September 2017 (2017-09-08), pages 2100 - 2109 * |
| 郑磊 等: "基于GIS的邹城工业园区大气污染物浓度时空变化研究", 《中国资源综合利用》, vol. 38, no. 5, 25 May 2020 (2020-05-25), pages 19 - 23 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115840793B (en) | 2024-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111523717B (en) | Inversion estimation method of atmospheric pollutant emission list | |
| Yue et al. | Ensemble projections of wildfire activity and carbonaceous aerosol concentrations over the western United States in the mid-21st century | |
| Rotmans et al. | Climate change implications for Europe: an application of the ESCAPE model | |
| CN109916788B (en) | PM pair for distinguishing emission change and meteorological condition change of different areas2.5Method for influencing concentration | |
| Gilliam et al. | New methods for evaluating meteorological models used in air quality applications | |
| Bonazountas et al. | Forest fire risk analysis | |
| Li et al. | Spatial and temporal variations of aerosol optical depth in China during the period from 2003 to 2006 | |
| Valari et al. | Using a chemistry transport model to account for the spatial variability of exposure concentrations in epidemiologic air pollution studies | |
| Guo et al. | Spatial distributions and temporal variations of atmospheric aerosols and the affecting factors: a case study for a region in central China | |
| Wang et al. | Spatiotemporal variability in long-term population exposure to PM2. 5 and lung cancer mortality attributable to PM2. 5 across the Yangtze River Delta (YRD) region over 2010–2016: A multistage approach | |
| Peng | Air quality prediction by machine learning methods | |
| Yuan et al. | The evolving distribution of relative humidity conditional upon daily maximum temperature in a warming climate | |
| Han et al. | Quantifying trade‐offs of land multifunctionality evaluated by set pair analysis in ecologically vulnerable areas of northwestern China | |
| Chen et al. | The influence of synoptic weather patterns on spatiotemporal characteristics of ozone pollution across Pearl River Delta of southern China | |
| Liu et al. | Age Structure and Carbon Emission with Climate-Extended STIRPAT Model-A Cross-Country Analysis | |
| Lin et al. | A data-driven framework for abnormally high building energy demand detection with weather and block morphology at community scale | |
| Kutty et al. | A systematic review of climate change implications on building energy consumption: impacts and adaptation measures in hot urban desert climates | |
| Hernández et al. | Land use change in central Florida and sensitivity analysis based on agriculture to urban extreme conversion | |
| CN115840793B (en) | Meteorological space normalization method and system based on random forest | |
| Ju et al. | Analysis and research of absorbing aerosols in Beijing-Tianjin-Hebei region | |
| Hassan et al. | Assessment of meteorological and air quality drivers of elevated ambient ozone in Beijing via machine learning approach | |
| Bowker et al. | Climate change and outdoor recreation participation in the Southern United States | |
| Peng et al. | A spatially explicit framework for assessing ecosystem service supply risk under multiple land‐use scenarios in the Xi'an Metropolitan Area of China | |
| CN111950813B (en) | Meteorological drought monitoring and predicting method | |
| Lei et al. | Analysis of remote sensing monitoring of atmospheric ozone in Japan from 2010 to 2021 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |