CN110989043A - Air quality index grade probability forecasting method and device and storage medium - Google Patents
Air quality index grade probability forecasting method and device and storage medium Download PDFInfo
- Publication number
- CN110989043A CN110989043A CN201911359217.0A CN201911359217A CN110989043A CN 110989043 A CN110989043 A CN 110989043A CN 201911359217 A CN201911359217 A CN 201911359217A CN 110989043 A CN110989043 A CN 110989043A
- Authority
- CN
- China
- Prior art keywords
- air quality
- quality index
- probability
- forecasting
- level
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method, e.g. intermittent, or the display, e.g. digital
- G01N33/0063—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method, e.g. intermittent, or the display, e.g. digital using a threshold to release an alarm or displaying means
Abstract
The application discloses an air quality index grade probability forecasting method, device and storage medium, wherein the method comprises the following steps: acquiring air quality data forecasted by various air quality forecasting methods; the air quality data comprises air quality fraction indices of a plurality of pollutants; calculating a class probability of an air quality index for each of the contaminants; the level probability of the air quality index is the probability that the air quality index belongs to each air quality index level; calculating a class probability of an air quality index based on the class probability of the air quality index of each of the pollutants; the level probability of the air quality index is the probability that the air quality index belongs to each air quality index level. The method carries out air quality prediction based on various prediction methods, and gives the air quality index level probability prediction result by adopting a conditional probability method, so that the accuracy of the prediction result is higher, and the service prediction requirements of relevant departments can be better met.
Description
Technical Field
The application relates to the technical field of air quality prediction, in particular to a method and a device for predicting air quality index grade probability and a storage medium.
Background
In recent years, the problem of air pollution has become serious and has attracted much attention. Reasonable air quality prediction can help government departments to make decisions so as to limit the discharge amount of artificial pollutants, guide the public to avoid pollution peak periods, reduce exposure time and reduce health risks caused by pollution. The air quality mode can simulate the physical and chemical reaction processes of pollutants and can provide four-dimensional pollutant concentration space-time characteristics with physical significance, and the air quality mode becomes a main means for short-time near and medium-term air quality prediction at present.
The air quality mode simulation pollutant concentration change is actually to solve a highly complex nonlinear partial differential equation system, and as more small-scale motion processes cannot be expressed explicitly in the system, and an absolutely correct initial and boundary condition cannot be obtained, the prediction value of the air quality mode is uncertain all the time. The deterministic forecast based on the model simulation results does not reflect the uncertainty of the model itself, which may lead the government department to make over-aggressive decisions, resulting in unnecessary economic loss.
Probability prediction can quantify uncertainty of prediction results, more information is given relative to the certainty prediction, and the probability prediction is a new direction of air quality prediction research. At present, probability forecasting of air quality is in a starting stage, the existing research mainly focuses on diagnosis, identification and analysis of key uncertainty sources of an air quality mode, the research content is complex and huge, a mode quantitative uncertainty diagnosis system is generally constructed by adopting methods such as sensitivity analysis, Bayesian statistical inference and the like, then, on the basis of numerical simulation, the probability forecasting is formed by incorporating various uncertainty analysis results of modes and input, and a pollutant concentration probability distribution result is obtained. At present, in the probability forecasting research in the air pollution field, a method for giving air quality index level probability forecasting based on air quality forecasting results of various forecasting methods does not exist, and the existing air quality probability forecasting cannot meet the business forecasting requirement.
Disclosure of Invention
The application aims to provide an air quality index grade probability forecasting method, an air quality index grade probability forecasting device and a storage medium. The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview and is intended to neither identify key/critical elements nor delineate the scope of such embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.
According to an aspect of an embodiment of the present application, there is provided an air quality index level probability forecasting method, including:
acquiring air quality data forecasted by various air quality forecasting methods; the air quality data comprises air quality fraction indices of a plurality of pollutants;
calculating a class probability of an air quality index for each of the contaminants; the level probability of the air quality index is the probability that the air quality index belongs to each air quality index level;
calculating a class probability of an air quality index based on the class probability of the air quality index of each of the pollutants; the level probability of the air quality index is the probability that the air quality index belongs to each air quality index level.
Further, the calculating of the class probability of the air quality score of each of the pollutants comprises:
according to the air quality data forecasted by the plurality of air quality forecasting methods, counting the air quality index grade to which the air quality index of each pollutant forecasted by each air quality forecasting method belongs;
and calculating the ratio of the air quality index grades corresponding to each pollutant, and taking the ratio as the grade probability of the air quality index of the pollutant.
Further, the step of counting the air quality index grade to which the air quality index of each pollutant forecasted by each air quality forecasting method belongs according to the air quality data forecasted by the plurality of air quality forecasting methods comprises the following steps: and comparing the air quality index of the air pollutants with the preset numerical range of each air quality index grade, finding out the numerical range of the air quality index grade to which the air quality index of the air pollutants belongs, and taking the air quality index grade corresponding to the numerical range of the air quality index grade as the air quality index grade of the air pollutants.
Further, the calculating the ratio of each air quality index level corresponding to each pollutant includes:
acquiring the forecast most accurate rate of each air quality forecasting method aiming at each pollutant;
and calculating the sum of the forecast most accurate rates of the same air quality index level aiming at each pollutant, and taking the sum of the forecast most accurate rates as the ratio.
Further, the obtaining of the forecast maximum accuracy of each air quality forecasting method for each of the pollutants comprises: and setting the forecast most accurate rates of the air quality forecasting methods to be equal, wherein the forecast most accurate rate of each air quality forecasting method is the reciprocal of the total number of the types of the air quality forecasting methods.
Further, the obtaining of the forecast maximum accuracy of each air quality forecasting method for each of the pollutants comprises:
collecting air quality forecast values of a plurality of historical time points forecasted by the plurality of air quality forecasting methods;
collecting live monitoring values for the plurality of historical time points;
comparing the air quality forecast value with a corresponding live monitoring value, and counting the forecast most accurate probability of each air quality forecast method; the most accurate forecasting probability is the frequency ratio of the air quality forecasting value closest to the corresponding live monitoring value.
Further, the comparing the air quality forecast value with the corresponding live monitoring value, and counting the forecast most accurate probability of each air quality forecast method includes: counting the number of times that the air quality forecast values of each air quality forecasting method at the plurality of historical time points are closest to the live monitoring value, calculating the ratio of the closest times to the total sampling times, and taking the ratio as the forecasting most accurate probability; the total number of samplings is equal to the total number of the plurality of historical time points.
Further, said calculating a class probability of an air quality index based on a class probability of an air quality score of said each of said contaminants comprises:
selecting the maximum air quality index as the corresponding air quality index according to the air quality data forecasted by each air quality forecasting method, and acquiring the corresponding air quality index grade;
for each air quality index level, solving the sum of the probabilities that all pollutants reach the level as primary pollutants according to the level probabilities of the air quality sub-indexes of the pollutants, and taking the sum as the probability that the air quality index belongs to each air quality index level;
wherein the primary contaminants are contaminants that satisfy the following conditions: the air quality index of the pollutant reaches the air quality index level; the air quality index of the other contaminants does not exceed the air quality index level.
According to another aspect of the embodiments of the present application, there is provided an air quality index level probability forecasting device, including:
the first module is used for acquiring air quality data forecasted by a plurality of air quality forecasting methods; the air quality data comprises air quality fraction indices of a plurality of pollutants;
a second module for calculating a class probability of an air quality score for each of said contaminants; the level probability of the air quality index is the probability that the air quality index belongs to each air quality index level;
a third module for calculating a class probability of an air quality index based on the class probability of the air quality index of each of the pollutants; the level probability of the air quality index is the probability that the air quality index belongs to each air quality index level.
According to another aspect of embodiments of the present application, there is provided a computer-readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the air quality index level probability forecasting method described above.
The technical scheme provided by one aspect of the embodiment of the application can have the following beneficial effects:
the air quality index grade probability forecasting method provided by the embodiment of the application can effectively quantify the forecasting uncertainty of different forecasting methods, is different from the existing pollutant concentration probability forecasting method, is used for forecasting the air quality based on various forecasting methods, and gives the air quality index grade probability forecasting result by adopting a conditional probability method, so that the forecasting result is high in accuracy, and the service forecasting requirements of relevant departments can be met.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the application, or may be learned by the practice of the embodiments. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 illustrates a flow chart of an air quality index class probability forecasting method of one embodiment of the present application;
FIG. 2 illustrates a flow chart of an air quality index class probability forecasting method of another embodiment of the present application;
fig. 3 shows an air quality index level probability prediction graph obtained by the method of an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is further described with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. 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 application.
It will be understood by those within the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As shown in fig. 1, an embodiment of the present application provides an air quality index level probability forecasting method, including the following steps:
s10, acquiring air quality data forecasted by a plurality of air quality forecasting methods; the air quality data includes air quality component indices (IAQI) of a plurality of pollutants.
For example, the air quality prediction method may be a prediction method in a plurality of different modes or modes, such as an air quality mode, a statistical prediction mode, an ensemble prediction mode, and the like, and the collection content is PM2.5, PM10, SO predicted by each prediction method2、NO2、CO、O3The site daily average concentration forecast result.
The forecasting methods of different air quality modes comprise, but are not limited to, a nested grid air quality forecasting mode system NAQPMS developed by the atmospheric physics research institute of the Chinese academy of sciences, a CMAQ mode of the United states environmental protection agency, an air quality comprehensive simulation system CAMx of the United states Environ company, and a WRF-Chem mode developed by a United states atmospheric ocean administration (NOAA) Forecasting System Laboratory (FSL); methods of statistical prediction include, but are not limited to, multiple linear regression, neural networks, support vectors; methods of ensemble prediction include, but are not limited to, weight ensemble, ridge regression, and the like.
Assuming that the pollutant concentration prediction results of M prediction methods are collected, the air quality index y of each pollutant can be calculated for the air quality prediction of a certain dayk:
In the formula, k represents the number of the contaminant.
For example, the pollutant species may include PM2.5, PM10, SO, and forecast using four air quality forecast methods2、NO2、CO、O3The numbers of the multiple contaminants may be set to 1,2,3,4,5,6 in sequence, i.e., k is 1,2,3,4,5, 6. Each pollutant will have four predicted values corresponding to four air quality indices.
S20, calculating the level probability of the air quality index of each pollutant; the level probability of the air quality score is the probability that the air quality score belongs to each air quality score level.
In certain embodiments, step S20, calculating a class probability of the air quality score index for each of the pollutants comprises:
s201, according to the air quality data forecasted by the plurality of air quality forecasting methods, counting the air quality index grade of the air quality index of each pollutant forecasted by each air quality forecasting method;
for example, four forecasting methods, six pollutants, four air quality index numbers corresponding to each pollutant, and the air quality index level to which each air quality index belongs is counted.
S202, calculating the ratio of each air quality index grade corresponding to each pollutant, and taking the ratio as the grade probability of the air quality index of the pollutant;
for example, the air quality index rating may be divided into six levels of excellent, good, light pollution, moderate pollution, heavy pollution, and severe pollution. Assuming that the four air quality index levels of the pollutant CO are respectively high, good and light pollution, the probability that the pollutant CO belongs to the high level is 2/4-0.5, the probability that the pollutant CO belongs to the good level is 1/4-0.25, the probability that the pollutant CO belongs to the light pollution level is 1/4-0.25, and the probabilities that the pollutants CO belong to the other levels are all 0.
Step S201 includes: and comparing the air quality index of the air pollutants with the preset numerical range of each air quality index grade, finding out the numerical range of the air quality index grade to which the air quality index of the air pollutants belongs, and taking the air quality index grade corresponding to the numerical range of the air quality index grade as the air quality index grade of the air pollutants.
In some embodiments, the calculating the ratio of the air quality index levels corresponding to each of the pollutants comprises:
s2021, aiming at each pollutant, acquiring the forecast most accurate rate of each air quality forecasting method;
s2022, calculating the sum of the forecast most accurate rates of the same air quality index level aiming at each pollutant, and taking the sum of the forecast most accurate rates as the ratio.
In some embodiments, step S2021, obtaining a forecast maximum accuracy for each air quality forecasting method for each of the pollutants comprises:
assuming that the forecast maximum accuracy rates of the air quality forecast methods are equal (namely, the forecast results of different forecast methods are equal to the probability that the actual monitoring value is closest), the forecast maximum accuracy rate of each air quality forecast method is the reciprocal of the total number of the air quality forecast methods, namely, the forecast maximum accuracy rate of each method
The probability of being closest to the live monitoring value is 1/M.
For example, for the CO pollutant, there are four forecasting methods, and assuming that the forecasting accuracy of each forecasting method is equal, the forecasting accuracy of each forecasting method is 1/4.
In some embodiments, step S2021, obtaining a forecast maximum accuracy for each air quality forecasting method for each of the pollutants comprises:
s20211, collecting air quality forecast values of a plurality of historical time points forecasted by the plurality of air quality forecasting methods;
s20212, collecting live monitoring values of the plurality of historical time points;
s20213, comparing the air quality forecast value with a corresponding live monitoring value aiming at each pollutant, and counting the forecast most accurate probability of each air quality forecast method; the most accurate forecasting probability is the frequency ratio of the air quality forecasting value closest to the corresponding live monitoring value.
Step S20213 includes: counting the number of times that the air quality forecast values of the plurality of historical time points of each air quality forecasting method are closest to the live monitoring value aiming at each pollutant, calculating the ratio of the closest times to the total sampling times, and taking the ratio as the forecasting most accurate probability; the total number of samplings is equal to the total number of historical time points.
For example, for the CO pollutant, assuming that there are 12 historical time points, four forecasting methods, and the total sampling times is 12, the times that the air quality forecast value of each pollutant at each historical time point of each forecasting method is closest to the corresponding live monitoring value are calculated, and assuming that the times that the four forecasting methods are closest to the corresponding live monitoring values are 3,4, 2, and 3, respectively, the most accurate forecasting probabilities of the four forecasting methods are 3/12, 4/12, 2/12, and 3/12, respectively.
In some embodiments, the probability of each pollutant at each air quality index level may be calculated based on the air quality prediction results of the various prediction methods and the corresponding prediction best accuracy. And taking the forecast most accurate rate of each forecasting method as a weight, and carrying out weighted summation on the forecast data of the pollutants forecasted by each forecasting method to obtain a sum, namely the air quality index of the pollutants.
In some embodiments, for each prediction method, the air quality score for each pollutant is compared to a threshold range for each air quality score level to obtain the air quality score level for each pollutant. The forecasting accuracy of the forecasting method is used as the probability of the air quality index level of each pollutant.
For example, if the air quality score of CO predicted by the first prediction method belongs to a good level, assuming that the prediction accuracy of the first prediction method is 0.2, and if there are two other prediction methods (assuming that the prediction accuracy of the two prediction methods is 0.1 and 0.2, respectively), the air quality score of CO predicted by the two other prediction methods belongs to a good level, the probability that the air quality score of CO belongs to a good level is the sum of the prediction accuracy of the three prediction methods, that is, 0.2+0.1+0.2 is 0.5.
The probability of a contaminant at each air quality index level is denoted as P (class ═ G | species)i) (2)
Where G represents the air quality index rating and i represents the number of contaminants.
For each of the pollutants, the method for obtaining the forecast maximum accuracy of each forecasting method comprises the following steps:
air quality forecast values for a plurality of historical time points forecasted by a plurality of different air quality forecast methods are collected.
Live monitoring values of the plurality of historical time points are collected.
And comparing the air quality forecast value with the corresponding live monitoring value, and counting the forecast most accurate probability of each forecasting method. The most accurate probability of forecasting, i.e., the number of times the forecast value is closest to the live monitoring value (i.e., the ratio to the total forecast number of times). The prediction accuracy probability of each prediction method actually reflects the prediction accuracy degree of the prediction method.
For example, numbers are respectively set for a forecasting method, pollutants and historical time points, F (x, y, z) is set to represent a forecasting value, P (y, z) is set to represent a live monitoring value, x represents a forecasting method number, y represents a pollutant number, and z represents a historical time point number; x, y and z are all positive integers, and x belongs to [1, M ]]，y∈[1,B]，z∈[1,T]M represents the total number of types of forecast methods, B represents the total number of types of pollutants, and T represents the total number of selected historical time points. For example, for pollutants PM2.5, PM10, SO2、NO2、CO、O3Numbered 1,2,3,4,5,6 in sequence. F (1,2,3) represents the forecast value of the third historical time point of the second pollutant forecasted by the first forecasting method. The value of the total number of forecasts is z for each of said pollutants (mass forecast of the same pollutant at the same historical point in time for all forecasting methods as one forecast). For each group (y, z), the number c of times F (x, y, z) is closest to P (y, z) (i.e. the number of times the predicted value of the xth prediction method is closest to the live monitoring value for the yth pollutant) is counted, and the most accurate probability of prediction is c/z.
For example, assuming that 10 historical time points are taken, six pollutants for forecasting and live monitoring are used, and four methods for forecasting are used, the total number of comparison times of each method for each pollutant is 10, the number of times (called the closest number) that the forecast value of each forecasting method is closest to the live monitoring value is counted, and the ratio of the closest number to the total number of comparison times is the forecasting accuracy. If the closest times of the first forecasting method is 2 times, the forecasting maximum accuracy of the first forecasting method is 0.2 when the number of times/10 times is 2 times, and if the closest times of the second forecasting method is 5 times, the forecasting maximum accuracy of the second forecasting method is 0.5 when the number of times/10 times is 5 times; … … are provided.
And S30, calculating the probability that the Air Quality Index (AQI) belongs to each air quality index grade according to the grade probability of the air quality score of each pollutant.
Step S30 includes:
s301, aiming at the air quality data forecasted by each air quality forecasting method, selecting the maximum air quality index as the corresponding air quality index, and acquiring the corresponding air quality index grade;
for example, suppose there are four forecasting methods, six pollutants PM2.5, PM10, SO2、NO2、CO、O3For the first forecasting method, if the air quality index of the CO is the maximum, the air quality index of the CO is taken as the air quality index, and if the air quality index of the CO is in a good grade, the air quality index grade forecasted by the first forecasting method is in a good grade; for the second forecasting method, SO2When the air quality index of (2) is maximum, the air quality index is SO2The air quality index of (1) is taken as the air quality index if SO2If the air quality index level is severe pollution, the air quality index level forecasted by the second forecasting method is severe pollution; … … are provided.
S302, aiming at each air quality index level, solving the sum of the probabilities that all pollutants reach the level as primary pollutants according to the level probability of the air quality sub-index of the pollutants, and taking the sum as the probability that the air quality index belongs to each air quality index level;
wherein the primary contaminants are contaminants that satisfy the following conditions: the air quality index of the pollutant reaches the air quality index level; the air quality index of the other contaminants does not exceed the air quality index level.
For example, if the air quality index level of the first prediction method is good, the air quality index level of the second prediction method is severe pollution, the air quality index level of the third prediction method is severe pollution, and the air quality index level of the fourth prediction method is good; for the good level of the air quality index, calculating the probability that the six pollutants corresponding to the first forecasting method reach the good level as the primary pollutants, calculating the probability that the six pollutants corresponding to the fourth forecasting method reach the good level as the primary pollutants, and calculating the sum of the two probabilities, namely the probability that the air quality index belongs to the good level; and for the air quality index level severe pollution level, solving the probability that the six pollutants corresponding to the second forecasting method reach the severe pollution level as the primary pollutants, solving the probability that the six pollutants corresponding to the third forecasting method reach the severe pollution level as the primary pollutants, and then summing the two probabilities, namely the probability that the air quality index belongs to the severe pollution level.
The air quality index calculation formula is as follows:
AQI＝max{IAQIl，IAQI2，IAQI3，…，IAQIn} (3)
wherein n is the number of pollutant species (e.g., pollutants PM2.5, PM10, SO)2、NO2、CO、O3Six, n ═ 6, the six pollutants can be sequentially assigned numbers 1,2,3,4,5, 6), the IAQI is air quality index, and when the AQI is greater than 50, the largest pollutant of the IAQI is the first pollutant.
And (3) calculating the probability of the occurrence of the air quality index AQI at each air quality index level, namely solving the sum of the probabilities of all pollutants as the primary pollutants reaching the level according to the level probability of the air quality index of the pollutants at each air quality index level, wherein the solving formula is shown as a formula (4).
While one pollutant as the primary pollutant reaches a certain air quality index level, the following two requirements must be satisfied at the same time:
(1) the air quality index (IAQI) of the pollutant reaches the air quality index level;
(2) the air quality index (IAQI) of other contaminants cannot exceed this air quality index level.
Specifically, by adopting the conditional probability, a probability calculation formula of the occurrence of the air quality index AQI at each air quality index level can be obtained:
wherein the pollutants are arranged in sequence, i and j are fixed positions of certain pollutants in the arrangement, for example, the arrangement sequence of the pollutants can be determined as PM2.5, PM10 and SO2、NO2、CO、O3。
In another embodiment, an air quality index grade probability forecasting method is provided, as shown in fig. 2, which is a flow chart of the method of the embodiment, and as shown in fig. 3, which is an air quality index grade probability forecasting graph obtained by the method of the embodiment, wherein the site air quality index grade probability forecasting results generally include forecasting on the current day and 3 days in the future, taking the results reported from "aosen station" on day 1 and 12 months, the probability of mild pollution occurring on day 2 and 12 months of the station is 5%, the probability of moderate pollution is 80%, and the probability of severe pollution is 15%. Wherein different colors in the histogram correspond to different air quality index levels, and a specific probability value is marked on the histogram only when the probability of the air quality index level exceeds 20%.
The present embodiment further provides an air quality index class probability forecasting device, including:
the first module is used for acquiring air quality data forecasted by a plurality of air quality forecasting methods; the air quality data comprises air quality fraction indices of a plurality of pollutants;
a second module for calculating a class probability of an air quality score for each of said contaminants; the level probability of the air quality index is the probability that the air quality index belongs to each air quality index level;
a third module for calculating a class probability of an air quality index based on the class probability of the air quality index of each of the pollutants; the level probability of the air quality index is the probability that the air quality index belongs to each air quality index level.
The present embodiment also provides a computer-readable storage medium, on which a computer program is stored, the program being executed by a processor to implement the air quality index level probability forecasting method.
It should be noted that:
the term "module" is not intended to be limited to a particular physical form. Depending on the particular application, a module may be implemented as hardware, firmware, software, and/or combinations thereof. Furthermore, different modules may share common components or even be implemented by the same component. There may or may not be clear boundaries between the various modules.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may be used with the teachings herein. The required structure for constructing such a device will be apparent from the description above. In addition, this application is not directed to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the present application as described herein, and any descriptions of specific languages are provided above to disclose the best modes of the present application.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the application, various features of the application are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: this application is intended to cover such departures from the present disclosure as come within known or customary practice in the art to which this invention pertains. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this application.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the application and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the present application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the creation apparatus of a virtual machine according to embodiments of the present application. The present application may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present application may be stored on a computer readable medium or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The above-mentioned embodiments only express the embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. An air quality index level probability forecasting method is characterized by comprising the following steps:
acquiring air quality data forecasted by various air quality forecasting methods; the air quality data comprises air quality fraction indices of a plurality of pollutants;
calculating a class probability of an air quality index for each of the contaminants; the level probability of the air quality index is the probability that the air quality index belongs to each air quality index level;
calculating a class probability of an air quality index based on the class probability of the air quality index of each of the pollutants; the level probability of the air quality index is the probability that the air quality index belongs to each air quality index level.
2. The method of claim 1, wherein said calculating a class probability of an air quality score for each of said contaminants comprises:
according to the air quality data forecasted by the plurality of air quality forecasting methods, counting the air quality index grade to which the air quality index of each pollutant forecasted by each air quality forecasting method belongs;
and calculating the ratio of the air quality index grades corresponding to each pollutant, and taking the ratio as the grade probability of the air quality index of the pollutant.
3. The method according to claim 2, wherein the step of counting the air quality index level of the air quality index of each pollutant forecasted by each air quality forecasting method according to the air quality data forecasted by the plurality of air quality forecasting methods comprises: and comparing the air quality index of the air pollutants with the preset numerical range of each air quality index grade, finding out the numerical range of the air quality index grade to which the air quality index of the air pollutants belongs, and taking the air quality index grade corresponding to the numerical range of the air quality index grade as the air quality index grade of the air pollutants.
4. The method of claim 2, wherein said calculating the air quality index rating for each of said contaminants comprises:
acquiring the forecast most accurate rate of each air quality forecasting method aiming at each pollutant;
and calculating the sum of the forecast most accurate rates of the same air quality index level aiming at each pollutant, and taking the sum of the forecast most accurate rates as the ratio.
5. The method of claim 4, wherein said obtaining a forecast maximum accuracy for each of said air quality forecast methods for each of said pollutants comprises: and setting the forecast most accurate rates of the air quality forecasting methods to be equal, wherein the forecast most accurate rate of each air quality forecasting method is the reciprocal of the total number of the types of the air quality forecasting methods.
6. The method of claim 4, wherein said obtaining a forecast maximum accuracy for each of said air quality forecast methods for each of said pollutants comprises:
collecting air quality forecast values of a plurality of historical time points forecasted by the plurality of air quality forecasting methods;
collecting live monitoring values for the plurality of historical time points;
comparing the air quality forecast value with a corresponding live monitoring value, and counting the forecast most accurate probability of each air quality forecast method; the most accurate forecasting probability is the frequency ratio of the air quality forecasting value closest to the corresponding live monitoring value.
7. The method according to claim 6, wherein comparing the air quality forecast value with a corresponding live monitoring value, and counting a forecast most accurate probability for each of the air quality forecast methods comprises: counting the number of times that the air quality forecast values of each air quality forecasting method at the plurality of historical time points are closest to the live monitoring value, calculating the ratio of the closest times to the total sampling times, and taking the ratio as the forecasting most accurate probability; the total number of samplings is equal to the total number of the plurality of historical time points.
8. The method of claim 1, wherein said calculating a class probability of an air quality index based on a class probability of an air quality score of said each of said contaminants comprises:
selecting the maximum air quality index as the corresponding air quality index according to the air quality data forecasted by each air quality forecasting method, and acquiring the corresponding air quality index grade;
for each air quality index level, solving the sum of the probabilities that all pollutants reach the level as primary pollutants according to the level probabilities of the air quality sub-indexes of the pollutants, and taking the sum as the probability that the air quality index belongs to each air quality index level;
wherein the primary contaminants are contaminants that satisfy the following conditions: the air quality index of the pollutant reaches the air quality index level; the air quality index of the other contaminants does not exceed the air quality index level.
9. An air quality index class probability forecasting device, comprising:
the first module is used for acquiring air quality data forecasted by a plurality of air quality forecasting methods; the air quality data comprises air quality fraction indices of a plurality of pollutants;
a second module for calculating a class probability of an air quality score for each of said contaminants; the level probability of the air quality index is the probability that the air quality index belongs to each air quality index level;
a third module for calculating a class probability of an air quality index based on the class probability of the air quality index of each of the pollutants; the level probability of the air quality index is the probability that the air quality index belongs to each air quality index level.
10. A computer-readable storage medium, on which a computer program is stored, which program is executable by a processor to implement the air quality index level probability prediction method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911359217.0A CN110989043B (en) | 2019-12-25 | 2019-12-25 | Air quality index grade probability forecasting method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911359217.0A CN110989043B (en) | 2019-12-25 | 2019-12-25 | Air quality index grade probability forecasting method and device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110989043A true CN110989043A (en) | 2020-04-10 |
| CN110989043B CN110989043B (en) | 2020-07-31 |
Family
ID=70076646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911359217.0A Active CN110989043B (en) | 2019-12-25 | 2019-12-25 | Air quality index grade probability forecasting method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110989043B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115097547A (en) * | 2022-07-04 | 2022-09-23 | 湖南省生态环境监测中心 | Atmospheric heavy pollution forecasting method based on combination of numerical mode and statistical analysis |
| CN116166924A (en) * | 2022-12-15 | 2023-05-26 | 中科三清科技有限公司 | Data processing method and device, storage medium and electronic equipment |
| CN117495208A (en) * | 2024-01-02 | 2024-02-02 | 中科三清科技有限公司 | Air quality forecast evaluation method and device, storage medium and electronic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273995A (en) * | 2016-04-08 | 2017-10-20 | 株式会社日立制作所 | Urban Air Pollution Methods |
| US20170322342A1 (en) * | 2016-05-04 | 2017-11-09 | Global Weather Corporation | Climatology and weather forecasts using mobile sensor data |
-
2019
- 2019-12-25 CN CN201911359217.0A patent/CN110989043B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273995A (en) * | 2016-04-08 | 2017-10-20 | 株式会社日立制作所 | Urban Air Pollution Methods |
| US20170322342A1 (en) * | 2016-05-04 | 2017-11-09 | Global Weather Corporation | Climatology and weather forecasts using mobile sensor data |
Non-Patent Citations (1)
| Title |
|---|
| 王茜等: "集合数值预报系统在上海市空气质量预测预报中的应用研究", 《环境监控与预警》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115097547A (en) * | 2022-07-04 | 2022-09-23 | 湖南省生态环境监测中心 | Atmospheric heavy pollution forecasting method based on combination of numerical mode and statistical analysis |
| CN116166924A (en) * | 2022-12-15 | 2023-05-26 | 中科三清科技有限公司 | Data processing method and device, storage medium and electronic equipment |
| CN116166924B (en) * | 2022-12-15 | 2023-11-21 | 中科三清科技有限公司 | Data processing method and device, storage medium and electronic equipment |
| CN117495208A (en) * | 2024-01-02 | 2024-02-02 | 中科三清科技有限公司 | Air quality forecast evaluation method and device, storage medium and electronic equipment |
| CN117495208B (en) * | 2024-01-02 | 2024-04-05 | 中科三清科技有限公司 | Air quality forecast evaluation method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110989043B (en) | 2020-07-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Predictive analysis of the air quality indicators in the Yangtze River Delta in China: An application of a novel seasonal grey model | |
| CN110989043B (en) | Air quality index grade probability forecasting method and device and storage medium | |
| CN110989044B (en) | Air quality index level probability forecasting method, device, equipment and storage medium | |
| Zhao et al. | Planning emergency shelters for urban disaster resilience: An integrated location-allocation modeling approach | |
| Nguyen et al. | Assessment of social vulnerability to climate change at the local scale: development and application of a Social Vulnerability Index | |
| Sztubecka et al. | An innovative decision support system to improve the energy efficiency of buildings in urban areas | |
| Groves et al. | A new analytic method for finding policy-relevant scenarios | |
| Dewangan et al. | Load forecasting models in smart grid using smart meter information: A review | |
| KR101341437B1 (en) | Method for multi criteria assessment of flood risk | |
| Li et al. | Application of a GIS-based fuzzy multi-criteria evaluation approach for wind farm site selection in China | |
| Wang et al. | Research and application of a hybrid wind energy forecasting system based on data processing and an optimized extreme learning machine | |
| CN111554408B (en) | City internal dengue space-time prediction method, system and electronic equipment | |
| Lizárraga-Mendiola et al. | Estimating the rainwater potential per household in an urban area: Case study in Central Mexico | |
| Lagos et al. | State-of-the-Art using bibliometric analysis of Wind-Speed and-Power forecasting methods applied in power systems | |
| Kloubert | Probabilistic load flow approach considering dependencies of wind speed, solar irradiance, electrical load and energy exchange with a joint probability distribution model | |
| Choi et al. | Development of combined heavy rain damage prediction models with machine learning | |
| Woo et al. | Optimal cooling shelter assignment during heat waves using real-time mobile-based floating population data | |
| Gholami et al. | Upscaling of spatial energy planning, phases, methods, and techniques: A systematic review through meta-analysis | |
| Ramnath et al. | Household electricity consumer classification using novel clustering approach, review, and case study | |
| Dudek et al. | Intelligent Forecasting and Optimization in Electrical Power Systems: Advances in Models and Applications | |
| El Bakali et al. | Day-ahead seasonal solar radiation prediction, combining VMD and STACK algorithms | |
| Hu et al. | Construction and demolition waste generation prediction and spatiotemporal analysis: a case study in Sichuan, China | |
| Konstantinos et al. | Smart cities data classification for electricity consumption & traffic prediction | |
| CN116629460A (en) | Subway passenger flow prediction method based on ST-RANet model | |
| Georgati et al. | Spatially explicit population projections: The case of Copenhagen, Denmark |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20200410 Assignee: Beijing Zhongke Sanqing Environmental Technology Co.,Ltd. Assignor: 3CLEAR TECHNOLOGY Co.,Ltd. Contract record no.: X2022980012305 Denomination of invention: Air quality index level probabilistic forecast method, device and storage medium Granted publication date: 20200731 License type: Common License Record date: 20220815 |
|
| EE01 | Entry into force of recordation of patent licensing contract |